As technology advances, so does the demand for electric power, steadily increasing over time. To ensure uninterrupted access to electricity round the clock, it’s imperative for generation facilities to synchronize with consumers’ evolving demands. Demand forecasting emerges as the key solution to avert any potential energy crises. In our latest endeavor, we’ve harnessed the power of artificial neural networks for precise electric demand forecasting. By leveraging data from an electric substation in Telangana, India, we’ve meticulously compared the performance of various neural network architectures. Through rigorous evaluation using metrics like MSE, RMSE, and MAPE, we’ve demonstrated the efficacy of our proposed support vector machine (SVM) approach. Our results unequivocally highlight that our SVM model stands out, delivering highly accurate forecasts for electric load demand.

Extreme weather events can cause power outages anywhere, but quite extensively along the U.S. southeastern coastline. Accurate outage prediction before a hurricane landfall is essential for reducing the impacts from distribution outage management and restoration planning perspectives. An outage prediction model (OPM) is developed to predict outages associated with substations based on data collated from multiple sources using tree-based ensemble machine learning regression algorithm. For this study, publicly available data as well as actual outage data from a major utility in the U.S. are employed. Performance validation of outage prediction models is done using several extreme weather events data over the past decade. Results confirm enhancement in accuracy for power outage predictions over baseline approaches.

Precise wind speed prediction is crucial for the management of the wind power generation systems. However, the stochastic nature of the wind speed makes optimal interval prediction very complicated. In this paper, a hybrid approach consisting of improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), temporal convolutional network with attention mechanism (ATCN), and bidirectional long short-term memory network (Bi-LSTM) is proposed for wind speed interval prediction (WSIP). First, ICEEMDAN is used to pre-process the raw data by decomposing the wind signal to several intrinsic mode functions. ATCN is used to reduce the uncertainty from the denoised data and extract the important temporal and spatial characteristics. Then, Bi-LSTM is used to forecast the high-quality intervals for the wind speed. Existing approaches observe a decline in the forecasting performance when the time ahead increases. As a result, the hybrid approach is evaluated using 5-min, 10-min, and 30-min ahead WSIP. To evaluate the novelty of the proposed approach, an experiment is conducted utilising wind speed data from the Garden City, Manhattan wind farm. The experimental results demonstrate that the proposed framework outperformed the comparison models with percentage improvements of 36%, 47%, and 17% for 5-min, 10-min, and 30-min ahead WSIP.

Wind energy generation, which has significant economic, social, and environmental benefits, requires accurate wind speed prediction. Due to the unpredictability and intermittency of wind, a robust methodology is essential for forecasting precise wind speeds. Addressing the challenges, this research proposes a hybrid and novel approach for accurate wind speed forecasting. The proposed method is split into data decomposition using robust complete ensemble empirical mode decomposition with adaptive noise, and wind speed prediction using adversarial approach. In the wind speed prediction, two robust forecasting models, convolutional neural network, and long short-term memory are adopted and trained in adversarial manner to enhance the prediction of wind speed. Long short term memory network functions as the generator which predicts the wind speed effectively for 1 h ahead wind speed prediction. Convolutional neural network model acts as a discriminator which enhances the forecasting performance of the generator. Various performance metrics are adopted to examine the performance of the proposed approach for 1 h ahead prediction, and the metrics are also compared to eight reference wind speed prediction models. The experimental findings demonstrate that the proposed adversarial hybrid model improved 25

This article discusses metaheuristic algorithms for optimizing controller gains for dynamic voltage restorers (DVRs) that use an impedance control strategy to compensate for unbalance in source voltages, voltage harmonics, and sag/swell in source voltages. The gains of the proportional‐integral (PI) controllers become critical for proper DVR load voltage extraction. Various techniques for optimization, such as whale optimization technique, gray wolf optimization technique, particle swarm optimization technique, and ant lion optimization technique, are used to obtain DC and AC PI controller gains for DVR. The impedance control strategy employs simple calculations to determine the resistance and reactance of a polluted source voltage, without the use of frame conversions as in synchronous reference theory, instantaneous reference power theory, and so on. The quick calculations of the impedance control scheme improve the power quality and dynamics. The Metaheuristic algorithms are used to calculate the number of iterations required to achieve the best possible controller gains, which further helps to improve power quality and dynamics. Among these optimization techniques, the antlion optimization technique provides fast convergence and the best possible controller gain values to improve the dynamics of the dc‐link voltage of voltage source converter and terminal voltage, thereby improving power quality. The proposed antlion optimization technique‐based DVR model is simulated in MATLAB R2019, and the results are validated with RT‐LAB.

