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

Short-term photovoltaic energy generation for solar powered high efficiency irrigation systems using LSTM with Spatio-temporal attention mechanism

Solar irrigation systems should become more practical and efficient as technology advances. Automation and AI-based technologies can optimize solar energy use for irrigation while reducing environmental impacts and costs. These innovations have the potential to make agriculture more environmentally friendly and sustainable. Solar irrigation system implementation can be hampered by a lack of technical expertise in installation, operation, and maintenance. It must be technically and economically feasible to be practical and continuous. Due to weather and solar irradiation, photovoltaic power generation is difficult for high-efficiency irrigation systems. As a result, more precise photovoltaic output calculations could improve solar power systems. Customers should benefit from increased power plant versatility and high-quality electricity. As a result, an artificial intelligence-powered automated irrigation power-generation system may improve the existing efficiency. To predict high-efficiency irrigation system power outputs, this study proposed a spatial and temporal attention block-based long-short-term memory (LSTM) model. Using MSE, RMSE, and MAE, the results have been compared to pre-existing ML and a simple LSTM network. Moreover, it has been found that our model outperformed cutting-edge methods. MAPE was improved by 6-7% by increasing Look Back (LB) and Look Forward (LF). Future goals include adapting the technology for wind power production and improving the proposed model to harness customer behavior to improve forecasting accuracy.

Intelligent Eye-Controlled Electric Wheelchair Based on Estimating Visual Intentions Using One-Dimensional Convolutional Neural Network and Long Short-Term Memory

When an electric wheelchair is operated using gaze motion, eye movements such as checking the environment and observing objects are also incorrectly recognized as input operations. This phenomenon is called the "Midas touch problem", and classifying visual intentions is extremely important. In this paper, we develop a deep learning model that estimates the user's visual intention in real time and an electric wheelchair control system that combines intention estimation and the gaze dwell time method. The proposed model consists of a 1DCNN-LSTM that estimates visual intention from feature vectors of 10 variables, such as eye movement, head movement, and distance to the fixation point. The evaluation experiments classifying four types of visual intentions show that the proposed model has the highest accuracy compared to other models. In addition, the results of the driving experiments of the electric wheelchair implementing the proposed model show that the user's efforts to operate the wheelchair are reduced and that the operability of the wheelchair is improved compared to the traditional method. From these results, we concluded that visual intentions could be more accurately estimated by learning time series patterns from eye and head movement data.

A Review on Machine Learning Applications for Solar Plants

A solar plant system has complex nonlinear dynamics with uncertainties due to variations in system parameters and insolation. Thereby, it is difficult to approximate these complex dynamics with conventional algorithms whereas Machine Learning (ML) methods yield the essential performance required. ML models are key units in recent sensor systems for solar plant design, forecasting, maintenance, and control to provide the best safety, reliability, robustness, and performance as compared to classical methods which are usually employed in the hardware and software of solar plants. Considering this, the goal of our paper is to explore and analyze ML technologies and their advantages and shortcomings as compared to classical methods for the design, forecasting, maintenance, and control of solar plants. In contrast with other review articles, our research briefly summarizes our intelligent, self-adaptive models for sizing, forecasting, maintenance, and control of a solar plant; sets benchmarks for performance comparison of the reviewed ML models for a solar plant's system; proposes a simple but effective integration scheme of an ML sensor solar plant system's implementation and outlines its future digital transformation into a smart solar plant based on the integrated cutting-edge technologies; and estimates the impact of ML technologies based on the proposed scheme on a solar plant value chain.

Reduction of the Risk of Inaccurate Prediction of Electricity Generation from PV Farms Using Machine Learning

Problems with inaccurate prediction of electricity generation from photovoltaic (PV) farms cause severe operational, technical, and financial risks, which seriously affect both their owners and grid operators. Proper prediction results are required for optimal planning the spinning reserve as well as managing inertia and frequency response in the case of contingency events. In this work, the impact of a number of meteorological parameters on PV electricity generation in Poland was analyzed using the Pearson coefficient. Furthermore, seven machine learning models using Lasso Regression, K–Nearest Neighbours Regression, Support Vector Regression, AdaBoosted Regression Tree, Gradient Boosted Regression Tree, Random Forest Regression, and Artificial Neural Network were developed to predict electricity generation from a 0.7 MW solar PV power plant in Poland. The models were evaluated using determination coefficient (R2), the mean absolute error (MAE), and root mean square error (RMSE). It was found out that horizontal global irradiation and water saturation deficit have a strong proportional relationship with the electricity generation from PV systems. All proposed machine learning models turned out to perform well in predicting electricity generation from the analyzed PV farm. Random Forest Regression was the most reliable and accurate model, as it received the highest R2 (0.94) and the lowest MAE (15.12 kWh) and RMSE (34.59 kWh).

