Recent research in Energy-aware Task Scheduling in Cloud Computing emphasizes designing intelligent scheduling algorithms that minimize energy consumption while maintaining optimal performance and quality of service. These studies propose dynamic and adaptive scheduling mechanisms that allocate tasks to virtual machines based on workload characteristics, resource availability, and power efficiency. Advanced approaches integrate reinforcement learning, evolutionary optimization, and hybrid meta-heuristics such as Cuckoo Search, Genetic Algorithms, and Particle Swarm Optimization to achieve an optimal trade-off between energy use and execution time. Energy-aware task scheduling also incorporates predictive models and AI-based workload forecasting to proactively manage resources, reduce idle energy consumption, and enhance sustainability. Recent frameworks extend these methods to green cloud, fog, and edge systems to ensure energy-efficient operations across distributed computing infrastructures.