Accurate photovoltaic power forecasting models using deep LSTM-RNN

Artificial Intelligence Techniques in Smart Grid: A Survey

The smart grid is enabling the collection of massive amounts of high-dimensional and multi-type data about the electric power grid operations, by integrating advanced metering infrastructure, control technologies, and communication technologies. However, the traditional modeling, optimization, and control technologies have many limitations in processing the data; thus, the applications of artificial intelligence (AI) techniques in the smart grid are becoming more apparent. This survey presents a structured review of the existing research into some common AI techniques applied to load forecasting, power grid stability assessment, faults detection, and security problems in the smart grid and power systems. It also provides further research challenges for applying AI technologies to realize truly smart grid systems. Finally, this survey presents opportunities of applying AI to smart grid problems. The paper concludes that the applications of AI techniques can enhance and improve the reliability and resilience of smart grid systems.

Designing a long short-term network for short-term forecasting of global horizontal irradiance

Long short-term memory (LSTM) models based on specialized deep neural network-based architecture have emerged as an important model for forecasting time-series. However, the literature does not provide clear guidelines for design choices, which affect forecasting performance. Such choices include the need for pre-processing techniques such as deseasonalization, ordering of the input data, network size, batch size, and forecasting horizon. We detail this in the context of short-term forecasting of global horizontal irradiance, an accepted proxy for solar energy. Particularly, short-term forecasting is critical because the cloud conditions change at a sub-hourly having large impacts on incident solar radiation. We conduct an empirical investigation based on data from three solar stations from two climatic zones of India over two seasons. From an application perspective, it may be noted that despite the thrust given to solar energy generation in India, the literature contains few instances of robust studies across climatic zones and seasons. The model thus obtained subsequently outperformed three recent benchmark methods based on random forest, recurrent neural network, and LSTM, respectively, in terms of forecasting accuracy. Our findings underscore the importance of considering the temporal order of the data, lack of any discernible benefit from data pre-processing, the effect of making the LSTM model stateful. It is also found that the number of nodes in an LSTM network, as well as batch size, is influenced by the variability of the input data.

Comparative Analysis of Machine Learning Models for Day-Ahead Photovoltaic Power Production Forecasting

A main challenge for integrating the intermittent photovoltaic (PV) power generation remains the accuracy of day-ahead forecasts and the establishment of robust performing methods. The purpose of this work is to address these technological challenges by evaluating the day-ahead PV production forecasting performance of different machine learning models under different supervised learning regimes and minimal input features. Specifically, the day-ahead forecasting capability of Bayesian neural network (BNN), support vector regression (SVR), and regression tree (RT) models was investigated by employing the same dataset for training and performance verification, thus enabling a valid comparison. The training regime analysis demonstrated that the performance of the investigated models was strongly dependent on the timeframe of the train set, training data sequence, and application of irradiance condition filters. Furthermore, accurate results were obtained utilizing only the measured power output and other calculated parameters for training. Consequently, useful information is provided for establishing a robust day-ahead forecasting methodology that utilizes calculated input parameters and an optimal supervised learning approach. Finally, the obtained results demonstrated that the optimally constructed BNN outperformed all other machine learning models achieving forecasting accuracies lower than 5%.

Exploitation of a New Short-Term Multimodel Photovoltaic Power Forecasting Method in the Very Short-Term Horizon to Derive a Multi-Time Scale Forecasting System

The relentless spread of photovoltaic production drives searches of smart approaches to mitigate unbalances in power demand and supply, instability on the grid and ensuring stable revenues to the producer. Because of the development of energy markets with multiple time sessions, there is a growing need of power forecasting for multiple time steps, from fifteen minutes up to days ahead. To address this issue, in this study both a short-term-horizon of three days and a very-short-term-horizon of three hours photovoltaic production forecasting methods are presented. The short-term is based on a multimodel approach and referred to several configurations of the Analog Ensemble method, using the weather forecast of four numerical weather prediction models. The very-short-term consists of an Auto-Regressive Integrated Moving Average Model with eXogenous input (ARIMAX) that uses the short-term power forecast and the irradiance from satellite elaborations as exogenous variables. The methods, applied for one year to four small-scale grid-connected plants in Italy, have obtained promising improvements with respect to refence methods. The time horizon after which the short-term was able to outperform the very-short-term has also been analyzed. The study also revealed the usefulness of satellite data on cloudiness to properly interpret the results of the performance analysis.

BIM architecture design from the perspective of smart city and its application in traditional residential design

This research mainly discusses the characteristics of BIM architecture design and its application in traditional residential design from the perspective of smart cities. Given the topics that people are more concerned about, this research mainly uses BIM modeling technology to initially build a virtualized building model. It discusses the convenience of intelligent automation technology in terms of resource consumption and house security. In terms of safety, different levels of wind blowing strength are mainly used to measure the distance moved by the house to evaluate the safety factor. Divide the wind blowing intensity into A, B, C, D, E, F, and 6 levels to test the strength of the house. When the wind intensity level is F, the safety factor is the weakest, which is 20%. When conducting a house consumption test, directly measure the house’s electricity consumption within a specified time to conduct a resource rate consumption test. Divide the time period into 1 h, 2 h, 3 h, 4 h, 5 h, 6 h, 6 different time periods to measure power consumption. The resource consumption rate reaches a maximum value of 96% when the length of time is 6 h. The experimental results show that the safety characteristics of BIM technology are the weakest when the wind strength level is F, and the safety performance is different when the wind strength level is different. In terms of resource consumption, the resource consumption rate reaches the maximum value when the time is 6 h, and the length of time directly determines the housing resource consumption rate. From the perspective of a smart city, BIM building design has the advantages of low resource consumption and high safety factor.

