Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{197978,
        author = {Perbhat Singh and Dr. Yogesh},
        title = {Machine Learning Driven Task Scheduling for Sustainable and Energy Efficient Cloud Infrastructure},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {8116-8124},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197978},
        abstract = {The rapid expansion of cloud computing has transformed the global digital ecosystem by enabling scalable, flexible, and on-demand computing services for governments, industries, academic institutions, and individual users. However, the large-scale growth of cloud infrastructure has also increased energy consumption, carbon footprint, heat generation, and operational complexity in data centers. In this context, task scheduling has emerged as one of the most critical mechanisms for improving resource utilization, service quality, and energy efficiency in cloud environments. Conventional scheduling methods are often rule-based, static, or reactive, and therefore they struggle to adapt to dynamic workloads, heterogeneous infrastructure, fluctuating user demand, and sustainability goals. This research article explores the role of machine learning-driven task scheduling as an intelligent and adaptive framework for building sustainable and energy-efficient cloud infrastructure. The study adopts an exploratory and conceptual research approach to examine how machine learning models can predict workload patterns, classify task behavior, optimize task placement, reduce idle resource consumption, and support green cloud operations. The article discusses the limitations of traditional scheduling methods, explains the relevance of supervised, unsupervised, and reinforcement learning techniques, and proposes an innovative framework for energy-aware task scheduling in cloud systems. It further evaluates the potential of machine learning to improve makespan, throughput, SLA compliance, load balancing, and power efficiency simultaneously. The findings suggest that machine learning-driven scheduling is not merely a technical enhancement but a strategic pathway toward sustainable cloud infrastructure. The article concludes that intelligent task scheduling can significantly contribute to the future of green computing by enabling adaptive, predictive, and context-aware resource management in cloud data centers.},
        keywords = {Cloud computing, task scheduling, machine learning, sustainable infrastructure, energy efficiency, green cloud computing, resource optimization, intelligent scheduling.},
        month = {April},
        }