In the last few decades, extreme weather events (EWEs) have become more frequent, especially in the southeastern part of the U.S. These EWEs affect the distribution grid greatly, resulting in long-duration power outages. To fully understand the outcomes of these catastrophic events and to correlate the impact on the reliability and resiliency of the utility company, multiple years of historical EWE-related outage data collected from a utility company are analyzed. Moreover, this study utilizes the System Average Interruption Duration Index (SAIDI) matrix to analyze the EWEs. This study finds overgrown vegetation as one of the main reasons for outages during EWEs. Besides, loss of transmission and generation also contribute significantly to outage events resulting in a high percentage of customers being affected for long periods.

Distribution system resilience enhancement is an important topic to ensure customers have access to power supply during extreme events. In fact, certain weather-related extreme events can be predicted ahead of time. Therefore, it is important to investigate how to predict grid outages using extreme weather forecasts, and how outage predictions can be incorporated into distribution system resilience enhancement. In this paper, a preventative scheduling model for distribution systems is proposed. The model targets at allocating resources, especially mobile responsive resources such as mobile backup generators and mobile energy storage systems, to prepare for an extreme event in the day-ahead context. To achieve efficient resource allocation and scheduling, a machine learning-based outage prediction module is developed to predict vulnerable or risky segments of the distribution system based on historical operating records and extreme weather event forecast. By integrating the outage prediction results into the scheduling model, optimal resource allocation can be derived to help distribution systems prepare for an upcoming event and improve resilience performance. A real distribution feeder in North Carolina, U.S. is used in the case study to validate the proposed approach.

To lower the risk of the electricity system from wind power uncertainties, accurate wind speed forecasting (WSF) is essential. However, the complex fluctuating properties of wind speed series make it challenging to get accurate results in wind speed prediction. Hence, this paper proposes a hybrid approach using complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and a robust attention mechanism based informer model for WSF. First, CEEMDAN is used to decompose raw wind speed data into a set of intrinsic mode functions to produce a new denoised signal. Then, the informer model extracts the dynamic characteristics of the denoised signals and predicts the wind speed. The 5-minute wind speed data from two wind farms located at Block island, Rhode Island State and Gulf Coast, Texas State are used to evaluate the proposed approach’s effectiveness. The proposed approach’s performance is compared using eight robust models and assessed through different performance indices. From the two case studies, the proposed approach outperforms the second-best WSF method by 56%, and 78%, respectively.

Accurate wind speed prediction is essential for optimal operation and planning. The unstable and stochastic nature of the wind makes the task complicated and challenging. As a result, a hybrid approach is implemented to enhance prediction accuracy and to overcome the difficulties and challenges in uncertainty modelling. Encoder and decoder are the two parts of the proposed hybrid model. In this study, a one-dimensional convolutional neural network (1D-CNN) is used as the encoder, and a bidirectional long short term memory network (Bi-LSTM) is used as the decoder. Encoder extracts the important characteristics and forms a latent representation. Then, wind speed is predicted by the decoder network by interpreting the characteristics of the encoded representation. The hybrid approach is validated using several regular and widely used benchmark forecasting models to assess and examine its prediction performance. The prediction results using the real-time dataset obtained from a wind measuring station in Idalia, Colorado are used for performance evaluation. The performance validation analysis showed that the proposed hybrid approach has an improvement of 42% over the reference approaches.

An accurate wind speed prediction is a fundamental prerequisite for enhanced wind energy integration with grid. Existing forecasting models are trained on the wind speed data. And these models rely on global accuracy without considering local variation of wind. Due to the local variation of wind, performance of each model varies for every time-step. As a result, this paper implements a robust and novel hybrid framework i.e. online model selection using Q-learning (OMS-QL) provided forecasting model pool (FMP). The proposed framework is the first model developed for online selection of best forecasting model dynamically using reinforcement learning (RL) approach. The proposed framework is mainly clustered into two parts: FMP, and Q-learning agent for online model selection. First, FMP is constructed using nine robust approaches, which are trained on the wind speed data. Then, Q-learning agent is developed to dynamically select the best prediction approach at every time-step for improved accuracy. Two experiments are conducted using the real-time wind speed datasets. Experimental results indicate that the proposed OMS-QL framework improved by 47% and 48% in both case studies compared to benchmark models.

