Ensemble incremental learning Random Vector Functional Link network for short-term electric load forecasting

Deep learning-driven hybrid model for short-term load forecasting and smart grid information management

Accurate power load forecasting is crucial for the sustainable operation of smart grids. However, the complexity and uncertainty of load, along with the large-scale and high-dimensional energy information, present challenges in handling intricate dynamic features and long-term dependencies. This paper proposes a computational approach to address these challenges in short-term power load forecasting and energy information management, with the goal of accurately predicting future load demand. The study introduces a hybrid method that combines multiple deep learning models, the Gated Recurrent Unit (GRU) is employed to capture long-term dependencies in time series data, while the Temporal Convolutional Network (TCN) efficiently learns patterns and features in load data. Additionally, the attention mechanism is incorporated to automatically focus on the input components most relevant to the load prediction task, further enhancing model performance. According to the experimental evaluation conducted on four public datasets, including GEFCom2014, the proposed algorithm outperforms the baseline models on various metrics such as prediction accuracy, efficiency, and stability. Notably, on the GEFCom2014 dataset, FLOP is reduced by over 48.8%, inference time is shortened by more than 46.7%, and MAPE is improved by 39%. The proposed method significantly enhances the reliability, stability, and cost-effectiveness of smart grids, which facilitates risk assessment optimization and operational planning under the context of information management for smart grid systems.

Industrial Process Monitoring Based on Dynamic Overcomplete Broad Learning Network

Most industrial processes feature high nonlinearity, non-Gaussianity, and time correlation. Models based on overcomplete broad learning system (OBLS) have been successfully applied in the fault monitoring realm, which may relatively deal with the nonlinear and non-Gaussian characteristics. However, these models barely take time correlation into full consideration, hindering the further improvement of the monitoring accuracy of the network. Therefore, an effective dynamic overcomplete broad learning system (DOBLS) based on matrix extension is proposed, which extends the raw data in the batch process with the idea of "time lag" in this article. Subsequently, the OBLS monitoring network is employed to continue the analysis of the extended dynamic input data. Finally, a monitoring model is established to tackle the coexistence of nonlinearity, non-Gaussianity, and time correlation in process data. To illustrate the superiority and feasibility, the proposed model is conducted on the penicillin fermentation simulation platform, the experimental result of which illustrates that the model can extract the feature of process data more comprehensively and be self-updated more efficiently. With shorter training time and higher monitoring accuracy, the proposed model can witness an improvement of average monitoring accuracy by 3.69% and 1.26% in 26 process fault types compared to the state-of-the-art fault monitoring methods BLS and OBLS, respectively.

Online dynamic ensemble deep random vector functional link neural network for forecasting

This paper proposes a three-stage online deep learning model for time series based on the ensemble deep random vector functional link (edRVFL). The edRVFL stacks multiple randomized layers to enhance the single-layer RVFL's representation ability. Each hidden layer's representation is utilized for training an output layer, and the ensemble of all output layers forms the edRVFL's output. However, the original edRVFL is not designed for online learning, and the randomized nature of the features is harmful to extracting meaningful temporal features. In order to address the limitations and extend the edRVFL to an online learning mode, this paper proposes a dynamic edRVFL consisting of three online components, the online decomposition, the online training, and the online dynamic ensemble. First, an online decomposition is utilized as a feature engineering block for the edRVFL. Then, an online learning algorithm is designed to learn the edRVFL. Finally, an online dynamic ensemble method, which can measure the change in the distribution, is proposed for aggregating all layers' outputs. This paper evaluates and compares the proposed model with state-of-the-art methods on sixteen time series.

