Wireless Sensor Network (WSN) has huge amount of sensor nodes that randomly deployed in the interested region to monitor the environment. In WSN, the energy efficiency is considered as a challenging task during data transmission. The mahalanobis distance based cluster head selection is proposed to solve the issues related to the energy constraint. Next, ad hoc on-demand distance vector routing protocol is used to find the optimal path between the source to base station via cluster heads. The performance of this mahalanobis method is analyzed in terms of energy consumption, throughput, packet loss ratio, End to End Delay (EED) and average delay ratio. The mahalanobis method is compared with Weighted Energy-efficient Clustering with Robust Routing (WECRR), improved Artificial Bee Colony (iABC), Adaptive Energy aware Cluster-based Routing (AECR), Evolutionary Multipath Energy-Efficient Routing (EMEER), K-means algorithm and Energy-aware Cluster-based Routing Protocol (ECRP). The energy consumption of the mahalanobis method is 0.641 J for 75 nodes, it is lesser than the existing methods.