Task scheduling in multi-cloud-based IoT is a very relevant issue as the demand on energy-efficient and environmentally conscious computing is growing. The proposed study suggests that a Quantum-Inspired Metaheuristic-based scheduling method based on a Quadratic Unconstrained Binary Optimization (QUBO) model could be used to optimize the task allocation among IoT devices over distributed cloud resources. The main goal is to reduce key performance parameters, such as temperature, cost, energy consumption, and carbon emissions, which are essential in sustainable cloud operations. The suggested approach is assessed on the CEA-Curie workload data set in the CloudSim simulation platform and compared to such traditional algorithms as Genetic Algorithm (GA), Deep Reinforcement Learning (DRL), and Asynchronous Advantage Actor-Critic (A3C). The experimental findings show that the QUBO-based algorithm is much better than the current method with an average temperature, operational cost, energy consumption, and carbon reduction of 21.8%, 19.5%, 24.3%, and 22.7% respectively relative to baseline algorithms. These enhancements indicate that quantum-inspired optimization is effective in solving more complicated multi-objective scheduling issues. The results indicate that the suggested model offers a scalable and sustainable solution to next-generation IoT-cloud ecosystems, which helps increase the impact of reduced environmental impact and improved resource efficiency in multi-cloud systems.
Ritu Singh, Srinivasa Reddy Arekuti, Sai Mounika Chintalapudi et al.· International Conference Com...· 0 citations
The rapid growth of Internet of Things (IoT) applications has introduced significant challenges in efficient task scheduling within distributed cloud environments, particularly in meeting Quality of Service (QoS) requirements while minimizing operational costs and SLA violations. To address this issue, this paper proposes an AI-Based Hybrid Detective Behavior Optimization (DBA) technique integrated with fuzzy systems for intelligent task scheduling of IoT workloads. The proposed approach leverages the exploration–exploitation capabilities of DBA along with fuzzy logic-based decision-making to dynamically prioritize and allocate tasks under uncertain and heterogeneous cloud conditions. The model is evaluated using the DigitalOcean cloud workload in the WorkflowSim simulation environment and compared against traditional methods including Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Deep Reinforcement Learning (DRL). Experimental results demonstrate that the proposed DBA-Fuzzy approach significantly outperforms baseline methods by reducing SLA violations by 24.6%, improving QoS by 21.3%, minimizing execution cost by 18.9%, and enhancing throughput by 26.7%. These improvements highlight the robustness and adaptability of the proposed model in handling dynamic IoT workloads. The findings suggest that integrating metaheuristic optimization with fuzzy reasoning provides an effective solution for multi-objective task scheduling, making it highly suitable for next-generation distributed cloud environments supporting large-scale IoT applications.
Suryateja Kothuru, Sudipta Priyadarshini, Sai Mounika Chintalapudi et al.· International Conference Com...· 0 citations
The fast growth of Internet of Things (IoT) applications within the distributed cloud has posed considerable difficulties in terms of secure, scalable and efficient task scheduling and adherence to strict Quality of Service (QoS) and Service Level Agreement (SLA) requirements. In order to overcome these challenges, this paper presents a proposal of an Intelligent Security-Aware Metaheuristic-based schedule tool using the Stochastic Paint Optimizer (SPO) on the CloudSim simulation platform. The suggested model combines security requirements and adaptive stochastic exploration to optimize the allocation of tasks with the help of the Google Cloud Jobs Dataset (GoCJ) and achieve a better system robustness and performance. The quality of the SPO method is compared to the state-of-the-art methods, such as Particle Swarm Optimization (PSO), Deep Reinforcement Learning (DRL), and Deep Deterministic Policy Gradient (DDPG). The experimental findings show that the proposed SPO method has high performance improvements, such as a latency decrease of 27.8%, scalability improvement of 31.4%, SLA compliance increase of 29.6%, and QoS improvement of 33.2% in comparison to the current methods. These findings suggest that the SPO-based scheduling framework does not only improve resource utilization and security awareness but also provides reliable and efficient execution of tasks in dynamic distributed clouds environments, which makes it a promising solution to next-generation IoT-cloud systems.
C. Veena, Sai Mounika Chintalapudi, Srinivasa Reddy Arekuti et al.· International Conference Com...· 0 citations