EdgeGuard-QoE: A Hybrid Autoencoder-LightGBM Framework for Secure and QoE-Preserving Video Transmission in Cloud-Edge 5G Networks
| International Journal of Electrical and Electronics Engineering |
| © 2026 by SSRG - IJEEE Journal |
| Volume 13 Issue 3 |
| Year of Publication : 2026 |
| Authors : Kumbha Ravi Kumar, Ayyagari.Srinagesh |
10.14445/23488379/IJEEE-V13I3P118
How to Cite?
Kumbha Ravi Kumar, Ayyagari.Srinagesh, "EdgeGuard-QoE: A Hybrid Autoencoder-LightGBM Framework for Secure and QoE-Preserving Video Transmission in Cloud-Edge 5G Networks," SSRG International Journal of Electrical and Electronics Engineering, vol. 13, no. 3, pp. 248-259, 2026. Crossref, https://doi.org/10.14445/23488379/IJEEE-V13I3P118
Abstract:
There is an increased utilization of adaptive video streaming over cloud-edge 5G networks, which subjects latency-sensitive multimedia services to multimedia threats other than Quality of Experience (QoE). To address the problem, this paper proposes EdgeGuard-QoE (Edge-based Guarded Quality of Experience Framework), a video transmission architecture of 5G networks to provide security and Quality of Experience (QoE). The hybrid model in the framework is GWO-SAE-LightGBM (Grey Wolf Optimized Stacked Autoencoder-LightGBM) that is oriented at the use of intelligent attacks prediction and mitigation. In such a technique, stacked autoencoders recognize normal traffic behavior based on network flow traffic of varying dimensions, that is, packet size, flow duration, transmission entropy, and header anomalies, and can identify patterns of attack (DoS, Man-in-the-Middle, and packet injection). Then, a LightGBM (Light Gradient Boosting Machine) network classifier on the edge of the network detects the anomalies and puts in place adaptive security precautions to prevent the degradation of the service, which comprises light encryption and localized attack quarantine. The Grey Wolf Optimization (GWO) algorithm is used to enhance the efficiency of the hyperparameter configuration of the stacked autoencoder and LightGBM models to enhance their detection and reduce the processing downtimes. The new EdgeGuard-QoE Framework can support exceptionally high accuracy attack detection, low alarm rates, and low latency, as well as support adaptive bitrate and stable QoE. Several experimental analyses performed in the conditions of realistic cloud-edge 5G video streaming verify the correctness of hybrid frameworks when it comes to real-time secure video transmission in the next-generation cloud-edge-based 5G networks.
Keywords:
Secure video transmission, 5G networks, Cloud-edge computing, Network, Intrusion detection, Autoencoder, LightGBM, Grey Wolf Optimization, Quality of Experience (QoE).
References:
[1] Shiqiu Liu et al., “Cloud-Edge Collaborative Transcoding for Adaptive Video Streaming: Enhancing QoE in Wireless Networks,” IEEE Transactions on Green Communications and Networking, vol. 10, pp. 791-802, 2026.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Arti Yadav et al., “Task Scheduling and Energy-Aware Workflow in the Cloud Through Hybrid Optimization Techniques,” Soft Computing for Problem Solving: Proceedings of the SocProS, Springer, Singapore, vol. 547, pp. 491-499, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Lili Zhang et al., “Research on Cloud-Edge Collaborative Computing Optimization based on 5G Dynamic Resource Scheduling: For Real-Time Industrial Video Analysis Scenarios,” International Conference on Advanced Electronics, Intelligent Technology, and Computing (AEITC 2025), Wuhan, China, vol. 14010, pp. 369-376, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Dan Wang et al., “Transcoding-Enabled Edge Caching Strategy Optimization: A Dual-Timescale Meta-Learning-based Stackelberg Game Approach,” IEEE Internet of Things Journal, vol. 12, no. 13, pp. 23309-23323, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Moner Alsader, Alcardo Alex Barakabitze, and Is-Haka Mkwawa, “QoE-Driven Adaptive Video Streaming: Architectures, Techniques, and Future Research Challenges Toward 6G Networks,” IEEE Access, vol. 13, pp. 157408-157441, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Irena Orsolic, and Lea Skorin-Kapov, “A Framework for in-Network QoE Monitoring of Encrypted Video Streaming,” IEEE Access, vol. 8, pp. 74691-74706, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Wei Wang et al., “Quality of Experience-Oriented Cloud-Edge Dynamic Adaptive Streaming: Recent Advances, Challenges, and Opportunities,” Symmetry, vol. 17, no. 2, pp. 1-25, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Zijiang Yan et al., “Semantic-Aware Adaptive Video Streaming using Latent Diffusion Models for Wireless Networks,” IEEE Wireless Communications, vol. 32, no. 5, pp. 30-38, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Wanxin Shi et al., “A Survey on Intelligent Solutions for Increased Video Delivery Quality in Cloud-Edge-End Networks,” IEEE Communications Surveys and Tutorials, vol. 27, no. 2, pp. 1363-1394, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Shuaibu Yau et al., “A Robust Throughput Estimation in Edge-Assisted Adaptive Bitrate Streaming Networks,” IEEE Access, vol. 13, pp. 152598-152607, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Xiaoteng Ma et al., “QAVA: QoE-Aware Adaptive Video Bitrate Aggregation for HTTP Live Streaming based on Smart Edge Computing,” IEEE Transactions on Broadcasting, vol. 68, no. 3, pp. 661-676, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Miran Taha, and Aree Ali, “Smart Algorithm in Wireless Networks for Video Streaming based on Adaptive Quantization,” Concurrency and Computation: Practice and Experience, vol. 35, no. 9, pp. 1-18, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Darius Chmieliauskas, and Šarūnas Paulikas, “Evaluation of Uplink Video Streaming QoE in 4G and 5G Cellular Networks using Real-World Measurements,” IEEE Access, vol. 13, pp. 53996-54018, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Xiuli Du, Xiaohui Ding, and Fan Tao, “Network Security Situation Prediction based on Optimized Clock-Cycle Recurrent Neural Network for Sensor-Enabled Networks,” Sensors, vol. 23, no. 13, pp. 1-25, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Chaofei Tang, Nurbol Luktarhan, and Yuxin Zhao, “An Efficient Intrusion Detection Method based on LightGBM and Autoencoder,” Symmetry, vol. 12, no. 9, pp. 1-16, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Minsu Kim, and Kwangsue Chung, “Edge Computing Assisted Adaptive Streaming Scheme for Mobile Networks,” IEEE Access, vol. 9, pp. 2142-2152, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Waqas ur Rahman, and Eui-Nam Huh, “Content-Aware QoE Optimization in MEC-Assisted Mobile Video Streaming,” Multimedia Tools and Applications, vol. 82, no. 27, pp. 42053-42085, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Jesús Aguilar-Armijo, Christian Timmerer, and Hermann Hellwagner, “SPACE: Segment Prefetching and Caching at the Edge for Adaptive Video Streaming,” IEEE Access, vol. 11, pp. 21783-21798, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Alcardo Alex Barakabitze et al., “QoEMultiSDN: Management of Multimedia Services using MPTCP/SR in Softwarized and Virtualized Networks,” IEEE Access, vol. 13, pp. 123151-123168, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[20] M. Karthikeyan, D. Manimegalai, and Karthikeyan RajaGopal, “Firefly Algorithm based WSN-IoT Security Enhancement with Machine Learning for Intrusion Detection,” Scientific Reports, vol. 14, no. 1, pp. 1-15, 2024.
[CrossRef] [Google Scholar] [Publisher Link]