Forecasting wind power using Optimized Recurrent Neural Network strategy with time‐series data

• Published in: Optimal control applications & methods Vol. 45; no. 4; pp. 1798 - 1814
• Main Authors: Kumar, Krishan, Prabhakar, Priti, Verma, Avnesh
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.07.2024; Wiley Subscription Services, Inc
• Subjects: Algorithms; Alternative energy sources; energy sources; Forecasting; hybrid optimization; load forecasting; Optimization; Recurrent neural networks; Search algorithms; time‐series data; Wind power
• ISSN: 0143-2087; 1099-1514
• DOI: 10.1002/oca.3122

Fuel prices are rising, bringing attention to the utilization of alternative energy sources (RES). Even though load forecasting is more accurate at making predictions than wind power forecasting is. To address the operational challenges with the supply of electricity, wind energy forecasts remain essential. A certain kind of technology has recently been applied to forecast wind energy. On wind farms, a variety of wind power forecasting methods have been developed and used. The main idea underlying recurrent networks is parameter sharing across the multiple layers and neurons, which results in cycles in the network's graph sequence. Recurrent networks are designed to process sequential input. A novel hybrid optimization‐based RNN model for wind power forecasting is proposed in this research. Using the SpCro algorithm, a proposed optimization method, the RNN's weights are adjusted. The Crow Search Optimization (CSA) algorithm and the Sparrow search algorithm are combined to form the SpCro Algorithm (SSA). The suggested Algorithm was developed using the crow's memory traits and the sparrow's detecting traits. The proposed system is simulated in MATLAB, and the usefulness of the suggested approach is verified by comparison with other widely used approaches, such as CNN and DNN, in terms of error metrics. Accordingly, the MAE of the proposed method is 45%, 10.02%, 10.04%, 33.58%, 94.81%, and 10.01% higher than RNN, SOA+RNN, CSO+RNN, SSA+DELM, CFU‐COA, and GWO+RNN method. Schematic diagrams of the proposed system. The suggested methodology's ultimate goal is to conduct wind power forecasting using an optimization attained in a deep learning approach. The overall block diagram of the proposed model is portrayed in this figure. A novel hybrid optimization‐based RNN model for wind power forecasting is proposed in this research. Using the SpCro algorithm, a proposed optimization method, the RNN's weights are adjusted. Through the proposed system, a potential solution can be achieved for WPF while taking into account the wind power history for a period of the past 24 h. The suggested Algorithm was developed using the crow's memory traits and the sparrow's detecting traits. It is found that the proposed method possesses fewer error measures as compared to the conventional methods, validating its superiority over other methods.