A bottom-up approach for community load prediction based on multi-agent model

Accurate prediction of community load is a prerequisite for community-scale demand matching and energy management. However, community-scale load prediction methods are challenging in characterizing complex energy-use scenarios caused by different building types and complicated occupant behaviors. The occupant behavior is the primary source of discrepancy between the predicted and realistic building performance, and this discrepancy will further widen on the community scale. This paper established the community occupant agent model (COAM) to generate occupancy data. The model delineates the agent system boundary from the perspective of complex adaptive systems (CAS). Anylogic was used to randomize and represent the decision behavior of community occupants. The bottom-up community building energy modeling (CBEM) workflow was applied to the case community of Xi'an (China). The measured and simulated values of the community building occupancy were compared, indicating the model's ability to reflect the interactions between single occupants and community building. The case community heating loads under different heating patterns were analyzed, and the workflow performance was evaluated. The proposed method might guide the district energy system to formulate the management strategy in the energy planning stage.