The increasing environmental challenges posed by fossil fuel dependence have accelerated global efforts to adopt renewable energy. Leveraging Egypt’s abundant solar and wind resources, this study develops an optimal framework for hybrid energy systems (HES) in the Shlateen region. The proposed HES integrates photovoltaic panels, wind turbines, diesel generators, and battery storage to ensure reliable and cost-effective electricity supply. An Improved Particle Swarm Optimization (IPSO) algorithm, coupled with the Point Estimate Method (PEM), is applied to address uncertainties in wind speed and solar irradiance. The Loss of Power Supply Probability (LPSP), the Cost of Electricity (COE) and carbon dioxide (CO2) emissions are chosen as three simultaneous objective functions. The number of PVs, WTs, batteries, inverter power, and the diesel engine’s nominal capacity are among the decision variables that are taken into consideration as design parameters via a new meta-heuristic optimization algorithm. Because the design cost is increased and system reliability is degraded, the results highlight the possible consequences for educating industry executives and policymakers about the design and evaluation of HES under uncertain environmental conditions. In order to analyze the suggested methodology, many case studies are explored and presented. Software called MATLAB is used to implement and solve the optimization problem. According to the findings, The lowest LPSP achieved using the IPSO algorithm is 7. 149 %, but this value rises to 7. 211 % in the PSO alone. The PV/BESU/DG configuration (scenario 1) delivers the lowest amount of losses with PV sizes of 45, 1. 0856 BESU, and 4 DG, Cost of Energy (COE) of 0. 65407 /kWh, Loss of Power Supply Probability (LPSP) of 21. 666%, and CO2 emissions of 2. 4125e+05 tons/year. The COE falls between 0. 24634 and 0. 72586 dollars per kWh. The WT/BESU/DG configuration has the greatest COE at 0. 72586 /kWh, while the PV/WT/BESU/DG configuration (scenario 3) has the lowest COE at 0. 24634 /kWh. This work demonstrates the application of computational intelligence and meta-heuristic algorithms as core computer science tools for solving real-world energy optimization problems.
Saleh et al. (2026) studied this question.