AUT Journal of Electrical Engineering

AUT Journal of Electrical Engineering

An Attention-Driven Deep Reinforcement Learning Framework for Energy-Efficient and Service-Level Agreement-Aware Cloud Task Scheduling

Document Type : Research Article

Authors
Rahul Bhatt 1
Ritika Mehra 2
Kamal Upreti 3
1 School of Engineering & Computing, Dev Bhoomi Uttarakhand University, Dehradun, Uttarakhand, India
2 School of Engineering & Computing, Dev Bhoomi Uttarakhand University Dehradun, Uttarakhand, India
3 Department of Computer Science, Christ University, Delhi NCR Campus, Ghaziabad, India
10.22060/eej.2026.25455.5936
Abstract
Dynamic cloud and edge-cloud platforms require task schedulers that can respond to stochastic workloads while minimizing energy use and preserving service-level agreement reliability. This study proposes an attention-driven deep reinforcement learning framework for energy-efficient and service-level agreement-aware cloud task scheduling. The framework combines lightweight convolutional neural network and long short-term memory-based spatial-temporal feature extraction with a multi-head self-attention actor-critic decision module. The convolutional neural network and long short-term memory components capture local virtual machine workload patterns, whereas self-attention models global virtual-machine-to-virtual-machine dependencies for parallel and context-aware scheduling. The scheduling problem is formulated as a Markov decision process using a 242-dimensional virtual-machine-level state representation, probabilistic virtual-machine-to-host assignment actions, and a multi-objective reward function covering makespan, energy consumption, operational resource cost, and service-level agreement penalties. Experiments were conducted in a heterogeneous CloudSim environment with 100 hosts and 100 virtual machines. The proposed framework achieved a normalized makespan of approximately 0.85, a 14.4% reduction in total energy consumption, consistently low service-level agreement violation behavior, and controlled migration activity. Logged analysis further showed a response time of 10.0000 milliseconds per completed task or virtual machine event, supporting interval-based real-time feasibility. Cost is treated as an operational reward component, not as a standalone billing analysis.
Keywords
Cloud Computing
Task Scheduling
Deep Reinforcement Learning
Multi-Head Self-Attention
Actor-Critic Learning
Energy Efficiency
Service-Level Agreement-Aware Scheduling
CloudSim
Subjects
[1]        S. Gupta et al., "Efficient prioritization and processor selection schemes for heft algorithm: A makespan optimizer for task scheduling in cloud environment," Electronics, vol. 11, no. 16, p. 2557, 2022.
[2]        T. Bezdan, M. Zivkovic, N. Bacanin, I. Strumberger, E. Tuba, and M. Tuba, "Multi-objective task scheduling in cloud computing environment by hybridized bat algorithm," Journal of Intelligent & Fuzzy Systems, vol. 42, no. 1, pp. 411–423, 2021.
[3]        R. Ghafari, F. H. Kabutarkhani, and N. Mansouri, "Task scheduling algorithms for energy optimization in cloud environment: a comprehensive review," Cluster Computing, vol. 25, no. 2, pp. 1035–1093, 2022.
[4]        P. Tank and R. Jain, "Big Data in the Internet of Things IoT Sensor Data Analysis and Edge Computing," in Advancements in Cloud-Based Intelligent Informative Engineering: IGI Global Scientific Publishing, 2025, pp. 79–94.
[5]        L. H. Al-Farhani, Y. Alqahtani, H. A. Alshehri, R. J. Martin, S. Lalar, and R. Jain, "[Retracted] IOT and Blockchain‐Based Cloud Model for Secure Data Transmission for Smart City," Security and Communication Networks, vol. 2023, no. 1, p. 3171334, 2023.
[6]        Z. Zhou, F. Li, H. Zhu, H. Xie, J. H. Abawajy, and M. U. Chowdhury, "An improved genetic algorithm using greedy strategy toward task scheduling optimization in cloud environments," Neural Computing and Applications, vol. 32, no. 6, pp. 1531–1541, 2020.
[7]        S. E. Shukri, R. Al-Sayyed, A. Hudaib, and S. Mirjalili, "Enhanced multi-verse optimizer for task scheduling in cloud computing environments," Expert Systems with Applications, vol. 168, p. 114230, 2021.
[8]        P. Pirozmand, H. Jalalinejad, A. A. R. Hosseinabadi, S. Mirkamali, and Y. Li, "An improved particle swarm optimization algorithm for task scheduling in cloud computing," Journal of Ambient Intelligence and Humanized Computing, vol. 14, no. 4, pp. 4313–4327, 2023.
[9]        S. K. Balam, R. Jain, J. S. Alaric, B. Pattanaik, and T. B. Ayele, "Renewable energy integration of IoT systems for smart grid applications," in 2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC), 2023: IEEE, pp. 374–379.
[10]      R. Jain, Y. Bekuma, B. Pattanaik, A. Assebe, and T. Bayisa, "Design of a smart wireless home automation system using fusion of IoT and machine learning over cloud environment," in 2022 3rd International Conference on Intelligent Engineering and Management (ICIEM), 2022: IEEE, pp. 840–847.
