Research On The Emergency Rescue Of Smart Cities Based On Mobile Social Network

In the face of disasters in modern society,traditional search and rescue methods have many problems,such as requiring a large amount of manpower,material resources,and financial resources,and being inefficient,making it difficult to minimize life and property losses to the greatest extent possible.So,various new technologies or information systems are needed to help rescue personnel better handle rescue tasks.By utilizing information technology,the situation and rescue measures in the affected areas can be promptly released,providing the public and rescue personnel with more comprehensive information and better cooperation with rescue work.Nearest Neighbor Mobile Social Network(PMSN)refers to the communication between mobile users who are close to the appropriate location through their social sensors.PMSN can provide users with more social and business opportunities.To carry out disaster relief work in a post disaster environment,it is necessary to collect accident information during the search process and report it in a timely manner.Close range mobile social networks provide flexible systems for emergency response and disaster relief.Therefore,finding a better data forwarding and routing strategy is a key issue in post disaster rescue,and the study of user mobility models is also the foundation of the aforementioned issues.The work of this article is as follows:Firstly,a Autonomous Intelligent Computing(AOCI)oriented Intelligent City Emergency Rescue Neighborhood Mobile Social Network Model(AOPSMN)was proposed to simulate the network operating environment and investigate the performance of autonomous oriented neighboring mobile social network models in self-organization,scalelessness,aggregation,and community structure.Based on research on the coverage area of mobile sensors,its rescue efficiency has been proven.The performance of the routing strategy based on the autonomous oriented PMSN model was analyzed,and the effectiveness of this method was verified.Secondly,based on the proposed mobile social network model,after comparing the efficiency of genetic algorithm(GA),ant colony algorithm(ACS),and particle swarm optimization(PSO)under the same conditions,the PSO algorithm was selected.Based on this,an improved Particle Swarm Rolling Optimization(PSRO)with rolling time domain optimization was proposed.Afterwards,the PSRO algorithm with non full process scheduling concept was introduced into the AOPSMN model,and a rolling time domain optimized AOPSMN-RO model was proposed.A search and rescue experimental scenario was designed for simulation experiments.Through experiments,it was found that the improved PSRO algorithm not only greatly improves the convergence of search and rescue time compared to the PSO algorithm,but also effectively solves the waste of resources and time in the early scheduling of rolling optimization.Finally,the search and rescue experimental scenes in the rectangular area will be extended to real-world search and rescue scenes.Research the search efficiency problem in real scenarios through an intelligent agent simulation platform,compare various distribution patterns of searched targets,and design behavior analysis and comparison of searchers in real scenarios.Through simulation testing of the AOPSMN-RO model,it was confirmed that compared with the AOPSMN model,the search and rescue efficiency of the AOPSMN-RO model has been significantly improved in real scenarios,and the model has good applicability.