A Semantic Driven Framework for Energy Efficient Task Scheduling in Dynamic Cloud Environment
Aarav Kannan Jayakumar, R. S. Amshavalli, Venkateswara Reddy D, Vineeth S. Varma, G. Kavitha · 2025
The rapid expansion of cloud computing has led to increased energy consumption, raising concerns about its environmental impact. Despite advancements in scheduling algorithms, existing methods face critical challenges, including suboptimal energy efficiency, limited adaptability to dynamic cloud environments, and insufficient context-aware decision-making. Recent techniques, such as Meta Reinforcement Learning, Genetic Algorithms, and Energy-Aware Scheduling, show potential but often struggle with high computational complexity, static resource allocation, or scalability issues. These shortcomings result in inefficient resource utilization, elevated energy usage, and difficulties in meeting Service Level Agreement (SLA) requirements. To address these challenges, this study introduces the Energy Efficient Semantic Scheduling Framework (ESSF), a novel approach combining semantic reasoning and energy profiling to optimize task scheduling in dynamic cloud environments. The framework integrates three key components: (1) Dynamic Energy Profiling (DEP) for real-time energy monitoring, (2) Semantic Resource Matching (SRM) utilizing knowledge graphs for context-aware allocation, and (3) Adaptive Workload Balancing (AWB) to dynamically redistribute tasks for improved resource utilization and energy efficiency. Experiments using the Google Cluster Trace Dataset demonstrate that ESSF reduces energy consumption by up to 25% compared to traditional methods while achieving 90% resource utilization and 97% SLA compliance. These results highlight the potential of the proposed framework to overcome existing limitations, offering a scalable, adaptive, and environmentally sustainable solution for task scheduling in cloud computing.