Online Learning for Offloading and Autoscaling in Energy Harvesting Mobile Edge Computing
Open accessThe DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
Abstract
Mobile edge computing (also known as fog computing) has recently emerged to enablein-situprocessing of delay-sensitive applications at the edge of mobile networks. Providing grid power supply in support of mobile edge computing, however, is costly and even infeasible (in certain rugged or under-developed areas), thus mandating on-site renewable energy as a major or even sole power supply in increasingly many scenarios. Nonetheless, the high intermittency and unpredictability of renewable energy make it very challenging to deliver a high quality of service to users in energy harvesting mobile edge computing systems. In this paper, we address the challenge of incorporating renewables into mobile edge computing and propose an efficient reinforcement learning-based resource management algorithm, which learns on-the-fly the optimal policy of dynamic workload offloading (to the centralized cloud) and edge server provisioning to minimize the long-term system cost (including both service delay and operational cost). Our online learning algorithm uses a decomposition of the (offline) value iteration and (online) reinforcement learning, thus achieving a significant improvement of learning rate and run-time performance when compared to standard reinforcement learning algorithms such as${Q}$-learning. We prove the convergence of the proposed algorithm and analytically show that the learned policy has a simple monotone structure amenable to practical implementation. Our simulation results validate the efficacy of our algorithm, which significantly improves the edge computing performance compared to fixed or myopic optimization schemes and conventional reinforcement learning algorithms.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“At this background, large state and action spaces in the whole offloading problem make the conventional learning algorithms [245] [256] [247] infeasible actually.”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [245]
Citations
Cites
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. G. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.1998.712192 · Cited by 27,225 · cited 5×
“The proposed PDS-based learning algorithm is compared with three benchmark schemes: • Q-learning [10]: Q-learning is a famous model-free reinforcement learning technique for solving MDP problems.”
BackgroundMethodInfluentialReinforcement Learning: An Introduction
(2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 24,496
(1995) · Cited by 10,558
Edge computing: Vision and challenges
Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016) · IEEE Internet of Things Journal · doi:10.1109/jiot.2016.2579198 · Cited by 8,733 · cited 4×
“backbone networks [1] but also result in (sometimes intolerable) large transmission latencies that degrade the quality of service [2]–[4].”
BackgroundInfluentialMarkov decision processes: Discrete stochastic dynamic programming
Hazeghi, K., & Puterman, M. L. (1995) · Journal of the American Statistical Association · doi:10.2307/2291177 · Cited by 8,037 · cited 1×
“battery state b and the power demand action a for any given λ,e,h. This is to prove that ∀b ≤ b′ and a ≤ a′, we have C(b,a ′)− C(b,a) ≥ C(b ,a′)− C(b′,a) (32) If the above is true, then we can apply [27] (Section 4.7) to show that π(s) is non-decreasing in b. Equation (32) is equivalent to V∗(b− a ′)− V ∗(b −a) ≥ V∗(b…”
InfluentialA Survey on Mobile Edge Computing: The Communication Perspective
Mao, Y., You, C., Zhang, J., Huang, K., & Letaief, K. B. (2017) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2017.2745201 · Cited by 5,607
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Baxter, L. A. (1995) · Technometrics · doi:10.1080/00401706.1995.10484354 · Cited by 2,415
Fog and IoT: An Overview of Research Opportunities
Chiang, M., & Zhang, T. (2016) · IEEE Internet of Things Journal · doi:10.1109/jiot.2016.2584538 · Cited by 2,362 · cited 2×
“Fog computing [5] is a related concept that refers to the same computing paradigm.”
BackgroundStochastic Network Optimization with Application to Communication and Queueing Systems
Neely, M. J. (2010) · Synthesis lectures on communication networks · doi:10.2200/s00271ed1v01y201006cnt007 · Cited by 2,218
Energy Harvesting Sensor Nodes: Survey and Implications
Sudevalayam, S., & Kulkarni, P. (2011) · IEEE Communications Surveys & Tutorials · doi:10.1109/surv.2011.060710.00094 · Cited by 1,981 · cited 2×
“and/or solar radiation is embraced as a major or even sole power supply for edge systems in the field, thanks to the recent advancements of energy harvesting techniques [8], [9].”
