Deep reinforcement learning based computation offloading and resource allocation for MEC
The DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
Mobile edge computing (MEC) has the potential to enable computation-intensive applications in 5G networks. MEC can extend the computational capacity at the edge of wireless networks by migrating the computation-intensive tasks to the MEC server. In this paper, we consider a multi-user MEC system, where multiple user equipments (UEs) can perform computation offloading via wireless channels to an MEC server. We formulate the sum cost of delay and energy consumptions for all UEs as our optimization objective. In order to minimize the sum cost of the considered MEC system, we jointly optimize the offloading decision and computational resource allocation. However, it is challenging to obtain an optimal policy in such a dynamic system. Besides immediate reward, Reinforcement Learning (RL) also takes a long-term goal into consideration, which is very important to a time-variant dynamic systems, such as our considered multi-user wireless MEC system. To this end, we propose RL-based optimization framework to tackle the resource allocation in wireless MEC. Specifically, the Q-learning based and Deep Reinforcement Learning (DRL) based schemes are proposed, respectively. Simulation results show that the proposed scheme achieves significant reduction on the sum cost compared to other baselines.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Mobile Edge Computing: A Survey on Architecture and Computation Offloading
Mach, P., & Becvar, Z. (2017) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2017.2682318 · Cited by 3,258 · cited 1×
“Therefore, the computation offloading and computational resource allocation themes have attracted great interests as a key point in the MEC system [3].”
BackgroundEfficient multi-user computation offloading for mobile-edge cloud computing
Chen, X., Jiao, L., Li, W., & Fu, X. (2016) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2015.2487344 · Cited by 2,675 · cited 1×
“But according to [14], [15], the download data rate is very high in general, and the data size of the result is much smaller than that of input data, so the delay and energy consumptions of this step are neglected in the rest of this paper.”
BackgroundCloud computing for mobile users: can offloading computation save energy?
Kumar, K., & Lu, Y.-H. (2010) · Computer · doi:10.1109/mc.2010.98 · Cited by 1,493 · cited 1×
“The work in [5] proposed general guidelines to make offloading decision for energy consumption minimization, where the communication links were easily assumed to have a fixed rate.”
BackgroundSelf-citationEnergy-Efficient Offloading for Mobile Edge Computing in 5G Heterogeneous Networks
Zhang, K., Mao, Y., Leng, S., Zhao, Q., Li, L., Peng, X., Pan, L., Maharjan, S., & Zhang, Y. (2016) · IEEE Access · doi:10.1109/access.2016.2597169 · Cited by 855 · cited 1×
“But according to [14], [15], the download data rate is very high in general, and the data size of the result is much smaller than that of input data, so the delay and energy consumptions of this step are neglected in the rest of this paper.”
BackgroundDelay-optimal computation task scheduling for mobile-edge computing systems
Liu, J., Mao, Y., Zhang, J., & Letaief, K. B. (2016) · 2016 IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit.2016.7541539 · Cited by 759 · cited 1×
“The work in [8] designed the single-user delay-optimal task scheduling policies based on the theory of MDP, which controlled the states of the local processing and transmission units and the task buffer queue length based on the channel state.”
MethodJaszkiewicz, A. (2002) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2002.802873 · Cited by 474
Communicating While Computing: Distributed mobile cloud computing over 5G heterogeneous networks
Barbarossa, S., Sardellitti, S., & Di Lorenzo, P. (2014) · IEEE Signal Processing Magazine · doi:10.1109/msp.2014.2334709 · Cited by 468 · cited 2×
“Since the data rates for wireless communications are not constant, the optimal binary computation offloading decision using convex optimization was proposed in [6], where the the famous Shannon-Hartley formula gave the power-rate function.”
BackgroundMobile-edge computing architecture: the role of mec in the internet of things
Sabella, D., Vaillant, A., Kuure, P., Rauschenbach, U., & Giust, F. (2016) · IEEE Consumer Electronics Magazine · doi:10.1109/mce.2016.2590118 · Cited by 413 · cited 1×
“MEC is a new paradigm in C-RAN, which can enhance the computation capacity at the edge of mobile networks by deploying high-performance servers [2].”
BackgroundEnergy-optimal mobile application execution: Taming resource-poor mobile devices with cloud clones
Wen, Y., Zhang, W., & Luo, H. (2012) · 2012 Proceedings IEEE INFOCOM · doi:10.1109/infcom.2012.6195685 · Cited by 394 · cited 1×
“We set zn = 10−27 ( f l n )2 according to the practical measurement in [13].”
