Optimization of Deep Integration of Data Analysis and Intelligent Scheduling for University Public Resource Allocation Systems
DOI:
https://doi.org/10.54097/zk3xc947Keywords:
Public Resource Allocation, Data Analysis, Intelligent Scheduling, Data-Driven Decision-Making, Deep Reinforcement LearningAbstract
This paper studies the deep integration and optimization of data analysis and intelligent scheduling for university public resource allocation systems. To address the issues of inaccurate prediction, single algorithm, and disconnection between data and scheduling in traditional rule-driven systems, a data-driven intelligent decision scheme is proposed. The LSTM prediction model is optimized by integrating university-specific contextual features, and a PPO-based deep reinforcement learning algorithm is employed for dynamic multi-objective scheduling and optimization. A closed-loop feedback is constructed to realize real-time linkage between data and scheduling. Experiments show that the proposed method significantly improves resource utilization, reduces conflicts and abnormal occupation, and upgrades resource scheduling from rule-driven to data-driven intelligent decision-making.
Downloads
References
[1] Wang, L., & Lu, K. (2026). A reinforcement learning framework for modeling the reinforcement of cultural inertia in the allocation of public welfare resources. Scientific Reports, [https:// doi.org/ 10. 1038/ s41598] (https://doi. org/10. 1038/ s41598) ‑026‑50004‑4.
[2] Yang, C. (2025). Analysis of real‑time and accurate balance strategies for main grid dispatching based on big data technology. Electronic Technology, 54(7), 298‑299.
[3] Song, Y. (2019). Optimization design analysis of real‑time system scheduling algorithms. Computer Products and Circulation, (12), 93‑94.
[4] Chen, B., Pan, T., & Xie, Z. (2026). Research on intelligent management and data‑driven decision‑making in hydraulic engineering. Science and Technology Innovation, (1), 154‑157.
[5] Ding, B. (2020). Research on image and video retrieval algorithms based on nonlinear hashing (Master’s thesis, Beijing University of Posts and Telecommunications).
[6] Song, J., Tan, L., Cao, Z., & Wang, S. (2010). A new real‑time scheduling algorithm. Computer Technology and Development, 20(12), 73‑76.
[7] Wang, B., & Lei, L. (2013). A distributed parallel algorithm optimized by big data analysis. Computer and Digital Engineering, 41(11), 1720‑1724, 1861.
[8] Xing, Y., Li, S., Zhai, C., & Wang, D. (2008). Iterative learning control algorithm based on quadratic optimization. Journal of Liaoning University of Petrochemical Technology, 28(3), 53‑55.
[9] Chen, J., Wang, J., Hu, J., & Xu, Y. (2025). Priority queue traffic scheduling algorithm for diversified network demands. Computer Engineering, 51(11), 152‑161.
[10] Lu, P., Song, C., Bai, L., & Song, C. (2013). A frequency‑homogeneous interference cancellation algorithm based on secondary iteration. Communication Technology, 46(8), 1‑4.
[11] Liu, J., & Peng, P. (2026). A multi‑UAV cooperative task decision‑making method based on improved PPO algorithm. Journal of Weaponry and Equipment Engineering, 47(4), 9‑15, 48.
[12] Chi, X., Zhang, J., & Yu, H. (2026). Control‑communication co‑optimization for wireless cloud robotic system via multi‑agent transfer reinforcement learning. IEEE/CAA Journal of Automatica Sinica, 13(2), 311‑326. [https://doi.org/ 10.1109/ JAS. 2026. 1241228] (https://doi.org/10. 1109/ JAS. 2026. 1241228).
[13] Lu, Y., & Yu, H. (2025). Artificial intelligence‑driven dynamic decision‑making in supply chain: Modeling and analysis based on complex system theory. Supply Chain Management, 6(12), 97‑112.
[14] Wang, X., Gui, J., Li, J., & Song, Q. (2023). Comparative study on iterative pure phase hologram generation algorithms. Laser and Optoelectronics Progress, 60(6), 29‑36.
[15] Feng, H., & Ren, F. (2025). Application and performance comparison study of numerical analysis algorithms in computer experiments. Information and Computers, 37(1), 26‑28.
[16] Mustafa, E., Shuja, J., Rehman, F., & Gumbley, S. J. (2025). Computation offloading in vehicular communications using PPO‑based deep reinforcement learning. The Journal of Supercomputing, 81, 547.
[17] Qi, Y., Wang, C., & Liu, J. (2026). PPO‑RR: Virtual machine scheduling algorithm and deep reinforcement learning method for green computing. Intelligent Decision Technologies, 20(1), 392‑413.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Frontiers in Computing and Intelligent Systems
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
