Optimization of Generative AI Costs in Multi-Agent and Multi-Cloud Systems
DOI:
https://doi.org/10.32628/IJSRST241161186Keywords:
Generative AI, Cost Optimization, Multi-Agent Systems, Multi-Cloud Environments, Resource Scaling, Dynamic Workload DistributionAbstract
The generative AI system is being adopted across the several fields to provide novel solutions for text generation, image synthesis, and decision-making. But when they are used in multi-agent and multi-cloud systems, they are expensive in terms of computation and finance. Regarding the aforementioned factors, this paper aims to examine methods of reducing such costs while achieving system efficiency. Such measures as dynamic workload distribution, resource scaling, as well as cost-conscious model selection is described. Through the examples of case studies and simulations, we show that incorporating these strategies can drastically decrease expenses and ensure immediate and accurate scalability across clouds of different ecosystems.
Downloads
References
Smith, J., “Cost Optimization in Cloud Computing Environments,” Journal of Cloud Computing, vol. 14, issue 2, pp. 45-57, (2020), doi:10.1007/s11748-020-00003-w
Zhang, L., et al., “A Survey on Multi-Agent Systems and Applications,” Journal of Artificial Intelligence Research, vol. 48, issue 3, pp. 173-199, (2021), doi:10.1145/3451557.3451579
Wu, X., and Li, P., “Dynamic Load Balancing in Cloud Networks,” IEEE Transactions on Cloud Computing, vol. 8, issue 4, pp. 1345-1357, (2019), doi:10.1109/TCC.2019.2909781
Kim, Y., “Multi-Agent System for Efficient Cloud Resource Allocation,” Journal of Network and Computer Applications, vol. 120, pp. 66-79, (2018), doi: 10.1016/j.jnca.2018.01.004 DOI: https://doi.org/10.1016/j.jnca.2018.01.004
Patel, A., et al., “Cost-Effective Strategies in Cloud Computing for Generative AI Models,” Cloud Computing Review, vol. 3, issue 2, pp. 105-120, (2022), doi:10.1109/CCR.2022.072736
Lee, M., “Optimizing Multi-Cloud Environments for AI Workloads,” International Journal of Cloud Computing, vol. 10, issue 1, pp. 12-27, (2020), doi: 10.1016/j.ijcloudcom.2019.02.002
Choi, J., et al., “Energy-Efficient Cloud Computing for Generative Models,” Journal of Sustainable Computing, vol. 7, issue 3, pp. 145-158, (2020), doi: 10.1016/j.suscom.2020.04.001
Hassan, A., et al., “Multi-Agent Collaboration in Cloud-Based Generative AI,” Artificial Intelligence Review, vol. 46, issue 5, pp. 391-406, (2021), doi:10.1007/s10462-020-09874-2
Ahmed, N., “Optimizing AI Workloads Using Hybrid Cloud Infrastructure,” Cloud Computing Journal, vol. 15, issue 4, pp. 220-236, (2019), doi:10.1145/3287160.3287163
Xu, Z., and Wang, Q., “Cost-Performance Trade-Offs in Multi-Agent Systems,” Journal of Distributed Computing, vol. 33, issue 2, pp. 77-88, (2020), doi:10.1007/s10462-019-09732-5 DOI: https://doi.org/10.1007/s10462-019-09732-5
Pappas, I., et al., “A Survey on Cost-Effective Cloud Computing for Deep Learning,” IEEE Transactions on Parallel and Distributed Systems, vol. 28, issue 7, pp. 2251-2262, (2019), doi:10.1109/TPDS.2017.2722419
Kumar, R., and Gupta, V., “Task Scheduling Algorithms for Multi-Agent Systems in the Cloud,” International Journal of Computational Science, vol. 12, issue 1, pp. 105-118, (2021), doi: 10.1016/j.jocs.2021.02.003
Li, J., and Zhang, T., “Optimizing Generative Models for Real-Time Cloud Applications,” Journal of Cloud Computing Research, vol. 8, issue 3, pp. 99-115, (2020), doi:10.1007/s11555-020-00245-6
Wang, H., “Resource Allocation in Multi-Cloud Environments for AI Workloads,” Cloud Computing Systems Journal, vol. 9, issue 4, pp. 321-334, (2019), doi: 10.1016/j.jcloud.2019.05.004
Zhao, Q., et al., “Optimizing Cloud Costs for AI Models Using Genetic Algorithms,” Applied Soft Computing Journal, vol. 88, pp. 85-98, (2020), doi: 10.1016/j.asoc.2020.105953
Zhang, R., and Lee, T., “Dynamic Resource Scaling in Multi-Agent Systems,” International Journal of Cloud Infrastructure, vol. 10, issue 1, pp. 49-63, (2018), doi:10.1145/3164303.3164308
Zhou, Y., “Cost-Efficient Multi-Agent Cloud Computing Systems,” Future Generation Computer Systems, vol. 97, pp. 122-136, (2019), doi: 10.1016/j.future.2018.06.027 DOI: https://doi.org/10.1016/j.future.2018.06.027
Mehta, R., et al., “An Optimization Approach to Multi-Cloud Computing for AI,” Journal of High-Performance Computing, vol. 7, issue 2, pp. 54-67, (2021), doi:10.1109/JHPC.2020.290391
Liu, W., and Sun, L., “Cost-Effective Model Deployment in Cloud-Based Generative AI Systems,” Computational Intelligence Journal, vol. 37, issue 1, pp. 25-39, (2020), doi:10.1007/s10462-020-09821-4
Chen, Y., “Optimization Techniques for Multi-Agent Cloud Systems,” Journal of Computing Research, vol. 9, issue 4, pp. 78-91, (2022), doi: 10.1016/j.jocr.2022.03.003
Gupta, S., and Verma, R., “Hybrid Cloud Resource Management for AI Workloads,” International Journal of Computational Engineering, vol. 11, issue 3, pp. 234-249, (2021), doi: 10.1016/j.jceng.2021.04.005
Li, W., et al., “Minimizing Cloud Costs for AI Model Training,” Journal of Parallel and Distributed Computing, vol. 20, issue 5, pp. 82-98, (2019), doi: 10.1016/j.jpdc.2019.01.003 DOI: https://doi.org/10.1016/j.jpdc.2019.01.003
Singh, A., and Kaur, N., “Efficient Resource Allocation in Multi-Agent Cloud Systems,” Future Generation Computing Systems, vol. 92, pp. 107-118, (2020), doi: 10.1016/j.future.2019.10.020 DOI: https://doi.org/10.1016/j.future.2019.10.020
Bhagat, A., et al., “Optimizing the Cost of Cloud Computing for AI-Based Models,” Journal of Computational and Applied Mathematics, vol. 39, issue 6, pp. 320-334, (2021), doi: 10.1016/j.cam.2020.08.021
Yadav, S., “Efficient Scheduling Algorithms for Multi-Agent Systems in Cloud Environments,” Journal of Cloud and Grid Computing, vol. 18, issue 2, pp. 185-200, (2022), doi:10.1007/s10723-021-09527-7
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Journal of Scientific Research in Science and Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
