{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,19]],"date-time":"2026-04-19T05:46:52Z","timestamp":1776577612729,"version":"3.51.2"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013076","name":"National Major Science and Technology Projects of China","doi-asserted-by":"publisher","award":["2025ZD0804700"],"award-info":[{"award-number":["2025ZD0804700"]}],"id":[{"id":"10.13039\/501100013076","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Networks"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.comnet.2026.112257","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T07:57:53Z","timestamp":1774425473000},"page":"112257","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Eco-efficient task scheduling for MLLMs in edge-cloud continuum"],"prefix":"10.1016","volume":"282","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6086-5813","authenticated-orcid":false,"given":"Manjun","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1213-5642","authenticated-orcid":false,"given":"Ying","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0402-5390","authenticated-orcid":false,"given":"Peng","family":"Yu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7899-539X","authenticated-orcid":false,"given":"Xuesong","family":"Qiu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2033-8431","authenticated-orcid":false,"given":"Shaoyong","family":"Guo","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.comnet.2026.112257_bib0001","doi-asserted-by":"crossref","first-page":"1616","DOI":"10.4028\/www.scientific.net\/AMM.291-294.1616","article-title":"Economic growth, energy consumption and carbon emissions in china: a cointegration analysis","volume":"291\u2013294","author":"Wang","year":"2013","journal-title":"Appl. Mech. Mater."},{"key":"10.1016\/j.comnet.2026.112257_bib0002","unstructured":"Z. Wan, X. Wang, C. Liu, S. Alam, Y. Zheng, J. Liu, Z. Qu, S. Yan, Y. Zhu, Q. Zhang, et al., Efficient large language models: A survey, (2023). arxiv: 2312.03863."},{"key":"10.1016\/j.comnet.2026.112257_bib0003","unstructured":"Z. Zhou, X. Ning, K. Hong, T. Fu, J. Xu, S. Li, Y. Lou, L. Wang, Z. Yuan, X. Li, et al., A survey on efficient inference for large language models, (2024). arxiv: 2404.14294."},{"key":"10.1016\/j.comnet.2026.112257_bib0004","first-page":"1","article-title":"Self-Adaptive auxiliary cube for multi-Tenant slicing in multi-Layer computing power networks","author":"Ma","year":"2025","journal-title":"J. Lightwave Technol."},{"key":"10.1016\/j.comnet.2026.112257_bib0005","first-page":"24611","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"5","key":"10.1016\/j.comnet.2026.112257_bib0006","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1109\/MNET.2024.3420755","article-title":"An edge-cloud collaboration framework for generative ai service provision with synergetic big cloud model and small edge models","volume":"38","author":"Tian","year":"2024","journal-title":"IEEE Netw."},{"issue":"5","key":"10.1016\/j.comnet.2026.112257_bib0007","first-page":"10","article-title":"Online service placement, task scheduling, and resource allocation in hierarchical collaborative MEC systems","volume":"38","author":"Du","year":"2025","journal-title":"IEEE Trans. Serv. Comput."},{"issue":"3","key":"10.1016\/j.comnet.2026.112257_bib0008","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3664200","article-title":"Adaptation in edge computing: a review on design principles and research challenges","volume":"19","author":"Golpayegani","year":"2024","journal-title":"ACM Trans. Auton. Adapt. Syst."},{"key":"10.1016\/j.comnet.2026.112257_bib0009","first-page":"950","article-title":"Rethinking low-Carbon edge computing system design with renewable energy sharing","author":"Liao","year":"2024","journal-title":"Proceed. 53rd Int. Conf. Parallel Process."},{"issue":"1","key":"10.1016\/j.comnet.2026.112257_bib0010","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1109\/TNSM.2021.3112796","article-title":"Towards sustainable edge computing through renewable energy resources and online, distributed and predictive scheduling","volume":"19","author":"Perin","year":"2021","journal-title":"IEEE Trans. Netw. Serv. Manage."