Advanced Energy Management in Smart Grids using Lyrebird Optimization Algorithm

Integration of a hybrid wind turbine (HWT) and a battery energy system (BES) is expected to take place under the framework of a Smart Grid (SG) to optimize energy generation, storage, and distribution and enhance stability and efficiency. One aspect of such systems is a challenge concerning the effective management of Renewable Energy (RE) fluctuation to achieve balanced operation among renewable generation and energy demand. This paper proposes a Lyrebird Optimization Algorithm (LOA) to optimize energy demand forecasting and management within the hybrid system. The LOA is used to minimize Mean Absolute Percentage Error (MAPE) in energy demand forecasting within the SG system. By optimizing energy demand forecasting, the LOA effectively improves accuracy in energy management and forecasting within the SG. Its adaptive optimization ensures that forecasting errors are minimized across various operating conditions, enhancing overall efficiency of the energy distribution system. By then the proposed LOA method is implemented on the MATLAB platform, and its performance is evaluated by comparing it with existing optimization techniques such as Improved Grey Wolf Optimization (IGWO), Multi-Objective Optimization (MOO), Multi-Objective Wind Driven Optimization (MOWDO), and Coati Optimization Algorithm (COA). The results show that the proposed LOA method provides superior performance in minimizing MAPE, achieving the lowest MAPE value of 2.90%, indicating its enhanced accuracy in energy demand forecasting and optimization.