The energy harvesting cognitive wireless sensor network (EHCWSN) introduces energy harvesting technology and cognitive radio technology into the traditional wireless sensor network (WSN), which significantly prolongs the working life of the sensor node and effectively alleviates the congestion problem of the unlicensed spectrum. Due to the uncertainty of the energy harvesting process and the behavior of the primary user (PU), how to allocate and manage limited network resources is a crucial problem in the EHCWSN. In this work, a new Q-learning-based channel selection method is proposed for the energy harvesting process and the randomness of the PU's behavior in the sensor network. By continuously interacting and learning with the environment, the method guides the secondary user (SU) to select the channel with better channel quality. Moreover, we also propose a resource management and allocation mechanism with guaranteed QoS requirements for node traffic based on the framework of Lyapunov optimization theory. We design a low-complex online algorithm based on the optimization framework, which is then validated through extensive simulations. The results demonstrate that our design achieves higher accuracy with the QoS guarantee.

中文翻译：

---

能量收集认知无线传感器网络中的智能资源分配方案

能量采集认知无线传感器网络（EHCWSN）将能量采集技术和认知无线电技术引入到传统无线传感器网络（WSN）中，显着延长了传感器节点的工作寿命，有效缓解了非授权频谱的拥塞问题。由于能量收集过程和主用户（PU）行为的不确定性，如何分配和管理有限的网络资源是 EHCWSN 中的一个关键问题。在这项工作中，针对能量收集过程和传感器网络中 PU 行为的随机性，提出了一种新的基于 Q 学习的信道选择方法。该方法通过与环境的不断交互和学习，引导次用户（SU）选择信道质量更好的信道。而且，我们还基于李雅普诺夫优化理论的框架提出了一种对节点流量有保证的QoS要求的资源管理和分配机制。我们基于优化框架设计了一个低复杂度的在线算法，然后通过广泛的模拟进行验证。结果表明，我们的设计在 QoS 保证下实现了更高的准确性。