Background
Research works printed but not linked: 4
- reiss, 2011, Google Cluster-usage Traces Format+ Schema, 1
- patel, 2014, Mobile-Edge Computing—Introductory Technical White Paper
- 2017, Elia Power Generation
- rivera, 2014, Gartner Says the Internet of Things Will Transform the Data Center
Cited by
Items 201–300 of 368
Power optimisation in UAV‐assisted wireless powered cooperative mobile edge computing systems
Lu, W., Xu, X., Ye, Q., Li, B., Peng, H., Hu, S., & Gong, Y. (2020) · IET Communications · doi:10.1049/iet-com.2019.1063 · Cited by 19
Energy‐Efficient Task Migration and Path Planning in UAV‐Enabled Mobile Edge Computing System
Gong, C., Li, W., Gong, D., Li, T., & Feng, F. (2022) · Complexity · doi:10.1155/2022/4269102 · Cited by 17
A ${Q}$ -Learning Based Framework for Congested Link Identification
Pan, S., Li, P., Zeng, D., Guo, S., & Hu, G. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2930459 · Cited by 19
“Just as some pioneer studies [21]–[23] that empower networking with reinforcement learning to adaptively manage”
BackgroundGarcía, C. E., Camana, M. R., & Koo, I. (2020) · Energies · doi:10.3390/en13215540 · Cited by 16
“It is assumed that the communications and power transferred from the PB and the AP are sent over the same frequency band and that all nodes are equipped with a single antenna, similar to the research in [11,19,20].”
BackgroundHou, J., Chen, M., Geng, H., Li, R., & Lu, J. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.11.025 · Cited by 15
Mobile Cloud Storage Over 5G: A Mechanism Design Approach
Siddavaatam, R., Woungang, I., Carvalho, G. H. S., & Anpalagan, A. (2019) · IEEE Systems Journal · doi:10.1109/jsyst.2019.2908391 · Cited by 15
“[23] applied the re-”
Wireless Powered Cognitive-Based Mobile Edge Computing With Imperfect Spectrum Sensing
Liu, B., Li, W., Ma, Y., Wang, J., & Lu, G. (2019) · IEEE Access · doi:10.1109/access.2019.2923429 · Cited by 15
“However, the intermittency and randomness of renewable energymake EH hard to provide high quality of service (QoS) of theMEC system [10].”
BackgroundMethodJoint Task and Resource Allocation in SDN-based UAV-assisted Cellular Networks
Zhu, Y., Wang, S., Liu, X., Tong, H., & Yin, C. (2020) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc49849.2020.9238969 · Cited by 15
“Since the data size of the returned result is much smaller than the uplink, we ignore the delay and energy consumption of the downlink transmission [13].”
BackgroundLing, X., Gong, J., Li, R., Yu, S., Ma, Q., & Chen, X. (2021) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2021.3086007 · Cited by 15
Scaling and Offloading Optimization in Pre-CORD and Post-CORD Multi-Access Edge Computing
Yahya, W., Oki, E., Lin, Y., & Lai, Y. (2021) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2021.3101862 · Cited by 17
“The authors of [9]–[11], [16]–[18], [21] considered an MEC site for accomodating UEs in a particular area.”
BackgroundInfluentialLiu, T., Sheng, S., Fang, L., Zhang, Y., Zhang, T., & Tong, W. (2019) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads47876.2019.00059 · Cited by 15
Chen, L., & Xu, J. (2020) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2020.3036953 · Cited by 16
“, reinforcement learning [11], multi-armed”
Self-citationChen, F., Yu, H., Jiang, W., & Ha, Y. (2022) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2022.3142188 · Cited by 15
“No matter Gt > Ed or Gt < Ed, the battery state Bt+1 for the next time t + 1 can always be modeled as follows [37]: Bt+1 = Bt + Gt − Ed (13)”
BackgroundLearning-Based Offloading of Tasks with Diverse Delay Sensitivities for Mobile Edge Computing
Zhang, T., Chiang, Y.-H., Borcea, C., & Ji, Y. (2019) · Globecom · doi:10.1109/globecom38437.2019.9013498 · Cited by 15
“[15] develop a post-decision state-based RL algorithm to minimize service delays and operational costs.”
