Cloud computing has become a fundamental computing paradigm that provides scalable, virtualized, andon-demandcomputational resources for executing large volumes of user tasks. As cloud data centers continue to expand, increasingcomputationalworkloads have led to significant energy consumption, operational costs, and environmental concerns. Efficient taskschedulinghastherefore emerged as a critical research area for optimizing resource utilization while minimizing energy consumptionwithoutcompromising Quality of Service (QoS). This experimental study proposes an energy-efficient task scheduling frameworkforcloudcomputing using classical machine learning techniques to improve scheduling decisions through intelligent workloadanalysisandresource allocation. The proposed framework integrates cloud resource management, task classification, machine learning-basedscheduling, virtualization, and energy-aware optimization into a unified computational architecture. A mathematical frameworkandalgorithmic strategy are developed to evaluate scheduling efficiency, energy utilization, processing performance, resourceallocation,andsystem scalability. Experimental evaluation demonstrates that machine learning-assisted scheduling significantlyreducesenergyconsumption, improves processor utilization, decreases task execution time, and enhances overall cloud performance comparedwithconventional scheduling approaches. The proposed framework provides valuable guidance for researchers, cloud serviceproviders,anddata center administrators seeking to develop scalable, energy-efficient, and intelligent cloud scheduling systems. Keywords: Cloud Computing, Energy-Ef icient Task Scheduling, Machine Learning, Resource Allocation, Virtualization