Statistical and Machine Learning Approaches for Cloud Optimization: An Evaluation of Genetic Programming, Regression Analysis, and Finite-State Models
Keywords:
Cloud Optimization, Genetic Programming (GP), Regression Analysis (RA), Finite- State Models (FSM), Task Scheduling, Resource Allocation, Cloud ComputingAbstract
Cloud computing optimization is critical for increasing system efficiency, managing resources, and lowering operating costs. This study compares the effectiveness of Genetic Programming (GP), Regression Analysis (RA), and Finite-State Models (FSM) for optimizing cloud resource allocation and task scheduling. The Combined Optimization Method, which incorporates several techniques, is compared to separate models to evaluate performance across important metrics such as execution time, cost efficiency, prediction accuracy, resource utilization, system reliability, throughput, and latency. The Combined Optimization Method regularly outperforms separate
models, with considerable gains in system reliability (94.3%), throughput (170 requests/sec), and prediction accuracy (0.88 R²). This hybrid method provides an adaptable, scalable, and efficient option for improving cloud settings
References
Nyathi, T., Pillay, N., & Pillay, N. (2018). Comparison of a genetic algorithm to grammatical evolution for automated design of genetic programming classification algorithms. Expert Systems With Applications, 104, 213–234. https://doi.org/10.1016/J.ESWA.2018.03.030
Peddi, S., Narla, S., & Valivarthi, D. T. (2018). Advancing geriatric care: Machine learning algorithms and AI applications for predicting dysphagia, delirium, and fall risks in elderly patients. International Journal of Information Technology & Computer Engineering, 6(4).
Hwang, J.-S., & Hu, T.-H. (2015). A stepwise regression algorithm for high-dimensional variable selection. Journal of Statistical Computation and Simulation, 85(9), 1793–1806. https://doi.org/10.1080/00949655.2014.902460
Chernukho, E. V. (2015). Regression Algorithm Using the Rank Measure. Journal of Engineering Physics, 88(4), 1034–1043. https://doi.org/10.1007/S10891-015-1282-7
Chen, D., Wang, Z., & Su, Q. (2018). Finite-Time $$H_ ext{∞}$$ Model Reference Control for Linear Systems Based on Average Dwell-Time Approach. Circuits Systems and Signal Processing, 37(11), 4773–4788. https://doi.org/10.1007/S00034-018-0801-0
Jia, S., Tang, R., Lv, J., Yuan, Q., & Peng, T. (2017). Energy consumption modeling of machining transient states based on finite state machine. The International Journal of Advanced Manufacturing Technology, 88(5), 2305–2320. https://doi.org/10.1007/S00170- 016-8952-2
Guerrero, C., Lera, I., and Juiz, C. (2018). Genetic algorithm for multi-objective optimization of container allocation in cloud architecture. Journal of Grid Computing, 16, 113-135.
Gobalakrishnan, N., and Arun, C. (2018). A new multi-objective optimal programming model for task scheduling using genetic gray wolf optimization in cloud computing. The Computer Journal, 61(10), 1523-1536.
Buzhinsky, I. P., Ulyantsev, V. I., Chivilikhin, D. S., and Shalyto, A. A. (2014). Inducing finite state machines from training samples using ant colony optimization. Journal of Computer and Systems Sciences International, 53, 256-266.
Rao, N., Lal, P. K., and Venkatarathanam, K. (2018). Optimizing the Cloud Service Provider and its User in Cloud. Journal of Emerging Technologies and Innovative Research, 5(7), 1320–1326. https://www.jetir.org/view?paper=JETIRC006228
Guo, L., and Qiu, J. (2018). Optimization technology in cloud manufacturing. The International Journal of Advanced Manufacturing Technology, 97(1), 1181–1193. https://doi.org/10.1007/S00170-018-1991-0
Jun, S., Lee, S.-J., and Ryu, J.-B. (2015). A Divided Regression Analysis for Big Data. International Journal of Software Engineering and Its Applications, 9(5), 21–32. https://doi.org/10.14257/IJSEIA.2015.9.5.03
Huynh, Q. N., Chand, S., Singh, H. K., and Ray, T. (2018). Genetic programming with mixed-integer linear programming-based library search. IEEE Transactions on Evolutionary Computation, 22(5), 733-747.
Santos, A., Carvalho, C. R., Almeida, J. M., Moura, E. S. de, Silva, A. S. da, and Ziviani, N. (2015). A genetic programming framework to schedule webpage updates. Information Retrieval, 18(1), 73–94. https://doi.org/10.1007/S10791-014-9248-5
Kudjo, P. K., Ocquaye, E. N. N., and Ametepe, W. (2017). Review of Genetic Algorithm and Application in Software Testing. International Journal of Computer Applications, 160(2), 1–6. https://doi.org/10.5120/IJCA2017912965
Sharma, A., Patani, R., and Aggarwal, A. (2016). Software testing using genetic algorithms. International Journal of Computer Science & Engineering Survey, 7(2), 21– 33. https://doi.org/10.5121/IJCSES.2016.7203
Madhavi, D., and nagineni, S. kumar. (2018). A Review on Machine Learning Based Resource Allocation in Cloud Computing. International Journal of Research, 5(01), 3840– 3850. https://journals.pen2print.org/index.php/ijr/article/download/13476/12720
Basu, S., and R, S. (2017). Cloud Computing and Big Data for Genomics: A Review. International Journal of Advanced Research in Computer Science, 8(3), 728–731. https://doi.org/10.26483/IJARCS.V8I3.3085
Veeramachaneni, K., Arnaldo, I., Derby, O., & O’Reilly, U. M. (2015). FlexGP: Cloudbased ensemble learning with genetic programming for large regression problems. Journal of Grid Computing, 13, 391-407.
Natarajan, D. R. (2018). A hybrid particle swarm and genetic algorithm approach for optimizing recurrent and radial basis function networks in cloud computing for healthcare disease detection. International Journal of Engineering Research and Science & Technology, 14(4).
Jadon, R. (2018). Optimized machine learning pipelines: Leveraging RFE, ELM, and SRC for advanced software development in AI applications. International Journal of Information Technology & Computer Engineering, 6(1).
Nippatla, R. P. (2018). Secure cloud-based financial analysis system for enhancing Monte Carlo simulations and deep belief network models using bulk synchronous parallel processing. International Journal of Information Technology & Computer Engineering, 6(3).