BackgroundLoad Optimization Based on Edge Collaboration in Software Defined Ultra-Dense Networks
Yang, P., Zhang, Y., & Lv, J. (2020) · IEEE Access · doi:10.1109/access.2020.2973041 · Cited by 14
“[19] solved the challenge of incorporating renewable energy into MEC and proposed an effective reinforcement learning-based resource management algorithm to minimize long-term system costs (including service delays and operations cost).”
BackgroundHan, P., Liu, Y., Zhang, X., & Guo, L. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3194543 · Cited by 19
“AccordingtoPollaczek-Khinchin (P-K) formula of M/G/1 queuing system [55], the expected queuing delay of data packets on edge j in service k with allocated bandwidth where F is the average packet size and X 2 denotes the second moment of service time for data packets.”
BackgroundEnergy and Latency Efficient Caching in Mobile Edge Networks: Survey, Solutions, and Challenges
Mohammed, L. B., Anpalagan, A., & Jaseemuddin, M. (2023) · Wireless Personal Communications · doi:10.1007/s11277-023-10187-9 · Cited by 12
“…e s e qu e n ti a l o ffl o a d i ng g a m e a pp r o ac h a nd d e s i gn a m u lti - u s e r c o m pu t a ti on o ffl o a d i ng a l go r it h m [ 49 ] M a r kov d ec i s i on p r o ce ss D e v e l op a po s t - d ec i s i on s t a t e b a s e d l ea r n i ng a l go r it h m t h a t l ea r n s t…”
BackgroundLet's Share the Resource When We’re Co-Located: Colocation Edge Computing
Nguyen, M. N. H., Zaw, C. W., Kim, K. T., Tran, N. H. K., & Hong, C. S. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2020.2982679 · Cited by 13
“Therefore, edge computing recently receives lots of attention in wireless communications research [2]–[9].”
BackgroundTang, L., & Qin, H. (2023) · IEEE Access · doi:10.1109/access.2023.3302528 · Cited by 14
“Studies of different performance metrics in the task offloading problem, such as [28], [29], [30], [31], [32], [33],”
BackgroundQu, B., Bai, Y., Chu, Y., Wang, L.-E., Feng, Y., & Li, X. (2022) · Computer Networks · doi:10.1016/j.comnet.2022.109181 · Cited by 14
Self-adaptive Container Deployment in the Fog: A Survey
Cardellini, V., Presti, F. L., Nardelli, M., & Rossi, F. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58628-7_6 · Cited by 18
Tefera, G., She, K., Chen, M., & Ahmed, A. (2020) · IET Communications · doi:10.1049/iet-com.2020.0630 · Cited by 13
Adaptive Processor Frequency Adjustment for Mobile-Edge Computing With Intermittent Energy Supply
Huang, T., Lin, W., Hong, X., Wang, X., Wu, Q., Li, R., Hsu, C., & Zomaya, A. Y. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3119866 · Cited by 13
Liu, M., Wang, Y., Chen, Y., & Jia, H. (2020) · IEEE Access · doi:10.1109/access.2020.3033615 · Cited by 11
“Thus, the total computation bits executed at the kth device at time slot t and the total consumed energy at the kth device at time slot t are respectively given by [19]”
MethodA novel D2D–MEC method for enhanced computation capability in cellular networks
Liu, X., Zheng, J., Zhang, M., Yang, L., Wang, R., & Yun, H. (2021) · Scientific Reports · doi:10.1038/s41598-021-96284-w · Cited by 12
Optimization of Mobile MEC Offloading with Energy Harvesting and Dynamic Voltage Scaling
Zhuang, Y., Li, X., Ji, H., & Zhang, H. (2019) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc.2019.8885971 · Cited by 11
“In [12], the resource management problem is considered for EH-MEC from the server side.”
BackgroundPrivacy-Aware Task Offloading via Two-Timescale Reinforcement Learning
Dong, J., Geng, D., & He, X. (2020) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc49849.2020.9238906 · Cited by 11
“For this reason, there has been a substantial amount of research efforts devoted to the offloading problem in MEC [7]–[11].”
