Power management for smart grids integrating renewable energy sources using Greylag goose optimization and anti-interference dynamic integral neural network

Abstract

This paper proposes a hybrid power management strategy for smart grids (SGs) that integrates renewable energy sources (RESs), such as battery energy storage systems (BESS), fuel cells (FCs), wind turbines (WT), and solar photovoltaic (PV). The GGO-AIDINN approach integrates Greylag Goose Optimization (GGO) and an Anti-Interference Dynamic Integral Neural Network (AIDINN) to address high emissions during low renewable energy (RE) availability and rising operational costs from advanced infrastructure. The GGO optimizes resource allocation and energy distribution, maximizing the use of available RE. Meanwhile, AIDINN predicts energy consumption patterns based on weather conditions, improving overall system performance. The proposed GGO-AIDINN model is implemented on MATLAB and evaluated against several existing methods, including Fuzzy Logic Control (FLC), Non-dominated Sorting Genetic Algorithm (NSGA-II), and others. Results show the hybrid method achieves significant improvements, with an operational cost of $1328 per MW, emissions of 13.76 kg per MW, and an efficiency of 98.7 %. These outcomes demonstrate that GGO-AIDINN outperforms traditional techniques, offering lower costs, reduced emissions, and enhanced system efficiency. This makes it a superior solution for sustainable power management in SGs incorporating RESs and BESS.