},{"issue":"8","key":"10.1016\/j.comnet.2026.112257_bib0011","first-page":"1","article-title":"A review on edge large language models: design, execution, and applications","volume":"57","author":"Zheng","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.comnet.2026.112257_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.adhoc.2024.103671","article-title":"Multi-agent reinforcement learning for task offloading with hybrid decision space in multi-access edge computing","volume":"166","author":"Wang","year":"2025","journal-title":"Ad Hoc Netw."},{"issue":"1","key":"10.1016\/j.comnet.2026.112257_bib0013","doi-asserted-by":"crossref","first-page":"4","DOI":"10.3390\/e27010004","article-title":"Multi-agent hierarchical graph attention actor\u2013critic reinforcement learning","volume":"27","author":"Li","year":"2024","journal-title":"Entropy"},{"issue":"4","key":"10.1016\/j.comnet.2026.112257_bib0014","doi-asserted-by":"crossref","first-page":"1191","DOI":"10.1109\/TCC.2016.2567392","article-title":"Using proactive fault-tolerance approach to enhance cloud service reliability","volume":"6","author":"Liu","year":"2018","journal-title":"IEEE Trans. Cloud Comput."},{"issue":"8","key":"10.1016\/j.comnet.2026.112257_bib0015","doi-asserted-by":"crossref","first-page":"8787","DOI":"10.1007\/s11227-020-03601-7","article-title":"CMODLB: An efficient load balancing approach in cloud computing environment","volume":"77","author":"Negi","year":"2021","journal-title":"J. Supercomput."},{"issue":"4","key":"10.1016\/j.comnet.2026.112257_bib0016","doi-asserted-by":"crossref","first-page":"4322","DOI":"10.1109\/TVT.2022.3147027","article-title":"Greenedge: joint green energy scheduling and dynamic task offloading in multi-tier edge computing systems","volume":"71","author":"Ma","year":"2022","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10.1016\/j.comnet.2026.112257_bib0017","doi-asserted-by":"crossref","first-page":"82","DOI":"10.2516\/stet\/2024076","article-title":"Energy and carbon-aware distributed machine learning tasks scheduling scheme for the multi-renewable energy-based edge-cloud continuum","volume":"79","author":"Miao","year":"2024","journal-title":"Sci. Technol. Energy Transit."},{"key":"10.1016\/j.comnet.2026.112257_bib0018","first-page":"1","article-title":"Machine learning-based timeliness-Guaranteed and energy-Efficient task assignment in edge computing","author":"Sen","year":"2019","journal-title":"2019 IEEE 3rd International Conference on Fog and Edge Computing (ICFEC)"},{"key":"10.1016\/j.comnet.2026.112257_bib0019","first-page":"222","article-title":"Edge computing energy-Efficient resource scheduling based on deep reinforcement learning","author":"Tang","year":"2021","journal-title":"International Conference on Bio-Inspired Computing: Theories and Applications"},{"key":"10.1016\/j.comnet.2026.112257_bib0020","article-title":"Deep reinforcement learning for delay and energy-Aware task scheduling in edge-Cloud systems","author":"Xun","year":"2023","journal-title":"CCF Conference on Computer Supported Cooperative Work and Social Computing"},{"key":"10.1016\/j.comnet.2026.112257_bib0021","doi-asserted-by":"crossref","first-page":"2065","DOI":"10.1109\/ICAACE65325.2025.11019615","article-title":"Research on edge computing and cloud collaborative resource scheduling optimization based on deep reinforcement learning","author":"Wang","year":"2025","journal-title":"2025 8th International Conference on Advanced Algorithms and Control Engineering (ICAACE)"},{"key":"10.1016\/j.comnet.2026.112257_bib0022","first-page":"825","article-title":"Resource allocation and task scheduling for computing power aware networks","volume":"13552","author":"Peng","year":"2025","journal-title":"International Conference on Physics, Photonics, and Optical Engineering (ICPPOE 2024)"},{"key":"10.1016\/j.comnet.2026.112257_bib0023","doi-asserted-by":"crossref","DOI":"10.1109\/TNSE.2024.3476968","article-title":"An energy-efficient collaborative offloading scheme with heterogeneous tasks for satellite edge computing","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Network Sci. Eng."