BackgroundSiddavaatam, R., Woungang, I., & Anpalagan, A. (2019) · IET Wireless Sensor Systems · doi:10.1049/iet-wss.2019.0015 · Cited by 10
On the Allocation of Computing Tasks under QoS Constraints in Hierarchical MEC Architectures
Berno, M., Alcaraz, J. J., & Rossi, M. (2019) · International Conference on Fog and Mobile Edge Computing (FMEC) · doi:10.1109/fmec.2019.8795345 · Cited by 10
“, through a weighted sum of power consumption and delay [11] or by solving two problems at different timescales (revenue and delay) [12].”
BackgroundTwo-Stage Computation Offloading Scheduling Algorithm for Energy-Harvesting Mobile Edge Computing
Park, L., Lee, C. W., Na, W., Choi, S., & Cho, S. (2019) · Energies · doi:10.3390/en12224367 · Cited by 10
“In [20], the authors proposed MEC scheduling algorithm in EH MEC environment.”
BackgroundLoad-balancing of computing resources in vehicular fog computing
Hameed, A. R., Munir, K., Islam, S. U., & Ahmad, I. (2020) · International Conference on Data Intelligence and Security (ICDIS) · doi:10.1109/icdis50059.2020.00020 · Cited by 12
“In [17], the authors propose a reinforcement learning technique to manage the fog resources for improving average time cost, computing power demand, task distribution, and offloading.”
BackgroundHeat Behind the Meter: A Hidden Threat of Thermal Attacks in Edge Colocation Data Centers
Shao, Z., Islam, M. A., & Ren, S. (2021) · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca51647.2021.00035 · Cited by 10
“Thus, we adopt batch Q-learning [53], by extending the widely-used standard Q-learning [52], [53].”
MethodSelf-citationYang, N. D., & Liu, H. (2024) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2024.3386622 · Cited by 9
AIHO: Enhancing task offloading and reducing latency in serverless multi-edge-to-cloud systems
Li, X., Chen, L., Yuan, Z., & Liu, G. (2024) · Future Generation Computer Systems · doi:10.1016/j.future.2024.107607 · Cited by 9
Self-citationJoint Heterogeneous Tasks Offloading and Resource Allocation in Mobile Edge Computing Systems
Wang, S., Pan, C., & Yin, C. (2018) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp.2018.8555725 · Cited by 10
Muslim, N., Islam, S., & Grégoire, J. (2020) · International Journal of Network Management · doi:10.1002/nem.2146 · Cited by 9
“Xu et al. 41 proposed an optimal energy computation offloading policy for EH MEC system using a RL algorithm.”
MethodDeep Reinforcement Learning for Dependent Task Offloading in Multi-Access Edge Computing
Ye, H., Li, J., & Lu, Q. (2024) · IEEE Access · doi:10.1109/access.2024.3494775 · Cited by 8
A Survey on Computation Offloading and Current Trends
Kumar, A., & Pal, A. (2025) · IEEE Access · doi:10.1109/access.2025.3625187 · Cited by 12
Offloading for Edge Computing in Low Power Wide Area Networks With Energy Harvesting
Lin, H., Chen, Z., & Wang, L. (2019) · IEEE Access · doi:10.1109/access.2019.2922399 · Cited by 8
“Our model can greatly reduce the state complexity comparing to the model with fixed time slot as for example in [5], [22].”
BackgroundMethodInfluentialDeep-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
“[23] developed a post-decision state-based RL algorithm to minimize service delays and operational costs.”
BackgroundA Reinforcement Learning Algorithm for Resource Provisioning in Mobile Edge Computing Network
Bình, H. T. T., Nguyen, P. L., Minh, N. B., Hai, T. T., Minh, N. Q., & Son, D. B. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9206947 · Cited by 8
“The authors of [20] investigated the optimal resource provisioning policy of an energy harvesting MEC, in which the state space is formulated as discrete and finite.”
BackgroundMethodInfluentialPartial 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
“[6] consider the dynamic task arrival and energy collection mechanism.”
BackgroundTefera, G., She, K., Shelke, M., & Ahmed, A. (2021) · Sustainable Computing: Informatics and Systems · doi:10.1016/j.suscom.2021.100555 · Cited by 9
Energy Harvesting Network With Wireless Distributed Computing
Alfaqawi, M., Habaebi, M. H., Islam, M. R., & Siddiqi, M. U. (2019) · IEEE Systems Journal · doi:10.1109/jsyst.2019.2893248 · Cited by 10
“, the speed and the availability of internet connection, leads to a new paradigm of the MCC defined as mobile edge computing (MEC) [6].”
