Abstract:

Existing parameter design for power forecasting in park integrated energy systems (PIESs) focuses on minimizing the forecasting error of either source or load power, aiming at obtaining prediction results closest to the actual power without considering the comprehensive impact of forecasting results on operation objectives. This limitation leads to reduced overall economic benefits when the forecasting parameters are applied in practice. To address this issue, this paper proposes an operational target-oriented joint parameter optimization method for source-load power forecasting in PIESs. First, a joint optimization objective function for forecasting parameters is constructed based on a two-stage day-ahead and intraday operational model, integrating total economic operational indices from both day-ahead and intraday stages. Then, a joint parameter optimization model for source-load power forecasting with an embedded two-stage operation strategy is built, formulated by constructing the optimality conditions of the day-ahead model. Simultaneously, a warm-start scheme for the forecasting model is designed to accelerate the solution process of the joint parameter optimization problem. Finally, a simulation model is established based on commercial and residential energy consumption data from Anchorage, USA, to validate the proposed method, of which the results indicate that the proposed method can effectively reduce the operating costs of urban PIESs, decrease the curtailment of wind and solar energy, and increase the operational revenue of energy storage.

Key words: park integrated energy system (PIES), joint optimization of forecasting parameter, optimality condition, two-stage operation, warm-start method