Deep Learning for Time Series Forecasting: A Survey

Time series forecasting has become a very intensive field of research, which is even increasing in recent years. Deep neural networks have proved to be powerful and are achieving high accuracy in many application fields. For these reasons, they are one of the most widely used methods of machine learning to solve problems dealing with big data nowadays. In this work, the time series forecasting problem is initially formulated along with its mathematical fundamentals. Then, the most common deep learning architectures that are currently being successfully applied to predict time series are described, highlighting their advantages and limitations. Particular attention is given to feed forward networks, recurrent neural networks (including Elman, long-short term memory, gated recurrent units, and bidirectional networks), and convolutional neural networks. Practical aspects, such as the setting of values for hyper-parameters and the choice of the most suitable frameworks, for the successful application of deep learning to time series are also provided and discussed. Several fruitful research fields in which the architectures analyzed have obtained a good performance are reviewed. As a result, research gaps have been identified in the literature for several domains of application, thus expecting to inspire new and better forms of knowledge.

Solar Photovoltaic Forecasting of Power Output Using LSTM Networks

The penetration of renewable energies has increased during the last decades since it has become an effective solution to the world’s energy challenges. Among all renewable energy sources, photovoltaic (PV) technology is the most immediate way to convert solar radiation into electricity. Nevertheless, PV power output is affected by several factors, such as location, clouds, etc. As PV plants proliferate and represent significant contributors to grid electricity production, it becomes increasingly important to manage their inherent alterability. Therefore, solar PV forecasting is a pivotal factor to support reliable and cost-effective grid operation and control. In this paper, a stacked long short-term memory network, which is a significant component of the deep recurrent neural network, is considered for the prediction of PV power output for 1.5 h ahead. Historical data of PV power output from a PV plant in Nicosia, Cyprus, were used as input to the forecasting model. Once the model was defined and trained, the model performance was assessed qualitative (by graphical tools) and quantitative (by calculating the Root Mean Square Error (RMSE) and by applying the k-fold cross-validation method). The results showed that our model can predict well, since the RMSE gives a value of 0.11368, whereas when applying the k-fold cross-validation, the mean of the resulting RMSE values is 0.09394 with a standard deviation 0.01616.

Deep RNN-Based Photovoltaic Power Short-Term Forecast Using Power IoT Sensors

Photovoltaic (PV) power fluctuations caused by weather changes can lead to short-term mismatches in power demand and supply. Therefore, to operate the power grid efficiently and reliably, short-term PV power forecasts are required against these fluctuations. In this paper, we propose a deep RNN-based PV power short-term forecast. To reflect the impact of weather changes, the proposed model utilizes the on-site weather IoT dataset and power data, collected in real-time. We investigated various parameters of the proposed deep RNN-based forecast model and the combination of weather parameters to find an accurate prediction model. Experimental results showed that accuracies of 5 and 15 min ahead PV power generation forecast, using 3 RNN layers with 12 time-step, were 98.0% and 96.6% based on the normalized RMSE, respectively. Their R2-scores were 0.988 and 0.949. In experiments for 1 and 3 h ahead of PV power generation forecasts, their accuracies were 94.8% and 92.9%, respectively. Also, their R2-scores were 0.963 and 0.927. These experimental results showed that the proposed deep RNN-based short-term forecast algorithm achieved higher prediction accuracy.

Self-Powered, Hybrid, Multifunctional Sensor for a Human Biomechanical Monitoring Device

For personal and daily activities, it is highly desirable to collect energy from multiple sources, not only for charging personal electronics but also for charging devices that may in the future sense and transmit information for healthcare and biomedical applications. In particular, hybridization of triboelectric and piezoelectric energy-harvesting generators with lightweight components and relatively simple structures have shown promise in self-powered sensors. Here, we present a self-powered multifunctional sensor (SPMS) based on hybridization with a novel design of a piezoelectrically curved spacer that functions concurrently with a zigzag shaped triboelectric harvester for a human biomechanical monitoring device. The optimized SPMS had an open-circuit voltage (VOC) of 103 V, short-circuit current (ISC) of 302 µA, load of 100 kΩ, and maximum average power output of 38 mW under the operational processes of compression/deformation/touch/release. To maximize the new sensor’s usage as a gait sensor that can detect and monitor human motion characteristics in rehabilitation circumstances, the deep learning long short-term memory (LSTM) model was developed with an accuracy of the personal sequence gait SPMS signal recognition of 81.8%.

Solar Photovoltaic Power Forecasting

The management of clean energy is usually the key for environmental, economic, and sustainable developments. In the meantime, the energy management system (EMS) ensures the clean energy which includes many sources grouped in a small power plant such as microgrid (MG). In this case, the forecasting methods are used for helping the EMS and allow the high efficiency to the clean energy. The aim of this review paper is providing the necessary data about the basic principles and standards of photovoltaic (PV) power forecasting by stating numerous research studies carried out on the PV power forecasting topic specifically in the short-term time horizon which is advantageous for the EMS and grid operator. At the same time, this contribution can offer a state of the art in different methods and approaches used for PV power forecasting along with a careful study of different time and spatial horizons. Furthermore, this current review paper can support the tenders in the PV power forecasting.

A Review on Deep Learning Models for Forecasting Time Series Data of Solar Irradiance and Photovoltaic Power

Presently, deep learning models are an alternative solution for predicting solar energy because of their accuracy. The present study reviews deep learning models for handling time-series data to predict solar irradiance and photovoltaic (PV) power. We selected three standalone models and one hybrid model for the discussion, namely, recurrent neural network (RNN), long short-term memory (LSTM), gated recurrent unit (GRU), and convolutional neural network-LSTM (CNN–LSTM). The selected models were compared based on the accuracy, input data, forecasting horizon, type of season and weather, and training time. The performance analysis shows that these models have their strengths and limitations in different conditions. Generally, for standalone models, LSTM shows the best performance regarding the root-mean-square error evaluation metric (RMSE). On the other hand, the hybrid model (CNN–LSTM) outperforms the three standalone models, although it requires longer training data time. The most significant finding is that the deep learning models of interest are more suitable for predicting solar irradiance and PV power than other conventional machine learning models. Additionally, we recommend using the relative RMSE as the representative evaluation metric to facilitate accuracy comparison between studies.

