Resource Allocation Strategy for Virtualized Wireless Sensor Networks Based on Actor-Critic

Aiming at the problem of effective utilization of virtualized WSN resources, a reinforcement learning-based resource allocation strategy for virtualized WSNs is proposed from the perspective of service requests of virtualized WSNs. A virtual sensor network request deployment utility maximization model is established based on the quality requirements of service sensing information and resource capacity constraints. Considering the randomness of service requests and the dynamic changes in the network environment, the resource optimization problem is transformed into MDP and solved using Actor-Critic reinforcement learning methods, and the best resource allocation strategy is obtained. Finally, a large number of simulation experiments are carried out to verify the effectiveness of the proposed method.