HHGPSO: A Novel Approach to Power System Load Forecasting and Optimization

The Hunger Games Search (HGS) algorithm and Particle Swarm Optimization (PSO) are two very effective metaheuristic methods that are often used to solve intricate optimization issues. However, each approach has drawbacks. For example, PSO has a tendency to converge too soon, whereas HGS may see sluggish convergence in high-dimensional environments. In order to overcome these obstacles, we suggest a novel hybrid algorithm called Hybrid Hunger Games Particle Swarm Optimizer (HHGPSO), which blends the local refining power of HGS with the global exploration potential of PSO. With power system load forecasting, where precision and resilience are crucial, this hybrid method is especially advantageous. After training and testing HHGPSO using machine learning approaches, we are able to estimate load needs with an astounding 70 % accuracy rate. The improved search efficiency and optimization accuracy of HHGPSO are shown by performance evaluations utilizing twentythree classical benchmark functions. This study demonstrates how HHGPSO may be used to address high-dimensional optimization problems in energy systems.