MethodPeng, M., Sun, Y., Li, X., Mao, Z., & Wang, C. (2016) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2016.2548658 · Cited by 386
Cited by
Items 301–400 of 560
Chou, P.-Y., Chen, W.-Y., Wang, C.-Y., Hwang, R., & Chen, W.-T. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3128741 · Cited by 13
Hu, Z., Gao, H., Wang, T., Han, D., & Lu, Y. (2022) · Sensors · doi:10.3390/s22093217 · Cited by 14
“Because an MEC system is deployed at the edge of IoT networks and near the access network, it is capable of bridging the divide between the limited resources in the proximity of users and the ever-increasing computational demand of IoT applications [20].”
BackgroundSelf-citationMarwan, M., Temghart, A. A., Ouhmi, S., & Lazaar, M. (2024) · Results in Engineering · doi:10.1016/j.rineng.2024.102902 · Cited by 11
Optimizing Workflow Offloading and Migration under Timed Constraints in Fog and Cloud Computing
Boubaker, N. E. H., Zarour, K., Guermouche, N., & Benmerzoug, D. (2025) · Journal of Grid Computing · doi:10.1007/s10723-025-09795-5 · Cited by 11
“A comparative analysis of the reviewed studies is presented in Table 1 2.1 Static Placement Li et al. [24] employed Q-learning and DQN algorithms to optimize offloading decisions in Mobile Edge Computing (MEC), aiming to minimize both delay and energy consumption for all users.”
InfluentialBlockchain-based Trustworthy Service Caching and Task Offloading for Intelligent Edge Computing
Zhou, Y., Li, X., Ji, H., & Zhang, H. (2021) · Globecom · doi:10.1109/globecom46510.2021.9685168 · Cited by 11
“We first compare the proposed DRL algorithm with Q-learning [15] and deep Q-network (DQN) [16].”
MethodMEC and Blockchain-Enabled Energy-Efficient Internet of Vehicles Based on A3C Approach
Ye, X., Li, M., Yu, F. R., Si, P., Wang, Z., & Zhang, Y. (2021) · Globecom · doi:10.1109/globecom46510.2021.9685402 · Cited by 11
“where the value of k is 10−27 based on the actual measurement [11], Fl is the computing capacity of all vehicles, as well as cn(t) is the required CPU cycles to complete the computing task n at time slot t.”
BackgroundAbdalla, A. S., Behfarnia, A., & Marojevic, V. (2022) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc51071.2022.9771893 · Cited by 11
Zhu, Y., & Lu, D. (2023) · Computer Networks · doi:10.1016/j.comnet.2023.110050 · Cited by 11
Double Broad Q-Network for Overtaking Control of Autonomous Driving
Peng, X.-T., Bu, X.-Y., Zhang, X.-Y., Dong, M.-X., & Ota, K. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3390571 · Cited by 7
“AndLi, etal.proposedaQ-learning-basedthemeandaDQN-based themetosolvethecomputationoffloadingproblemin[20].”
Yin, S., Liu, L., Cai, M., Chai, Y., Jiao, Y., Duan, Z., Li, Y., & Huang, S. (2024) · Journal of Optical Communications and Networking · doi:10.1364/jocn.533206 · Cited by 12
“In [32], a deep-RL-based algorithm to make the optimal sampling rate adaption and resource allocation decisions of collaborative DNN inference in IIoT was proposed.”
MethodLoad-Aware Orchestrator for Edge-Computing-Aided Wireless Augmented Reality
Qian, W., & Coutinho, R. W. L. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3494533 · Cited by 11
“As in [18] and [38], we assume that an eNB small cell is used to serve multiple MAR user devices and the available bandwidth W is equally shared among MAR user devices in the service area.”
A Two-Stage Cooperative Reinforcement Learning Scheme for Energy-Aware Computational Offloading
Avgeris, M., Mechennef, M., Leivadeas, A., & Lambadaris, I. (2023) · IEEE International Conference on High Performance Switching and Routing (HPSR) · doi:10.1109/hpsr57248.2023.10147932 · Cited by 10
“Following [4], we assume that the task’s output size is much smaller than the input size and that the downlink rate from an ES to an MD is high enough, to allow for neglecting the transmission time 2023 IEEE 24th International Conference on High Performance Switching and Routing (HPSR)”
BackgroundMethodInfluentialGeneralizable Pareto-Optimal Offloading With Reinforcement Learning in Mobile Edge Computing
Yang, N., Wen, J., Zhang, M., & Tang, M. (2025) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2025.3604371 · Cited by 21
“In contrast, a majority of other studies [2], [5], [6], [7], [14] have predominantly disregarded the aspect of generalization in their methodologies.”
