In many researches on load balancing in multi-sink WSN, sensors usually choose the nearest sink as destination for sending data. However, in WSN, events often occur in specific area. If all sensors in this area all follow the nearest-sink strategy, sensors around nearest sink called hotspot will exhaust energy early. It means that this sink is isolated from network early and numbers of routing paths are broken. In this paper, we propose an adaptive learning scheme for load balancing scheme in multi-sink WSN. The agent in a centralized mobile anchor with directional antenna is introduced to adaptively partition the network into several zones according to the residual energy of hotspots around sink nodes. In addition, machine learning is applied to the mobile anchor to make it adaptable to any traffic pattern. Through interactions with the environment, the agent can discovery a near-optimal control policy for movement of mobile anchor. The policy can achieve minimization of residual energy's variance among sinks, which prevent the early isolation of sink and prolong the network lifetime.
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Artificial Intelligence