The optimal operation of Wireless Sensor Network (WSN) requires a sustainable topology. A dead node may result in a breach of end-to-end connectivity in the network. The thermal sensitivity of any sensor affects the lifetime of the node. Every sensor node has a typical operating temperature zone. Beyond the operating temperature threshold, the system reduces the performances and consequently forms a disconnected network. Network entropy represents the evaluation of the anisotropy of the temperature distribution profile of the system that measures the network stability. In this work, an intelligent sleep scheduling algorithm ‘iSleep’ is proposed based on available neighboring nodes, associated network entropy, and traffic flow pattern. iSleep enables the sensor nodes to auto-control the sleep state of the nodes and maintain network connectivity for a longer amount of time. The proposed algorithm is tested for numerous representative networks on MATLAB 2016a and the Cooja simulator on Instant Contiki-2.7 with two energy models of Tmote Sky and Zolertia Z1. It is found that the proposed algorithm outperforms the existing scheduling algorithms in terms of the lifetime of a network for both the energy models.

无线传感器网络（WSN）的最佳运行需要可持续的拓扑。死节点可能会导致网络中的端到端连接中断。任何传感器的热灵敏度都会影响节点的寿命。每个传感器节点都有一个典型的工作温度区。超出工作温度阈值，系统会降低性能，并因此形成断开的网络。网络熵表示对测量网络稳定性的系统温度分布曲线的各向异性的评估。在这项工作中，基于可用的相邻节点，关联的网络熵和业务流模式，提出了一种智能睡眠调度算法“ i Sleep”。一世睡眠使传感器节点能够自动控制节点的睡眠状态，并保持较长时间的网络连接。在MATLAB 2016a上的众多代表性网络和Instant Contiki-2.7上的Cooja模拟器上，使用Tmote Sky和Zolertia Z1的两个能量模型，对该算法进行了测试。发现在两种能量模型的网络寿命方面，所提出的算法都优于现有的调度算法。