Adaptive Latency-Aware Predictive Framework for Mobile Edge Systems Using Dynamic Feature Reduction and Intelligent Scheduling

Mursalim Nohong; Nora’asikin Abu Bakar; Siti Roshaida Abd Razak; Andi Nur Ildha Arfanita; Helen Dias Andhini

doi:10.3991/ijim.v20i15.62597

Authors

Mursalim Nohong Hasanuddin University, Makassar, Indonesia
Nora’asikin Abu Bakar Management and Science University, Selangor, Malaysia
Siti Roshaida Abd Razak Management and Science University, Selangor, Malaysia
Andi Nur Ildha Arfanita Hasanuddin University, Makassar, Indonesia https://orcid.org/0000-0001-9793-2784
Helen Dias Andhini Hasanuddin University, Makassar, Indonesia

DOI:

https://doi.org/10.3991/ijim.v20i15.62597

Keywords:

Mobile Edge Computing, Adaptive Feature Reduction Latency-Aware Scheduling, Principal Component Analysis (PCA), Human Activity Recognition (HAR), Ridge Regression

Abstract

Low-latency and resource-efficient predictive analytics are essential for mobile edge computing applications, including smartphone-based human activity recognition (HAR). This study presents the Adaptive Latency Prediction and Scheduling (ALPS) framework, which aims to minimize inference latency, hardware energy consumption, and computational overhead while maintaining predictive accuracy. The ALPS framework comprises three primary modules: an adaptive principal component analysis (PCA) mechanism for real-time feature reduction, a lightweight ridge classifier optimized with an L regularization loss 2 function for rapid multi-class activity prediction, and a dynamic task scheduler that minimizes a combined latency-energy cost function to allocate processing tasks across mobile, edge, and cloud layers. Evaluation on the high-dimensional UCI-HAR smartphone dataset (10,299 samples, 561 features) demonstrated that the adaptive feature reduction module reduced the feature space to 68 principal components, resulting in an 87.9% reduction in dimensionality while maintaining 95% cumulative explained variance. Relative to conventional standalone models and isolated optimization baselines, ALPS achieved a 32% reduction in average end-to-end latency (120 ms), a 25% decrease in energy consumption (180 J), and a classification accuracy of 96.4% across six physical activities. The primary contribution of this study is the unified integration of adaptive data compression and distributed infrastructure scheduling into a scalable and energy-efficient pipeline for real-time edge intelligence.

References

[1] Ali, Y. A., Awwad, E. M., Al-Razgan, M., & Maarouf, A, “Hyperparameter Search for Machine Learning Algorithms for Optimizing the Computational Complexity”, Processes, Vol.11, No.2, pp.349, 2023. https://doi.org/10.3390/pr11020349

[2] Chen, Xihan, Cai, Yunlong, Li, Liyan, Zhao, Minjian, Champagne, Benoit and Hanzo, Lajos, “Energy-efficient resource allocation for latency-sensitive mobile edge computing”, IEEE Transactions on Vehicular Technology, Vol.69, No.2, pp.2246-2262, 2020. http://dx.doi.org/10.1109/TVT.2019.2962542.

[3] Collin A., Siddiqi A., Imanishi Y., Rebentisch E., Tanimichi T., de Weck O.L, “Autonomous driving systems hardware and software architecture exploration: Optimizing latency and cost under safety constraints”, Syst. Eng, Vol.23, No.3, pp.327–337, 2020. doi: 10.1002/sys.21528.

[4] Czarnul, P., Antal, M., Baniata, H. et al, “Optimization of resource-aware parallel and distributed computing: a review”, J Super comput, Vol.81, pp.848, 2025. https://doi.org/10.1007/s11227-025-07295-7.

[5] Feng, C.; Han, P.; Zhang, X.; Yang, B.; Liu, Y.; Guo, L, “Computation offloading in mobile edge computing networks: A survey”, J. Netw, Comput. Appl, Vol. 202, pp.103366, 2022. https://doi.org/10.1016/j.jnca.2022.103366

[6] Hadi, Yasser & Hadi, Ali, “AI-assisted predictive modeling for latency reduction in next-generation IoT communication systems”, International Journal of Computing Programming and Database Management, Vol.7, No. 2, pp. 07-18, 2026. DOI: 10.33545/27076636.2026.v7.i2a.163.

