Sustainable Smart Farm Networks: Enhancing Resilience and Efficiency with Decision Theory-Guided Deep Reinforcement Learning

TL;DR

The paper tackles resilient, energy-aware animal monitoring for solar-powered smart farms under cyber threats. It introduces a decision-theory-guided deep reinforcement learning (DT-guided DRL) framework that combines DT utilities with PPO-based learning to accelerate convergence and improve robustness, complemented by transfer learning strategies. Key contributions include uncertainty-aware data aggregation, deceptive-data detection via Subjective Logic, and a comprehensive simulation study showing that DT-guided DRL achieves higher monitoring quality and faster training times (e.g., 47.5% reduction vs TL-based DRL) while maintaining resilience to cyber-attacks. The work demonstrates practical impact for sustainable, scalable IoT-fueled farming, offering a pathway toward secure, energy-efficient, autonomous livestock monitoring in resource-constrained environments.

Abstract

Solar sensor-based monitoring systems have become a crucial agricultural innovation, advancing farm management and animal welfare through integrating sensor technology, Internet-of-Things, and edge and cloud computing. However, the resilience of these systems to cyber-attacks and their adaptability to dynamic and constrained energy supplies remain largely unexplored. To address these challenges, we propose a sustainable smart farm network designed to maintain high-quality animal monitoring under various cyber and adversarial threats, as well as fluctuating energy conditions. Our approach utilizes deep reinforcement learning (DRL) to devise optimal policies that maximize both monitoring effectiveness and energy efficiency. To overcome DRL's inherent challenge of slow convergence, we integrate transfer learning (TL) and decision theory (DT) to accelerate the learning process. By incorporating DT-guided strategies, we optimize monitoring quality and energy sustainability, significantly reducing training time while achieving comparable performance rewards. Our experimental results prove that DT-guided DRL outperforms TL-enhanced DRL models, improving system performance and reducing training runtime by 47.5%.

Figures (7)

• Figure 1: The considered multi-agent DRL environment.
• Figure 2: The considered wireless solar sensor-based smart farm network.
• Figure 3: Decision-making procedure of a DT-guided DRL agent.
• Figure 4: Comparative performance analysis during training time with $P_A = 0.1$.
• Figure 5: Effect of Varying Attack Severity ($P_A$) on Solar Sensors.