JATO: Deep Reinforcement Learning-based Joint Optimization for Task Offloading and Adaptive Transmission in Multimedia IoT Systems

Gina Purnama; Irma Amelia Dewi; Armein Z. R. Langi; Yoanes Bandung

doi:10.5614/itbj.ict.res.appl.2026.20.2.6

Authors

Gina Purnama School of Electrical Engineering and Informatics, Institut Teknologi Bandung, Jalan Ganesa No. 10, Bandung, 40132
Irma Amelia Dewi School of Electrical Engineering and Informatics, Institut Teknologi Bandung, Jalan Ganesa No. 10, Bandung, 40132
Armein Z. R. Langi ITB Research Center for Information and Communication Technology, Institut Teknologi Bandung, Jalan Ganesa No. 10, Bandung, 40132
Yoanes Bandung ITB Research Center for Information and Communication Technology, Institut Teknologi Bandung, Jalan Ganesa No. 10, Bandung, 40132

DOI:

https://doi.org/10.5614/itbj.ict.res.appl.2026.20.2.6

Keywords:

adaptive transmission, deep reinforcement learning, edge-cloud computing, joint optimization, quality of service, task offloading, multimedia IoT

Abstract

As the Multimedia Internet of Things (M-IoT) evolves, the orchestration of numerous resources that offer support for high-bandwidth, low-latency applications arises as a key challenge. Architecturally, the edge-cloud framework alleviates structural concerns, but the linked nature of compute and data transfer poses problems of resource management. Approaches that tackle task offloading and adaptive transmission that think independently of each other tend to have problems such as user-server cross-region overloads or network congestion. This paper presents JATO, a framework to jointly tackle the problems of adaptive task offloading and transmission optimization using Deep Reinforcement Learning. JATO offers a mono-faceted solution, learning a policy to simultaneously determine the best offloading target and the transmission quality. The framework was implemented for evaluation with a combination of different edge devices in a testbed alongside a simulation environment. JATO recorded a result of 0.9321 as the holistic score of the overall framework endpoint, a score significantly better than that of all the other frameworks that were used as functional baselines. JATO was able to resource optimally with a network lag of 131.65 milliseconds and a network freeze of 0.09% with the resources utilized. This is evidence that offloading and rate control in combination provides better resource elasticity for M-IoT systems.

Downloads

Download data is not yet available.

Author Biography

Yoanes Bandung, ITB Research Center for Information and Communication Technology, Institut Teknologi Bandung, Jalan Ganesa No. 10, Bandung, 40132

University Page |Â Google Scholar | ScopusÂ | ResearchGate

References

Nauman, A., Qadri, Y.A., Amjad, M., Bin Zikria, Y., Afzal, M.K. & Kim, S.W., Multimedia Internet of Things: A Comprehensive Survey, IEEE Access, 8, pp. 8202-8250, 2020, doi: 10.1109/ACCESS.2020.2964280.

de Moraes, A.L.S., de Macedo, D.D.J. & Pioli, L., Video Streaming on Fog and Edge Computing Layers: A Systematic Mapping Study, Dec. 01, 2024, Elsevier B.V. doi: 10.1016/j.iot.2024.101359.

Dai, P., Song, F., Liu, K., Dai, Y., Zhou, P. & Guo, S., Edge Intelligence for Adaptive Multimedia Streaming in Heterogeneous Internet of Vehicles, IEEE Trans. Mob. Comput., 22(3), pp. 1464-1478, Mar. 2023, doi: 10.1109/TMC.2021.3106147.

Eliviani, R. & Bandung, Y., WSN-IoT Forecast: Wireless Sensor Network Throughput Prediction Framework in Multimedia Internet of Things,? Journal of ICT Research and Applications, 17(3), pp. 336-355, Dec. 2023, doi: 10.5614/itbj.ict.res.appl.2023.17.3.4.

