arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.03365eess.SYcs.AIcs.SY
收藏

住宅建筑供暖的需求响应：基于物理信息神经网络的高效蒙特卡洛树搜索控制

Demand response for residential building heating: Effective Monte Carlo Tree Search control based on physics-informed neural networks

IDLab Ghent university – imec（IDLab 根特大学 – 校际微电子中心（imec））；Beebop

Fabio Pavirani, Gargya Gokhale, Bert Claessens, Chris Develder

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文针对住宅建筑供暖需求响应控制问题，提出结合多步预测物理信息神经网络的改进蒙特卡洛树搜索方法，相比黑盒神经网络方案降低了预测误差与能源成本，同时引入AlphaZero思路减少计算量。

摘要：

为减少全球碳排放并遏制气候变化，控制建筑能耗是关键一环。本文专门研究利用需求响应（demand response, DR）算法在保障用户热舒适的前提下限制住宅建筑供暖系统的能耗。在该领域，强化学习（Reinforcement learning, RL）方法已被证明十分有效，蒙特卡洛树搜索（Monte Carlo Tree Search, MCTS）便是其中之一，它在棋类游戏（围棋、国际象棋）中已取得瞩目成就。MCTS的一个独特优势是其决策树结构可天然整合外部约束（例如通过修剪违反约束的分支），而传统强化学习方案需要更复杂的技术（例如通过在成本/奖励函数中添加惩罚项间接实现，或通过备用控制器修正违反约束的动作）。本文的主要目标是研究MCTS在建筑控制中的应用，因为据我们所知，该方向目前仍鲜有探索。MCTS的一个特性是需要模拟器组件，能够根据采取的动作预测后续系统状态。一种直接的数据驱动方案是使用黑盒神经网络（Neural Networks, NNs），但本文将扩展物理信息神经网络（Physics-informed Neural Network, PiNN）模型以实现多时间步预测，并证明与黑盒NN相比，PiNN的优势在于预测误差更低（平均绝对误差MAE降低32%），且能提升MCTS性能（能源成本降低4%，热舒适度提升7%）。本文的第二项贡献是对基础版MCTS进行扩展，采用AlphaZero中应用的思路（即使用学习得到的先验函数、价值函数以及动作选择启发式算法），在保持控制性能的同时降低计算成本。

英文摘要：

To reduce global carbon emissions and limit climate change, controlling energy consumption in buildings is an important piece of the puzzle. Here, we specifically focus on using a demand response (DR) algorithm to limit the energy consumption of a residential building's heating system while respecting user's thermal comfort. In that domain, Reinforcement learning (RL) methods have been shown to be quite effective. One such RL method is Monte Carlo Tree Search (MCTS), which has achieved impressive success in playing board games (go, chess). A particular advantage of MCTS is that its decision tree structure naturally allows to integrate exogenous constraints (e.g., by trimming branches that violate them), while conventional RL solutions need more elaborate techniques (e.g., indirectly by adding penalties in the cost/reward function, or through a backup controller that corrects constraint-violating actions). The main aim of this paper is to study the adoption of MCTS for building control, since this (to the best of our knowledge) has remained largely unexplored. A specific property of MCTS is that it needs a simulator component that can predict subsequent system states, based on actions taken. A straightforward data-driven solution is to use black-box neural networks (NNs). We will however extend a Physics-informed Neural Network (PiNN) model to deliver multi-timestep predictions, and show the benefit it offers in terms of lower prediction errors ($-$32\% MAE) as well as better MCTS performance ($-$4\% energy cost, $+$7\% thermal comfort) compared to a black-box NN. A second contribution will be to extend a vanilla MCTS version to adopt the ideas applied in AlphaZero (i.e., using learned prior and value functions and an action selection heuristic) to obtain lower computational costs while maintaining control performance.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