004.632

data backup, machine learning, proximal policy optimization, backup strategy, compression solution, reinforcement learning, application server.

Efficient data compression is a critical component of modern data backup systems, particularly in environments with diverse file types and different performance features. Backups safeguard critical application server data against unexpected failures, such as hardware malfunctions, software bugs, or cyberattacks, ensuring business continuity. Many industries maintain secure data backups to meet legal and regulatory requirements, ensuring loyalty to data protection and privacy laws. However regular backup solutions are often unable to adapt effectively to the changing data of the application server. This paper proposes a novel reinforcement learning (RL) approach using the Proximal Policy Optimization (PPO) model to dynamically optimize data archiving strategy, which is part of backup systems. The model is trained to predict the most efficient combination of compression parameters based on the attributes of files in the target file system. By learning from file-specific observations and rewards, it adapts to work in a backup-specific environment to minimize consumed disk storage and backup time. This adaptive approach enables real-time decision-making tailored to workload variations of the application server environment. The proposed solution performs backup operations across various file types and configurations for the learning phase, where the model evaluates and adjusts policy to maximize its efficiency. To evaluate the results another client should perform all possible combinations of action parameters to determine all possible observations and rewards. The rewards are compared to decisions made by the proposed solution to ensure PPO model has correct and best possible predictions during the evaluation phase. This study highlights the potential of RL in automating and optimizing data backup tasks, providing a scalable solution for high-performance systems or environments with frequent data writes. The results obtained contribute to improving the software backup systems and DevOps specialists' work and reduce disk storage consumption and time elapsed for backup tasks for the application server.

1. Ferdous J., Islam R., Mahboubi A., Islam Z. (2023). A Review of State-of-the-Art Malware Attack Trends and Defense Mechanisms. Institute of Electrical and Electronics Engineers (IEEE) Access, pp. 121118–121141.
2. Number of Internet of Things (IoT) connections worldwide from 2022 to 2023, with forecasts from 2024 to 2033. Available at: https://www.statista.com/statistics/1183457/iot-connected-devices-worldwide/ (accessed 09.12.2024).
3. Vanness R., Chowdhury M., Rifat N. (2023). Malware: A Software for Cybercrime // Institute of Electrical and Electronics Engineers (IEEE) International Conference on Electro Information Technology (eIT), pp. 513–518.
4. Arányi G., Vathy-Fogarassy Á., Szücs V. (2024) Evaluation of a New-Concept Secure File Server Solution. Future Internet, Multidisciplinary Digital Publishing Institute (MDPI), 16 (9), p.306.
5. Chang D., Li L., Chang Y., Qiao Z. (2021) Cloud Computing Storage Backup and Recovery Strategy Based on Secure IoT and Spark. Mobile Information SystemsVolume 2021, issue 1, volume 6, p. 9505249.
6. Wang Z., Goudarzi M., Gong M., Buyya R. (2024). Deep Reinforcement Learning-based scheduling for optimizing system load and response time in edge and fog computing environments. Future Generation Computer Systems 152, pp. 55–69.
7. Zhou G., Tian W., Buyya R., Xue R., Song L. (2024). Deep reinforcement learning‑based methods for resource scheduling in cloud computing: a review and future directions. Artificial Intelligence Review, pp. 57–124.
8. Lee S., Kang J., Kim J., Baek W., Yoon H. (2024) A Study on Developing a Model for Predicting the Compression Index of the South Coast Clay of Korea Using Statistical Analysis and Machine Learning Techniques. Applied Sciences (Switzerland), volume 14, issue 3, p. 952.
9. Dantas P., Sabino da Silva W., Cordeiro L., Carvalho C. (2024) A comprehensive review of model compression techniques in machine learning. Applied Intelligence, volume 54, issue 22, pp. 11804–11844.
10. RL Algorithms – Stable Baselines3 2.5.0a0 documentation, Available at: https://stable-baselines3. readthedocs.io/en/master/guide/algos.html#rl-algorithms/ (accessed: 09.12.2024).
11. Stefanyshyn V., Stefanyshyn I., Pastukh O., Kulikov S. (2024) Comparison of the accuracy of machine learning algorithms for brain-computer interaction based on high-performance computing technologies. Scientific Journal of TNTU (Tern.), vol. 115, no. 3, pp. 82–90.
12. Zhao L., Gatsis K., Papachristodoulou A.. Stable and Safe Reinforcement Learning via a Barrier-Lyapunov Actor-Critic Approach. 62nd Institute of Electrical and Electronics Engineers (IEEE) Conference on Decision and Control (CDC), 2023, pp.1320–1325.
13. Varshosaz M., Ghaffari M., Johnsen E., Wąsowski A. Formal Specification and Testing for Reinforcement Learning. 2022 Institute of Electrical and Electronics Engineers (IEEE) International Conference on Electro Information Technology (eIT), 2022, pp. 513–518.
14. Pawlicki M., Pawlicka A., Uccello F., Szelest S., D’Antonio S., Kozik R., Choraś M. (2024) Evaluating the necessity of the multiple metrics for assessing explainable AI: A critical examination. Neurocomputing, volume 602, p. 128282.
15. Stefanyshyn V., Stefanyshyn I., Pastukh O., Kulikov S.. (2024) Comparison of the accuracy of machine learning algorithms for brain-computer interaction based on high-performance computing technologies // Scientific Journal of TNTU (Tern.), vol. 115, no. 3, pp. 82–90.
16. Abdulhameed A. S., Lupenko S. (2022) Potentials of reinforcement learning in contemporary scenarios // Scientific Journal of TNTU (Tern.), vol. 106, no. 2, pp. 92–100.