[11]      R. Medara and R. S. Singh, "Energy-efficient and reliability-aware workflow task scheduling in cloud environment," Wireless Personal Communications, vol. 119, no. 2, pp. 1301–1320, 2021.
[12]      A. Amini Motlagh, A. Movaghar, and A. M. Rahmani, "Task scheduling mechanisms in cloud computing: A systematic review," International Journal of Communication Systems, vol. 33, no. 6, p. e4302, 2020.
[13]      M. Masdari and M. Zangakani, "Efficient task and workflow scheduling in inter-cloud environments: challenges and opportunities: M. Masdari, M. Zangakani," The Journal of Supercomputing, vol. 76, no. 1, pp. 499–535, 2020.
[14]      R. Jain and M. Varshney, "Group Key Management Protocols for Non-Network: A survey," Iraqi Journal for Electrical and Electronic Engineering, vol. 20, no. 1, pp. 214–225, 2024.
[15]      R. Jain and M. Varshney, "A Trust-Based Group Key Management Protocol for Non-Networks," International Journal on Recent and Innovation Trends in Computing and Communication, vol. 11, no. 6s, pp. 483–489, 2023.
[16]      G. Rjoub, J. Bentahar, and O. A. Wahab, "BigTrustScheduling: Trust-aware big data task scheduling approach in cloud computing environments," Future Generation Computer Systems, vol. 110, pp. 1079–1097, 2020.
[17]      M. Lavanya, B. Shanthi, and S. Saravanan, "Multi-objective task scheduling algorithm based on SLA and processing time suitable for cloud environment," Computer Communications, vol. 151, pp. 183–195, 2020.
[18]      S. C. Nayak, S. Parida, C. Tripathy, and P. K. Pattnaik, "An enhanced deadline constraint-based task scheduling mechanism for cloud environment," Journal of King Saud University-Computer and Information Sciences, vol. 34, no. 2, pp. 282–294, 2022.
[19]      S. Swarup, E. M. Shakshuki, and A. Yasar, "Task scheduling in cloud using deep reinforcement learning," Procedia Computer Science, vol. 184, pp. 42–51, 2021.
[20]      S. H. H. Madni, M. S. Abd Latiff, M. Abdullahi, S. I. M. Abdulhamid, and M. J. Usman, "Performance comparison of heuristic algorithms for task scheduling in IaaS cloud computing environment," PloS one, vol. 12, no. 5, p. e0176321, 2017.
[21]      D. Alsadie, "Advancements in heuristic task scheduling for IoT applications in fog-cloud computing: challenges and prospects," PeerJ Computer Science, vol. 10, p. e2128, 2024.
[22]      F. Juarez Pérez, J. Ejarque, and R. M. Badia Sala, "Dynamic energy-aware scheduling for parallel task-based application in cloud computing."
[23]      J.-M. Pierson, P. Stolf, H. Sun, and H. Casanova, "MILP formulations for spatio-temporal thermal-aware scheduling in Cloud and HPC datacenters," Cluster Computing, vol. 23, no. 2, pp. 421–439, 2020.
[24]      S. Mangalampalli et al., "Efficient deep reinforcement learning-based task scheduler in multi-cloud environment," Scientific Reports, vol. 14, no. 1, p. 21850, 2024.
[25]      X. Yu, J. Mi, L. Tang, L. Long, and X. Qin, "Dynamic multi-objective task scheduling in cloud computing using reinforcement learning for energy and cost optimization," Scientific Reports, 2025.
[26]      B. Kruekaew and W. Kimpan, "Multi-objective task scheduling optimization for load balancing in cloud computing environment using hybrid artificial bee colony algorithm with reinforcement learning," IEEE Access, vol. 10, pp. 17803–17818, 2022.
[27]      A. R. Khan, "Dynamic load balancing in cloud computing: optimized RL-based clustering with multi-objective optimized task scheduling," Processes, vol. 12, no. 3, p. 519, 2024.
[28]      P. Varshney and Y. Simmhan, "Characterizing application scheduling on edge, fog, and cloud computing resources," Software: Practice and Experience, vol. 50, no. 5, pp. 558–595, 2020.
[29]      Y. Ye and P. Ruan, "Enhanced Osprey Optimization Algorithm for task scheduling in cloud computing environment," Journal of Engineering and Applied Science, vol. 72, no. 1, p. 141, 2025.
[30]      Z. Chen, L. Zhang, X. Wang, and K. Wang, "Cloud–edge collaboration task scheduling in cloud manufacturing: An attention-based deep reinforcement learning approach," Computers & Industrial Engineering, vol. 177, p. 109053, 2023.
[31]      X. Wang, L. Zhang, Y. Liu, and C. Zhao, "Logistics-involved task scheduling in cloud manufacturing with offline deep reinforcement learning," Journal of Industrial Information Integration, vol. 34, p. 100471, 2023.
[32]      Z. Wang, M. Goudarzi, and R. Buyya, "TF-DDRL: A transformer-enhanced distributed DRL technique for scheduling IoT applications in edge and cloud computing environments," IEEE Transactions on Services Computing, vol. 18, no. 2, pp. 1039–1053, 2025.
[33]      K. Li, "Design and analysis of heuristic algorithms for energy-constrained task scheduling with device-edge-cloud fusion," IEEE Transactions on Sustainable Computing, vol. 8, no. 2, pp. 208–221, 2022.
AUT Journal of Electrical Engineering
Volume 58, Issue 4
2026
Pages 695-718