Sensors equipped with energy harvesting and cooperative communication capabilities are a viable solution to the power limitations of Wireless Sensor Networks (WSNs) associated with current battery technology. However, the optimal scheduling of transmissions in such networks is challenging due to the requirement of complete state information of the relay nodes. This paper addresses the problem of transmission scheduling in such networks when only {em partial} state information about the relays is available at the source. We formulate the scheduling problem as a Partially Observable Markov Decision Process (POMDP), and show that it can be decomposed into an equivalent Markov Decision Process (MDP) problem. Simulation results are used to show the performance of the scheduler.
展开▼
