This review examines current approaches to real-time decision-making and task optimization in Internet of Things systems through the application of machine learning models deployed at the network edge. Existing literature shows that edge-based distributed intelligence reduces cloud dependency. It addresses transmission latency, device energy use, and bandwidth limits. Recent optimization strategies employ dynamic task offloading mechanisms to determine optimal workload placement across local devices and edge servers without centralized coordination. Empirical findings from the literature indicate performance improvements with latency reductions of approximately 32.8% and energy efficiency gains of 27.4% compared to conventional cloud-centric models. However, critical gaps remain in current methodologies. Most studies focus on static network topologies and do not adequately address load balancing across multiple edge nodes. Security vulnerabilities during task transmission are underexplored, and privacy considerations for sensitive data remain insufficiently integrated into existing frameworks. Task caching strategies and fault tolerance mechanisms require further investigation in highly dynamic environments. The ability of existing approaches to handle large-scale deployments and complex edge-cloud collaborative scenarios has not been thoroughly validated. This review synthesizes current progress while identifying fundamental challenges that must be resolved for practical deployment in time-sensitive applications spanning smart manufacturing, autonomous systems, and healthcare monitoring. Future work should prioritize robust security integration, efficient load distribution, and scalability across heterogeneous edge infrastructures.
Hitesh Mohapatra (Thu,) studied this question.