Dynamic Power Management for Sensor Node in WSN Using Average Reward MDP
WASA '09 Proceedings of the 4th International Conference on Wireless Algorithms, Systems, and Applications
Simulation of large wireless sensor networks using Cell-DEVS
Winter Simulation Conference
| Hi-index | 0.01 |
One of the most important constraints in wireless sensor networks is the energy efficiency problem. To maximize the wireless sensor networks lifetime after the sensor nodes deployment, Dynamic Power Management (DPM) should be carefully taken into account in wireless sensor networks. The goal of DPM is to reduce power dissipation by putting the sensor node into different states. In this paper, a new method of DPM based on wavelet neural networks is proposed to conserve energy. There are two salient aspects to this approach. First, the next event's time which is a non-stationary series is predicted as accurate as possible by wavelet neural networks. Nodes in deeper sleep states consume lower energy while asleep, but incur a longer delay and higher energy cost to awaken. Second, the nodes state in which lie wireless sensor network should lie is decided through the predictable time associated with the threshold time, residual power. The simulation results show that the energy consumption is significantly reduced and the whole lifetime of the wireless sensor networks is greatly prolonged through the proposed method.