Forecast-integrated techno-economic optimization of off-grid hybrid renewable system in hyper-arid regions: Application to Tamanrasset, Algeria

This study presents a novel framework for the optimal design of an off-grid residential energy system, applied to the hyper-arid region of Tamanrasset, Algeria. The proposed hybrid renewable energy system (HRES) integrates photovoltaic panels, wind turbines, battery storage, and diesel generators. A key innovation is the integration of a green energy forecasting module within a multi-objective techno-economic optimization process. Various machine learning and deep learning models suited for time series prediction were evaluated, and the best-performing models for each meteorological parameter were selected which enables precise long-term hourly forecasts, improving system design and operational efficiency compared to conventional methods based on historical averages. The optimization targets three objectives: minimizing the Levelized Cost of Energy (LCOE), reducing the Loss of Power Supply Probability (LPSP), and maximizing the Reliability Factor (RF). Using the Multi-Objective Particle Swarm Optimization (MOPSO) algorithm, the system achieves an LCOE of $0.05433/kWh, an LPSP of 3.1 %, and an RF of 98 %, indicating a strong balance between cost and reliability. Energy contributions are 47 % from solar PV, 35 % from batteries, 12 % from wind, and 6 % from diesel. Comparison with HOMER Pro simulations confirms the superior economic performance of the MOPSO-based configuration. Sensitivity analyses underscore the critical role of forecast accuracy in HRES performance, while environmental assessments show an 80 % reduction in CO2 emissions compared to diesel-only systems. The integrated forecasting module serves as a valuable decision-support tool for rural electrification, particularly in resource-constrained and climate-challenged regions.