BackgroundMethodInfluentialGe, S., Lu, B., Xiao, L., Gong, J., Chen, X., & Liu, Y. (2020) · Mobile Networks and Applications · doi:10.1007/s11036-020-01572-w · Cited by 9
Deep Reinforcement Learning based Energy Scheduling for Edge Computing
Yang, Q., & Li, P. (2020) · IEEE International Conference on Smart Cloud (SmartCloud) · doi:10.1109/smartcloud49737.2020.00041 · Cited by 8
“In [2], the authors show that is costly and even infeasible to offer grid power supply to support MEC which mandates on-site renewable energy as a crucial or even single power supply in many growingly situations.”
BackgroundDeep Reinforcement Learning Based Energy-efficient Task Offloading for Secondary Mobile Edge Systems
Zhang, X., Pal, A., & Debroy, S. (2020) · IEEE LCN Symposium on Emerging Topics in Networking (LCN Symposium) · doi:10.1109/lcnsymposium50271.2020.9363256 · Cited by 10
“Works such as [27]–[30] are aimed at optimize long-term performance of edge systems with respect to the energy preservation.”
BackgroundAddressing the Challenges in Federating Edge Resources
Baktır, A. C., Sonmez, C., Ersoy, C., Özgövde, A., & Varghese, B. (2019) · Wiley eBooks · doi:10.1002/9781119525080.ch2 · Cited by 10
Green hybrid energy harvesting for intelligent mobile edge computing in internet of things
Ge, P., Zhao, J., Zhang, H., Zou, D., & Wang, M. (2023) · Physical Communication · doi:10.1016/j.phycom.2023.102171 · Cited by 7
Pour-Hosseini, M. R., Abbasi, M., Salimi, A., Elmroth, E., Haghighi, H., Moradi, P., & Javadi, B. (2025) · Cluster Computing · doi:10.1007/s10586-025-05289-x · Cited by 10
Edge resource slicing approaches for latency optimization in AI-edge orchestration
Chandrika, P. K., Mekala, M. S., & Srivastava, G. (2022) · Cluster Computing · doi:10.1007/s10586-022-03817-7 · Cited by 11
Hybrid Task Offloading for Serverless Computing in the Multi-edge-to-Cloud Environment
Li, X., & Chen, L. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-4402-6_4 · Cited by 7
Self-citationGreen Fog Offloading Strategy for Heterogeneous Wireless Edge Networks
Hsu, Y.-L., Wei, H., & Bennis, M. (2018) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/glocomw.2018.8644285 · Cited by 7
“[13] considered both edge computing and edge caching in fog networks, and [14] jointly considered energy harvesting, battery residual power and weather condition in task offloading.”
BackgroundDeep Reinforcement Learning Based Traffic Offloading Scheme for Vehicular Networks
Guo, Y., Ning, Z., & Kwok, Y. R. (2019) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc47050.2019.9064365 · Cited by 7
“Reinforcement Learning (RL), as one category of machine learning, has many applications for current MEC systems and could be used to solve problems of optimal computational offloading strategy [11,12].”
BackgroundGao, Z., Hao, W., Zhang, R., & Yang, S. (2020) · IET Communications · doi:10.1049/iet-com.2020.0062 · Cited by 9
Learning to Charge RF-Energy Harvesting Devices in WiFi Networks
Luo, Y., & Chin, K. (2021) · IEEE Systems Journal · doi:10.1109/jsyst.2021.3058109 · Cited by 7
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 [11], considering the dynamic arrival and energy collection mechanism of the task, in order to minimize the delay and energy consumption, an online learning algorithm is proposed.”
