The Internet of Things (IoT) signifies a revolutionary technological advancement, enhancing various applications through device interconnectivity while introducing significant challenges due to these devices' limited hardware and communication capabilities. To navigate these complexities, the Internet Engineering Task Force (IETF) has tailored the Routing Protocol for Low-Power and Lossy Networks (RPL) to meet the unique demands of IoT environments. However, RPL struggles with traffic congestion and load distribution issues, negatively impacting network performance and reliability. This paper presents a novel enhancement to RPL by integrating learning automata designed to optimize network traffic distribution. This enhanced protocol, the Learning Automata-based Load-Aware RPL (LALARPL), dynamically adjusts routing decisions based on real-time network conditions, achieving more effective load balancing and significantly reducing network congestion. Extensive simulations reveal that this approach outperforms existing methodologies, leading to notable improvements in packet delivery rates, end-to-end delay, and energy efficiency. The findings highlight the potential of our approach to enhance IoT network operations and extend the lifespan of network components. The effectiveness of learning automata in refining routing processes within RPL offers valuable insights that may drive future advancements in IoT networking, aiming for more robust, efficient, and sustainable network architectures.

翻译：物联网（IoT）代表着一项革命性的技术进步，通过设备互联增强了各类应用，同时也因这些设备有限的硬件与通信能力带来了重大挑战。为应对这些复杂性，互联网工程任务组（IETF）专门为低功耗有损网络设计了路由协议（RPL），以满足物联网环境的独特需求。然而，RPL在流量拥塞与负载分配方面存在不足，对网络性能与可靠性产生了负面影响。本文提出了一种新颖的RPL增强方案，通过集成学习自动机来优化网络流量分布。该增强协议——基于学习自动机的负载感知RPL（LALARPL）能够根据实时网络状态动态调整路由决策，实现更有效的负载均衡并显著降低网络拥塞。大量仿真实验表明，该方法优于现有技术，在数据包投递率、端到端时延和能效方面均取得了显著提升。研究结果凸显了本方法在改善物联网网络运行与延长网络组件寿命方面的潜力。学习自动机在优化RPL内部路由过程中的有效性为未来物联网网络发展提供了重要启示，有助于构建更稳健、高效和可持续的网络架构。