Femminella, M., & Reali, G. (2024) · Algorithms · doi:10.3390/a17080320 · Cited by 10
Partial Task Offloading Strategy Based on Deep Reinforcement Learning
Wang, Z., & Zhu, Q. (2020) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc51575.2020.9345003 · Cited by 10
“Li, Ji, et al. [9] put forward an offloading model based on Q learning and gets the optimal offloading result by continually updating the Q table.”
MethodDeep Q-Learning for Joint Server Selection, Offloading, and Handover in Multi-access Edge Computing
Ho, T. M., & Nguyen, K.-K. (2021) · International Conference on Communications · doi:10.1109/icc42927.2021.9500353 · Cited by 10
“In [6] a deep Q-learning based framework is proposed to jointly optimize the offloading decision and computational resource allocation that minimizes the sum cost of delay and energy consumption of all user equipment.”
MethodICRAN: Intelligent Control for Self-Driving RAN Based on Deep Reinforcement Learning
Ahmed, A. H., & Elmokashfi, A. M. (2022) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2022.3191746 · Cited by 11
Content-centric data and computation offloading in AI-supported fog networks for next generation IoT
Kök, İ., & Özdemir, S. (2022) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2022.101654 · Cited by 14
EdgeMap: CrowdSourcing High Definition Map in Automotive Edge Computing
Liu, Q., Zhang, Y., & Wang, H. (2022) · International Conference on Communications · doi:10.1109/icc45855.2022.9838617 · Cited by 10
“The mode-free approaches [19], [20], [21], [22] exploited the advanced machine learning techniques, e.g., DRL, to handle the high-dim network state and dynamics.”
MethodGuo, Z., Chen, H., & Li, S. (2023) · Sensors · doi:10.3390/s23063237 · Cited by 10
“In [42], this kind of problem proved to be an NP-hard problem, and it is difficult to find an optimal solution.”
BackgroundMulti-Agent Vehicle Formation Control Based on MPC and Particle Swarm Optimization Algorithm
Huang, J., Ji, Z., Xiao, S., Jia, C., Jia, Y., & Wang, X. (2022) · IEEE Information Technology and Mechatronics Engineering Conference (ITOEC) · doi:10.1109/itoec53115.2022.9734371 · Cited by 10
Lyu, S., Feng, M., Xiao, L., Zhou, J., & Jiang, T. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3608832 · Cited by 9
“In [28], a DQN-based task offloading and resource allocation scheme was proposed, which reduces task completion latency and energy consumption in dynamic network environments.”
Task Offloading Optimization in Mobile Edge Computing based on Deep Reinforcement Learning
Silva, C., Magaia, N., & Grilo, A. (2023) · ACM International Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems (MSWiM) · doi:10.1145/3616388.3617539 · Cited by 9
“The proposed system is build upon [9], by addressing the following shortcomings: • Expanding the number of MEC servers that must be orchestrated from one to 𝑀 servers, better representing a 5G network with several SCeNBs enhanced with computation capabilities; • Testing the management agent in a…”
BackgroundDuan, Y., Li, J., Sun, H., Zhou, F., Chen, J., Wu, T., Li, W., & Fan, Y. (2024) · Simulation Modelling Practice and Theory · doi:10.1016/j.simpat.2023.102885 · Cited by 9
Self-citationShu, Z., Deng, X., Wang, L., Gui, J., Wan, S., Zhang, H., & Min, G. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3439332 · Cited by 9
“Therefore, some works [2], [8], [9], [10] have adopted DRL to solve the task offloading and load balancing problems.”
MethodAI at the Physical Layer for Wireless Network Security and Privacy
Abdalla*, A. S., Tang, B., & Marojevic, V. (2024) · Wiley eBooks · doi:10.1002/9781394227952.ch10 · Cited by 12
Wang, L., & Jiao, H. (2024) · Sensors · doi:10.3390/s24248014 · Cited by 10
“Referring to the works [14,30–34], similar values are set in our simulations.”
