Machine Learning Theory and Practice, 2026, 6(1); doi: 10.38007/ML.2026.060112.
Zheng Li
Jacobs School of Engineering, University of California, San Diego, La Jolla, 92093, California, United States
Given the problems of limited computing resources, unstable network conditions, high cloud round-trip latency, and privacy risks in complex perception, real-time inference, and multimedia processing of Android mobile intelligent applications, this paper proposes an edge-cloud collaborative architecture. Add a task profiling, device state awareness and security caching module on the Android side, and set up service registration, dynamic scheduling, model caching and elastic resource pools at the edge. A multi-objective cost function is employed to optimise the ratio of task segmentation, edge node selection and computing resource allocation simultaneously. Monte Carlo simulations are carried out with publicly available reproducible parameters, and each data point is independently sampled 1200 times. Based on the above results, the proposed architecture can achieve an average response latency of 436.2 ms for a 6 MB task; this is a reduction of 60.3% and 59.0% compared with pure local execution and cloud execution, respectively, and reduces device-side power consumption by 84.1% over local execution. Therefore, the cooperative offloading of Android intelligent systems should not be based on a simple binary decision of "local or cloud", but should incorporate factors such as task granularity, link quality, device power consumption and edge load into a unified control loop.
Android; edge computing; mobile intelligent system; task offloading; resource collaboration; low latency
Zheng Li. Design of Collaborative Architecture for Android Mobile Smart Systems Based on Edge Computing. Machine Learning Theory and Practice (2026), Vol. 6, Issue 1: 107-115. https://doi.org/10.38007/ML.2026.060112.
[1] Akhlaqi MY, Mohd Hanapi ZB Task offloading paradigm in mobile edge computing—current issues, adopted approaches, and future directions. Journal of Network and Computer Applications , 2023, 212: 103568. DOI: 10.1016/j.jnca.2022.103568.
[2] Lu H., Yan Z. Mobile application tasks refactoring and offloading in Edge Environments. In: Proceedings of the 2023 7th International Conference on Control Engineering and Artificial Intelligence (CCEAI 2023) , 2023: 17–22. DOI: 10.1145/3580219.3580224.
[3] Chen X., Li M., Zhong H., Chen X., Ma Y., Hsu C.-H. FUNOff: Offloading Applications at Function Granularity for Mobile Edge Computing. IEEE Transactions on Mobile Computing , 2024, 23(2): 1717–1734. DOI: 10.1109/TMC.2023.3240741.
[4] Wang, B. (2025). Methods of Load Optimization for Computer Systems Based on Physical Principles.
[5] Yu, X. (2026). Exploration of Multi-Channel Conversion Path Optimization Methods Based on A/B Testing.
[6] Guo, X. (2025, March). Research on Blockchain-Based Financial AI Algorithm Integration Methods and Systems. In 2025 IEEE International Conference on Electronics, Energy Systems and Power Engineering (EESPE) (pp. 816-821). IEEE.
[7] Jing, X. (2025, November). In-Depth Analysis of the Optimization Decision Model of Financial Investment Portfolio Based on Machine Learning Algorithms in Python Scikit-Learn Library. In International Conference on Computational Technologies for Research in Data Analytics (pp. 130-140). Cham: Springer Nature Switzerland.
[8] Liu, X. (2026). Research on the Application of Artificial Intelligence in Consumer Privacy Data Protection. Procedia Computer Science, 279, 956-965.
[9] Guo, X. (2025, April). Research on Financial Trading Algorithms Based on Deep Reinforcement Learning. In 2025 IEEE 3rd International Conference on Control, Electronics and Computer Technology (ICCECT) (pp. 1711-1715). IEEE.
[10] Liu, X. (2026). Construction of Consumer Data Privacy Protection System Based On Blockchain Technology. Procedia Computer Science, 282, 2082-2091.
[11] Yang, Y. (2026). Causal Inference-based Identification of Incremental Effects in Digital Advertising and Optimization Pathways for Resource Allocation. Advances in Computer and Communication, 7(2).
[12] Han, W. (2025, November). An Empirical Study on Building a High-precision Forecasting System for Financial Market Trends Based on the PyTorch Deep Learning Framework. In International Conference on Computational Technologies for Research in Data Analytics (pp. 518-528). Cham: Springer Nature Switzerland.
[13] Yuan, Y. (2026). Research on Memory Management and Dynamic Reasoning Methods for Intelligent Agents Based on Large Language Models.
[14] Sun, L. (2026). Consistency Optimization Strategies for Distributed Advertising Systems Under Cross-regional Deployment. Advances in Computer and Communication, 7(2).