An Evolutive Frequent Pattern Tree-based Incremental Knowledge Discovery Algorithm

To understand current situation in specific scenarios, valuable knowledge should be mined from both historical data and emerging new data. However, most existing algorithms take the historical data and the emerging data as a whole and periodically repeat to analyze all of them, which results in heavy computation overhead. It is also challenging to accurately discover new knowledge in time, because the emerging data are usually small compared to the historical data. To address these challenges, we propose a novel knowledge discovery algorithm based on double evolving frequent pattern trees that can trace the dynamically evolving data by an incremental sliding window. One tree is used to record frequent patterns from the historical data, and the other one records incremental frequent items. The structures of the double frequent pattern trees and their relationships are updated periodically according to the emerging data and a sliding window. New frequent patterns are mined from the incremental data and new knowledge can be obtained from pattern changes. Evaluations show that this algorithm can discover new knowledge from evolving data with good performance and high accuracy.

A Hybrid System Based on Dynamic Selection for Time Series Forecasting

Hybrid systems, which combine statistical and machine learning (ML) techniques using residual (error forecasting) modeling, have been highlighted in the literature due to their accuracy and ability to forecast time series with different characteristics. In these architectures, a crucial task is the proper modeling of the residuals since they may present random fluctuations, complex nonlinear patterns, and heteroscedastic behavior. Hence, the selection, specification, and training of one ML model to forecast the residuals are costly and challenging tasks since issues, such as underfitting, overfitting, and misspecification, can lead to a system with low accuracy or even deteriorate the linear forecast of the time series. This article proposes a hybrid system, named dynamic residual forecasting (DReF), that employs a modified dynamic selection (DS) algorithm to decide: the most suitable ML model to forecast a pattern of the residual series and if it is a promising candidate to increase the accuracy of the time series forecast from the linear combination. Thus, the DReF aims to reduce the uncertainty of the ML model selection and avoid the deterioration of the time series forecast. Furthermore, the proposed system searches for the most suitable parameters of the DS algorithm for each data set. In this article, the proposed method uses a pool of five ML models widely adopted in the literature: multilayer perceptron, support vector regression, radial basis function, long short-term memory, and convolutional neural network. An experimental evaluation was conducted using ten well-known time series. The results show that the DReF obtains superior results for the majority of the data sets compared with single and hybrid models of the literature.

A novel transfer deep learning model with reinforcement-learning-based hyperparameter optimization for short-term load forecasting during the COVID-19 pandemic

The coronavirus disease 2019 pandemic has significantly impacted the world. The sudden decline in electricity load demand caused by strict social distancing restrictions has made it difficult for traditional models to forecast the load demand during the pandemic. Therefore, in this study, a novel transfer deep learning model with reinforcement-learning-based hyperparameter optimization is proposed for short-term load forecasting during the pandemic. First, a knowledge base containing mobility data is constructed, which can reflect the changes in visitor volume in different regions and buildings based on mobile services. Therefore, the sudden decline in load can be analyzed according to the socioeconomic behavior changes during the pandemic. Furthermore, a new transfer deep learning model is proposed to address the problem of limited mobility data associated with the pandemic. Moreover, reinforcement learning is employed to optimize the hyperparameters of the proposed model automatically, which avoids the manual adjustment of the hyperparameters, thereby maximizing the forecasting accuracy. To enhance the hyperparameter optimization efficiency of the reinforcement-learning agents, a new advance forecasting method is proposed to forecast the state-action values of the state space that have not been traversed. The experimental results on 12 real-world datasets covering different countries and cities demonstrate that the proposed model achieves high forecasting accuracy during the coronavirus disease 2019 pandemic.

