ISCC: Intelligent Semantic Caching and Control for NDN-Enabled Industrial IoT Networks
Zupash Awais, Muzammil Hussain, Ayman Elshenawy, Ahmad Arsalan, Muhammad Anwar, Muhammad Asif Habib, Sohail Jabbar, Mudassar Ahmad
Abstract
Effective content caching plays a crucial role in meeting the latency and reliability requirements of Industrial Internet of Things (IIoT) networks. However, existing caching mechanisms in NDN-based IIoT networks often exhibit problems in adaptability, semantic awareness, and structural efficiency, resulting in limited performance in dynamic and resource-constrained environments. This paper introduces the Intelligent Semantic-Aware Caching and Control framework (ISCC), which integrates Cuckoo Hashing with Reinforcement Learning (RL) to enhance content replacement decisions in IIoT networks based on Named Data Networking (NDN). The framework presents a semantic scoring model that integrates content domain, source reliability, and criticality to enhance caching prioritisation. A reinforcement learning (RL) agent utilising Q-learning dynamically chooses actions by using unified caching scores that take into account frequency, time, and semantic fidelity. The results of the simulation indicate that ISCC outperforms conventional strategies, such as FIFO, LRU, and LRFU, in terms of cache hit ratio, semantic fidelity, and latency, achieving up to 23% fewer replacements and a 16% improvement in preserving semantic content. The results show ISCC’s capability to facilitate intelligent and adaptive caching in memory-constrained IIoT environments.