Answers are grounded in this paper and cite their sources.
Grid-connected multi-energy microgrids face two interrelated challenges: the volatility of wind and photovoltaic generation, load demand, and electricity prices renders dispatch inputs uncertain, while the limited flexibility of conventional electrical storage and controllable units makes it difficult to simultaneously achieve economic operation, smooth output adjustment, and low network loss. To address these challenges, this study proposes a multi-objective integrated forecasting and active-balancing control framework. First, an LSTM-BPNN hybrid model jointly predicts wind power, photovoltaic power, load demand, and day-ahead electricity prices at a 30 min resolution. The model provides 48-step day-ahead forecasts and four-step intraday forecasts. Second, a rolling optimization controller targets operating cost, controllable-source output adjustment, network loss, and day-ahead schedule deviation, and employs MOEA/D to solve the constrained optimization problem. In the case study, the LSTM-BPNN model achieves superior forecasting accuracy in terms of MAE, RMSE, and other metrics compared with standalone LSTM, BPNN, and GRU models. At the dispatch level, compared with NSGA-II, MOEA/D increases HV by approximately 4.7% and decreases SP by 29.2%, demonstrating its superiority in solving the multi-objective dispatch problem. Removing the SOFC, HST, and hydrogen market increases daily operating cost, controllable-source output adjustment, and day-ahead deviation by approximately 11.02%, 4.45%, and 13.73%, respectively. Under the representative summer and winter scenarios, the system maintains stable operation, with the SOFC playing a key role in compensating for renewable generation shortfalls and load fluctuations, thereby supporting the economic efficiency and operational stability of the system under varying external operating conditions.
No takes yet. Share an insight, caveat, or question.
Yang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: