An Overview of Q-learning based Energy Efficient Power Allocation in WBAN(Q-EEPA)

Energy-efficient routing is one of the key techniques to design an efficient sensor network. In Wireless Body Area Networks (WBAN), Transmission Power Control algorithms, interference mitigation algorithms, and efficient routing schemes helps to save energy. The proposed Q-learning-based energy-efficient power allocation (Q-EEPA) provides a high packet delivery ratio with minimum power level, mitigating interference, and minimum hop count. This work considers the design issues in tier 1 and tier 2 of WBAN architecture and gave an overview to solve the issues using the Q-learning algorithm. Q-learning algorithm will allocate the power and routing path during data transmission. Heterogenous activities of a wearer and extensive game theory algorithm act as input to the Q-learning model to choose transmission power level and the next hop in both interference and non-interference scenarios.