PV Power Prediction, Using CNN-LSTM Hybrid Neural Network Model. Case of Study: Temixco-Morelos, México

Due to the intermittent nature of solar energy, accurate photovoltaic power predictions are very important for energy integration into existing energy systems. The evolution of deep learning has also opened the possibility to apply neural network models to predict time series, achieving excellent results. In this paper, a five layer CNN-LSTM model is proposed for photovoltaic power predictions using real data from a location in Temixco, Morelos in Mexico. In the proposed hybrid model, the convolutional layer acts like a filter, extracting local features of the data; then the temporal features are extracted by the long short-term memory network. Finally, the performance of the hybrid model with five layers is compared with a single model (a single LSTM), a CNN-LSTM hybrid model with two layers and two well known popular benchmarks. The results also shows that the hybrid neural network model has better prediction effect than the two layer hybrid model, the single prediction model, the Lasso regression or the Ridge regression.

Benchmark Comparison of Analytical, Data-Based and Hybrid Models for Multi-Step Short-Term Photovoltaic Power Generation Forecasting

Accurately forecasting power generation in photovoltaic (PV) installations is a challenging task, due to the volatile and highly intermittent nature of solar-based renewable energy sources. In recent years, several PV power generation forecasting models have been proposed in the relevant literature. However, there is no consensus regarding which models perform better in which cases. Moreover, literature lacks of works presenting detailed experimental evaluations of different types of models on the same data and forecasting conditions. This paper attempts to fill in this gap by presenting a comprehensive benchmarking framework for several analytical, data-based and hybrid models for multi-step short-term PV power generation forecasting. All models were evaluated on the same real PV power generation data, gathered from the realisation of a small scale pilot site in Thessaloniki, Greece. The models predicted PV power generation on multiple horizons, namely for 15 min, 30 min, 60 min, 120 min and 180 min ahead of time. Based on the analysis of the experimental results we identify the cases, in which specific models (or types of models) perform better compared to others, and explain the rationale behind those model performances.

Key Operational Issues on the Integration of Large-Scale Solar Power Generation—A Literature Review

Solar photovoltaic (PV) power generation has strong intermittency and volatility due to its high dependence on solar radiation and other meteorological factors. Therefore, the negative impact of grid-connected PV on power systems has become one of the constraints in the development of large scale PV systems. Accurate forecasting of solar power generation and flexible planning and operational measures are of great significance to ensure safe, stable, and economical operation of a system with high penetration of solar generation at transmission and distribution levels. In this paper, studies on the following aspects are reviewed: (1) this paper comprehensively expounds the research on forecasting techniques of PV power generation output. (2) In view of the new challenge brought by the integration of high proportion solar generation to the frequency stability of power grid, this paper analyzes the mechanisms of influence between them and introduces the current technical route of PV power generation participating in system frequency regulation. (3) This section reviews the feasible measures that facilitate the inter-regional and wide-area consumption of intermittent solar power generation. At the end of this paper, combined with the actual demand of the development of power grid and PV power generation, the problems that need further attention in the future are prospected.

Energy and Resource Efficiency in Apatite-Nepheline Ore Waste Processing Using the Digital Twin Approach

The paper presents a structure of the digital environment as an integral part of the “digital twin” technology, and stipulates the research to be carried out towards an energy and recourse efficiency technology assessment of phosphorus production from apatite-nepheline ore waste. The problem with their processing is acute in the regions of the Russian Arctic shelf, where a large number of mining and processing plants are concentrated; therefore, the study and creation of energy-efficient systems for ore waste disposal is an urgent scientific problem. The subject of the study is the infoware for monitoring phosphorus production. The applied study methods are based on systems theory and system analysis, technical cybernetics, machine learning technologies as well as numerical experiments. The usage of “digital twin” elements to increase the energy and resource efficiency of phosphorus production is determined by the desire to minimize the costs of production modernization by introducing advanced algorithms and computer architectures. The algorithmic part of the proposed tools for energy and resource efficiency optimization is based on the deep neural network apparatus and a previously developed mathematical description of the thermophysical, thermodynamic, chemical, and hydrodynamic processes occurring in the phosphorus production system. The ensemble application of deep neural networks allows for multichannel control over the phosphorus technology process and the implementation of continuous additional training for the networks during the technological system operation, creating a high-precision digital copy, which is used to determine control actions and optimize energy and resource consumption. Algorithmic and software elements are developed for the digital environment, and the results of simulation experiments are presented. The main contribution of the conducted research consists of the proposed structure for technological information processing to optimize the phosphorus production system according to the criteria of energy and resource efficiency, as well as the developed software that implements the optimization parameters of this system.

Sea Surface Temperature and High Water Temperature Occurrence Prediction Using a Long Short-Term Memory Model

Recent global warming has been accompanied by high water temperatures (HWTs) in coastal areas of Korea, resulting in huge economic losses in the marine fishery industry due to disease outbreaks in aquaculture. To mitigate these losses, it is necessary to predict such outbreaks to prevent or respond to them as early as possible. In the present study, we propose an HWT prediction method that applies sea surface temperatures (SSTs) and deep-learning technology in a long short-term memory (LSTM) model based on a recurrent neural network (RNN). The LSTM model is used to predict time series data for the target areas, including the coastal area from Goheung to Yeosu, Jeollanam-do, Korea, which has experienced frequent HWT occurrences in recent years. To evaluate the performance of the SST prediction model, we compared and analyzed the results of an existing SST prediction model for the SST data, and additional external meteorological data. The proposed model outperformed the existing model in predicting SSTs and HWTs. Although the performance of the proposed model decreased as the prediction interval increased, it consistently showed better performance than the European Center for Medium-Range Weather Forecast (ECMWF) prediction model. Therefore, the method proposed in this study may be applied to prevent future damage to the aquaculture industry.

