To address time unfairness access problems in the dynamic channel, an underwater adaptive contention window (CW) adjustment backoff algorithm (QL-UACW) based on Q-learning is presented in this paper. That algorithm employs the concept of reinforcement learning to adaptively adjust the competition window by autonomously learning the network communication process. Based on QL-UACW and in order to address space unfairness access issues of nodes location, a load adaptive hybrid media access control (MAC) protocol with competition for the same directional nodes and time slot allocation for different directional nodes called SDHA is also presented. The protocol divides the nodes into co-nodes and counter-nodes according to the relative communication directions of the nodes. The co-nodes use competition protocol and the counter-nodes use time slot allocation protocol to solve the hidden terminal problem of node communication in order to prevent space access unfairness. Theoretical and simulation analysis show that the QL-UACW algorithm effectively improves the fairness of node access channels, reduces the collision rate of data frames, and increases network throughput. Additionally, the SDHA protocol is proven to provide advantages in normalized network throughput, average end-to-end delay, and the success rate of data frame transmission.

针对动态通道中时间不公平的访问问题，提出了一种基于Q学习的水下自适应竞争窗口（CW）调整退避算法（QL-UACW）。该算法采用增强学习的概念，通过自主学习网络通信过程来自适应地调整竞争窗口。基于QL-UACW，并且为了解决节点位置的空间不公平访问问题，还提出了一种负载自适应混合媒体访问控制（MAC）协议，该协议竞争相同的定向节点，并为不同的定向节点分配时隙，称为SDHA。该协议根据节点的相对通信方向将节点分为协节点和对节点。协节点使用竞争协议，反节点使用时隙分配协议来解决节点通信的隐藏终端问题，以防止空间访问不公平。理论和仿真分析表明，QL-UACW算法有效地提高了节点访问信道的公平性，降低了数据帧的冲突率，提高了网络吞吐量。此外，事实证明，SDHA协议在标准化网络吞吐量，平均端到端延迟和数据帧传输成功率方面具有优势。降低数据帧的冲突率，并增加网络吞吐量。此外，事实证明，SDHA协议在标准化网络吞吐量，平均端到端延迟和数据帧传输成功率方面具有优势。降低数据帧的冲突率，并增加网络吞吐量。此外，事实证明，SDHA协议在标准化网络吞吐量，平均端到端延迟和数据帧传输成功率方面具有优势。