A data-driven robust optimization for multi-objective renewable energy location by considering risk

Using Renewable Energy (RE) is growing day by day. We need to locate RE in the best place to maximize energy production and supplier profit. As a result, we propose a novel method for RE location (REL). This model suggests a Data-Driven Robust Optimization (DDRO) for multi-objective REL by considering Risk (DDROMORELR). We consider risk by adding min function in energy and profit objectives (government and supplier objectives). A DDRO approach is added to the model to tackle uncertainty and be close to the real world. We utilize an improved Augmented ε -constraint (AUGEPS2) to solve objectives and produce a Pareto front. We compare problems with DDRO and without considering DDRO, and the profit and energy production without DDRO is less than with DDRO, and its gap is -7%. We change the conservativity coefficient, the Rate Of Return (ROR), and the scale of the problem. The supplier’s profit and energy production increase by decreasing the conservativity coefficient. By increasing the ROR, the profit function and energy production decrease. By increasing the scale of the problem, the time solution increased. Finally, we suggest regression between time solution and sets.