Color constancy with an optimized regularized random vector functional link based on an improved equilibrium optimizer

In order to improve the accuracy of illumination estimation, this paper proposes a color constancy algorithm based on an improved equilibrium optimizer (IEO) to optimize the network structure parameters and common parameters of the regularized random vector functional link (RRVFL) at the same time. First, the initial search agent (population) of the equilibrium optimizer algorithm is generated through opposition-based learning, and the particles (individuals in the population) of the search agent are updated using the IEO algorithm. Compared with the completely randomly generated search agent, the method of initializing the search agent through the IEO algorithm has a better convergence effect. Then, each segment of the search agent is mapped to the corresponding parameters of the RRVFL, and the effective input weight and hidden layer bias are selected according to the node activation to generate the network structure, which can realize the simultaneous optimization of hyperparameters and common parameters. Finally, by calculating the output weight, the light source color prediction of the image under unknown illumination is performed, and the image is corrected. Comparison experiments show that the IEO-RRVFL color constancy algorithm proposed in this paper has higher accuracy and better stability than other comparison algorithms.

Random vector functional link with ε-insensitive Huber loss function for biomedical data classification

BACKGROUND AND OBJECTIVE

Biomedical data classification has been a trending topic among researchers during the last decade. Biomedical datasets may contain several features noises. Hence, the conventional machine learning model cannot efficiently handle the presence of noise in datasets. Among the several machine learning model, the random vector functional link (RVFL) is one of the most popular and efficient models for task related to both classification and regression. Despite its excellent classification performance, its performance degrades while dealing with the datasets with noise. Researchers are searching for powerful models to minimize the influence of noise in datasets. Therefore, to enhance the classification ability of RVFL on noisy datasets, this paper suggests a novel random vector functional link with ε-insensitive Huber loss function (ε-HRVFL) for biomedical data classification problems.

METHODS

The optimization problem of ε-HRVFL is reformulated as strongly convex minimization problems with a simple function iterative approach to find solutions. To have a better understanding of the scope of the biomedical data classification problem and potential solutions, we conducted experiments with three different types of label noise in biomedical datasets as well as a few non-biomedical datasets. The classification accuracy of the proposed ε-HRVFL model is compared statistically using Friedman test with the support vector machine, extreme learning machine with radial basis function (RBF) and sigmoid activation functions and RVFL with RBF and sigmoid activation functions.

RESULTS

For non-biomedical datasets, the proposed model showed the highest accuracy of 98.1332%. Moreover, for the biomedical datasets, the proposed model showed the best accuracy of 96.5229%. The proposed ε-HRVFL model with sigmoid activation function reveals the best mean ranks among the reported classifiers for both, biomedical and non-biomedical datasets.

CONCLUSION

Numerical results show the applicability of the proposed ε-HRVFL model. In future, the proposed ε-HRVFL can be developed to solve multiclass biomedical data classification problems. Moreover, ε-insensitive asymmetric Huber loss function based RVFL model can be developed for dealing more efficiently with these noisy biomedical datasets.

Ensemble system for short term carbon dioxide emissions forecasting based on multi-objective tangent search algorithm

Carbon emissions play a crucial role in inducing global warming and climate change. Accurate and stable carbon emissions forecasting is beneficial for formulating emissions reduction schemes and achieving carbon neutrality as early as possible. Although previous studies have concentrated on employing one or several methods for carbon emissions forecasting, the improvement in forecasting performance is limited because they ignore the importance of objectively selecting the models and the necessity of interval forecasting. In this paper, a novel ensemble prediction system, composed of data decomposition, model selection, phase space reconstruction, ensemble point prediction, and interval prediction, is proposed to conduct both point and interval predictions, which has been proven to be effective in prompting carbon emissions forecasting accuracy and stability. According to the empirical results, the mean MAPE results of our proposed forecasting strategy in point prediction are 1.1102% (in Dataset A) and 1.1382% (in Dataset B), and the mean CWC values in the interval forecasting are 0.3512 and 0.1572, respectively. Thus, the proposed forecasting system improves the forecasting performance relative to other models considerably, which can provide meaningful references for policymakers.

