RSUs Site Selection Optimization Method for Intelligent Transportation Systems in Complex Mountain Environment

In the complex mountain environment, the problem of difficult site selection and low accuracy of Roadside Unit (RSU) deployment is waste of resources caused by incomplete or overlapping coverage of RSUs deployment. Typical complex mountain environments are targeted by the ray tracing method to model and simulate the wireless channel transmission characteristics of the actual geographical environment. Multi-objective Particle Swarm Optimization (MOPSO) algorithms may not perform fine search for populations and are easy to fall into local optimization. An improved multi-objective particle swarm optimization algorithm based on adaptive parameter adjustment is proposed. Objective functions are network deployment coverage, total transmit power and communication quality. Decisions are made by using the ordinal preference method based on information entropy on the Pareto solution set, which solves the problem of site selection optimization of RSUs deployment in complex terrain environment. Compared with the competition-based multi-objective particle swarm algorithm, the convergence speed of the improved algorithm is significantly improved, along with the uniformity increased by 39.99%. Compared with the empirical site selection method, the network deployment coverage are increased by 31.66% and 23.01% and 23.01% respectively through the proposed method in this paper, and the communication system quality index are increased by 52.59% and 51.21% respectively, under the conditions of constraints or not.