Data Scheduling Algorithm for Scalable and Efficient IoT Sensing in Cloud Computing

TL;DR

This paper introduces a hybrid deep Reinforcement Learning and Ant Colony Optimization algorithm for scalable, efficient IoT data scheduling in cloud computing, improving response time, resource use, and energy efficiency under diverse workloads.

Contribution

It presents a novel hybrid scheduling approach combining RL and ACO to adaptively optimize IoT data processing in cloud environments, addressing workload variability and QoS demands.

Findings

Up to 18.4% reduction in response time

12.7% improvement in resource utilization

9.3% decrease in energy consumption

Abstract

The rapid growth of Internet of Things (IoT) devices produces massive, heterogeneous data streams, demanding scalable and efficient scheduling in cloud environments to meet latency, energy, and Quality-of-Service (QoS) requirements. Existing scheduling methods often lack adaptability to dynamic workloads and network variability inherent in IoT-cloud systems. This paper presents a novel hybrid scheduling algorithm combining deep Reinforcement Learning (RL) and Ant Colony Optimization (ACO) to address these challenges. The deep RL agent utilizes a model-free policy-gradient approach to learn adaptive task allocation policies responsive to real-time workload fluctuations and network states. Simultaneously, the ACO metaheuristic conducts a global combinatorial search to optimize resource distribution, mitigate congestion, and balance load across distributed cloud nodes. Extensive experiments on large-scale synthetic IoT datasets, reflecting diverse workloads and QoS constraints, demonstrate that the proposed method achieves up to 18.4% reduction in average response time, 12.7% improvement in resource utilization, and 9.3% decrease in energy consumption compared to leading heuristics and RL-only baselines. Moreover, the algorithm ensures strict Service Level Agreement (SLA) compliance through deadline-aware scheduling and dynamic prioritization. The results confirm the effectiveness of integrating model-free RL with swarm intelligence for scalable, energy-efficient IoT data scheduling, offering a promising approach for next-generation IoT-cloud platforms.