International Journal of Information Technology and Computer Science (IJITCS)
IJITCS Vol. 18, No. 5, 8 Oct. 2026
Cover page and Table of Contents: PDF (size: 1077KB)
GreenCloud-RL: Carbon-Aware Multi-Cloud Scheduling with SLA Guarantees
PDF (1077KB), PP.122-137
Views: 0 Downloads: 0
Author(s)
T. Venkata Ramanao
1,*
Narendra Kumar
2
Karthi Govindharaju
3
D. Lakshmi
4
Javvaji Venkata Rao
5
B. H. Krishna Mohan
6
Index Terms
Multi-cloud Fleets, Queueing-based Latency Predictors, Short-horizon Forecasts, Grid Carbon Intensity, Electricity Price
Abstract
We present GreenCloud-RL, a formally defined scheduler for multi-cloud fleets that jointly optimizes carbon emissions, operational cost, and service-level agreement (SLA) risk. The scheduling problem is modeled as a constrained Markov decision process (CMDP) in which expected cost–carbon reward is maximized subject to aggregate SLA-risk and power-cap constraints. The framework integrates (i) a physics-informed DVFS power model, (ii) queueing-theoretic latency predictors, (iii) probabilistic short-term forecasts of regional grid carbon intensity and electricity price with uncertainty penalties, and (iv) a dual-variable actor–critic algorithm that provably enforces constraint satisfaction online. We analyze the algorithm’s convergence under bounded rewards and provide distributed complexity bounds for large-scale multi-cloud control. Empirical evaluation on production-like workloads shows that GreenCloud-RL reduces SLA-violation rate by 37.6% and power-cap violations by 53.8%, while lowering mean tardiness to 1.9 s and improving throughput by 4.2% compared with strong baselines. A region×regime analysis (load ∈ {low, medium, high}; grid ∈ {clean, neutral, dirty}) demonstrates consistent reductions in both cost and carbon emissions without degrading SLA satisfaction. Post-hoc calibration improves reliability (ECE 4.8%→1.7%, lower Brier score), enabling trustworthy on-time probability estimates for risk-aware admission and tenant-tier guarantees. Scalability tests show a p95 scheduling latency of ≈41 ms at 100k jobs, ≈0.25 ms inference per decision, modest CPU/GPU overhead, and ≈5 s controller failover. These results establish, both theoretically and empirically, that multi-objective optimization of carbon, cost, and reliability is achievable in production-scale cloud environments while maintaining contractual SLA guarantees.
Cite This Paper
T. Venkata Ramanao, Narendra Kumar, Karthi Govindharaju, D. Lakshmi, Javvaji Venkata Rao, B. H. Krishna Mohan, "GreenCloud-RL: Carbon-Aware Multi-Cloud Scheduling with SLA Guarantees", International Journal of Information Technology and Computer Science(IJITCS), Vol.18, No.5, pp.122-137, 2026. DOI:10.5815/ijitcs.2026.05.08
Reference
[1]P. B. Jawade, & S. Ramachandram, “Task scheduling in multi-cloud environment via improved optimisation theory”. International Journal of Wireless and Mobile Computing, vol 27, no.1, pp 64-77. 2024.
[2]S.Makkar, J.Sidhu, T.Zaidi, R., Batra, P., Garg, & J. Shekhawat, “Advanced model for maximizing multi-cloud security through job scheduling”. International Journal of System Assurance Engineering and Management, pp1-9. 2024."
[3]P.B.Jawade, & S.Ramachandram. “DAGWO based secure task scheduling in Multi-Cloud environment with risk probability”. Multimedia Tools and Applications, vol 83, no 1, pp 2527-2550. ,2024.
[4]K. J., Merseedi, & S. R. Zeebaree, “The cloud architectures for distributed multi-cloud computing: a review of hybrid and federated cloud environment”. The Indonesian Journal of Computer Science, vol 13, no 2. 2024.
[5]W. Zhang, S., Kosta, &, P. Mogensen, “Multi-cloud containerized service scheduling optimizing computation and communication”. In 2024 27th Conference on Innovation in Clouds, Internet and Networks (ICIN), pp. 186-193. IEEE. 2024, March.
[6]M. A. Altahat, T., Daradkeh& A. Agarwal, “Optimized encryption-integrated strategy for containers scheduling and secure migration in multi-cloud data centers”. IEEE Access, 12, pp 51330-51345. 2024.
[7]S. W. Jeong, & E. N. Huh, “A faster multi-cloud provisioning framework for microservice users”. In 2024 IEEE International Conference on Consumer Electronics (ICCE), pp. 1-4. IEEE. 2024, January.
