An Efficient Short-Term Solar Power Forecasting by Hybrid WOA-Based LSTM Model in Integrated Energy System

Abstract

Objectives: Due to the irregular nature of sun irradiation and other meteorological conditions, solar power generation is constantly loaded with risks. When solar radiation data isn't captured and sky imaging equipment isn't available, improving forecasting becomes a more difficult endeavor. So our objective to improve the forecasting accuracy for next year solar power generation data. Methods: Our research used a real numerical solar power dataset of Australia and Germany and a standard approach for preprocessing. The feature selection in this research uses the Whale Optimization Algorithm (WOA). A Long Short-Term Memory (LSTM) method is utilized to determine the accuracy of solar power forecasts. The HHO (Harris Hawks Optimization) technique is also used to improve solar power forecasting accuracy. The performances were analyzed and the proposed method is employed in the python platform. Findings: The findings show that the suggested technique considerably increases the accuracy of short-term solar power forecasts for proposed method is 3.07 in comparison of LSTM and SVM at different data types and 15 min and 60 min interval. Novelty: The key novelties of this research is hybrid strategy for improving the precision of solar power forecasting for short periods of time. Including the Whale Optimization Algorithm (WOA), Long Short-Term Memory (LSTM), and Harris Hawks Optimization (HHO). Keywords: Power generation, Solar power forecasting, Whale optimization algorithm, Long Short­Term Memory, Harris hawk's optimization