[7] Haibeh, L. A., Yagoub, M. C. & Jarray, A, “A survey on mobile edge computing infrastructure: Design, resource management, and optimization approaches”, IEEE Access, Vol. 10, pp. 27591–27610, 2022. https://doi.org/10.1109/access.2022.3152787

[8] Heydari, G., Rahbari, D. & Nickray, M, “Energy saving scheduling in a fog-based iot application by Bayesian task classification approach. Turk”, J. Electr. Eng. Comput. Sci, Vol.27, No.6, pp. 4167–4187, 2019. https://doi.org/10.3906/elk-1902-152

[9] Kumar, G., et.al, “Dynamic routing approach for enhancing source location privacy in wireless sensor networks”, Wireless Networks, Vol. 29, No.6, pp.2591-2607, 2023. https://doi.org/10.1007/s11276-023-03322-8

[10] Kocot B, Czarnul P, Proficz J, “Energy-aware scheduling for high-performance computing systems: a survey”, Energies, Vol. 16, No.2, pp.890, 2023. https://doi.org/10.3390/en16020890.

[11] Katal A, Dahiya S, Choudhury T, “Energy efficiency in cloud computing data centers: a survey on software technologies”, Clust Comput, Vol.26, No.3, pp.1845–1875, 2023. https://doi.org/10.1007/s10586-022-03713-0

[12] Boudmagh, M., Kerboua, A., & Redjimi, M. (2026). Multimodal Human Action Recognition for Ubiquitous Systems: Cross-Attention of Skeleton and Audio. International Journal of Interactive Mobile Technologies (iJIM), 20(05), pp. 70–86. https://doi.org/10.3991/ijim.v20i05.58381.

[13] Li P, Wang X, Huang K, Huang Y, Li S, Iqbal M, “Multi-Model Running Latency Optimization in an Edge Computing Paradigm. Sensors (Basel)”, Vol. 22, No.16, pp. 6097, 2022. doi: 10.3390/s22166097.

[14] Ma, Y.; Zhao, Y.; Hu, Y.; He, X.; Feng, S, “"Multi-Agent Deep Reinforcement Learning for Joint Task Offloading and Resource Allocation in IIoT with Dynamic Priorities”, Sensors, Vol. 25, pp.6160, 2025. https://doi.org/10.3390/s25196160.

[15] Mehran N, Samani ZN, Kimovski D, Prodan R, “Matching-based scheduling of asynchronous data processing workflows on the computing continuum”, In: 2022 IEEE International Conference on Cluster Computing (CLUSTER), pp.58–70, 2022. https://doi.org/10.1109/CLUSTER51413.2022.00021

[16] Nikolow D, Slota R, Polak S, Pogoda M, Kitowski J, “Policy-based SLA storage management model for distributed data storage services”, Comput Sci, Vol.19, No.4, 2018. https://doi.org/10.7494/csci.2018.19.4.2878.

[17] L. Pacheco, D. Rosário, E. Cerqueira, L. Villas, T. Braun, and A. A. Loureiro, “Distributed user-centric service migration for edge enabled networks”, in Proc. IFIP/IEEE Int. Symp. Integr. Netw. Manag. (IM), pp. 618–622, 2021. https://dl.ifip.org/db/conf/im/im2021short/211092.pdf

[18] Pandey, V.K., et.al, “An Efficient and Robust Framework for IoT Security using Machine Learning Techniques”, Procedia Computer Science, Vol. 258, pp.118-124, 2025. https://doi.org/10.1016/j.procs.2025.04.205

[19] Premsankar, Gopika & Ghaddar, Bissan, “Energy-Efficient Service Placement for Latency-Sensitive Applications in Edge Computing”, IEEE Internet of Things Journal, Vol.9, pp. 17926-17937, 2022. 10.1109/JIOT.2022.3162581.

[20] Gadebe, M. L., & Kogeda, O. P. (2020). Top-K Human Activity Recognition Dataset. International Journal of Interactive Mobile Technologies (iJIM), 14(18), pp. 68–86. https://doi.org/10.3991/ijim.v14i18.16965.

[21] Sahu, D., Nidhi, Chaturvedi, R. et al, “Optimizing energy and latency in edge computing through a Boltzmann driven Bayesian framework for adaptive resource scheduling”, Sci Rep, 15, pp. 30452, 2025. https://doi.org/10.1038/s41598-025-16317-6.

[22] Satouf, A. et al, “Metaheuristic-based task scheduling for latency-sensitive IoT applications in edge computing”, Clust. Comput, Vol. 28, No.2, pp. 1–17, 2025. https://doi.org/10.1007/s10586-024-04878-6.