Multi-Objective Optimal Roadside Units Deployment in Urban Vehicular Networks

Abstract

The significance of transportation efficiency, safety, and related services\nis increasing in urban vehicular networks. Within such networks, roadside units\n(RSUs) serve as intermediates in facilitating communication. Therefore, the\ndeployment of RSUs is of utmost importance in ensuring the quality of\ncommunication services. However, the optimization objectives, such as time\ndelay and deployment cost, are commonly developed from diverse perspectives. As\na result, it is possible that conflicts may arise among the objectives.\nFurthermore, in urban environments, the presence of various obstacles, such as\nbuildings, gardens, lakes, and other infrastructure, poses challenges for the\ndeployment of RSUs. Hence, the deployment encounters significant difficulties\ndue to the existence of multiple objectives, constraints imposed by obstacles,\nand the necessity to explore a large-scale optimization space. To address this\nissue, two versions of multi-objective optimization algorithms are proposed in\nthis paper. By utilizing a multi-population strategy and an adaptive\nexploration technique, the methods efficiently explore a large-scale\ndecision-variable space. In order to mitigate the issue of an overcrowded\ndeployment of RSUs, a calibrating mechanism is adopted to adjust RSU density\nduring the optimization procedures. The proposed methods also take care of data\noffloading between vehicles and RSUs by setting up an iterative best response\nsequence game (IBRSG). By comparing the proposed algorithms with several\nstate-of-the-art algorithms, the results demonstrate that our strategies\nperform better in both high-density and low-density urban scenarios. The\nresults also indicate that the proposed solutions substantially improve the\nefficiency of vehicular networks.\n