Wind speed forecasting (WSF) is a viable option for increasing energy consumption efficiency. Previous forecasting methods rely on global accuracy, and the performance of these models changes with each time step due to local variations in wind characteristics, which is not ideal. Considering this problem, a novel dynamic selection of the best model (DSM) approach using reinforcement learning (RL) is proposed based on-policy state action reward state action (SARSA) for improved wind speed forecasting. DSM is defined as an RL problem and solved with an on-policy SARSA agent. The proposed approach is divided into a forecasting pool of models (FPM) and a learning agent, respectively. FPM comprises five robust forecasting approaches that have been trained and tuned. These models perform the WSF individually, and the SARSA agent is developed to perform the DSM for each step. The proposed approach is evaluated for 1 h ahead (1HA) WSF using two real-time wind speed datasets from Garden City, Manhattan, and Idalia, Colorado. This study provides a thorough examination of the proposed approach performance with an off-policy Q-learning algorithm for the DSM (QL-DSM). Compared to FPM's models, the proposed SARSA-DSM approach enhanced prediction accuracy by 24.27% and 39.73% in two case studies. The proposed approach also improves 14.57% and 30.25% over the QL-DSM.

Wind speed forecasting is required for better wind energy grid integration. Predicting wind speed becomes difficult due to the stochastic nature of the wind. So, this study implemented a hybrid forecasting framework using the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) based convolutional bidirectional long short-term memory (Bi-LSTM) autoencoder for wind speed forecasting (WSF). ICEEMDAN is used for eliminating residual auxiliary noise of the raw wind speed data. Then, a convolutional network encodes the optimal features from the denoised data and the Bi-LSTM decoder interprets the encoded representation to forecast the wind speed effectively. Existing benchmark approaches fail to provide consistency for the different time horizons, addressing this, the proposed framework is tested using 5-min, 10-min and 30min ahead wind speed data. Two experiments have been performed utilizing data from wind farms in Idalia and Garden city to evaluate the novelty and proposed framework's performance. The experimental results of the proposed framework are compared with seven different state-of-the-art models. The proposed approach is evaluated using various performance metrics and the results of experiments I and II demonstrate that the proposed hybrid method outperformed the state-of-the-art WSF models by 21% and 48%, respectively.

Accurate wind speed forecasting is a precondition for improving grid integration of wind energy. High-dimensional input is required for wind speed prediction models to deliver reliable results. However, owing to the failure of data measuring instruments, the process of obtaining wind speed data encounters various problems. Missing data must be imputed, and dynamic properties must be interpreted accurately in order to forecast successfully. Addressing these, in this study, hybrid forecasting approach using generative adversarial network (GAN) and temporal convolutional network based gated recurrent unit (TCN-GRU) for 5-min, 10-min and 30-min ahead missing value imputation and wind speed forecasting is proposed. TCN is utilized for the feature extraction and GRU forecasts the wind speed. To prove the novelty and performance of the proposed approach, experiments are conducted using data acquired from wind farms located in Bend, and Idalia. The results of the two experiments are compared with robust approaches for imputation as well as forecasting. The proposed hybrid approach is assessed using different performance metrics, and experimental results reveal that the proposed approach's performance for the imputation is improved by 30% and 37% and WSF is improved by 45%, 37% respectively in the two experiments.

Wind energy is a clean, green energy source that is used effectively in power system grids. Wind forecasting is the key requirement for enhanced integration. Wind speed forecasting is more challenging due to the unpredictable and intermittent nature of the wind. As a result, a robust and novel frame-work is proposed by hybridizing complete ensemble empirical decomposition with adaptive noise (CEEMDAN), convolutional neural network (CNN), and support vector machine (SVM). The CEEMDAN algorithm is used to remove noise from the raw data. Then, to extract the dominating characteristics from the noiseless wind speed data, CNN is used. Finally, SVM forecasts the wind speed. The hybridization of CNN and SVM enhanced the computational efficiency as well as the performance. For comparative analysis, six different state-of-the-art forecasting approaches are employed. An experimental study is carried out utilising real-time 5-minute interval data obtained from Manhattan's Garden City. The proposed framework performance is assessed through various statistical metrics. With relatively low error metrics and higher R2 score, the proposed framework outperformed all other comparative models, according to the experimental results.

