Reducing VR Delivery Latency in UAV-Enabled Mobile Edge Computing using PSO, GA, and Gradient-Based Approaches
DOI:
https://doi.org/10.4108/airo.13507Keywords:
wireless networks, UAV-enabled MEC, Rician fading, latency minimization, particle swarm optimization, genetic algorithm, gradient-based optimizationAbstract
Virtual reality (VR) services delivered through UAV-enabled mobile edge computing (MEC) require joint decisions on user association, caching, computing-resource allocation, and UAV placement. This study benchmarks three CVX-free placement solvers, namely Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and gradient-based L-BFGS-B, within the same alternating-optimization framework for N ∈ {15, 18, 21, 24, 27, 30} VR users served by M = 2 UAV base stations (UBSs). The channel rate follows the outage-constrained logistic approximation of an elevation-angle-dependent Rician fading model. To account for stochastic variability, the evaluation uses 30 independent Monte Carlo system realizations for every N , paired across solvers, and includes random and centroid placement baselines. The optimized maximum aggregate UBS task-completion latency increases from approximately 225 ms at N = 15 to 723 ms at N = 30. PSO and GA achieve numerically identical latency values, while L-BFGS-B yields comparable latency at each tested user load, differing by at most 0.714 ms in any paired comparison; after Holm correction, only the N = 15 difference is statistically significant and its median magnitude is only 0.054 ms. Relative to random placement, optimization reduces mean aggregate latency by approximately 21–33%, whereas the gain over centroid placement is modest (about 0.26–0.47%). L-BFGS-B has the lowest average runtime over all loads, although PSO is faster at several individual load levels, and GA is consistently the slowest. The reported objective is an aggregate task-level latency metric inherited from the reference UAV-MEC model and must not be interpreted as per-frame motion-to-photon latency
Downloads
References
[1] Bastug E, Bennis M, Médard M, Debbah M. Toward interconnected virtual reality: Opportunities, challenges, and enablers. IEEE Commun Mag. 2017; 55(6):110–7. doi:10.1109/MCOM.2017.1601089.
[2] Chen M, Saad W, Yin C, Debbah M. Data correlation-aware resource management in wireless virtual reality: An echo state transfer learning approach. IEEE Trans Commun. 2019;67(6):4267–80. doi:10.1109/TCOMM.2019.2900624.
[3] Nasir AA. Latency optimization of UAV-enabled MEC system for virtual reality applications under Rician fading channels. IEEE Wirel Commun Lett. 2021; 10(8):1633–7. doi:10.1109/LWC.2021.3075762.
[4] Yuan H, Wang M, Bi J, Shi S, Yang J, Zhang J, et al. Cost-efficient task offloading in mobile edge computing with layered unmanned aerial vehicles. IEEE Internet Things J. 2024;11(19):30496–509. doi:10.1109/JIOT.2024.3408216.
[5] Liu J, Zhang Y, Wang J, Cui T, Zhang L, Li C, et al. Outage probability analysis for UAV-aided mobile edge computing networks. EAI Endorsed Trans Ind Netw Intell Syst. 2022;9(31):e4. doi:10.4108/eetinis.v9i31.960.
[6] Zarei M, Moshayedi AJ, Zhong Y, Khan AS, Kolahdooz A, Andani ME. Indoor UAV object detection algorithms on three processors: Implementation test and comparison. In: 2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE). Piscataway (NJ): IEEE; 2023. p. 812–9. doi:10.1109/ICCECE58074.2023.10135199.
[7] Mazinani A, Norouzi M, Talaeizadeh A, Alasty A, Saadat Foumani M, Kolahdooz A. Innovative real-time palm tree detection, geo-localization and counting from unmanned aerial vehicle (UAV) aerial images using deep learning. Automation. 2026;7(2):51. doi:10.3390/automation7020051.
[8] Wang M, Moshayedi AJ, Lu H, Guo B, Bassir D. Integration of electronic noses and UAVs for intelligent gas detection: A review of methods and challenges. In: Smart Manufacturing, Structural Health Monitoring and Digital Twins: Proceedings of the 1st International Conference (ICSSD 2025); Dongguan, China. SAGE Publications; 2025. p. 82–9. doi:10.3233/ATDE251175.
[9] Moshayedi AJ, Khan AS, Geng K, Hu J, Kolahdooz A. Advancing agricultural practices: Analyzing the role of robotics in corn farming. Int J Eng Trans A Basics. 2025; 38(7):1517–32. doi:10.5829/IJE.2025.38.07A.07.