Research on multi-effect evaporation salt prediction based on feature extraction

In the multi-effect evaporation salt making process, the smooth operation of the salt making process is crucial. As the salt production process continues, many unstable factors will cause the salt production process not to proceed smoothly. These factors can be discovered in advance by predicting the salt production data, thus, it is of great significance to predict the multi-effect evaporation salt production data. In the process of multi-effect evaporation and salt production, the multiple salt-making devices make the influence between the parameters closer, and the influence of a single parameter on itself is sometimes ductile. Therefore, the data of multi-effect evaporation and salt production have the characteristics of high dimensions, high complexity and temporal information. If the historical salt production data is used for data prediction directly, the prediction model will take a long time and the prediction effect is not good. Thus, how to predict the multi-effect evaporation salt production data is the main research problem of this paper. In view of the above problems, according to the characteristics of multi-effect evaporation salt production data, this paper analyzes and improves the self encoder for feature extraction of multi effect-evaporation salt production data, so as to solve the problem of high dimensions and high complexity of salt production data. On this basis, combined with the time-series information contained in the salt production data, a multi-effect evaporation salt production data prediction model is proposed based on long-term and short-term memory cycle neural network to solve the prediction problem of time-series salt production data. Experiments show that the prediction model can predict and prevent the problems in salt production line in advance. It has a certain theoretical research value and application value in the intelligent production process and production line optimization of salt chemical industry.

Training and Testing of a Single-Layer LSTM Network for Near-Future Solar Forecasting

Increasing integration of renewable energy sources, like solar photovoltaic (PV), necessitates the development of power forecasting tools to predict power fluctuations caused by weather. With trustworthy and accurate solar power forecasting models, grid operators could easily determine when other dispatchable sources of backup power may be needed to account for fluctuations in PV power plants. Additionally, PV customers and designers would feel secure knowing how much energy to expect from their PV systems on an hourly, daily, monthly, or yearly basis. The PROGNOSIS project, based at the Cyprus University of Technology, is developing a tool for intra-hour solar irradiance forecasting. This article presents the design, training, and testing of a single-layer long-short-term-memory (LSTM) artificial neural network for intra-hour power forecasting of a single PV system in Cyprus. Four years of PV data were used for training and testing the model (80% for training and 20% for testing). With a normalized root mean squared error (nRMSE) of 10.7%, the single-layer network performed similarly to a more complex 5-layer LSTM network trained and tested using the same data. Overall, these results suggest that simple LSTM networks can be just as effective as more complicated ones.

Forecasting Day-Ahead Hourly Photovoltaic Power Generation Using Convolutional Self-Attention Based Long Short-Term Memory

The problem of Photovoltaic (PV) power generation forecasting is becoming crucial as the penetration level of Distributed Energy Resources (DERs) increases in microgrids and Virtual Power Plants (VPPs). In order to improve the stability of power systems, a fair amount of research has been proposed for increasing prediction performance in practical environments through statistical, machine learning, deep learning, and hybrid approaches. Despite these efforts, the problem of forecasting PV power generation remains to be challenging in power system operations since existing methods show limited accuracy and thus are not sufficiently practical enough to be widely deployed. Many existing methods using long historical data suffer from the long-term dependency problem and are not able to produce high prediction accuracy due to their failure to fully utilize all features of long sequence inputs. To address this problem, we propose a deep learning-based PV power generation forecasting model called Convolutional Self-Attention based Long Short-Term Memory (LSTM). By using the convolutional self-attention mechanism, we can significantly improve prediction accuracy by capturing the local context of the data and generating keys and queries that fit the local context. To validate the applicability of the proposed model, we conduct extensive experiments on both PV power generation forecasting using a real world dataset and power consumption forecasting. The experimental results of power generation forecasting using the real world datasets show that the MAPEs of the proposed model are much lower, in fact by 7.7%, 6%, 3.9% compared to the Deep Neural Network (DNN), LSTM and LSTM with the canonical self-attention, respectively. As for power consumption forecasting, the proposed model exhibits 32%, 17% and 44% lower Mean Absolute Percentage Error (MAPE) than the DNN, LSTM and LSTM with the canonical self-attention, respectively.

Multi-Step Solar Irradiance Forecasting and Domain Adaptation of Deep Neural Networks

The problem of forecasting hourly solar irradiance over a multi-step horizon is dealt with by using three kinds of predictor structures. Two approaches are introduced: Multi-Model (MM) and Multi-Output (MO). Model parameters are identified for two kinds of neural networks, namely the traditional feed-forward (FF) and a class of recurrent networks, those with long short-term memory (LSTM) hidden neurons, which is relatively new for solar radiation forecasting. The performances of the considered approaches are rigorously assessed by appropriate indices and compared with standard benchmarks: the clear sky irradiance and two persistent predictors. Experimental results on a relatively long time series of global solar irradiance show that all the networks architectures perform in a similar way, guaranteeing a slower decrease of forecasting ability on horizons up to several hours, in comparison to the benchmark predictors. The domain adaptation of the neural predictors is investigated evaluating their accuracy on other irradiance time series, with different geographical conditions. The performances of FF and LSTM models are still good and similar between them, suggesting the possibility of adopting a unique predictor at the regional level. Some conceptual and computational differences between the network architectures are also discussed.

