分布式约束优化的震后救援路径规划  

Distributed constrained optimization for post-earthquake rescue path planning

作　　者：石美凤 梁飞鹏 陈媛[1] SHI Meifeng;LIANG Feipeng;CHEN Yuan(College of Computer Science and Engineering,Chongqing University of Technology,Chongqing 400054,China;Faculty of Information Science and Electrical Engineering,Kyushu University,Fukuoka 819-0395,Japan)

机构地区：[1]重庆理工大学计算机科学与工程学院,重庆400054 [2]九州大学信息科学与电气工程学院,福冈819-0395

出　　处：《重庆理工大学学报（自然科学）》2024年第10期88-94,共7页Journal of Chongqing University of Technology：Natural Science

基　　金：重庆市教育委员会科学技术研究计划青年项目(KJQN202401101);重庆理工大学研究生创新项目(gzlcx20232064)。

摘　　要：提出一种基于分布式约束优化的震后救援路径规划模型。通过分析地震烈度、震害指数、路段可靠性等因素,结合实际震后救援地图构建数学模型,提出一种新的自适应局部代价模拟算法(ALCS)对模型进行求解。算法中智能体在优化初期使用偏差修正策略对局部代价进行修正,以获得更好的初始解集。设计了一种自适应策略,提高算法的泛化能力。实验结果表明:基于分布式约束优化技术构建的数学模型能够有效提高震后救援效率,提出的ALCS算法比前沿的分布式约束优化问题(DCOPs)局部搜索算法的收敛质量更好,也能更有效地通过求解震后救援路径规划模型得出多条分布式救援最优路径。This paper proposes a post-earthquake rescue path planning model based on Distributed Constrained Optimization Problems(DCOPs).The mathematical model is built by analyzing factors such as seismic intensity,seismic damage index and roadway reliability.Coupled with actual post-earthquake rescue maps,a novel Adaptive Local Cost Simulation-based algorithm(ALCS)is proposed to solve the model.The agent in ALCS employs a bias correction strategy to pre-correct the local cost and obtain a better solution at the initial stage.Meanwhile,an adaptive strategy is designed to improve the generalization ability of the algorithm.Our extensive experimental results on benchmark problems demonstrate the constructed DCOPs-based rescue path planning model effectively improves the efficiency of post-earthquake rescue,and the proposed ALCS algorithm outperforms the state-of-the-art local search-based DCOPs solving algorithms,and also effectively plans multiple rescue paths by solving the post-earthquake rescue path planning model.

关 键 词：分布式约束优化 震后救援路径规划 自适应局部代价模拟 局部搜索算法 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]