ICT2TSK: An improved clustering algorithm for WSN using a type-2 Takagi-Sugeno-Kang Fuzzy Logic System

The routing protocol in the network layer has played a decisive role in the WSN (Wireless Sensor Network). Balance the network load, improve energy efficiency, and consequently increase the lifespan of the network are the main purpose of these protocols. For these, this paper proposes the ICT2TSK (Improved Clustering Algorithm Using a Type-2 Takagi-Sugeno-Kang Fuzzy Logic System) protocol. Compare with the classical LEACH protocol and the recently developed CHEATS protocol, two aspects of improvements are concerned: on one hand, a type-2 TSK FLS (Takagi-Sugeno-Kang Fuzzy Logic System) is employed to choose the cluster-head by calculating the probability of every node, which can deal with the rule uncertainties better than a type-1 TSK FLS; on the other hand, a fixed competition radius for each cluster-head is introduced to balance the network load and improve energy efficiency. Simulation results demonstrate that our proposed protocol ICT2TSK performs much better than LEACH and CHEATS, and also better than the unequal clustering algorithm named EEUC, according to metrics such as FND (First Node Dies) and HND (Half the Nodes Die) and ECPR (Energy Consumption Per Round).