Predicting Energy Consumption Using LSTM, Multi-Layer GRU and Drop-GRU Neural Networks

With the steep rise in the development of smart grids and the current advancement in developing measuring infrastructure, short term power consumption forecasting has recently gained increasing attention. In fact, the prediction of future power loads turns out to be a key issue to avoid energy wastage and to build effective power management strategies. Furthermore, energy consumption information can be considered historical time series data that are required to extract all meaningful knowledge and then forecast the future consumption. In this work, we aim to model and to compare three different machine learning algorithms in making a time series power forecast. The proposed models are the Long Short-Term Memory (LSTM), the Gated Recurrent Unit (GRU) and the Drop-GRU. We are going to use the power consumption data as our time series dataset and make predictions accordingly. The LSTM neural network has been favored in this work to predict the future load consumption and prevent consumption peaks. To provide a comprehensive evaluation of this method, we have performed several experiments using real data power consumption in some French cities. Experimental results on various time horizons show that the LSTM model produces a better result than the GRU and the Drop-GRU forecasting methods. There are fewer prediction errors and its precision is finer. Therefore, these predictions based on the LSTM method will allow us to make decisions in advance and trigger load shedding in cases where consumption exceeds the authorized threshold. This will have a significant impact on planning the power quality and the maintenance of power equipment.

Time-series analysis with smoothed Convolutional Neural Network

CNN originates from image processing and is not commonly known as a forecasting technique in time-series analysis which depends on the quality of input data. One of the methods to improve the quality is by smoothing the data. This study introduces a novel hybrid exponential smoothing using CNN called Smoothed-CNN (S-CNN). The method of combining tactics outperforms the majority of individual solutions in forecasting. The S-CNN was compared with the original CNN method and other forecasting methods such as Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM). The dataset is a year time-series of daily website visitors. Since there are no special rules for using the number of hidden layers, the Lucas number was used. The results show that S-CNN is better than MLP and LSTM, with the best MSE of 0.012147693 using 76 hidden layers at 80%:20% data composition.

Virtual Power Plant Optimization in Smart Grids: A Narrative Review

Virtual power plants (VPPs) are promising solutions to address the decarbonization and energy efficiency goals in the smart energy grid. They assume the coordination of local energy resources such as energy generation, storage, and consumption. They are used to tackle problems brought by the stochastic nature of renewable energy, lack of energy storage devices, or insufficient local energy flexibility on the demand side. VPP modeling, management, and optimization are open to research problems that should consider, on one side, the local constraints in the operation of the energy resources and power flows and the energy grid’s sustainability objectives on the other side. There are multiple goals to create a VPP, such as to deliver energy services on a market or to the grid operator, to operate a microgrid in autonomy decoupled from the main grid, or to sustain local energy communities. In this paper, we present the results of a narrative review carried out on the domain of VPP optimization for the local energy grid integration. We have defined a search strategy that considers highly rated international databases (i.e., Elsevier, IEEE, and MDPI) in a six-year timeframe and applied objective inclusion/exclusion criteria for selecting articles and publications for the review; 95 articles have been analyzed and classified according to their objectives and solutions proposed for optimizing VPP integration in smart grids. The results of the study show that VPP concepts and applications are well addressed in the research literature, however, there is still work to be done on: engaging prosumers and citizens in such a virtual organization, developing heuristics to consider a wider range of local and global constraints and non-energy vectors, and to decentralize and make transparent the services delivery and financial settlement towards community members. This study can help researchers to understand the current directions for VPP integration in smart grids. As a next step we plan to further analyze the open research directions related to this problem and target the development of innovative solutions to allow the integration of multi-energy assets and management of cross energy sector services in energy communities.