[8]S. Mangalampalli, G. R.Karri, M. V.Ratnamani, S. N. Mohanty, B. A.Jabr, Y. A. Ali, & B. S. Abdullaeva, “Efficient deep reinforcement learning based task scheduler in multi cloud environment”. Scientific Reports, vol 14, no 1, pp 21850. 2024.
[9]S. S.Mangalampalli, G. R.Karri, S. N.Mohanty, S.Ali, M. I Khan, S.Abdullaev,& S. A. AlQahtani, “Multi-objective Prioritized Task Scheduler using improved Asynchronous advantage actor critic (a3c) algorithm in multi cloud environment”. IEEE Access, vol 12, pp11354-11377. 2024.
[10]S. Bolormaa, “lable Computational Frameworks for Big Data Processing in Multi-Cloud Environments”. American International Journal of Computer Science and Technology, vol 6, pp13-24. 2024.
[11]A. Chaiyasit, “Multi-Cloud Migration: A Framework for Selecting and Integrating Multiple Cloud Providers to Achieve Business Objectives”. Transactions on Machine Learning, Artificial Intelligence, and Advanced Intelligent Systems, vol 14, no. 10, pp27-40. 2024.
[12]M. K. Kar, S. K Swain, & S. S. Mangalampalli, “A Comprehensive Task Scheduling Algorithms in Cloud Computing: Approaches Research Directions”. In 2024 2nd International Conference on Signal Processing, Communication, Power and Embedded System (SCOPES), pp. 1-6. IEEE. 2024, December.
[13]N. Elsakaan, & K. Amroun, “A novel multi-level hybrid load balancing and tasks scheduling algorithm for cloud computing environment”. Journal of Supercomputing, vol 80, no 9. 2024.
[14]K. Jain, P.Cajla, S., Yadav, GN, M., S., Khurana, & J. Shekhawat, “QoS improvement in multi-cloud system: installation cost optimization strategy”. International Journal of System Assurance Engineering and Management, pp1-10., 2024.
[15]S. S.Sefati, M.Keymasi , R.Craciunescu, S.Maiduc, M.Bayram, & B. Arasteh, “Adaptive Resource Scheduling in Multi-Cloud Computing Using Recurrent Neural Forecasting and Memory-Based Metaheuristic Optimization”. Journal of Grid Computing, vol 23, no 4, pp 1-25. 2025.
[16]B. Nikose., & G. M. Borkar, “Toward Efficient and Secure Task Scheduling Using Trust Optimizer Multi‐Cloud Scheduler”. Security and Privacy, vol 6, pp e70104. 2025.
[17]D. Dhaanish, & N. R. Reddy,” SLA-Aware Load Balancing In Cloud Computing Using Machine Learning Based Virtual Machine Scheduling”. Journal of Computer Allied Intelligence (JCAI, ISSN: 2584-2676), vol 3, no 3, pp 11-27. 2025.
[18]V. K. S. K.Vadapalli, P. V. GurujukotaChintalapati, S., Murty, G. Kumar, & S. K. Kode, “An Effective Secure Multi-Objective Task Scheduling Algorithm in Multi-Cloud Environment”. Karbala International Journal of Modern Science, vol 11, no1, pp14. 2025.
[19]Y.Liang, G.Xu, Y.Wang, & N. Ruan, “Multi-Agent Reinforcement Learning-Based Job Scheduling for Cumulative Data Processing in Multi-Cloud Environments”. In 2025 5th International Conference on Computer, Control and Robotics (ICCCR). pp. 483-488. IEEE. 2025, May.
[20]X.Tang, F.Liu, B.Wang, J. ZhangJiang, Q.Tang, & C. P. Chen, “Cost and Makespan-Aware Task Scheduling With Deep Reinforcement Learning in Multicloud Environments”. IEEE Transactions on Computational Social Systems. 2025.
[21]N. Selvamuthukumaran, K.Aravinda, B. Manjunatha, & A. Thirumalraj, “Breast cancer detection using Mother Optimisation Algorithm based chaotic map with private AI model”. In Sustainable Development Using Private AI. pp. 278-294. CRC Press. 2024.
[22]J. P.Appadurai, T. Rajesh, R.Yugha, R.Sarkar, A.Thirumalraj, B. P. Kavin, &, G. H. Seng.”Prediction of EV charging behavior using BOA-based deep residual attention network”. Revista Internacional de Metodos Numericos para Calculo y Diseno en Ingenieria, vol 40, no.2, pp16. 2024.