Combinations of generative adversarial network and reinforcement learning: A survey
Yau, K., Chong, Y.-W., Fan, X., Nejati, F., Chamran, M. K., & Darmaraju, S. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130847 · Cited by 7
Task Distribution Offloading Algorithm Based on DQN for Sustainable Vehicle Edge Network
Feng, T., Wang, B., Zhao, H., Zhang, T., Tang, J., & Wang, Z. (2021) · IEEE International Conference on Network Softwarization (NetSoft) · doi:10.1109/netsoft51509.2021.9492640 · Cited by 9
Deep Reinforcement Learning Based Task Offloading Strategy Under Dynamic Pricing in Edge Computing
Shi, B., Chen, F., & Tang, X. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-91431-8_36 · Cited by 9
Yang, M., Yu, P., Wang, Y., Huang, X., Miu, W., Yu, P., Li, W., Yang, R., Tao, M., & Shi, L. (2020) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc48107.2020.9148169 · Cited by 9
“In the paper [9], in order to optimize the energy and delay consumption, a reinforcement learning based scheme was proposed to minimize the energy and delay consumption by jointly optimizing computational resources and network resource allocation.”
MethodReinforcement Learning on Computational Resource Allocation of Cloud-based Wireless Networks
Chen, B., Zhang, Y., Iosifidis, G., & Liu, M. (2020) · IEEE World Forum on Internet of Things (WF-IoT) · doi:10.1109/wf-iot48130.2020.9221234 · Cited by 9
“instance, authors in [5] used reinforcement learning to optimise the computational task offloading problem from mobile users to edge computing servers.”
BackgroundD2D-Assisted Multi-User Cooperative Partial Offloading in MEC Based on Deep Reinforcement Learning
Guan, X., Lv, T., Lin, Z., Huang, P., & Zeng, J. (2022) · Sensors · doi:10.3390/s22187004 · Cited by 9
“In full offloading, each task can be completely offloaded to the resource device or run completely locally [2,16,17].”
BackgroundMethodSelf-citationMuslim, N., Islam, S., & Grégoire, J. (2020) · International Journal of Network Management · doi:10.1002/nem.2146 · Cited by 9
“Li et al. 38 proposed to optimize resource allocation for MEC using DRL-based computation offloading technique.”
MethodDistributed Multiagent Reinforcement Learning Approach for Multiserver Multiuser Task Offloading
Zhang, H., Tian, Z., Zeng, L., Lu, L., Qiao, S., Chen, S., & Liu, X. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3585025 · Cited by 9
“In the partial offloading scenario, UD i offloads a portion As in [35] and [53], the downlink transmission time and energy cost are ignored, since the downlink rate is much higher than the uplink rate.”
Guan, Z., Li, Y., Yu, S., & Yang, Z. (2023) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.4724 · Cited by 9
“8,9 The scheduling management of delay-constrained medical packet transmissions in IoT-based healthcare networks is studied in Reference 10.”
MethodInfluentialPPO-Based Joint Optimization for UAV-Assisted Edge Computing Networks
Liu, Z., Zhang, Q., & Su, Y. (2023) · Applied Sciences · doi:10.3390/app132312828 · Cited by 8
Reinforcement Learning for Service Function Chain Allocation in Fog Computing
Santos, J., Wauters, T., Volckaert, B., & Turck, F. D. (2021) · Wiley eBooks · doi:10.1002/9781119675525.ch7 · Cited by 8
Khani, M., Jamali, S., & Sohrabi, M. K. (2024) · Cluster Computing · doi:10.1007/s10586-023-04252-y · Cited by 8
“DQN’s application extends across diverse domains, including network slicing [41], resource allocation [42], and slice admission systems [29].”
Mobile Task Offloading Under Unreliable Edge Performance
Hossen, M. R., & Islam, M. A. (2021) · ACM SIGMETRICS Performance Evaluation Review · doi:10.1145/3466826.3466838 · Cited by 8
“5 GHz processor, and a transmission power of 500 mW [5].”
BackgroundMethodDouble DQN Based Computing Offloading Scheme for Fog Radio Access Networks
Jiang, F., Zhu, X., & Sun, C. (2021) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc52777.2021.9580391 · Cited by 8
Auxiliary-Task-Based Energy-Efficient Resource Orchestration in Mobile Edge Computing
Zhu, K., Zhang, Z., & Zhao, M. (2022) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2022.3201615 · Cited by 8
He, C., Jiang, W., Wang, X., Wang, W., Wang, J., & Xie, X. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3558228 · Cited by 7
“Li et al. [18] used DRL for computational offloading and resource allocation based on MEC.”
Zhang, B., Jing, T., Gao, Q., Li, X., & Zhu, M. (2025) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2025.3598495 · Cited by 7
“Since P 0 has been proved to be an nondeterministic polynomial hard problem [26], we convert it into a Markov decision process (MDP) problem, which can be solved by DRL-based algorithms.”
