• Anurag Pathak
• Ayan Rajput

Energy-harvesting Wireless Sensor Networks (WSNs) have emerged as a sustainable solution for long-term monitoring applications such as environmental surveillance, disaster management, healthcare monitoring, and intelligent transportation systems. By harvesting energy from renewable sources including solar, radio frequency (RF), vibration, and thermal gradients, these networks aim to overcome the inherent limitations of battery-powered sensor nodes. However, the stochastic and intermittent nature of harvested energy introduces significant challenges in task scheduling, routing, and real-time decision making. Mobile agents provide an efficient paradigm for in-network processing and distributed intelligence by reducing communication overhead and enabling localized computation. Nevertheless, existing mobile agent–based approaches predominantly rely on static or rule-based decision mechanisms, which are ineffective in highly dynamic energy-harvesting environments. Such approaches often lead to inefficient agent migration, increased decision latency, task failures, and reduced network lifetime. This paper proposes an AI-driven adaptive mobile agent framework for energy-harvesting WSNs that enables energy-aware scheduling and real-time decision making. The proposed framework integrates a lightweight artificial intelligence model for short-term energy prediction and employs reinforcement learning–based adaptive scheduling to dynamically adjust agent behaviour. Extensive NS-3–based simulations demonstrate that the proposed approach significantly improves decision latency, task success ratio, energy efficiency, and network lifetime compared to conventional static and rule-based mobile agent systems.

"AI-Driven Adaptive Mobile Agents for Energy-Aware Scheduling and Real-Time Decision Making in Energy-Harvesting Wireless Sensor Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 1, page no.a389-a398, January-2026, Available :http://www.jetir.org/papers/JETIR2601047.pdf

"AI-Driven Adaptive Mobile Agents for Energy-Aware Scheduling and Real-Time Decision Making in Energy-Harvesting Wireless Sensor Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 1, page no. ppa389-a398, January-2026, Available at : http://www.jetir.org/papers/JETIR2601047.pdf