},{"issue":"3","key":"10.1016\/j.comnet.2026.112257_bib0024","doi-asserted-by":"crossref","DOI":"10.1002\/cpe.8362","article-title":"A dynamic energy-Efficient scheduling method for periodic workflows based on collaboration of edge-Cloud computing resources","volume":"37","author":"Chen","year":"2025","journal-title":"Concurr. Comput. Pract. Exp."},{"issue":"9","key":"10.1016\/j.comnet.2026.112257_bib0025","article-title":"A task offloading and resource allocation strategy based on multi-Agent reinforcement learning in mobile edge computing","volume":"16","author":"Jiang","year":"2024","journal-title":"Future Int."},{"key":"10.1016\/j.comnet.2026.112257_bib0026","unstructured":"P. Veli\u010dkovi\u0107, G. Cucurull, A. Casanova, A. Romero, P. Lio, Y. Bengio, Graph attention networks, (2017). arxiv: 1710.10903."},{"key":"10.1016\/j.comnet.2026.112257_bib0027","first-page":"94","article-title":"Load balancing for task scheduling based on multi-Agent reinforcement learning","author":"Li","year":"2024","journal-title":"Proceedings of the 2024 8th International Conference on Machine Learning and Soft Computing"},{"key":"10.1016\/j.comnet.2026.112257_bib0028","doi-asserted-by":"crossref","DOI":"10.1109\/TCC.2025.3620615","article-title":"A graph-Based deep reinforcement learning model for task scheduling on heterogeneous resource-Elastic management of resource pool","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Cloud Comput."},{"key":"10.1016\/j.comnet.2026.112257_bib0029","doi-asserted-by":"crossref","unstructured":"W. Shen, W. Lin, W. Wu, H. Wu, K. Li, Reinforcement Learning-Based Task Scheduling for Heterogeneous Computing in End-Edge-Cloud Environment, Cluster Comput. 28(3) (2025) 1\u201319.","DOI":"10.1007\/s10586-024-04828-2"},{"key":"10.1016\/j.comnet.2026.112257_bib0030","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2025.3560781","article-title":"Federated synergy: hierarchical multi-Agent learning for sustainable edge computing in IIot","volume":"13","author":"Benila","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.comnet.2026.112257_bib0031","unstructured":"H. Touvron, T. Lavril, G. Izacard, X. Martinet, M.-A. Lachaux, T. Lacroix, B. Rozi\u00e8re, N. Goyal, E. Hambro, F. Azhar, et al., Llama: Open and efficient foundation language models, (2023). arxiv: 2302.13971."},{"key":"10.1016\/j.comnet.2026.112257_bib0032","series-title":"ICC 2025-IEEE International Conference on Communications","first-page":"1578","article-title":"JPPO: Joint power and prompt optimization for accelerated large language model services","author":"You","year":"2025"},{"key":"10.1016\/j.comnet.2026.112257_bib0033","doi-asserted-by":"crossref","DOI":"10.1109\/TPDS.2026.3665358","article-title":"Floe: federated specialization for real-Time LLM\u2013SLM inference","author":"Tian","year":"2026","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"10.1016\/j.comnet.2026.112257_bib0034","article-title":"Adaptlink: a heterogeneity-aware adaptive framework for distributed mllm inference","author":"Hu","year":"2025","journal-title":"AAAI 2025 Workshop on Artificial Intelligence for Wireless Communications and Networking (AI4WCN)"},{"key":"10.1016\/j.comnet.2026.112257_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.comcom.2025.108152","article-title":"A hybrid swarm intelligence approach for optimizing multimodal large language models deployment in edge-cloud-based federated learning environments","volume":"237","author":"Rjoub","year":"2025","journal-title":"Comput. Commun."},{"key":"10.1016\/j.comnet.2026.112257_bib0036","article-title":"A cloud-edge collaborative architecture for multimodal llms-based advanced driver assistance systems in iot networks","author":"Hu","year":"2024","journal-title":"IEEE Internet Things J."},{"issue":"11","key":"10.1016\/j.comnet.2026.112257_bib0037","first-page":"73","article-title":"Optimizing resource allocation and request routing for AI-generated content (AIGC) services in mobile edge networks with cell coupling","author":"Deng","year":"2024","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"11","key":"10.1016\/j.comnet.2026.112257_bib0038","doi-asserted-by":"crossref","first-page":"10523","DOI":"10.1109\/TMC.2024.3376550","article-title":"Dynamic parallel multi-Server selection and allocation in collaborative edge computing","volume":"23","author":"Xu","year":"2024","journal-title":"IEEE Trans. Mob. Comput."