Due to its vast range of applications in various fields, Wireless Sensor Networks (WSNs) have received a lot of attention in the modern technological world. Limited energy source of the sensor impacts the lifetime of the network. Various techniques and approaches have been proposed in this regard. However, these techniques only extend the lifetime of the network to some extent. The evolution of Wireless Energy Transfer (WET) technology in recent years has resulted in the deployment of Wireless Rechargeable Sensor Networks (WRSN), in which sensors are equipped with rechargeable batteries that can be recharged using Wireless Mobile Charger (WMC). However, scheduling of WMC is one of the challenging issues and to recharge the sensor nodes is also a well-referenced research topic. To determine the ideal charging path for the WMC, a Genetic Algorithm (GA)-based energy-efficient on-demand charging scheme with a novel mutation operation is proposed in this work. The proposed novel mutation operation aids in improving performance and accelerating convergence with the goal of finding the optimal charging path for the WMC.