Load balance vs utility maximization in mobile crowd sensing: A distributed approach

This paper focuses on workload allocation among mobile nodes in a mobile crowd sensing system. We take both two important objectives into account, including load balance and sensing data utility maximization. However, workload allocation achieving both objectives is particularly challenging. First, there is an intrinsic tradeoff between load balance and utility maximization. The system should strike a good balance between the two important objectives. Second, the number of mobile users can be large. A simple exhaustive search of workload allocation results can be prohibitively expensive. In this paper, we model workload allocation as a Nash bargaining game. We propose a distributed algorithm to solve the Nash bargaining game and determine the workload to each individual smartphone. It effectively decomposes the complex optimization problem into subproblems, and obtains the workload allocation solution by an iterative procedure imitating the bargaining process. This distributed algorithm can achieve a fair tradeoff between workload balance and data utility maximization, which is provably Pareto-efficient. We have conducted extensive simulations, and the results demonstrate that our algorithm achieves Pareto optimality and fairness between the two important objectives.