MethodTowards Low-latent & Load-balanced VNF Placement with Hierarchical Reinforcement Learning
Vasilakos, X., Bunyakitanon, M., Nejabati, R., & Simeonidou, D. E. (2021) · IEEE International Mediterranean Conference on Communications and Networking (MeditCom) · doi:10.1109/meditcom49071.2021.9647532 · Cited by 9
Green city: An efficient task joint execution strategy for mobile micro-learning
Yang, L., Zheng, R., Zhu, J., Zhang, M., Liu, R., & Wu, Q. (2018) · International Journal of Distributed Sensor Networks · doi:10.1177/1550147718780933 · Cited by 7
“17: Adding q ~j, ~k ~i to Dmp 18: Else 19: Adding q ~j, ~k ~i to Dcl 20: Else 21: Adding q ~j, ~k ~i to Dcl 22: Start encoding for task 23: Initialization solution 24: Evaluating solution according to F(E) and F(I) 25: If termination condition is satisfied 26: Performing (33) 27: Else 28: Performing the selection stra…”
BackgroundMethodInfluentialRobust Bandit Learning with Imperfect Context
Yang, J., & Ren, S. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i12.17267 · Cited by 11
Self-citationOnline Geographical Load Balancing for Mobile Edge Computing with Energy HarvestingPreprint
Xu, J., Wu, H., Chen, L., Shen, C., & Wen, W. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.00107 · Cited by 7
“solar and wind), rather than the conventional electric grid [3], [4], [5], due to various reasons such as location, reliability, carbon footprint and cost.”
BackgroundSelf-citationBibi, M., Ullah, S. A., Jung, H., & Hassan, S. A. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3563195 · Cited by 6
Patel, Y. S., & Townend, P. (2024) · IEEE International Symposium on Service-Oriented System Engineering (SOSE) · doi:10.1109/sose62363.2024.00010 · Cited by 11
“In a wind and solar hybrid system, wind turbines and photovoltaic modules aggregate their outputs to charge the batteries [29].”
BackgroundMethodInfluentialDeep Reinforcement Learning Cloud-Edge-Terminal Computation Resource Allocation Mechanism for IoT
Shu, X., Wu, L., Qin, X., Yang, R., Wu, Y., Wang, D., & Liao, B. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-8462-6_177 · Cited by 6
Safety-Critical Task Offloading Heuristics for Workflow Applications in Mobile Edge Computing
Wang, Y., Sun, T., Yang, G., Yang, K., Song, X., & Zheng, C. (2022) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126623501864 · Cited by 8
Adaptive elasticity policies for staging-based in situ visualization
Wang, Z., Dorier, M., Subedi, P., Davis, P. E., & Parashar, M. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.12.010 · Cited by 6
Zhu, H., Li, X., Chen, L., & Ruíz, R. (2023) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws60048.2023.00088 · Cited by 6
“By comparing with ITAGS [1], dynamic priority-based offloading [2], and PDS-based learning [3], experimental results indicate that OnRLO can efficiently minimize the total tardiness under the study and outperform in terms of the number of workflows and MEC servers as shown in Fig.”
MethodResultSelf-citationWin with What You Have: QoS-Consistent Edge Services with Unreliable and Dynamic Resources
Song, Z., & Tilevich, E. (2020) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs47774.2020.00196 · Cited by 6
“The execution failure ratio of edge services tends to be higher than that of cloud services [2], [21], as it is often mobile or energyharvesting [12], [24], [36] devices that supply edge resources.”
BackgroundZhou, Y.-T., Ye, Q., Huang, H., & Du, H. (2021) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2021-fall52928.2021.9625281 · Cited by 6
Brief Review on Computing Resource Allocation Algorithms in Mobile Edge Computing
Lyu, N. (2021) · 2021 2nd International Conference on Computing and Data Science (CDS) · doi:10.1109/cds52072.2021.00025 · Cited by 6
Data offloading in mobile edge computing: A coalitional game based pricing approachPreprint
Zhang, T., Chen, W., & Yang, F. P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.04148 · Cited by 6
“In [12], energy harvesting aided MEC has been investigated, and an online learning algorithm for offloading and auto-scaling is proposed.”
BackgroundImmersive Multimedia Service Caching in Edge Cloud with Renewable Energy
Hossain, M. S., Hao, Y., Hu, L., Liu, J., Wei, G., & Chen, M. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3643818 · Cited by 5
A Survey on Task Scheduling in Edge-Cloud
Sahoo, S. K., & Mishra, S. K. (2025) · SN Computer Science · doi:10.1007/s42979-025-03757-0 · Cited by 8
“By doing this, they significantly outperform more conventional reinforcement learning algorithms, such as Q-learning, in terms of learning speed and runtime performance [69].”
