An energy efficient location aware geographic routing protocol based on anchor node path planning and optimized Q-learning model

A wireless sensor network (WSN) is made up of many nodes that can send sensed data to the base station or sink directly or through intermediary nodes. However, geographically based routing requires accurate sensor node location data. The precise localization of dispersed sensors within a designated region is a critical problem in WSN development. This study proposes a new location-aware geographic routing protocol, which is based on the Q-learning model and anchor node path planning. Initially, the location of an unknown node is detected using an Integrated Received Signal Strength Indicator (RSSI) and Cosine rule-based path planning model. After detecting the unknown nodes, each node is forwarded through a HELLO message to identify the routing neighbour nodes. Then, the Optimal Osprey Q-Learning (O²QL) model is used in multi-objective optimization to choose the best path routing. Then, the Q-learning model's reward function is responsible for both end-to-end latency and energy consumption. Moreover, the Q-learning parameters of the suggested protocol can be adaptively updated to accommodate the high process degrees found in WSNs. Simulations have been conducted to prove the efficacy of the method based on different metrics. The proposed approach has been compared with the existing recently introduced routing protocols in WSN. As a result, the proposed location-aware energy-efficient geographic routing techniques show performance in terms of average end-to-end delay of nodes (2.88), packet loss ratio of nodes (0.058), residual energy of nodes (0.199), average energy consumption of nodes (1.53) and packet delivery rate of nodes (98.96).