Multi-objective optimal planning study of integrated regional energy system considering source-load forecasting uncertainty

The operation scenarios of regional integrated energy systems are becoming increasingly complex, with uncertainty issues becoming more prominent. To enhance the reliability of regional integrated energy systems, reduce carbon dioxide emissions, and lower investment and operational costs, this paper proposes a multi-objective optimization planning method that accounts for the uncertainty of source-load forecasting errors. First, the basic structure is established, and a set of uncertainty scenarios for source-load forecasting errors is generated using the latin hypercube sampling method. Next, clustering techniques are employed to reduce the uncertainty scenario set and extract typical scenarios of source-load uncertainty. Then, a multi-objective optimization model is constructed, considering the uncertainty of source-load forecasting, with total cost, carbon dioxide emissions, and system reliability as objective functions. Subsequently, a non-dominated sorting genetic algorithm is used to solve the multi-objective optimization function, resulting in a Pareto front set. The optimal solutions from the Pareto front set are selected using a strategy that combines fuzzy entropy theory with comprehensive evaluation, yielding multi-objective optimization planning results for each typical scenario. Through case analysis, compared to the application of single-objective optimization planning that does not consider the uncertainty of source-load forecasting and multi-objective optimization planning that also does not consider this uncertainty,the proposed planning model reduces annual total costs by 1.46 million CNY and 940,000 CNY respectively, carbon dioxide emissions by 16.9% and 9.5% respectively, and improves reliability by 13% and 5% respectively. This indicates the effectiveness of the multi-objective optimization planning model that accounts for the uncertainty of source-load forecasting errors.