Direct Normal Irradiance Forecasting Using Multivariate Gated Recurrent Units

Power grid operators rely on solar irradiance forecasts to manage uncertainty and variability associated with solar power. Meteorological factors such as cloud cover, wind direction, and wind speed affect irradiance and are associated with a high degree of variability and uncertainty. Statistical models fail to accurately capture the dependence between these factors and irradiance. In this paper, we introduce the idea of applying multivariate Gated Recurrent Units (GRU) to forecast Direct Normal Irradiance (DNI) hourly. The proposed GRU-based forecasting method is evaluated against traditional Long Short-Term Memory (LSTM) using historical irradiance data (i.e., weather variables that include cloud cover, wind direction, and wind speed) to forecast irradiance forecasting over intra-hour and inter-hour intervals. Our evaluation on one of the sites from Measurement and Instrumentation Data Center indicate that both GRU and LSTM improved DNI forecasting performance when evaluated under different conditions. Moreover, including wind direction and wind speed can have substantial improvement in the accuracy of DNI forecasts. Besides, the forecasting model can accurately forecast irradiance values over multiple forecasting horizons.

Multistep-Ahead Solar Radiation Forecasting Scheme Based on the Light Gradient Boosting Machine: A Case Study of Jeju Island

Smart islands have focused on renewable energy sources, such as solar and wind, to achieve energy self-sufficiency. Because solar photovoltaic (PV) power has the advantage of less noise and easier installation than wind power, it is more flexible in selecting a location for installation. A PV power system can be operated more efficiently by predicting the amount of global solar radiation for solar power generation. Thus far, most studies have addressed day-ahead probabilistic forecasting to predict global solar radiation. However, day-ahead probabilistic forecasting has limitations in responding quickly to sudden changes in the external environment. Although multistep-ahead (MSA) forecasting can be used for this purpose, traditional machine learning models are unsuitable because of the substantial training time. In this paper, we propose an accurate MSA global solar radiation forecasting model based on the light gradient boosting machine (LightGBM), which can handle the training-time problem and provide higher prediction performance compared to other boosting methods. To demonstrate the validity of the proposed model, we conducted a global solar radiation prediction for two regions on Jeju Island, the largest island in South Korea. The experiment results demonstrated that the proposed model can achieve better predictive performance than the tree-based ensemble and deep learning methods.

Exploring Signals for a Nuclear Future Using Social Big Data

Since the start of the new Korean government in 2017, the Korean nuclear energy system has undergone a major change. This change in national energy policy can be forecasted by analyzing social big data. This study verifies whether future forecasting methodologies using weak signals can be applied to Korean nuclear energy through text mining the data of web news between 2005 and 2018, comparing and applying the methodology to notable events (i.e., the UAE nuclear power plant (NPP) contract and nuclear phase-out). In addition, we predict what changes will be made in the Korean nuclear energy system post-2019. Keywords extracted through text mining were quantitatively classified into a weak signal or a strong signal using a Keyword Emergence Map (KEM) and a Keyword Issue Map (KIM). The extracted keywords predicted the contract of the UAE NPPs in 2009 and nuclear phase-out in 2017. Furthermore, keywords revealing future signals beyond 2019 were found to be ‘nuclear phase-out’ and ‘wind energy’. The weak-signal methodology can be applied as a tool to predict future energy trends during the current circumstance of the rapidly changing world energy market.

Bi-Level Optimal Strategy of Islanded Multi-Microgrid Systems Based on Optimal Power Flow and Consensus Algorithm

Aiming at problems of power allocation and economic scheduling for independent multi-microgrid systems, a bi-level optimization method based on optimal power flow and consensus algorithm is proposed. The novelty of the method is that an independent multi-microgrid system is divided into two layers: in the upper layer, with the predicted output range of the microgrids as the input data, each microgrid is considered as a virtual power supply or virtual load, and taking the minimum network loss as the goal, the energy mutual aid and power allocation among the microgrids are transformed into solving the optimal power flow; in the lower layer, taking the upper layer power distribution scheme as the constraint condition, considering load fluctuation and wind/solar generation uncertainty, the optimal dispatch model of the controllable distributed generator is established based on the distributed theory and the consensus algorithm of equal cost increment, and the "plug and play" of the distributed generator is also realized. An islanded multi-microgrid cluster is taken as an example to verify the economy, security, and reliability of the proposed scheme. The advantages of the scheme have been shown by the simulation example. Simulation results show that the upper-layer method not only realizes the optimal power allocation of microgrids, but also reduces the power loss of the energy mutual aid among the microgrids; through the optimal scheduling of controllable power supply in the microgrid, the lower-level scheme not only improves the economic benefit of the microgrid, but also well suppresses the negative effects of the uncertainties, prediction errors and power fault removal on the multi-microgrid system, which improves the robustness of the system.

An Ensemble Learner-Based Bagging Model Using Past Output Data for Photovoltaic Forecasting

As the world is aware, the trend of generating energy sources has been changing from conventional fossil fuels to sustainable energy. In order to reduce greenhouse gas emissions, the ratio of renewable energy sources should be increased, and solar and wind power, typically, are driving this energy change. However, renewable energy sources highly depend on weather conditions and have intermittent generation characteristics, thus embedding uncertainty and variability. As a result, it can cause variability and uncertainty in the power system, and accurate prediction of renewable energy output is essential to address this. To solve this issue, much research has studied prediction models, and machine learning is one of the typical methods. In this paper, we used a bagging model to predict solar energy output. Bagging generally uses a decision tree as a base learner. However, to improve forecasting accuracy, we proposed a bagging model using an ensemble model as a base learner and adding past output data as new features. We set base learners as ensemble models, such as random forest, XGBoost, and LightGBMs. Also, we used past output data as new features. Results showed that the ensemble learner-based bagging model using past data features performed more accurately than the bagging model using a single model learner with default features.

Technical and Economic Optimal Solutions for Utility-Scale Solar Photovoltaic Parks

Solar energy has shown to be a successful renewable source, wherefore large investments are planned in the upcoming decades. This work aims at developing technical and economical solutions to optimize a utility-scale grid connected solar photovoltaic park with an installed capacity of 24 MWp. Several successive simulations were automatically performed with the PVSyst software, so that each influencing parameter is individually analyzed. Moreover, a comprehensive study touching relevant aspects, such as central versus string inverters, landscape versus portrait dispositions, the optimal tilt angle (for fixed tilt systems), backtracking strategy (for single axis tracking systems), shading limit angle, and pitch is performed with the objective of finding the configuration leading to the higher grid injected energy output. The levelized cost of energy (LCOE) was obtained for 12 different cases in which, for both fixed tilt and single-axis tracking (SAT), central and string inverters and portrait/landscape disposition were considered. The lowest LCOE achieved was 32.23 €/MWh, which is a clear indication of the competitiveness of the solar Photovoltaic (PV) technology. The most economic viable solution is characterized by the employment of an SAT system with the backtracking strategy, together with string inverters and module portrait disposition.