Variational Autoencoders for Reliability Optimization in Multi-Access Edge Computing Networks
Ahmadi, A., Semiari, O., Bennis, M., & Debbah, M. A. (2022) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc51071.2022.9771710 · Cited by 8
“The downlink and uplink packet sizes are selected randomly from a uniform distribution with a range [1, 10] kbits.”
BackgroundMEC Computation Offloading-Based Learning Strategy in Ultra-Dense Networks
Duo, C., Dong, P., Gao, Q., Li, B., & Li, Y. (2022) · Information · doi:10.3390/info13060271 · Cited by 7
“[32], and Q-learning and DQN algorithms were, respectively, used in simulation experiments.”
BackgroundMethodLi, H., & Huang, J. (2024) · Vehicular Communications · doi:10.1016/j.vehcom.2024.100853 · Cited by 9
Khan, H., Ali, Z., Abbas, Z. H., Abbas, G., Khan, S., & Yahya, M. (2025) · Ad Hoc Networks · doi:10.1016/j.adhoc.2025.103787 · Cited by 9
Artificial intelligence techniques over the fifth generation mobile networks: a review
Hassan, A. N., Al-Chlaihawi, S. J., & Khekan, A. R. (2021) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v24.i1.pp317-328 · Cited by 11
Chen, N., Zhang, S., Quan, S., Ma, Z., Qian, Z., & Lu, S. (2021) · Computer Networks · doi:10.1016/j.comnet.2021.108513 · Cited by 8
Efficient Deep Learning Approach for Computational Offloading in Mobile Edge Computing Networks
Cheng, X., Liu, J., & Jin, Z. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/2976141 · Cited by 8
“DNN has a high accuracy rate when training big data [27].”
BackgroundDeep-Dual-Learning-Based Cotask Processing in Multiaccess Edge Computing Systems
Chiang, Y.-H., Chiang, T.-W., Zhang, T., & Ji, Y. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3004165 · Cited by 8
“Li et al. [24] aimed to minimize delay and energy consumption through Q -learning and deep Q -network (DQN) schemes.”
BackgroundPrivacy-Aware Offloading Strategy via Self-Supervised Feature Mapping in the End-Edge-Cloud System
Zhang, R., Zhao, X., Li, Y., Zheng, S., Ma, R., Tian, M., Xue, Y., Wang, Y., & Guan, H. (2024) · ACM Transactions on Sensor Networks · doi:10.1145/3685931 · Cited by 9
Li, J., Liu, R., & Liu, W. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103344 · Cited by 6
Self-citationSafeTail: Tail Latency Optimization in Edge Service Scheduling via Redundancy Management
Shokhanda, J., Pal, U., Kumar, A., Chattopadhyay, S., & Bhattacharya, A. (2025) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2025.3587752 · Cited by 6
“…services, with the number of edge servers selected based on the redundancy level x. (v) Deep Reinforcement Learning with Linear Model (DRL-Linear) [28] : This work minimizes execution delay and energy in multi-user settings via joint offloading and resource allocation, using a Q-learning and…”
Joint Computational Resource Allocation and Layer Partitioning for Federated Learning
Qiang, G., Fang, F., Chen, H., & Wang, X. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3592155 · Cited by 6
“Li et al. [20] used deep reinforcement learning (DRL) to optimize computation offloading and resource allocation, minimizing delay and energy consumption.”
NASP: Network slice as a service platform for 5G Networks
Grings, F. H., Bruno, G. Z., Prade, L. R., Brito, J. M. C., & Both, C. B. (2026) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2026.104479 · Cited by 6
“…services, and stringent performance requirements, motivates the need for a comprehensive, automated approach to NS. Existing studies have addressed aspects of resource allocation us-ing machine-learning techniques [14, 15] and developed frameworks for NS control or assurance [16, 17, 18].”
Smart stochastic routing for 6G-enabled massive Internet of Things
Abbas, G., Abbas, Z. H., Ali, Z., Shahwar, M., Ghosh, U., & Bilal, M. (2021) · Computer Communications · doi:10.1016/j.comcom.2021.09.015 · Cited by 6
Alhartomi, M. A. (2023) · IEEE Annual Computing and Communication Workshop and Conference (CCWC) · doi:10.1109/ccwc57344.2023.10099362 · Cited by 6
IEEE P1935 Edge/Fog Manageability and Orchestration: Standard and Usage Example
Chen, T.-Y., Chiang, Y., Wu, J.-H., Chen, H.-T., Chen, C. L., & Wei, H. (2023) · IEEE International Conference on Edge Computing and Communications (EDGE) · doi:10.1109/edge60047.2023.00025 · Cited by 6
Liu, Y., Zhao, T., Shou, G., & Zhang, Y. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3448627 · Cited by 6
“In [12], the multi-objective optimization problem is converted into a single-objective optimization problem through linear weighting method, and the optimal solution is obtained through DQN and Q-learning algorithm.”
