Nature-inspired approaches for clean energy integration in smart grids

Abstract

Optimizing domestic energy use and increasing the efficiency of residential power supply chains depend much on home energy management (HEM) systems. This paper examines the utilization of advanced meta-heuristics, namely the Siberian Tiger Optimization (STO) and Sand Cat Swarm Optimization (SCSO) algorithms, for developing HEM systems. The paper presents an integrated STSC algorithm, enhanced by artificial intelligence, that monitors and optimizes household energy usage. To optimize electricity distribution, this algorithm seeks a compromise between reducing costs and lowering the peak-to-average proportion of power. After extensive simulations, the STSC algorithm outperforms previous meta-heuristics in Peak Average Ratio. It demonstrates the possibility of substantial cost reductions in residential settings, reaching up to 8.5%. This improves the overall efficiency of households’ power supply chains. In addition to reducing costs, the STSC algorithm contributes to sustainability objectives by utilizing AI to minimize carbon emissions, including renewable energy sources, and facilitate adaptable demand solutions. This highlights its role in promoting sustainable supply chain practices in energy efficiency. The combined use of STO and SCSO algorithms in the STSC method is a new and innovative development in HEM systems. This study highlights the capacity of AI-driven technologies to effectively and environmentally optimize household energy consumption.

Keywords

• Home energy management systems
• Meta-heuristic algorithms
• Siberian tiger optimization
• Sand cat swarm optimization
• Peak average ratio
• AI-powered energy optimization