The vehicle-road cooperation system (VRCS) is set to be a critical component of intelligent transportation systems. The rapid and precise acquisition of substantial multisource traffic data is pivotal, with intelligent wireless sensor networks (IWSNs) emerging as a promising tool for developing VRCS. Nonetheless, the complexity of communication environment and the massive transmission of information have made VRCS optimization an increasingly difficult task, involving the intricate processes of coverage and routing optimization within IWSNs. This challenge essentially transforms into a very complicated many-objective optimization problem, where multiple conflicting objectives and resource constraints need to be tackled simultaneously. Traditional optimization methods struggle to offer satisfactory solutions. Our study introduces a many-objective evolutionary algorithm that concurrently manages coverage and routing optimization in IWSNs. Initially, we present a 3-D sensing model to delineate the perception range of an individual sensor. Subsequently, we propose a comprehensive four-objective optimization model, encompassing coverage, connectivity, energy consumption, and deployment cost, to accurately depict the performance of IWSNs. Especially this integrated model includes a swift connectivity evaluation method and a specialized routing forwarding strategy. Furthermore, we suggest a node sleeping strategy to minimize energy consumption further. To find a solution to the resultant many-objective optimization problem, which refers to numerous objectives and constraints, we developed a swarm optimization algorithm based on rapid fitness evaluation strategy and differential co-evolution, aimed at boosting convergence speed and accuracy of the proposed approach. Comparative experiments indicate that our model and algorithm outperform other algorithms in terms of efficiency and effectiveness.

At present, wireless sensor networks (WSNs) play an important role in collecting and processing information in smart transportation monitoring. Inevitably, the performance of the resource scheduling algorithm directly determines the quality of service of WSNs. In this paper, we present a novel large-scale resource scheduling algorithm of WSNs based on differential ion coevolution and multi-objective decomposition (DIC-MOD) to optimize the performance of WSNs. We first introduce a certain number of mobile nodes with higher configuration into WSNs and consider them as relay nodes to strengthen the balance of energy consumption in the entire WSNs. Subsequently, we build a multi-index service quality evaluation model, including coverage, connectivity, energy efficiency and the number of nodes required to work, to characterize the comprehensive performance of WSNs. Afterward, to optimize the above complex model effectively, we propose a multi-objective resource scheduling algorithm, in which a differential ion coevolution strategy and a fast individual selection strategy based on multi-objective decomposition optimization are proposed in specific. Compared with other state-of-the-art algorithms, the experimental results finally show that the performance of WSNs on multiple indicators obtained by the proposed algorithm has been improved considerably.