[10] You C, Zhang R. 3D trajectory optimization in Rician fading for UAV-enabled data harvesting. IEEE Trans Wirel Commun. 2019;18(6):3192–207. doi:10.1109/TWC.2019.2911939.
[11] Nguyen CKP, Do TA, Nguyen TV, Pham HTT, Dang NT. Optimizing UAV trajectories in optical IRS-aided hybrid FSO/RF aerial access networks using DRL technique. EAI Endorsed Trans Ind Netw Intell Syst. 2025;12(4). doi:10.4108/eetinis.124.10134.
[12] Suyanto S, Ariyanto AA, Ariyanto AF. Komodo mlipir algorithm. Appl Soft Comput. 2022;114:108043. doi:10.1016/j.asoc.2021.108043.
[13] Setiawan D, Suyanto S, Erfianto B, Gozali AA. Battlefield optimization algorithm. Expert Syst Appl. 2025;266:126097. doi:10.1016/j.eswa.2024.126097.
[14] Al-Shaikhi A, Nuha HH, Mohandes M, Rehman S, Adrian M. Vertical wind speed extrapolation model using long short-term memory and particle swarm optimization. Energy Sci Eng. 2022;10(12):4580–94. doi:10.1002/ese3.1291.
[15] Hosseinzadeh M, Tanveer J, Rahmani AM, Gharehchopogh FS, Yusof NM, Khoshvaght P, et al. A comprehensive overview of PSO-LSTM approaches: Applications, analytical insights, and future opportunities. Arch Comput Methods Eng. 2026; 33(4):5081–126. doi:10.1007/s11831-025-10445-y.
[16] Daviran M, Maghsoudi A, Ghezelbash R. Optimized AI-MPM: Application of PSO for tuning the hyperparameters of SVM and RF algorithms. Comput Geosci. 2025;195:105785. doi:10.1016/j.cageo.2024.105785.
[17] Chandola J, Pundir S, Sharma A, Song Y, Fekete G, Singh T. Recent advances in MPPT techniques for photovoltaic systems: A review of classical (P&O, IC), intelligent (ANN), optimization (PSO) and hybrid (ANN-PSO) methods. Results Eng. 2026;29:109395. doi:10.1016/j.rineng.2026.109395.
[18] Chang X, Ye L, Ma L, Chen S. Research on hybrid path planning algorithms for UAVs in complex environments. EAI Endorsed Trans Scalable Inf Syst. 2025;12(3). doi:10.4108/eetsis.8974.
[19] Deng W, Xu H, Guan Z, Sun Y, Ran X, Ma H, et al. PSO-K-means clustering-based NSGA-III for delay recovery. IEEE Trans Consum Electron. 2025; 71(4):10084–95. doi:10.1109/TCE.2025.3615937.
[20] Fauzan MN, Munadi R, Sumaryo S, Nuha HH. Enhanced grey wolf optimization for efficient transmission power optimization in wireless sensor network. Appl Syst Innov. 2025;8(2):36. doi:10.3390/asi8020036.
[21] Fauzan MN, Munadi R, Sumaryo S, Nuha HH. Enhanced wireless sensor network lifetime using EGWO-optimized neural network approach. Network. 2026;6(1):5. doi:10.3390/network6010005.
[22] Nuha HH, Ariyanto E, Yulita IN, Sailellah HRP. Clustered packet optimization for human-powered energy generation prediction. Discov Internet Things. 2026;6(1):111. doi:10.1007/s43926-026-00381-z.
[23] Zhu C, Byrd RH, Lu P, Nocedal J. Algorithm 778: L-BFGS-B: Fortran subroutines for large-scale bound-constrained optimization. ACM Trans Math Softw. 1997;23(4):550–60. doi:10.1145/279232.279236.
[24] Kennedy J, Eberhart R. Particle swarm optimization. In: Proceedings of the IEEE International Conference on Neural Networks (ICNN’95); 1995 Nov 27–Dec 1; Perth, Australia. Piscataway (NJ): IEEE; 1995. p. 1942–8. doi:10.1109/ICNN.1995.488968.
[25] Goldberg DE. Genetic algorithms in search, optimization and machine learning. Reading (MA): Addison-Wesley; 1989.
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2025 Hilal Hudan Nuha, M. Faris Fathoni, Hassan Rizky Putra Sailellah
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