Optimization of Electric Energy Sales Strategy Based on Probabilistic Forecasts

In this paper we propose an optimization scheme for a selling strategy of an electricity producer who in advance decides on the share of electricity sold on the day-ahead market. The remaining part is sold on the complementary (intraday/balancing) market. To this end, we use probabilistic forecasts of the future selling price distribution. Next, we find an optimal share of electricity sold on the day-ahead market using one of the three objectives: maximization of the overall profit, minimization of the sellers risk, or maximization of the median of portfolio values. Using data from the Polish day-ahead and balancing markets, we show that the assumed objective is achieved, as compared to the naive strategy of selling the whole produced electricity only on the day-ahead market. However, an increase of the profit is associated with a significant increase of the risk.

A Deep Neural Network-Assisted Approach to Enhance Short-Term Optimal Operational Scheduling of a Microgrid

The inherent variability of large-scale renewable energy generation leads to significant difficulties in microgrid energy management. Likewise, the effects of human behaviors in response to the changes in electricity tariffs as well as seasons result in changes in electricity consumption. Thus, proper scheduling and planning of power system operations require accurate load demand and renewable energy generation estimation studies, especially for short-term periods (hour-ahead, day-ahead). The time-sequence variation in aggregated electrical load and bulk photovoltaic power output are considered in this study to promote the supply-demand balance in the short-term optimal operational scheduling framework of a reconfigurable microgrid by integrating the forecasting results. A bi-directional long short-term memory units based deep recurrent neural network model, DRNN Bi-LSTM, is designed to provide accurate aggregated electrical load demand and the bulk photovoltaic power generation forecasting results. The real-world data set is utilized to test the proposed forecasting model, and based on the results, the DRNN Bi-LSTM model performs better in comparison with other methods in the surveyed literature. Meanwhile, the optimal operational scheduling framework is studied by simultaneously making a day-ahead optimal reconfiguration plan and optimal dispatching of controllable distributed generation units which are considered as optimal operation solutions. A combined approach of basic and selective particle swarm optimization methods, PSO&SPSO, is utilized for that combinatorial, non-linear, non-deterministic polynomial-time-hard (NP-hard), complex optimization study by aiming minimization of the aggregated real power losses of the microgrid subject to diverse equality and inequality constraints. A reconfigurable microgrid test system that includes photovoltaic power and diesel distributed generators is used for the optimal operational scheduling framework. As a whole, this study contributes to the optimal operational scheduling of reconfigurable microgrid with electrical energy demand and renewable energy forecasting by way of the developed DRNN Bi-LSTM model. The results indicate that optimal operational scheduling of reconfigurable microgrid with deep learning assisted approach could not only reduce real power losses but also improve system in an economic way.

A Machine Learning Approach to Low-Cost Photovoltaic Power Prediction Based on Publicly Available Weather Reports

A fully automated transferable predictive approach was developed to predict photovoltaic (PV) power output for a forecasting horizon of 24 h. The prediction of PV power output was made with the help of a long short-term memory machine learning algorithm. The main challenge of the approach was using (1) publicly available weather reports without solar irradiance values and (2) measured PV power without any technical information about the PV system. Using this input data, the developed model can predict the power output of the investigated PV systems with adequate accuracy. The lowest seasonal mean absolute scaled error of the prediction was reached by maximum size of the training set. Transferability of the developed approach was proven by making predictions of the PV power for warm and cold periods and for two different PV systems located in Oldenburg and Munich, Germany. The PV power prediction made with publicly available weather data was compared to the predictions made with fee-based solar irradiance data. The usage of the solar irradiance data led to more accurate predictions even with a much smaller training set. Although the model with publicly available weather data needed greater training sets, it could still make adequate predictions.

Improved Salp–Swarm Optimizer and Accurate Forecasting Model for Dynamic Economic Dispatch in Sustainable Power Systems

Worldwide, the penetrations of photovoltaic (PV) and energy storage systems are increased in power systems. Due to the intermittent nature of PVs, these sustainable power systems require efficient managing and prediction techniques to ensure economic and secure operations. In this paper, a comprehensive dynamic economic dispatch (DED) framework is proposed that includes fuel-based generators, PV, and energy storage devices in sustainable power systems, considering various profiles of PV (clear and cloudy). The DED model aims at minimizing the total fuel cost of power generation stations while considering various constraints of generation stations, the power system, PV, and energy storage systems. An improved optimization algorithm is proposed to solve the DED optimization problem for a sustainable power system. In particular, a mutation mechanism is combined with a salp–swarm algorithm (SSA) to enhance the exploitation of the search space so that it provides a better population to get the optimal global solution. In addition, we propose a DED handling strategy that involves the use of PV power and load forecasting models based on deep learning techniques. The improved SSA algorithm is validated by ten benchmark problems and applied to the DED optimization problem for a hybrid power system that includes 40 thermal generators and PV and energy storage systems. The experimental results demonstrate the efficiency of the proposed framework with different penetrations of PV.