Accurate wind speed prediction is a essential for enhanced wind energy integration with grid. A hybrid forecasting model is implemented to improve prediction accuracy. Decomposition technique is utilized to separate the input training wind speed data into intrinsic mode functions (IMFs). Deep neural network is used for the feature learning from each sub-series signal. Thus, the developed approach is tested with National Institute of Wind Energy (NIWE) dataset. Experimental evaluation in terms of statistical indices confirms that proposed hybrid model outperforms the existing benchmark approaches.

The main purpose of this paper is to develop an efficient machine learning model to estimate the electric power load. The developed machine learning model can be used by electric power utilities for proper operation and maintenance of grid and also to trade electricity effectively in energy market. This paper proposes a machine learning model using gated recurrent unit (GRU) and random forest (RF). GRU has been employed to predict the electric power load, whereas RF has been used to reduce the input dimensions of the model. GRU has been estimating the load with good accuracy. RF reduces the input dimensions of the GRU that leads lightweight GRU model. The main benefits of the lightweight GRU models are less computation time and memory space. However, lightweight GRU models will loss small amount of accuracy comparing to the original GRU model. GRU along with RF has been used for the first for short load forecasting. All the machine learning model’s performance has been observed in stochastic environment. Impact of weekends on load forecasting also observed by considering the last 3-week load data.

A precise forecast of wind speed is a fundamental requirement of wind power integration. The nonlinear and intermittent nature of the wind makes wind speed forecasting (WSF) complicated for linear approaches. Addressing the complications faced by the linear approaches, this paper proposed a novel and robust approach using long short-term memory (LSTM) autoencoder, convolutional neural network (CNN), and LSTM model for enhanced WSF. The proposed hybrid approach is divided into two main components: feature encoding, dimensionality reduction using LSTM autoencoder and forecasting using convolutional LSTM. In the first stage, the LSTM autoencoder eliminates the uncertainties present in raw wind speed data and also reduces the computational load on the forecasting convolutional LSTM approach. Then, in the second stage, CNN is used to extract the optimum features, and the LSTM network is used to forecast the wind speed. Five different benchmark forecasting models are used to evaluate and study the proposed hybrid approach's performance. The experiment is performed with real-time wind speed data from the Garden city wind farm, USA. The proposed hybrid approach performance is verified using various performance metrics. The experimental results demonstrate that the proposed approach improved by 40% over the second best benchmark forecasting approach.

Wind prediction is a significant prerequisite for look-ahead economic load dispatch. Wind speed data is normally exhibiting wide uncertainty nature. Evaluation of this wind data must be accurate to reduce the dangers of system operations. To address this problem, the hybrid approach is developed using long short-term memory (LSTM) network and ensemble empirical mode decomposition (EEMD). This decomposition technique is utilized to divide training data into distinct subseries. The features of uncertainty involved in each sub-series are extracted and utilized to enhance forecasting accuracy by LSTM to learn the characteristics of the decomposed signals. This developed hybrid deep learning model is comprehensively validated with real-time data. The performance validation analysis using statistical error values shows that the developed approach gives superior performance to the existing benchmark approaches.

Wind power is playing a pivotal part in global energy growth as it is clean and pollution-free. To maximize profits, economic scheduling, dispatching, and planning the unit commitment, there is a great demand for wind forecasting techniques. This drives the researchers and electric utility planners in the direction of more advanced approaches to forecast over broader time horizons. Key prediction techniques use physical, statistical approaches, artificial intelligence techniques, and hybrid methods. An extensive review of the current forecasting techniques, as well as their performance evaluation, is here presented. The techniques used for improving the prediction accuracy, methods to overcome major forecasting problems, evolving trends, and further advanced applications in future research are explored.

In this analytical study, a hybrid day-ahead wind speed prediction approach for high accuracy is implemented. The hybrid approach initially converts raw wind speed data series into actual hourly input structure for reducing uncertainty and the intermittent nature of wind speed. The back-propagation neural network is utilized for its better learning capability and also for its ability for nonlinear mapping among complex data. The teaching learning-based optimization algorithm is used to auto-tune the best weights of the artificial neural network. This optimization algorithm is used for its powerful ability to search and explore on a global scale. Then, the artificial neural network teaching learning-based optimization approach is implemented for wind speed forecasting. After that, the day-ahead prediction is performed using the proposed hybrid model for actual hourly input structure. The hybrid model prediction results give enhanced prediction accuracy when compared to existing approaches.