Ren, T., Niu, J., & Qiu, Y. (2022) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2022.102444 · Cited by 6
Morín, D. G., Morales, M. J. L., Pérez, P., & Villegas, Á. (2022) · ACM International Conference on Interactive Media Experiences · doi:10.1145/3505284.3529963 · Cited by 7
“Some studies [17] aim to apply ML approaches to optimize the resource usage toward low latency and reliable VR ofoading schemes.”
BackgroundEfficient Resource Allocation Policy for Cloud Edge End Framework by Reinforcement Learning
Yang, C., Xu, H., Fan, S., Cheng, X., Liu, M., & Wang, X. (2022) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc56324.2022.10065844 · Cited by 6
“But, the complex dynamics of MECC networks(e.g. random computation task arrival, fluctuation of wireless channel environment, inconstant service time of computation task) cause inefficient resource allocation and make it difficult to guarantee end-to-end delay QoS requirement [13], [14].”
BackgroundIntelligent Parking Management System Design from a Mobile Edge Computing (MEC) Perspective
Zhang, C., Wang, Q., Wang, M., Chen, J., Liu, H., & Fu, S. (2018) · IEEE Vehicular Technology Conference · doi:10.1109/vtcfall.2018.8691030 · Cited by 6
“Our work provides a scientific analysis method for the MEC implementation of the smart parking system.”
MethodInfluentialRevenue-Maximized Offloading Decision and Fine-Grained Resource Allocation in Edge Network
Ni, W., Tian, H., Fan, S., & Liu, B. (2019) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc.2019.8886041 · Cited by 6
“Whereas, if [4] had added communication resource allocation into the action set, the results might have been more convincing.”
BackgroundCutting the Cord: Key Performance Indicators for the Future of Wireless Virtual Reality Applications
Morín, D. G., Armada, A. G., & Pérez, P. (2020) · International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP) · doi:10.1109/csndsp49049.2020.9249445 · Cited by 6
“Similarly, in [8], the authors propose a reinforcement learning-based method in which the goal is to optimize the effective latency and energy consumption.”
BackgroundPreemptive Mobile Computation Offloading With Hard Deadlines and Concurrent Local Execution
Teymoori, P., Hekmati, A., Todd, T. D., Zhao, D., & Karakostas, G. (2021) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2021.3061106 · Cited by 6
“, [23], [24] can be used to effectively learn parameters of the system (e.”
Reliable Data Transmission over Energy-Efficient Vehicular Network Based on Blockchain and MEC
Ye, X., Li, M., Yu, F. R., Si, P., Wang, Z., & Zhang, Y. (2021) · International Conference on Communications · doi:10.1109/icc42927.2021.9500307 · Cited by 6
“where k is set to 10−27 according to the actual measurement [13].”
BackgroundZhou, Y.-T., Ye, Q., Huang, H., & Du, H. (2021) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2021-fall52928.2021.9625281 · Cited by 6
A2C Deep Reinforcement Learning-based MEC Network for Offloading and Resource Allocation
Cui, H., Wang, D., Li, Q. L., Liu, X., & Lü, H. (2021) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc54389.2021.9674631 · Cited by 6
Machine Learning-Based Medium Access Control Protocol for Heterogeneous Wireless Networks: A Review
Nayak, N. K. S., & Bhattacharyya, B. (2021) · Innovations in Power and Advanced Computing Technologies (i-PACT) · doi:10.1109/i-pact52855.2021.9696964 · Cited by 6
Distributed Cooperative Reinforcement Learning for Wireless Sensor Network Routing
Barker, A., & Martin Swany, A. (2022) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc51071.2022.9771591 · Cited by 6
“More recent research has looked at deep reinforcement learning (DRL) as a mechanism for learning effective offloading policies such as in [7].”
Background5G Radio Resource Allocation for Communication and Computation Offloading
Stan, C., Rommel, S., de Miguel, I., Olmos, J. J. V., Barroso, R. J. D., & Monroy, I. T. (2023) · Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit) · doi:10.1109/eucnc/6gsummit58263.2023.10188281 · Cited by 6
“A joint optimization problem for offloading decisions and computational resource allocation was proposed in [13] where deep reinforcement learning (DRL) was employed to find the optimal solution.”