Advanced Methods for Photovoltaic Output Power Forecasting: A Review

Forecasting is a crucial task for successfully integrating photovoltaic (PV) output power into the grid. The design of accurate photovoltaic output forecasters remains a challenging issue, particularly for multistep-ahead prediction. Accurate PV output power forecasting is critical in a number of applications, such as micro-grids (MGs), energy optimization and management, PV integrated in smart buildings, and electrical vehicle chartering. Over the last decade, a vast literature has been produced on this topic, investigating numerical and probabilistic methods, physical models, and artificial intelligence (AI) techniques. This paper aims at providing a complete and critical review on the recent applications of AI techniques; we will focus particularly on machine learning (ML), deep learning (DL), and hybrid methods, as these branches of AI are becoming increasingly attractive. Special attention will be paid to the recent development of the application of DL, as well as to the future trends in this topic.

Prediction of the Energy Consumption Variation Trend in South Africa based on ARIMA, NGM and NGM-ARIMA Models

South Africa’s energy consumption takes up about one-third of that in the whole African continent, ranking the first place in Africa. However, there are few researches on the prediction of energy consumption in South Africa. In this study, based on the data of South Africa’s energy consumption during 1998–2016, Autoregressive Integrated Moving Average (ARIMA) model, nonlinear grey model (NGM) and nonlinear grey model–autoregressive integrated moving average (NGM-ARIMA) model are adopted to predict South Africa’s energy consumption during 2017–2030. After using these NGM, ARIMA and NGM-ARIMA, the mean absolute percent errors (MAPE) are 2.827%, 2.655% and 1.772%, respectively, which indicates that the predicted result has very high reliability. The prediction results show that the energy consumption in South Africa will keep increasing with the growth rate of about 7.49% in the next 14 years. This research result will provide scientific basis for the policy adjustment of energy supply and demand in South Africa and the prediction techniques used in the research will have reference function for the energy consumption study in other African countries.

An Integrated Energy System Operating Scenarios Generator Based on Generative Adversarial Network

The convergence of energy security and environmental protection has given birth to the development of integrated energy systems (IES). However, the different physical characteristics and complex coupling of different energy sources have deeply troubled researchers. With the rapid development of AI and big data, some attempts to apply data-driven methods to IES have been made. Data-driven technologies aim to abandon complex IES modeling, instead mining the mapping relationships between different parameters based on massive volumes of operating data. However, integrated energy system construction is still in the initial stage of development and operational data are difficult to obtain, or the operational scenarios contained in the data are not enough to support data-driven technologies. In this paper, we first propose an IES operating scenario generator, based on a Generative Adversarial Network (GAN), to produce high quality IES operational data, including energy price, load, and generator output. We estimate the quality of the generated data, in both visual and quantitative aspects. Secondly, we propose a control strategy based on the Q-learning algorithm for a renewable energy and storage system with high uncertainty. The agent can accurately map between the control strategy and the operating states. Furthermore, we use the original data set and the expanded data set to train an agent; the latter works better, confirming that the generated data complements the original data set and enriches the running scenarios.

Hour-Ahead Solar Irradiance Forecasting Using Multivariate Gated Recurrent Units

Variation in solar irradiance causes power generation fluctuations in solar power plants. Power grid operators need accurate irradiance forecasts to manage this variability. Many factors affect irradiance, including the time of year, weather and time of day. Cloud cover is one of the most important variables that affects solar power generation, but is also characterized by a high degree of variability and uncertainty. Deep learning methods have the ability to learn long-term dependencies within sequential data. We investigate the application of Gated Recurrent Units (GRU) to forecast solar irradiance and present the results of applying multivariate GRU to forecast hourly solar irradiance in Phoenix, Arizona. We compare and evaluate the performance of GRU against Long Short-Term Memory (LSTM) using strictly historical solar irradiance data as well as the addition of exogenous weather variables and cloud cover data. Based on our results, we found that the addition of exogenous weather variables and cloud cover data in both GRU and LSTM significantly improved forecasting accuracy, performing better than univariate and statistical models.

Data-Driven Load Forecasting of Air Conditioners for Demand Response Using Levenberg–Marquardt Algorithm-Based ANN

Air Conditioners (AC) impact in overall electricity consumption in buildings is very high. Therefore, controlling ACs power consumption is a significant factor for demand response. With the advancement in the area of demand side management techniques implementation and smart grid, precise AC load forecasting for electrical utilities and end-users is required. In this paper, big data analysis and its applications in power systems is introduced. After this, various load forecasting categories and various techniques applied for load forecasting in context of big data analysis in power systems have been explored. Then, Levenberg–Marquardt Algorithm (LMA)-based Artificial Neural Network (ANN) for residential AC short-term load forecasting is presented. This forecasting approach utilizes past hourly temperature observations and AC load as input variables for assessment. Different performance assessment indices have also been investigated. Error formulations have shown that LMA-based ANN presents better results in comparison to Scaled Conjugate Gradient (SCG) and statistical regression approach. Furthermore, information of AC load is obtainable for different time horizons like weekly, hourly, and monthly bases due to better prediction accuracy of LMA-based ANN, which is helpful for efficient demand response (DR) implementation.

Recurrent Neural Networks Based Photovoltaic Power Forecasting Approach

The intermittency of solar energy resources has brought a big challenge for the optimization and planning of a future smart grid. To reduce the intermittency, an accurate prediction of photovoltaic (PV) power generation is very important. Therefore, this paper proposes a new forecasting method based on the recurrent neural network (RNN). At first, the entire solar power time series data is divided into inter-day data and intra-day data. Then, we apply RNN to discover the nonlinear features and invariant structures exhibited in the adjacent days and intra-day data. After that, a new point prediction model is proposed, only by taking the previous PV power data as input without weather information. The forecasting horizons are set from 15 to 90 minutes. The proposed forecasting method is tested by using real solar power in Flanders, Belgium. The classical persistence method (Persistence), back propagation neural network (BPNN), radial basis function (RBF) neural network and support vector machine (SVM), and long short-term memory (LSTM) networks are adopted as benchmarks. Extensive results show that the proposed forecasting method exhibits a good forecasting quality on very short-term forecasting, which demonstrates the feasibility and effectiveness of the proposed forecasting model.