},{"key":"10.1016\/j.comnet.2026.112257_bib0039","unstructured":"G. Zhou, P. Qiu, C. Chen, J. Wang, Z. Yang, J. Xu, M. Qiu, Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models,(2025). arxiv: 2504.21277."},{"issue":"2","key":"10.1016\/j.comnet.2026.112257_bib0040","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1109\/TGCN.2023.3339477","article-title":"Online collaborative energy-network resource scheduling for WPT-enabled green edge computing","volume":"8","author":"Chen","year":"2023","journal-title":"IEEE Trans. Green Commun. Netw."},{"issue":"6","key":"10.1016\/j.comnet.2026.112257_bib0041","first-page":"3529","article-title":"Two time-scale energy and spectrum allocation for MEC networks with hybrid energy supplies","volume":"10","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Network Sci. Eng."},{"key":"10.1016\/j.comnet.2026.112257_bib0042","first-page":"345","article-title":"Joint communication and computation scheduling for MEC-enabled AIGC services based on generative diffusion model","author":"Liu","year":"2024","journal-title":"2024 22nd International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)"},{"key":"10.1016\/j.comnet.2026.112257_bib0043","unstructured":"X. Liu, K. Zhang, Partially observable multi-agent reinforcement learning with information sharing, (2023). arxiv: 2308.08705."},{"issue":"11","key":"10.1016\/j.comnet.2026.112257_bib0044","first-page":"6327","article-title":"Collective deep reinforcement learning for intelligence sharing in the internet of intelligence-empowered edge computing","volume":"22","author":"Tang","year":"2022","journal-title":"IEEE Trans. Mob. Comput."},{"issue":"11","key":"10.1016\/j.comnet.2026.112257_bib0045","doi-asserted-by":"crossref","first-page":"8852","DOI":"10.1109\/JIOT.2021.3116108","article-title":"Revenue and energy efficiency-driven delay-constrained computing task offloading and resource allocation in a vehicular edge computing network: a deep reinforcement learning approach","volume":"9","author":"Huang","year":"2021","journal-title":"IEEE Internet Things J."},{"issue":"6","key":"10.1016\/j.comnet.2026.112257_bib0046","doi-asserted-by":"crossref","first-page":"4898","DOI":"10.1109\/JIOT.2020.2971323","article-title":"Decentralized computation offloading in IoT fog computing system with energy harvesting: a dec-POMDP approach","volume":"7","author":"Tang","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.comnet.2026.112257_bib0047","unstructured":"K. Tan, solar stations, 2025, (https:\/\/github.com\/tkzzzzzz6\/EEC_code)."},{"issue":"10","key":"10.1016\/j.comnet.2026.112257_bib0048","doi-asserted-by":"crossref","first-page":"6287","DOI":"10.1109\/TCOMM.2024.3397841","article-title":"Multi-agent DDPG based resource allocation in NOMA-enabled satellite IoT","volume":"72","author":"Chai","year":"2024","journal-title":"IEEE Trans. Commun."},{"issue":"12","key":"10.1016\/j.comnet.2026.112257_bib0049","doi-asserted-by":"crossref","first-page":"7798","DOI":"10.1109\/TCOMM.2024.3420733","article-title":"Toward dynamic resource allocation and client scheduling in hierarchical federated learning: a two-Phase deep reinforcement learning approach","volume":"72","author":"Chen","year":"2024","journal-title":"IEEE Trans. Commun."}],"container-title":["Computer Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1389128626002690?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1389128626002690?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,19]],"date-time":"2026-04-19T05:18:54Z","timestamp":1776575934000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1389128626002690"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":49,"alternative-id":["S1389128626002690"],"URL":"https:\/\/doi.org\/10.1016\/j.comnet.2026.112257","relation":{},"ISSN":["1389-1286"],"issn-type":[{"value":"1389-1286","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Eco-efficient task scheduling for MLLMs in edge-cloud continuum","name":"articletitle","label":"Article Title"},{"value":"Computer Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.comnet.2026.112257","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"112257"}}