<![CDATA[Building energy consumption accounts for a large proportion of the overall energy use in society, and energy-saving optimization scheduling is currently a research hotspot. However, traditional scheduling methods often struggle to achieve an effective balance between multiple objectives such as energy conservation, economy, and indoor comfort. To construct an energy-saving scheduling model that can consider multiple objectives, this paper puts forward a building energy scheduling model based on a Multi-Objective Grey Wolf Optimizer, taking total energy consumption, operating cost, and indoor comfort deviation as the optimization objectives. The model introduces a set of multi-energy collaborative constraints involving wind energy, photovoltaic systems, energy storage, and combined cooling, heating, and power systems. To improve algorithm performance, we innovatively integrated particle swarm optimization and simulated annealing to enhance the model's global search and local optimization capabilities, and introduced residual long short-term memory networks to improve load forecasting accuracy. Experimental results show that compared to similar models, the proposed algorithm improves the energy-saving rate by 13.3% in a typical household scenario. Its response time is 12 s, memory usage is 89 MB, and convergence speed is 42.86% faster than the slowest comparable model. The Multi-Objective Grey Wolf Optimizer effectively coordinates the multi-objective needs of building energy systems. It significantly improves energy savings and economic performance while ensuring indoor comfort. This algorithm provides strong support for intelligent building energy scheduling and offers practical value for promoting the carbon neutrality goals in the building sector.]]>
Copyrights © 2026
