AI-driven energy optimization and routing strategy for solar-powered wireless sensor networks in precision agriculture

Abstract:

Solar-powered wireless sensor networks are increasingly relevant for precision agriculture because they can support continuous observation of soil, crop, and microclimatic conditions without frequent battery replacement. Their practical use, however, is limited by uneven solar charging, spatially variable communication distance, packet loss, and the energy-hole effect around gateway nodes. This paper presents a revised artificial-intelligence-based framework for energy prediction, routing selection, and duty-cycle control in solar-powered agricultural sensor networks. The framework combines field sensing, energy-state monitoring, data cleaning, residual-energy forecasting, route scoring, and advisory-system integration. A routing score is proposed by jointly considering residual battery level, expected solar recharge, link quality, hop distance, forwarding load, and agronomic urgency of the sensed data. The model is designed for either gateway-level decision-making or lightweight distributed deployment, depending on farm size and sensor-node capacity. The proposed approach is evaluated conceptually through network-lifetime, packet-delivery, delay, dead-node, residual-energy, and data-continuity indicators. The discussion shows that energy-aware routing should not be treated only as a communication task; it also influences the availability of timely field information for irrigation scheduling, crop-stress detection, and farm resource management. Field validation across crop stages, seasons, and weather conditions is recommended before large-scale deployment.