Xiao, H., Zhuang, Y., Xu, C., Wang, W., Zhang, H., Ding, R., et al., Transcoding-Enabled Cloud-Edge-Terminal Collaborative Video Caching in Heterogeneous IoT Networks: An Online Learning Approach With Time-Varying Information, IEEE Internet Things J., 11(1), pp. 296-310, Jan. 2024, doi: 10.1109/JIOT.2023.3312916.

Benzerogue, S., Abdelatif, S., Merniz, S., Harous, S. & Khamer, L., Multi-Path Transmission Protocol for Video Streaming Over Vehicular Fog Computing Environments, IEEE Access, 12, pp. 87199-87216, 2024, doi: 10.1109/ACCESS.2024.3417288.

Sun, Y., Wei, T., Li, H., Zhang, Y. & Wu, W., Energy-Efficient Multimedia Task Assignment and Computing Offloading for Mobile Edge Computing Networks, IEEE Access, 8, pp. 36702-36713, 2020, doi: 10.1109/ACCESS.2020.2973359.

Nguyen, T., Katila, R. & Gia, T.N., An Advanced Internet-of-Drones System with Blockchain for improving Quality of Service of Search and Rescue: A Feasibility Study, Future Generation Computer Systems, 140, pp. 36-52, Mar. 2023, doi: 10.1016/j.future.2022.10.002.

Mehrabi, A., Siekkinen, M., Knen, T. & YlJski, A., Multi-Tier CloudVR: Leveraging Edge Computing in Remote Rendered Virtual Reality, ACM Transactions on Multimedia Computing, Communications and Applications,. 17(2), Jun. 2021, doi: 10.1145/3429441.

Alsmirat M. & Sarhan, N.J., Intelligent Optimization for Automated Video Surveillance at the Edge: A Cross-Layer Approach, Simul. Model. Pract. Theory, 105, Dec. 2020, doi: 10.1016/j.simpat.2020.102171.

Romero, J.S., Ponce, A.d.R., Nakimuli, W., Bermejo, D.J., Garcia-Reinoso, J, Contreras, L.M. & Alvarez, F., Design, Implementation, and Validation of a Multi-Site Gaming Streaming Service Over a 5G-Enabled Platform,? IEEE Transactions on Broadcasting, 68(2), pp. 464-474, Jun. 2022, doi: 10.1109/TBC.2022.3141615.

Kang, J. & Chung, K., RL-based HTTP adaptive streaming with edge collaboration in multi-client environment, Mar. 01, 2024, Academic Press. doi: 10.1016/j.jnca.2024.103833.

Ghosh, S.K., Raha, A., Raghunathan, V. & Raghunathan A., PArtNNer: Platform-Agnostic Adaptive Edge-Cloud DNN Partitioning for Minimizing End-to-End Latency, ACM Transactions on Embedded Computing Systems, 23(1), Jan. 2024, doi: 10.1145/3630266.

Feng, H., Qiao, L. & Lv, Z., Innovative soft computing-enabled cloud optimization for next-generation IoT in digital twins, Appl. Soft Comput., 136, Mar. 2023, doi: 10.1016/j.asoc.2023.110082.

Bandung, Y., Wicaksono, M.A., Pribadi, S., Langi, A.Z.R. & Tanjung, D., IoT Video Delivery Optimization through Machine Learning-Based Frame Resolution Adjustment, ACM Transactions on Multimedia Computing, Communications and Applications, 20(9), Sep. 2024, doi: 10.1145/3665929.

Badshah, A., Iwendi, C., Jalal, A., Ul Hasan, S.S., Said, G., Band, S.S. & Chang, A., Use of Regional Computing to Minimize the Social Big Data Effects, Comput. Ind. Eng., 171, 108433, Sep. 2022, doi: 10.1016/j.cie.2022.108433.

F. Santos, R. Immich, and E. R. M. Madeira, ?Multimedia Services Placement Algorithm for Cloud?Fog Hierarchical Environments, Comput. Commun., 191, pp. 78-91, Jul. 2022. doi: 10.1016/j.comcom.2022.04.009.