Joint Resource Scheduling and Computation Offloading for Energy Harvesting Communications
Fawaz, I., Sarkiss, M., & Ciblar, P. (2018) · doi:10.1109/ict.2018.8464942 · Cited by 5
“In [10], the resource management problem is also considered for EH-MEC but from the server side.”
BackgroundZhang, Y., Zhang, D., Vance, N., & Wang, D. (2019) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2019.101086 · Cited by 6
Maximizing Sensing and Computation Rate in Ad Hoc Energy Harvesting IoT Networks
Yu, H., & Chin, K. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3221945 · Cited by 5
Distributed Multi-Agent Empowered Resource Allocation in Deep Edge Networks
Gong, Y., Wang, J., & Yao, H. (2021) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc51323.2021.9498936 · Cited by 5
Analyse or Transmit: Utilising Correlation at the Edge with Deep Reinforcement Learning
Hribar, J., Shinkuma, R., Iosifidis, G., & Dusparić, I. (2021) · Globecom · doi:10.1109/globecom46510.2021.9685166 · Cited by 5
“For example, [5]–[8] consider offloading computational task from an EH-powered device to a server, but without considering the accuracy of the task.”
BackgroundBayesian Stackelberg Game for Risk-aware Edge Computation Offloading
Bai, Y., Chen, L., Song, L., & Xu, J. (2019) · ACM Workshop on Moving Target Defense (MTD) · doi:10.1145/3338468.3356772 · Cited by 5
Self-citationExploiting the Solar Energy Surplus for Edge Computing
Huerta, B. M., & Vilajosana, X. (2021) · IEEE Transactions on Sustainable Computing · doi:10.1109/tsusc.2021.3058588 · Cited by 7
A Survey on Scheduling Techniques in the Edge Cloud: Issues, Challenges and Future DirectionsPreprint
(2022) · Research Square · doi:10.21203/rs.3.rs-1360831/v2 · Cited by 6
Dynamic task offloading for multiple real-time workflows in a joint MD and MEC system
Zhu, H., & Li, X. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128751 · Cited by 4
Distributed user pairing and effective computation offloading in aerial edge networks
Liang, W., Wen, S., Lixin, L. I., & Cui, J. (2023) · Chinese Journal of Aeronautics · doi:10.1016/j.cja.2023.10.028 · Cited by 4
A Survey on Reduction of Energy Consumption in Fog Networks—Communications and Computations
Kopras, B., Idzikowski, F., & Bogucka, H. (2024) · Sensors · doi:10.3390/s24186064 · Cited by 8
Chougule, S., Chaudhari, B. S., Ghorpade, S. N., & Zennaro, M. (2024) · Elsevier eBooks · doi:10.1016/b978-0-44-322202-3.00008-7 · Cited by 5
Power Optimization in Self-Organizing MEC Based Heterogeneous Small Cell Networks
Tan, H., & Feng, Z. (2018) · IEEE Access · doi:10.1109/access.2018.2873379 · Cited by 4
“In order to improve the user’s experience quality (QoE) and reduce the corresponding resource consumption, the authors in [12] investigated the use of online learning algorithms for resource management and energy harvesting in MEC, which greatly reduced the power cost ofMEC.”
BackgroundLoad Balancing for Energy-Harvesting Mobile Edge Computing
Zhao, P., Jiawei, T. A. O., Rauf, A., Jia, F., & Xu, L. (2020) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.2020eal2012 · Cited by 4
Deep Reinforcement Learning based Access Control for Disaster Response Networks
Zhou, H., Wang, X., Umehira, M., Chen, X., Wu, C., & Ji, Y. (2020) · Globecom · doi:10.1109/globecom42002.2020.9322553 · Cited by 4
“And the researches [7] which propose to derive the optimal wireless access policy by exploiting reinforcement learning [8] is also inapplicable, since the extremely large environmental state space that considered in this work.”
BackgroundYao, X., Chen, N., Yuan, X., & Ou, P. (2022) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd54268.2022.9776166 · Cited by 4
Runtime Resource Management with Multiple-Step-Ahead Workload Prediction
Niknafs, M., Eles, P., & Peng, Z. (2023) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3605213 · Cited by 4
“In the second category, a Google dataset [33] that has been used in several works [24, 43] is used to produce realistic workload traces.”
