Monitoring of marine polluted areas is an emergency task, where efficiency and low-power consumption are challenging for the recovery of marine monitoring equipment. Wireless sensor networks (WSNs) offer the potential for low-energy recovery of marine observation beacons. Reducing and balancing network energy consumption are major problems for this solution. This paper presents an energy-saving clustering algorithm for wireless sensor networks based on k-means algorithm and fuzzy logic system (KFNS). The algorithm is divided into three phases according to the different demands of each recovery phase. In the monitoring phase, a distributed method is used to select boundary nodes to reduce network energy consumption. The cluster routing phase solves the extreme imbalance of energy of nodes for clustering. In the recovery phase, the inter-node weights are obtained based on the fuzzy membership function. The Dijkstra algorithm is used to obtain the minimum weight path from the node to the base station, and the optimal recovery order of the nodes is obtained by using depth-first search (DFS). We compare the proposed algorithm with existing representative methods. Experimental results show that the algorithm has a longer life cycle and a more efficient recovery strategy.
HCABS: The hierarchical clustering algorithm based on soft threshold and cluster member bounds for wireless sensor networks