MethodElgendy, I. A., Muthanna, A., Hammoudeh, M. A. A., Shaiba, H. A., Ünal, D., & Khayyat, M. M. (2021) · doi:10.36227/techrxiv.13635065 · Cited by 6
Deep learning approaches for computation offloading in edge computing: A critical review
Miriyala, S., & Chirra, V. R. (2026) · Telecommunication Systems · doi:10.1007/s11235-026-01426-y · Cited by 7
“Convolutional neural networks (CNNs) have similarly been applied to spatial-temporal workload prediction across geographically distributed edge servers [52].”
Reliable Layered Transmission and Task Offloading in UAV-Assisted MEC Networks for Disaster Relief
Desher, A. R., & Al-Shuwaili, A. (2026) · Drones · doi:10.3390/drones10030167 · Cited by 5
Shi, Y., & Liu, B. (2022) · International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE) · doi:10.1109/icbaie56435.2022.9985890 · Cited by 5
“…the core challenges faced by computing offload technology in MEC, such as mobility management, interference management and security; Literature [8] proposed a framework based on reinforcement learning to solve the resource allocation problem of MEC network, and minimize energy consumption and…”
BackgroundAhlawat, C., & Krishnamurthi, R. (2022) · International Conference on Contemporary Computing · doi:10.1145/3549206.3549230 · Cited by 5
“Abdullah Lakhan, et al. [11] use the deep reinforcement learning approach in a fog environment to attain the optimal cost and time for the task requested by reducing the delay and achieving better energy utilization with computation services.”
BackgroundRasool, M. A. E., Kumar, A., & Islam, A. (2024) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2024.01504122 · Cited by 7
“To overcome limitations of centralized clouds (e.g. congestion, reduced robustness [3]) and distributed clouds (e.g. complexity, management issues [4]), architectures like edge cloud computing [5] and multi-access edge computing (MEC) [6, 7] have emerged.”
BackgroundTripathi, S., Kumar, P. M., Chaitanya, M. S., Teja, N. S. T., Misra, R., & Singh, T. N. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825921 · Cited by 6
Du, X., & Fang, X. (2024) · Globecom · doi:10.1109/globecom52923.2024.10901620 · Cited by 5
“The data size of computing task is uniformly distributed between 2.4Mbits and 4Mbits, and the communication task is between 10Mbits and 20Mbits. λ is set to 0.8.”
InfluentialSecure and Energy-Efficient Computational Offloading Using LSTM in Mobile Edge Computing
Arif, M., Ajesh, F., Shamsudheen, S., & Shahzad, M. (2022) · Security and Communication Networks · doi:10.1155/2022/4937588 · Cited by 9
“[23] proposed a deep reinforcement learning strategy to strengthen the entire offloading system.”
BackgroundRetractedZhang, X., Hu, Z., Zheng, M., Liang, Y., Xiao, H., Zheng, H., & Xu, A. (2023) · Applied Sciences · doi:10.3390/app13106115 · Cited by 5
Wei, Z. F., He, R., & Li, Y. (2023) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/icccworkshops57813.2023.10233832 · Cited by 5
“Computing offloading as a primary strategy in MEC has been widely investigated recently [5-7].”
BackgroundLearning scheduling bursty requests in Mobile Edge Computing using DeepLoad
Chen, N., Zhang, S., Wu, J., Qian, Z., & Lu, S. (2020) · Computer Networks · doi:10.1016/j.comnet.2020.107655 · Cited by 6
Structure-Aware Reinforcement Learning for Node-Overload Protection in Mobile Edge Computing
Jitani, A., Mahajan, A., Zhu, Z., Abou-Zeid, H., Fapi, E. T., & Purmehdi, H. (2022) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2022.3195503 · Cited by 5
Dynamic Load Sharing in Memory Constrained Devices: A Survey
Nwafor, E., Robson, M. P., & Olufowobi, H. (2021) · IEEE World Forum on Internet of Things (WF-IoT) · doi:10.1109/wf-iot51360.2021.9594948 · Cited by 5
Energy-Efficient D2D-Aided Fog Computing under Probabilistic Time Constraints
Karatalay, O., Psaromiligkos, I., & Champagne, B. (2021) · Globecom · doi:10.1109/globecom46510.2021.9685231 · Cited by 5
“However, the computation capability of MEC servers is limited, and in situations involving extensive data traffic and high user density, some mobile devices might not be able to access them, which negatively impacts the quality of service [5].”
