An Optimized Hybrid Energy Forecasting: Efficient Simulated Chaotic Hormonal Search (SCHS) Model using Hybrid Energy Sources

Background: Rising energy demand and the high cost of fossil fuels in remote and island areas are driving increased interest in renewable energy sources (RES). These sources, while environmentally friendly, are often unpredictable and intermittent. Hybridization of different RES can help reduce these issues and improve overall system efficiency. Methods: This paper develops an optimization-based weather forecasting method for a hybrid energy system combining solar, wind, and hydrogen storage. The objective is to minimize the Total Life Cycle Cost (TLCC) and Loss of Power Supply Probability (LPSP) of the hybrid energy system. To achieve this, a novel optimization algorithm called Simulated Chaotic Hormonal Search (SCHS) is employed. Additionally, the Intelligent Simulated Neural Network (ISNN) mechanism is used to project a hybrid RES incorporating solar insolation, wind speed, and air temperature. Results: The proposed method optimally meets load demand using three different off-grid hybrid RES. Concluding Remarks: The innovative approach of combining SCHS and ISNN mechanisms provides an effective solution for optimizing hybrid renewable energy systems. The proposed method not only addresses the unpredictability and intermittency of RES but also ensures cost-effectiveness and reliability. The simulation results confirm the potential of this approach in enhancing the performance of hybrid RES in remote and island areas.