Solar Irradiance Forecasting to Short-Term PV Power: Accuracy Comparison of ANN and LSTM Models

The use of renewable energies, such as Photovoltaic (PV) solar power, is necessary to meet the growing energy consumption. PV solar power generation has intrinsic characteristics related to the climatic variables that cause intermittence during the generation process, promoting instabilities and insecurity in the electrical system. One of the solutions for this problem uses methods for the Prediction of Solar Photovoltaic Power Generation (PSPPG). In this context, the aim of this study is to develop and compare the prediction accuracy of solar irradiance between Artificial Neural Network (ANN) and Long-Term Short Memory (LSTM) network models, from a comprehensive analysis that simultaneously considers two distinct sets of exogenous meteorological input variables and three short-term prediction horizons (1, 15 and 60 min), in a controlled experimental environment. The results indicate that there is a significant difference (p < 0.001) in the prediction accuracy between the ANN and LSTM models, with better overall prediction accuracy skill for the LSTM models (MAPE = 19.5%), except for the 60 min prediction horizon. Furthermore, the accuracy difference between the ANN and LSTM models decreased as the prediction horizon increased, and no significant influence was observed on the accuracy of the prediction with both sets of evaluated meteorological input variables.

A Comparison of the Performance of Supervised Learning Algorithms for Solar Power Prediction

Science seeks strategies to mitigate global warming and reduce the negative impacts of the long-term use of fossil fuels for power generation. In this sense, implementing and promoting renewable energy in different ways becomes one of the most effective solutions. The inaccuracy in the prediction of power generation from photovoltaic (PV) systems is a significant concern for the planning and operational stages of interconnected electric networks and the promotion of large-scale PV installations. This study proposes the use of Machine Learning techniques to model the photovoltaic power production for a system in Medellín, Colombia. Four forecasting models were generated from techniques compatible with Machine Learning and Artificial Intelligence methods: K-Nearest Neighbors (KNN), Linear Regression (LR), Artificial Neural Networks (ANN) and Support Vector Machines (SVM). The results obtained indicate that the four methods produced adequate estimations of photovoltaic energy generation. However, the best estimate according to RMSE and MAE is the ANN forecasting model. The proposed Machine Learning-based models were demonstrated to be practical and effective solutions to forecast PV power generation in Medellin.

A Deep Learning Approach for Peak Load Forecasting: A Case Study on Panama

Predicting the future peak demand growth becomes increasingly important as more consumer loads and electric vehicles (EVs) start connecting to the grid. Accurate forecasts will enable energy suppliers to meet demand more reliably. However, this is a challenging problem since the peak demand is very nonlinear. This study addresses the research question of how deep learning methods, such as convolutional neural networks (CNNs) and long-short term memory (LSTM) can provide better support to these areas. The goal is to build a suitable forecasting model that can accurately predict the peak demand. Several data from 2004 to 2019 was collected from Panama’s power system to validate this study. Input features such as residential consumption and monthly economic index were considered for predicting peak demand. First, we introduced three different CNN architectures which were multivariate CNN, multivariate CNN-LSTM and multihead CNN. These were then benchmarked against LSTM. We found that the CNNs outperformed LSTM, with the multivariate CNN being the best performing model. To validate our initial findings, we then evaluated the robustness of the models against Gaussian noise. We demonstrated that CNNs were far more superior than LSTM and can support spatial-temporal time series data.

Leveraging Label Information in a Knowledge-Driven Approach for Rolling-Element Bearings Remaining Useful Life Prediction

Since bearing deterioration patterns are difficult to collect from real, long lifetime scenarios, data-driven research has been directed towards recovering them by imposing accelerated life tests. Consequently, insufficiently recovered features due to rapid damage propagation seem more likely to lead to poorly generalized learning machines. Knowledge-driven learning comes as a solution by providing prior assumptions from transfer learning. Likewise, the absence of true labels was able to create inconsistency related problems between samples, and teacher-given label behaviors led to more ill-posed predictors. Therefore, in an attempt to overcome the incomplete, unlabeled data drawbacks, a new autoencoder has been designed as an additional source that could correlate inputs and labels by exploiting label information in a completely unsupervised learning scheme. Additionally, its stacked denoising version seems to more robustly be able to recover them for new unseen data. Due to the non-stationary and sequentially driven nature of samples, recovered representations have been fed into a transfer learning, convolutional, long–short-term memory neural network for further meaningful learning representations. The assessment procedures were benchmarked against recent methods under different training datasets. The obtained results led to more efficiency confirming the strength of the new learning path.