1. Ferdous J., Islam R., Mahboubi A., Islam Z. (2023). A Review of State-of-the-Art Malware Attack Trends and Defense Mechanisms. Institute of Electrical and Electronics Engineers (IEEE) Access, pp. 121118–121141.
2. Number of Internet of Things (IoT) connections worldwide from 2022 to 2023, with forecasts from 2024 to 2033. Available at: https://www.statista.com/statistics/1183457/iot-connected-devices-worldwide/ (accessed 09.12.2024).
3. Vanness R., Chowdhury M., Rifat N. (2023). Malware: A Software for Cybercrime // Institute of Electrical and Electronics Engineers (IEEE) International Conference on Electro Information Technology (eIT), pp. 513–518.
4. Arányi G., Vathy-Fogarassy Á., Szücs V. (2024) Evaluation of a New-Concept Secure File Server Solution. Future Internet, Multidisciplinary Digital Publishing Institute (MDPI), 16 (9), p.306.
5. Chang D., Li L., Chang Y., Qiao Z. (2021) Cloud Computing Storage Backup and Recovery Strategy Based on Secure IoT and Spark. Mobile Information SystemsVolume 2021, issue 1, volume 6, p. 9505249.
6. Wang Z., Goudarzi M., Gong M., Buyya R. (2024). Deep Reinforcement Learning-based scheduling for optimizing system load and response time in edge and fog computing environments. Future Generation Computer Systems 152, pp. 55–69.
7. Zhou G., Tian W., Buyya R., Xue R., Song L. (2024). Deep reinforcement learning‑based methods for resource scheduling in cloud computing: a review and future directions. Artificial Intelligence Review, pp. 57–124.
8. Lee S., Kang J., Kim J., Baek W., Yoon H. (2024) A Study on Developing a Model for Predicting the Compression Index of the South Coast Clay of Korea Using Statistical Analysis and Machine Learning Techniques. Applied Sciences (Switzerland), volume 14, issue 3, p. 952.
9. Dantas P., Sabino da Silva W., Cordeiro L., Carvalho C. (2024) A comprehensive review of model compression techniques in machine learning. Applied Intelligence, volume 54, issue 22, pp. 11804–11844.
10. RL Algorithms – Stable Baselines3 2.5.0a0 documentation, Available at: https://stable-baselines3. readthedocs.io/en/master/guide/algos.html#rl-algorithms/ (accessed: 09.12.2024).
11. Stefanyshyn V., Stefanyshyn I., Pastukh O., Kulikov S. (2024) Comparison of the accuracy of machine learning algorithms for brain-computer interaction based on high-performance computing technologies. Scientific Journal of TNTU (Tern.), vol. 115, no. 3, pp. 82–90.
12. Zhao L., Gatsis K., Papachristodoulou A.. Stable and Safe Reinforcement Learning via a Barrier-Lyapunov Actor-Critic Approach. 62nd Institute of Electrical and Electronics Engineers (IEEE) Conference on Decision and Control (CDC), 2023, pp.1320–1325.
13. Varshosaz M., Ghaffari M., Johnsen E., Wąsowski A. Formal Specification and Testing for Reinforcement Learning. 2022 Institute of Electrical and Electronics Engineers (IEEE) International Conference on Electro Information Technology (eIT), 2022, pp. 513–518.
14. Pawlicki M., Pawlicka A., Uccello F., Szelest S., D’Antonio S., Kozik R., Choraś M. (2024) Evaluating the necessity of the multiple metrics for assessing explainable AI: A critical examination. Neurocomputing, volume 602, p. 128282.
15. Stefanyshyn V., Stefanyshyn I., Pastukh O., Kulikov S.. (2024) Comparison of the accuracy of machine learning algorithms for brain-computer interaction based on high-performance computing technologies // Scientific Journal of TNTU (Tern.), vol. 115, no. 3, pp. 82–90.
16. Abdulhameed A. S., Lupenko S. (2022) Potentials of reinforcement learning in contemporary scenarios // Scientific Journal of TNTU (Tern.), vol. 106, no. 2, pp. 92–100.