Development of a Two-Stage ESS-Scheduling Model for Cost Minimization Using Machine Learning-Based Load Prediction Techniques

Effective use of energy storage systems (ESS) is important to reduce unnecessary power consumption. In this paper, a day-ahead two-stage ESS-scheduling model based on the use of a machine learning technique for load prediction has been proposed for minimizing the operating cost of the energy system. The proposed algorithm consists of two stages of ESS. In the first stage, ESS is used to minimize demand charges by reducing the peak load. Then, the remaining capacity is used to reduce energy charges through arbitrage trading, thereby minimizing the total operating cost. To achieve this purpose, accurate load prediction is required. Machine learning techniques are promising methods owing to the ability to improve forecasting performance. Among them, ensemble learning is a well-known machine learning method which helps to reduce variance and prevent overfitting of a model. To predict loads, we employed bootstrap aggregating (bagging) or random forest technique-based decision trees after Holt–Winters smoothing for trends. Our combined method can increase the prediction accuracy. In the simulation conducted, three combined prediction models were evaluated. The prediction task was performed using the R programming language. The effectiveness of the proposed algorithm was verified by using Python’s PuLP library.

A Novel Adaptive Intelligent Ensemble Model for Forecasting Primary Energy Demand

Effectively forecasting energy demand and energy structure helps energy planning departments formulate energy development plans and react to the opportunities and challenges in changing energy demands. In view of the fact that the rolling grey model (RGM) can weaken the randomness of small samples and better present their characteristics, as well as support vector regression (SVR) having good generalization, we propose an ensemble model based on RGM and SVR. Then, the inertia weight of particle swarm optimization (PSO) is adjusted to improve the global search ability of PSO, and the improved PSO algorithm (APSO) is used to assign the adaptive weight to the ensemble model. Finally, in order to solve the problem of accurately predicting the time-series of primary energy consumption, an adaptive inertial weight ensemble model (APSO-RGM-SVR) based on RGM and SVR is constructed. The proposed model can show higher prediction accuracy and better generalization in theory. Experimental results also revealed outperformance of APSO-RGM-SVR compared to single models and unoptimized ensemble models by about 85% and 32%, respectively. In addition, this paper used this new model to forecast China’s primary energy demand and energy structure.

Short-Term Photovoltaic Power Output Prediction Based on k-Fold Cross-Validation and an Ensemble Model

Short-term photovoltaic power forecasting is of great significance for improving the operation of power systems and increasing the penetration of photovoltaic power. To improve the accuracy of short-term photovoltaic power forecasting, an ensemble-model-based short-term photovoltaic power prediction method is proposed. Firstly, the quartile method is used to process raw data, and the Pearson coefficient method is utilized to assess multiple features affecting the short-term photovoltaic power output. Secondly, the structure of the ensemble model is constructed, and a k-fold cross-validation method is used to train the submodels. The prediction results of each submodel are merged. Finally, the validity of the proposed approach is verified using an actual data set from State Power Investment Corporation Limited. The simulation results show that the quartile method can find outliers which contributes to processing the raw data and improving the accuracy of the model. The k-fold cross-validation method can effectively improve the generalization ability of the model, and the ensemble model can achieve higher prediction accuracy than a single model.

A Two-Step Approach to Solar Power Generation Prediction Based on Weather Data Using Machine Learning

Photovoltaic systems have become an important source of renewable energy generation. Because solar power generation is intrinsically highly dependent on weather fluctuations, predicting power generation using weather information has several economic benefits, including reliable operation planning and proactive power trading. This study builds a model that predicts the amounts of solar power generation using weather information provided by weather agencies. This study proposes a two-step modeling process that connects unannounced weather variables with announced weather forecasts. The empirical results show that this approach improves a base approach by wide margins, regardless of types of applied machine learning algorithms. The results also show that the random forest regression algorithm performs the best for this problem, achieving an R-squared value of 70.5% in the test data. The intermediate modeling process creates four variables, which are ranked with high importance in the post-analysis. The constructed model performs realistic one-day ahead predictions.

Using Smart Persistence and Random Forests to Predict Photovoltaic Energy Production

Solar energy forecasting is an active research problem and a key issue to increase the competitiveness of solar power plants in the energy market. However, using meteorological, production, or irradiance data from the past is not enough to produce accurate forecasts. This article aims to integrate a prediction algorithm (Smart Persistence), irradiance, and past production data, using a state-of-the-art machine learning technique (Random Forests). Three years of data from six solar PV modules at Faro (Portugal) are analyzed. A set of features that combines past data, predictions, averages, and variances is proposed for training and validation. The experimental results show that using Smart Persistence as a Machine Learning input greatly improves the accuracy of short-term forecasts, achieving an NRMSE of 0.25 on the best panels at short horizons and 0.33 on a 6 h horizon.

Sensorless PV Power Forecasting in Grid-Connected Buildings through Deep Learning

Existing works in photovoltaic (PV) power generation focus on accurately predicting the PV power output on a forecast horizon. As the solar power generation is heavily influenced by meteorological conditions such as solar radiation, the weather forecast is a critical input in the prediction performance. However, the weather forecast is traditionally considered to have coarse granularity, so many are compelled to use on-site meteorological sensors to complement it. However, the approach involving on-site sensors has several issues. First, it incurs the cost in the installation, operation, and management of the sensors. Second, the physical model of the sensor dynamics itself can be a source of forecast errors. Third, it requires an accumulation of sensory data that represent all seasonal variations, which takes time to collect. In this paper, we take an alternative approach to use a relatively large deep neural network (DNN) instead of the on-site sensors to cope with the coarse-grained weather forecast. With historical PV output power data from our grid-connected building with a rooftop PV power generation facility and the publicly available weather forecast history data, we demonstrate that we can train a six-layer feedforward DNN for the day-ahead forecast. It achieves the average mean absolute error (MAE) of 2.9%, comparable to that of the conventional model, but without involing the on-site sensors.