Energy-Aware Medium Access Control Protocols with Load Balancing Network for Solar-Powered Wireless Sensor Networks

In recent years, the increasing demand for solarpowered Wireless Sensor Networks (WSNs) for edge Internet of things (IoT) applications has intensified the need for intelligent load-balancing mechanisms under dynamic environmental conditions. Existing Prediction-based Adaptive Duty Cycle Medium Access Control (PADC-MAC) energy-aware protocols lack scalable task distribution strategies and real-time adaptation across edge clusters. To overcome these limitations, this study proposes a Solar-Aware Load-Balancing Network (SOLA-LBNet), which is a solar-powered adaptive loadbalancing framework for edge-based energy-harvesting WSNs. This framework combines a hybrid Long Short-Term Memory with a Gated Recurrent Unit (LSTM-GRU) predictor for accurate solar irradiance forecasting based on historical sunlight data, weather patterns, and time features. Next, the nodes in the harvesting WSNs utilize the predicted energy levels with the proposed Energy-Aware Fuzzy C-Means (EA-FCM) algorithm, which forms adaptive clusters for nodes. Subsequently, tasks are scheduled using a Priority-Weighted Round-Robin (PWRR) scheduling protocol based on energy availability, task urgency, and packet transmission time delays. Finally, each cluster has an energy-resilient MAC controller that adjusts the duty cycle and transceiver activity through realtime prediction feedback. The experimental results demonstrated significant improvements over the PADC-MAC model, achieving a reduction in energy consumption of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{7 5. 2 \%}$</tex> per bit.