MethodDeepPM: Efficient Power Management in Edge Data Centers using Energy Storage
Shao, Z., Islam, M. A., & Ren, S. (2020) · IEEE ... International Conference on Cloud Computing · doi:10.1109/cloud49709.2020.00058 · Cited by 4
“We use deep Q-learning with long short-term memory (LSTM) network to learn the optimum action at each MDP state.”
BackgroundInfluentialSelf-citationCoalition and Pricing Based Data Offloading in Mobile Edge Computing
Zhang, T. (2018) · IEEE Vehicular Technology Conference · doi:10.1109/vtcspring.2018.8417603 · Cited by 4
“In [10], energy harvesting aided MEC has been investigated.”
BackgroundLiu, T., Zhu, Y., Yang, Y., Ye, F., & Yu, J. (2018) · CCF Transactions on Networking · doi:10.1007/s42045-018-0008-8 · Cited by 4
“Similarly, renewable energy harvesting mobile edge computing is considered in Xu et al. (2017).”
BackgroundEnergy and latency aware mobile task assignment for green cloudlets
Chalapathi, G., Chamola, V., Johal, W., Aryal, J., & Buyya, R. (2022) · Simulation Modelling Practice and Theory · doi:10.1016/j.simpat.2022.102531 · Cited by 6
“e have not compared our work with [39] because of the reasons mentioned above.”
BackgroundMethodResultInfluentialResearch on energy transmission strategy based on MEC in green communication
Xue, J., Wu, S., Wang, Z., Wang, H., & Hu, Q. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12997-8 · Cited by 3
“In [24], a delay-sensitive task unloading and energy tradeoff problem in MEC is studied.”
BackgroundDynamic Computation Offloading Based on Deep Reinforcement Learning
Cheng, B., Zhang, Z., & Liu, D. (2019) · EAI International Conference on Mobile Multimedia Communications (MobiMedia) · doi:10.4108/eai.29-6-2019.2282108 · Cited by 4
Hotspot Mitigation for Mobile Edge Computing
Chang, W.-C., Chen, Y., & Wang, P. (2018) · IEEE Transactions on Sustainable Computing · doi:10.1109/tsusc.2018.2878438 · Cited by 3
Caching on Vehicles: A Lyapunov Based Online Algorithm
Zhang, Y., Li, C., Luan, T. H., Fu, Y., & Zhu, L. (2018) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-05888-3_2 · Cited by 3
Deep Reinforcement Learning Online Offloading for SWIPT Multiple Access Edge Computing Network
Tiong, T., Saad, I., Teo, K. T. K., & bin Lago, H. (2021) · IEEE International Conference on System Engineering and Technology (ICSET) · doi:10.1109/icset53708.2021.9612551 · Cited by 3
Edge Accelerated Big Data Intelligence for 6G Network Analysis
Etikala, C., & Sharma, V. K. (2026) · IEEE International Conference for Convergence in Computing Technology (I3CTCON) · doi:10.1109/i3ctcon68242.2026.11507924 · Cited by 3
“Simultaneously, AI-based intelligent orchestration systems have been suggested to dynamically distribute resources across heterogeneous systems and, thus, increase their efficiency and scalability [22].”
Metadata
- Authors
- Xu, J., Chen, L., & Ren, S.
- Affiliations
- University of Miami (US)
- University of California, Riverside (US)
- Venue
- IEEE Transactions on Cognitive Communications and Networking
- Published
- 2017-09
- Volume
- 3
- Issue
- 3
- Pages
- 361-373
- ISSN
- 2332-7731 (ISSN-L)
- OpenAlex
- W2599106590
- Cited by
- 368
- References
- 33
- Citations by year
- 2026: 14 · 2025: 15 · 2024: 32 · 2023: 24 · 2022: 41 · 2021: 55 · 2020: 87 · 2019: 59 · 2018: 34 · 2017: 7
- FWCI
- 34.02
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Cognitive Communications and Networking (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- U.S. NSF (CNS-1551661, CNS-1565474, ECCS-1610471)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Hardware and Architecture › Energy Efficiency in Computing
- Physical Sciences › Computer Science › Information Systems › Cloud Computing and Resource Management
- Keywords
- mobile edge computing, fog computing, energy harvesting, renewable energy, workload offloading, auto-scaling, reinforcement learning, online learning, service delay, operating costs, convergence analysis
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.