BackgroundLyapunov-based Dynamic Computation Offloading Optimization in Heterogeneous Vehicular Networks
Yue, Y., & Wang, J. (2022) · IEEE International Symposium on Product Compliance Engineering - Asia (ISPCE-ASIA) · doi:10.1109/ispce-asia57917.2022.9971076 · Cited by 5
“At each time slot, the input size of offloaded task is uniformly distributed within [300, 500] Kbits, and the required CPU cycles obeys uniform distribution between [900, 1100] megacycles [10].”
BackgroundAmalgamation of Computational Intelligence and 6G-Enabled AIoT Networks for Industry 4.0
Walia, G. K., Kumar, M., Kumar, S., & Gill, S. S. (2025) · Advances in Science, Technology & Innovation/Advances in science, technology & innovation · doi:10.1007/978-3-031-82733-4_16 · Cited by 4
Ma, C., Cao, Q., & Zhou, P. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.107651 · Cited by 4
A Dual-Agent Approach for Coordinated Task Offloading and Resource Allocation in MEC
Dong, J., Pan, K., Zheng, C., Chen, L., Wu, S., & Zhang, X. (2023) · Journal of Electrical and Computer Engineering · doi:10.1155/2023/6134837 · Cited by 4
A GNN-DRL-based Collaborative Edge Computing Strategy for Partial Offloading
Tao, T., Hou, J., & Nayak, A. R. (2023) · Globecom · doi:10.1109/globecom54140.2023.10436825 · Cited by 4
“In recent years, many researchers [5]–[14] have proposed offloading strategies based on deep reinforcement learning (DRL), a promising tool for solving a wide range of complex real-world problems.”
BackgroundLai, Y., Yang, H., & Yang, C. (2024) · International Conference on Advanced Computational Intelligence (ICACI) · doi:10.1109/icaci60820.2024.10536998 · Cited by 4
“The related work of RL-based network slicing can be classified into three categories, communication resources only [3-11], computation resources only [12], and communication and computation resources both [13-18].”
BackgroundMethodInfluentialNovel multi-dimensional task offloading techniques for vehicular edge computing networks
Abuthahir, S. S., & Peter, J. S. P. (2024) · International Journal of Systems Assurance Engineering and Management · doi:10.1007/s13198-024-02616-0 · Cited by 4
“Li et al. (2018) have designed a MEC system based on multiple users, where several pieces of equipment are capable of performing computation offloading through wireless channels to a server.”
Robust Learning Algorithms for Task Scheduling in MEC-Enabled IoT Networks
Masih, V., & Roy, A. (2025) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2025.3589467 · Cited by 4
“For MEC-assisted IoT networks, traditional RL (such as Q-learning [9]) based task scheduling approaches [10], [11] are proposed in the literature.”
InfluentialA Multi-Layered Distributed Computing Framework for Enhanced Edge Computing
Ma, K., & Xie, J. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3614551 · Cited by 4
“Reinforcement learning has also emerged as a promising tool for computation offloading [7, 25].”
BackgroundMethodInfluentialShi, B., Pan, Y., & Huang, L. (2024) · Service Oriented Computing and Applications · doi:10.1007/s11761-024-00419-6 · Cited by 4
“Li et al. [12] provided an in-depth study of task offloading and resource allocation for dynamically changing multi-user mobile edge computing environments and proposed a solution based on the Q-learning algorithm and deep reinforcement learning algo-rithm, aiming to minimize the sum of latency and…”
Sum computation rate maximization for wireless powered OFDMA-based mobile edge computing network
Shen, G., Wei, X., Chi, K., Alqahtani, F. H., & Tolba, A. K. R. (2024) · Computer Networks · doi:10.1016/j.comnet.2024.110961 · Cited by 4
Metadata
- Authors
- Li, J., Gao, H., Lv, T., & Lu, Y.
- Affiliations
- Beijing University of Posts and Telecommunications (CN)
- Venue
- 2018 IEEE Wireless Communications and Networking Conference (WCNC)
- Publisher
- IEEE
- Published
- 2018-04
- Pages
- 1-6
- ISSN
- 1525-3511 (ISSN-L)
- OpenAlex
- W2808381205
- Cited by
- 548
- References
- 17
- Citations by year
- 2026: 16 · 2025: 45 · 2024: 73 · 2023: 83 · 2022: 92 · 2021: 96 · 2020: 94 · 2019: 45 · 2018: 4
- FWCI
- 49.38
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Wireless Communications and Networking Conference (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Network Optimization
- Physical Sciences › Engineering › Aerospace Engineering › UAV Applications and Optimization
- Keywords
- mobile edge computing, computation offloading, resource allocation, deep reinforcement learning, Q-learning, multi-user systems, energy consumption, delay cost, 5G
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.