Underwater wireless sensors communicate information from different depth of water column to sink positioned on the surface of water. Monotonically increasing data traffic occurs as it reaches surface of water column causing an imbalance of routing and resulting in congested nodes. Underwater wireless sensor node can be either in normal, overloaded state, congested state. The purpose of this work is achieving control over normal and isolated states. The congested node use the permutation of links and it observe the transition probabilities for routing. Then it determines the state of node based on the immediate reward and the action to be taken within the time episode. Thus nodes are isolated and recovered after the time episode. Improved estimate in forwarding scenario of overloaded and isolating nodes is observed via simulation results in NS2 simulator.

水下无线传感器将信息从不同深度的水柱传递到位于水面上的水槽。当数据流量到达水柱表面时，会单调增加数据流量，从而导致路由不平衡并导致节点拥塞。水下无线传感器节点可以处于正常，过载状态，拥塞状态。这项工作的目的是实现对正常状态和隔离状态的控制。拥塞的节点使用链接的排列，并观察路由的转移概率。然后，它根据即时奖励和在该时间段内要采取的行动来确定节点的状态。因此，节点在时间间隔后被隔离并恢复。