面向能源调度的物理约束智能体AI
Physically Constrained Agentic AI for Energy Scheduling
浏览论文内容
中文总结 AI 辅助
该研究提出分层式ReAct能源管理系统，通过分离物理授权与语言生成，实现智能体能源调度，在Qwen 3.5检查点上验证了多模型耦合调度的可行性与成本表现。
中文摘要 AI 辅助
智能体AI将能源管理从固定形式交互扩展至将自然语言请求转化为协调调度行动。我们提出了分层式ReAct能源管理系统（EMS），其中一个协调器为可转移电器、电动汽车充电和热控制协调专门智能体类型。物理授权与语言生成分离：确定性评判器重构每个综合日前候选方案，检查其模式、电器周期、设备功率、热舒适度，以及在运行时检查整个馈线功率限制。在Qwen 3.5检查点上，单电器混合整数调度在83.3%的运行中可行。局部反馈未产生可接受的耦合调度，而多步策略授权了6/6当前耦合运行：27B的3/3和35B-A3B的3/3。标准占用窗口策略允许预调节，从09:00至18:00强制舒适度。每个可接受的调度都通过了独立的最终重放。27B的可行成本为2522.499日元，35B-A3B为1592.697日元，略高于数学优化最优值1343.380日元。这些结果为声明的物理模型下的智能体MIP和MILP能源调度建立了故障关闭工作流。
英文摘要
Agentic AI extends energy management beyond fixed-form interaction by translating natural-language requests into coordinated scheduling actions. We present a hierarchical ReAct Energy Management System (EMS) in which one orchestrator coordinates specialist agent types for shiftable appliances, EV charging, and thermal control. Physical authorization is separated from language generation: a deterministic critic reconstructs each integrated day-ahead candidate and checks its schema, appliance cycles, device power, thermal comfort, and, when active, the whole power feeder limit. Across Qwen 3.5 checkpoints, single-appliance mixed-integer schedules were feasible in 83.3 percent of runs. Localized feedback produced no accepted coupled schedule, whereas a multi-step policy authorized 6/6 current coupled runs: 3/3 for 27B and 3/3 for 35B-A3B. The standard occupied-window policy permits pre-conditioning, enforces comfort from 09:00-18:00. Every accepted schedule passed an independent final replay. Feasible costs were 2522.499 JPY for 27B and 1592.697 JPY for 35B-A3B, which are slightly higher than the mathematical optimization optimum of 1343.380 JPY. These results establish a fail-closed workflow for agentic MIP and MILP energy scheduling under the declared physical model.
