Solar Power Forecasting Using Deep Learning Model Based Improved Particle Swarm Optimization Method

Abstract

Accurately forecasting solar power is essential for secure and efficient operations of contemporary power systems, particularly in the smart grid and renewable energy integration context. In this paper, we present a new hybrid deep learning model, the BiLSTM Model using Improved PSO (BiLSTM-IPSO), for improved short-term prediction of solar power, which incorporates the Bidirectional Long Short-Term Memory (BiLSTM) model with an Improved Particle Swarm Optimization (IPSO) algorithm. The IPSO algorithm successively arranges the BiLSTM hyperparameters with chaotic initialization, adaptive inertia weights, and velocity clamping, to converge globally and avoid stagnating locally. The proposed BiLSTM-IPSO model performance is compared with various state-of-the-art techniques, including TLBO-DL, CNN-LBO, BiLSTM-AADC, and HCLN, using standard indicators, such as MSE, RMSE, MAE, MBE, and R². Results show that our model consistently performs better than all the baselines, and the lowest RMSE and the highest R² are 0.0565 and 0.955, respectively, on the 0.5-hour horizon. The excellent generalization performance of the framework in all of its forecast horizons indicates its feasibility for applications in real-time deployment in solar energy management systems and smart-grid operations.