Modeling Energy Demand—A Systematic Literature Review

In this article, a systematic literature review of 419 articles on energy demand modeling, published between 2015 and 2020, is presented. This provides researchers with an exhaustive overview of the examined literature and classification of techniques for energy demand modeling. Unlike in existing literature reviews, in this comprehensive study all of the following aspects of energy demand models are analyzed: techniques, prediction accuracy, inputs, energy carrier, sector, temporal horizon, and spatial granularity. Readers benefit from easy access to a broad literature base and find decision support when choosing suitable data-model combinations for their projects. Results have been compiled in comprehensive figures and tables, providing a structured summary of the literature, and containing direct references to the analyzed articles. Drawbacks of techniques are discussed as well as countermeasures. The results show that among the articles, machine learning (ML) techniques are used the most, are mainly applied to short-term electricity forecasting on a regional level and rely on historic load as their main data source. Engineering-based models are less dependent on historic load data and cover appliance consumption on long temporal horizons. Metaheuristic and uncertainty techniques are often used in hybrid models. Statistical techniques are frequently used for energy demand modeling as well and often serve as benchmarks for other techniques. Among the articles, the accuracy measured by mean average percentage error (MAPE) proved to be on similar levels for all techniques. This review eases the reader into the subject matter by presenting the emphases that have been made in the current literature, suggesting future research directions, and providing the basis for quantitative testing of hypotheses regarding applicability and dominance of specific methods for sub-categories of demand modeling.

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.

Day-Ahead Electric Load Forecast for a Ghanaian Health Facility Using Different Algorithms

Ghana suffers from frequent power outages, which can be compensated by off-grid energy solutions. Photovoltaic-hybrid systems become more and more important for rural electrification due to their potential to offer a clean and cost-effective energy supply. However, uncertainties related to the prediction of electrical loads and solar irradiance result in inefficient system control and can lead to an unstable electricity supply, which is vital for the high reliability required for applications within the health sector. Model predictive control (MPC) algorithms present a viable option to tackle those uncertainties compared to rule-based methods, but strongly rely on the quality of the forecasts. This study tests and evaluates (a) a seasonal autoregressive integrated moving average (SARIMA) algorithm, (b) an incremental linear regression (ILR) algorithm, (c) a long short-term memory (LSTM) model, and (d) a customized statistical approach for electrical load forecasting on real load data of a Ghanaian health facility, considering initially limited knowledge of load and pattern changes through the implementation of incremental learning. The correlation of the electrical load with exogenous variables was determined to map out possible enhancements within the algorithms. Results show that all algorithms show high accuracies with a median normalized root mean square error (nRMSE) <0.1 and differing robustness towards load-shifting events, gradients, and noise. While the SARIMA algorithm and the linear regression model show extreme error outliers of nRMSE >1, methods via the LSTM model and the customized statistical approaches perform better with a median nRMSE of 0.061 and stable error distribution with a maximum nRMSE of <0.255. The conclusion of this study is a favoring towards the LSTM model and the statistical approach, with regard to MPC applications within photovoltaic-hybrid system solutions in the Ghanaian health sector.

An unsupervised parameter learning model for RVFL neural network

With the direct input-output connections, a random vector functional link (RVFL) network is a simple and effective learning algorithm for single-hidden layer feedforward neural networks (SLFNs). RVFL is a universal approximator for continuous functions on compact sets with fast learning property. Owing to its simplicity and effectiveness, RVFL has attracted significant interest in numerous real-world applications. In reality, the performance of RVFL is often challenged by randomly assigned network parameters. In this paper, we propose a novel unsupervised network parameter learning method for RVFL, named sparse pre-trained random vector functional link (SP-RVFL for short) network. The proposed SP-RVFL uses a sparse autoencoder with ℓ₁-norm regularization to adaptively learn superior network parameters for specific learning tasks. By doing so, the learned network parameters in SP-RVFL are embedded with the valuable information of input data, which alleviate the randomly generated parameter issue and improve the algorithmic performance. Experiments and comparisons on 16 diverse benchmarks from different domains confirm the effectiveness of the proposed SP-RVFL. The corresponding results also demonstrate that RVFL outperforms extreme learning machine (ELM).