Lekharu, A., Gupta, P., Sur, A. & Patra, M., Collaborative Video Caching in the Edge Network using Deep Reinforcement Learning, ACM Transactions on Internet of Things, 5(3), Jun. 2024, doi: 10.1145/3664613.

V. Mnih et al., ?Human-level control through deep reinforcement learning,? Nature, 518(7540), pp. 529?533, Feb. 2015, doi: 10.1038/nature14236.

Tan, X., Wang, S., Xu, X., Zheng, Q., Yang, J. & Chen, S., DACOD360: Deadline-Aware Content Delivery for 360-Degree Video Streaming Over MEC Networks, IEEE Trans. Multimedia, 26, pp. 4168-4182, 2024, doi: 10.1109/TMM.2023.3321439.

Xu, X., Fang, Z., Qi, L. Zhang, X., He, Q. & Zhou, X., TripRes: Traffic Flow Prediction Driven Resource Reservation for Multimedia IoV with Edge Computing, ACM Transactions on Multimedia Computing, Communications and Applications, 17(2), Jun. 2021, doi: 10.1145/3401979.

Li, B., Dong, W., Guan, G., Zhang, J., Gu, T., Bu, J. & Gao, Y., Queec: QoE-aware edge computing for iot devices under dynamic workloads, ACM Trans. Sens. Netw., 17(3), pp. 1-23, Aug. 2021, doi: 10.1145/3442363.

Baccour, E., Erbad, A., Bilal, K., Mohamed, A. & Guizani, M., PCCP: Proactive Video Chunks Caching and Processing in edge networks, Future Generation Computer Systems, 105, pp. 44?60, Apr. 2020, doi: 10.1016/j.future.2019.11.006.

Lei, J., Yang, P., Kong, L., Ma, Y., Lin, D., Chen, G. &Zhao, E., ACORN+: Adaptive Compression-Reconstruction for Device-Cloud Collaboration Video Services, ACM Transactions on Autonomous and Adaptive Systems, Nov. 2024, doi: 10.1145/3703000.

Chen, L., Tang, Y., Xia, J., Chen, S., Zheng, C., Lin, H., Wang, W., Multi-MEC Collaboration for VR Video Transmission: Architecture and Cache Algorithm Design, Computer Networks, 234, 109864, Oct. 2023, doi: 10.1016/j.comnet.2023.109864.

Hu, Z., Fang, C., Wang, Z., Tseng, S.M. & Dong, M., Many-Objective Optimization-Based Content Popularity Prediction for Cache-Assisted Cloud-Edge-End Collaborative IoT Networks,? IEEE Internet Things J., 11(1), pp. 1190-1200, Jan. 2024, doi: 10.1109/JIOT.2023.3290793.

Kumar, S., Bhagat, L., A, A.F. & Jin, J. Multi-neural network based tiled 360video caching with Mobile Edge Computing, Journal of Network and Computer Applications, 201, 103342, May 2022, doi: 10.1016/j.jnca.2022.103342.

Davronbekov, D., Pisetskiy, Y., Khayrullaev, A., Khamidov, K., Pulatov, S., Isroilov, J. & Votinov, K., , Intelligent Approaches to Managing Communication Channels in Hybrid Terrestrial-Satellite Networks with LEO Segment, Journal of ICT Research and Applications, 20(1), pp. 1-20, Jun. 2026, doi: 10.5614/itbj.ict.res.appl.2026.20.1.1.

Wang, F., Zhang, C., Wang, F., Liu, J., Zhu, H. & Pang, H., , DeepCast: Towards Personalized QoE for Edge-assisted Crowdcast with Deep Reinforcement Learning, IEEE/ACM Transactions on Networking, 28(3), pp. 1255-1268, Jun. 2020, doi: 10.1109/TNET.2020.2979966.

Guozhang, L., Alfred, R., Pailus, R., Fengchang, X. & Haviluddin, Scalable and Efficient Student Behavior Prediction using Parallelized Clustering and AHP-weighted KNN,? Journal of ICT Research and Applications, 19(2), pp. 142-165, Jan. 2025, doi: 10.5614/itbj.ict.res.appl.2025.19.2.3.