Q-Learning-Based Hyperheuristic Evolutionary Algorithm for Dynamic Task Allocation of Crowdsensing

Task allocation is a crucial issue of mobile crowdsensing. The existing crowdsensing systems normally select the optimal participants giving no consideration to the sudden departure of mobile users, which significantly affects the sensing quality of tasks with a long sensing period. Furthermore, the ability of a mobile user to collect high-precision data is commonly treated as the same for different types of tasks, causing the unqualified data for some tasks provided by a competitive user. To address the issue, a dynamic task allocation model of crowdsensing is constructed by considering mobile user availability and tasks changing over time. Moreover, a novel indicator for comprehensively evaluating the sensing ability of mobile users collecting high-quality data for different types of tasks at the target area is proposed. A new Q-learning-based hyperheuristic evolutionary algorithm is suggested to deal with the problem in a self-learning way. Specifically, a memory-based initialization strategy is developed to seed a promising population by reusing participants who are capable of completing a particular task with high quality in the historical optima. In addition, taking both sensing ability and cost of a mobile user into account, a novel comprehensive strength-based neighborhood search is introduced as a low-level heuristic (LLH) to select a substitute for a costly participant. Finally, based on a new definition of the state, a Q-learning-based high-level strategy is designed to find a suitable LLH for each state. Empirical results of 30 static and 20 dynamic experiments expose that this hyperheuristic achieves superior performance compared to other state-of-the-art algorithms.

Automated summary

Task allocation in mobile crowdsensing is a crucial issue, as existing systems do not consider the sudden departure of users, impacting the quality of long-term sensing tasks. To address this, a dynamic task allocation model is proposed, along with a novel indicator for evaluating the sensing ability of users. A Q-learning-based hyperheuristic evolutionary algorithm is suggested, showing superior performance compared to other algorithms.