Multi-objective integrated performance prediction and active balancing control for grid-connected multi-energy microgrids with hydrogen storage and SOFCs

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.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-14
DOI
https://doi.org/10.1038/s41598-026-78040-0
Primary Topic
Microgrid Control and Optimization
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Multi-objective integrated performance prediction and active balancing control for grid-connected multi-energy microgrids with hydrogen storage and SOFCs

金喆禹, Zhonghua Deng, Xingbo Liu, Bosi Yi et al.
Scientific Reports
Microgrid Control and Optimization
article

Multi-objective integrated performance prediction and active balancing control for grid-connected multi-energy microgrids with hydrogen storage and SOFCs

金喆禹, Zhonghua Deng, Xingbo Liu, Bosi Yi, Mingjiang Peng, Hui Yang, Dongfeng Ren, Lei Luo, Pengchao Zhang
article en

Abstract

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.

Scientific Reports
Tianjin University (CN), Xiangtan Electric Manufacturing Group (China) (CN), Wuhan Ship Development & Design Institute (CN), Huazhong University of Science and Technology (CN)
Microgrid Control and Optimization
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon