{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T22:25:46Z","timestamp":1770330346962,"version":"3.49.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T00:00:00Z","timestamp":1764201600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T00:00:00Z","timestamp":1767052800000},"content-version":"vor","delay-in-days":33,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J. King Saud Univ. Comput. Inf. Sci."],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Efficient task scheduling is essential for the success of deep space exploration missions, where communication delays, dynamic link availability, and limited on-board resources pose significant challenges. However, existing deep-space scheduling frameworks cannot effectively coordinate multi-agent decisions across interplanetary regions due to long delays, dynamic link conditions, and highly unbalanced resources, resulting in inefficient and unstable task allocation. To address these issues, we propose Fed-ASTRA, a novel scheduling framework that integrates a hierarchical deep space network architecture with federated multi-agent reinforcement learning. In the proposed architecture, base stations such as Earth and Mars ground centers act as regional control centers, orbital satellites function as edge intelligence nodes, and rovers serve as terminal execution units, forming a three-tier collaborative system. This hierarchical organization enables both local autonomy and cross-domain coordination, effectively balancing real-time responsiveness and long-term availability. On the algorithmic side, we model the scheduling process as a multi-agent Markov decision process and design environment-constrained action pruning (ECAP) to filter out infeasible actions caused by link outages, energy thresholds, and deadline violations. In addition, a prioritized experience replay (PER) mechanism improves sample efficiency by emphasizing high-cost task experiences. These enhancements ensure that agents learn feasible and efficient scheduling strategies under severe environmental constraints. We evaluate Fed-ASTRA using a high-fidelity deep space network simulator driven by real orbital data. Experimental results demonstrate that our framework outperforms traditional optimization approaches, heuristic methods, and baseline MARL algorithms in terms of rapidity, availability, fairness, and real-time capability. Overall, this work highlights the potential of combining hierarchical network architectures and federated reinforcement learning to achieve robust and efficient task scheduling in future deep space missions.<\/jats:p>","DOI":"10.1007\/s44443-025-00392-w","type":"journal-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T09:16:50Z","timestamp":1764235010000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A federated reinforcement learning framework for balancing rapidity and availability in deep space networks"],"prefix":"10.1007","volume":"38","author":[{"given":"Xuewei","family":"Niu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiabin","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lili","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keke","family":"Zha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,27]]},"reference":[{"issue":"1\u20134","key":"392_CR1","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s11214-010-9687-2","volume":"165","author":"V Angelopoulos","year":"2011","unstructured":"Angelopoulos V (2011) The artemis mission. Space Sci Rev 165(1\u20134):3\u201325. https:\/\/doi.org\/10.1007\/s11214-010-9687-2","journal-title":"Space Sci Rev"},{"key":"392_CR2","doi-asserted-by":"publisher","first-page":"13013","DOI":"10.1109\/TVT.2025.3555594","volume":"74","author":"K Chen","year":"2025","unstructured":"Chen K, Yu Q, Li L, Chen J (2025) Deep reinforcement learning for dynamic task scheduling in data relay satellite networks. IEEE Trans Veh Technol 74:13013\u201313028. https:\/\/doi.org\/10.1109\/TVT.2025.3555594","journal-title":"IEEE Trans Veh Technol"},{"key":"392_CR3","doi-asserted-by":"publisher","first-page":"12879","DOI":"10.1109\/TVT.2025.3553625","volume":"74","author":"L Cheng","year":"2025","unstructured":"Cheng L, Li X, Feng G, Peng Y, Qin S, Quek TQS (2025) Cooperative transmission for space-air-ground integrated networks: A multi-agent cooperation method. IEEE Trans Veh Technol 74:12879\u201312894. https:\/\/doi.org\/10.1109\/TVT.2025.3553625","journal-title":"IEEE Trans Veh Technol"},{"issue":"19","key":"392_CR4","doi-asserted-by":"publisher","first-page":"4059","DOI":"10.3390\/math11194059","volume":"11","author":"J Chun","year":"2023","unstructured":"Chun J, Yang W, Liu X, Wu G, He L, Xing L (2023) Deep reinforcement learning for the agile earth observation satellite scheduling problem. Mathematics 11(19):4059. https:\/\/doi.org\/10.3390\/math11194059","journal-title":"Mathematics"},{"key":"392_CR5","doi-asserted-by":"publisher","first-page":"41330","DOI":"10.1109\/ACCESS.2022.3164213","volume":"10","author":"T Claudet","year":"2022","unstructured":"Claudet T, Alimo R, Goh E, Johnston MD, Madani R, Wilson B (2022) Milp: Deep space network scheduling via mixed-integer linear programming. IEEE Access 10:41330\u201341340. https:\/\/doi.org\/10.1109\/ACCESS.2022.3164213","journal-title":"IEEE Access"},{"key":"392_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2024.102362","volume":"60","author":"X Feng","year":"2024","unstructured":"Feng X, Li Y, Xu M-Q (2024) Multi-satellite cooperative scheduling method for large-scale tasks based on hybrid graph neural network and metaheuristic algorithm. Adv Eng Inform 60:102362. https:\/\/doi.org\/10.1016\/j.aei.2024.102362","journal-title":"Adv Eng Inform"},{"key":"392_CR7","doi-asserted-by":"publisher","unstructured":"Mohanan G, Vasudev S, Kurian RJ, Devatha KS, Jose D, Bansod M (2024) Designing a federated learning satellite system to incentivize space situational awareness and mitigate space debris. In: 2024 IEEE Space, Aerospace and Defence Conference (SPACE), pp. 226\u2013229. https:\/\/doi.org\/10.1109\/SPACE63117.2024.10668136","DOI":"10.1109\/SPACE63117.2024.10668136"},{"key":"392_CR8","doi-asserted-by":"crossref","unstructured":"Claudet, T., Alimo, R., Goh, E., Johnston, M.D., Madani, R., Wilson, B.: Milp: Deep space network scheduling via mixed-integer linear programming. IEEE Access. 10, 41330\u201341340 (2022). 10.1109\/ACCESS.2022.3164213","DOI":"10.1109\/ACCESS.2022.3164213"},{"key":"392_CR9","doi-asserted-by":"publisher","unstructured":"Lee CH, Cheung K-M (2012) Mixed integer programming & heuristic scheduling for space communication networks. In: 2012 IEEE Aerospace Conference, pp. 1\u201310 . https:\/\/doi.org\/10.1109\/AERO.2012.6187096","DOI":"10.1109\/AERO.2012.6187096"},{"key":"392_CR10","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2022.805823","volume":"5","author":"KM Lee","year":"2022","unstructured":"Lee KM, Ganapathi Subramanian S, Crowley M (2022) Investigation of independent reinforcement learning algorithms in multi-agent environments. Frontiers in Artificial Intelligence 5:805823. https:\/\/doi.org\/10.3389\/frai.2022.805823","journal-title":"Frontiers in Artificial Intelligence"},{"issue":"2","key":"392_CR11","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1109\/TNSM.2023.3250395","volume":"20","author":"Y Li","year":"2023","unstructured":"Li Y, Li J, Lv Z, Li H, Wang Y, Xu Z (2023) Gasto: A fast adaptive graph learning framework for edge computing empowered task offloading. IEEE Trans Netw Serv Manag 20(2):932\u2013944. https:\/\/doi.org\/10.1109\/TNSM.2023.3250395","journal-title":"IEEE Trans Netw Serv Manag"},{"key":"392_CR12","doi-asserted-by":"publisher","first-page":"10978","DOI":"10.1109\/TMC.2025.3573278","volume":"24","author":"C Li","year":"2025","unstructured":"Li C, Deng C, Zhang Y, Wan S (2025) Federated meta-learning based computation offloading approach with energy-delay tradeoffs in uav-assisted vec. IEEE Trans Mob Comput 24:10978\u201310991. https:\/\/doi.org\/10.1109\/TMC.2025.3573278","journal-title":"IEEE Trans Mob Comput"},{"issue":"8","key":"392_CR13","doi-asserted-by":"publisher","first-page":"10091","DOI":"10.1109\/TWC.2024.3368689","volume":"23","author":"Z Lin","year":"2024","unstructured":"Lin Z, Ni Z, Kuang L, Jiang C, Huang Z (2024) Satellite-terrestrial coordinated multi-satellite beam hopping scheduling based on multi-agent deep reinforcement learning. IEEE Trans Wireless Commun 23(8):10091\u201310103. https:\/\/doi.org\/10.1109\/TWC.2024.3368689","journal-title":"IEEE Trans Wireless Commun"},{"issue":"23","key":"392_CR14","doi-asserted-by":"publisher","first-page":"4436","DOI":"10.3390\/rs16234436","volume":"16","author":"D Liu","year":"2024","unstructured":"Liu D, Zhou G (2024) Deep reinforcement learning-based attention decision network for agile earth observation satellite scheduling. Remote Sensing 16(23):4436. https:\/\/doi.org\/10.3390\/rs16234436","journal-title":"Remote Sensing"},{"issue":"6","key":"392_CR15","doi-asserted-by":"publisher","first-page":"4845","DOI":"10.1109\/JIOT.2022.3220677","volume":"10","author":"Y Liu","year":"2023","unstructured":"Liu Y, Jiang L, Qi Q, Xie S (2023) Energy-efficient space\u2013air\u2013ground integrated edge computing for internet of remote things: A federated drl approach. IEEE Internet Things J 10(6):4845\u20134856. https:\/\/doi.org\/10.1109\/JIOT.2022.3220677","journal-title":"IEEE Internet Things J"},{"issue":"4","key":"392_CR16","doi-asserted-by":"publisher","first-page":"763","DOI":"10.3390\/electronics13040763","volume":"13","author":"Z Liu","year":"2024","unstructured":"Liu Z, Zhang L, Wang L, Dong X, Rong J (2024) Research on multi-dag satellite network task scheduling algorithm based on cache-composite priority. Electronics 13(4):763. https:\/\/doi.org\/10.3390\/electronics13040763","journal-title":"Electronics"},{"key":"392_CR17","doi-asserted-by":"crossref","unstructured":"Lin, Z., Ni, Z., Kuang, L., Jiang, C., Huang, Z.: Satellite-terrestrial coordinated multi-satellite beam hopping scheduling based on multi-agent deep reinforcement learning. IEEE Transactions on Wireless Communications. 23(8), 10091\u201310103 (2024) 10.1109\/TWC.2024.3368689","DOI":"10.1109\/TWC.2024.3368689"},{"key":"392_CR18","doi-asserted-by":"crossref","unstructured":"Feng, X., Li, Y., Xu, M.-Q.: Multi-satellite cooperative scheduling method for large-scale tasks based on hybrid graph neural network and metaheuristic algorithm. Advanced Engineering Informatics. 60, 102362 (2024). 10.1016\/j.aei.2024.102362","DOI":"10.1016\/j.aei.2024.102362"},{"issue":"1","key":"392_CR19","doi-asserted-by":"publisher","first-page":"810","DOI":"10.1109\/TWC.2024.3502394","volume":"24","author":"S Pala","year":"2025","unstructured":"Pala S, Singh K, Li C-P, Dobre OA (2025) Empowering isac systems with federated learning: A focus on satellite and ris-enhanced terrestrial integrated networks. IEEE Trans Wireless Commun 24(1):810\u2013824. https:\/\/doi.org\/10.1109\/TWC.2024.3502394","journal-title":"IEEE Trans Wireless Commun"},{"key":"392_CR20","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1007\/s10951-024-00816-x","volume":"27","author":"TG Shai Krigman","year":"2024","unstructured":"Shai Krigman TG, Dery L (2024) Scheduling of earth observing satellites using distributed constraint optimization. J Sched 27:507\u2013524. https:\/\/doi.org\/10.1007\/s10951-024-00816-x","journal-title":"J Sched"},{"key":"392_CR21","doi-asserted-by":"publisher","first-page":"2161","DOI":"10.7717\/peerj-cs.2161","volume":"10","author":"Y Sun","year":"2024","unstructured":"Sun Y, Yang B (2024) A priority experience replay actor-critic algorithm using self-attention mechanism for strategy optimization of discrete problems. PeerJ Computer Science 10:2161. https:\/\/doi.org\/10.7717\/peerj-cs.2161","journal-title":"PeerJ Computer Science"},{"key":"392_CR22","doi-asserted-by":"publisher","first-page":"2921","DOI":"10.1016\/j.asr.2023.12.036","volume":"73","author":"Z Wang","year":"2024","unstructured":"Wang Z, Hu X, Ma H, Xia W (2024) Learning multi-satellite scheduling policy with heterogeneous graph neural network. Adv Space Res 73:2921\u20132935. https:\/\/doi.org\/10.1016\/j.asr.2023.12.036","journal-title":"Adv Space Res"},{"issue":"4","key":"392_CR23","doi-asserted-by":"publisher","first-page":"04025044","DOI":"10.1061\/JAEEEZ.ASENG-6187","volume":"38","author":"W Wu","year":"2025","unstructured":"Wu W, Wu X, Liu F, Liu S, Wang T, Xing Z (2025) Single-pass imaging planning with a hybrid genetic tabu search algorithm for agile earth observation satellites. J Aerosp Eng 38(4):04025044. https:\/\/doi.org\/10.1061\/JAEEEZ.ASENG-6187","journal-title":"J Aerosp Eng"},{"key":"392_CR24","doi-asserted-by":"publisher","unstructured":"Yang L, Guo X, Meng Z, Qin J, Li X, Ma X, Ren S, Yang J (2023) A hierarchical resource scheduling method for satellite control system based on deep reinforcement learning. Electronics 12(19):3991. https:\/\/doi.org\/10.3390\/electronics12193991","DOI":"10.3390\/electronics12193991"},{"key":"392_CR25","doi-asserted-by":"publisher","unstructured":"Yu J, Alhilal AY, Zhou T, Hui P, Tsang DHK (2024) Attention-based qoe-aware digital twin empowered edge computing for immersive virtual reality. IEEE Trans Wireless Commun 23(9):11276\u201311290. https:\/\/doi.org\/10.1109\/TWC.2024.3380820","DOI":"10.1109\/TWC.2024.3380820"},{"issue":"5","key":"392_CR26","doi-asserted-by":"publisher","first-page":"350","DOI":"10.3390\/aerospace11050350","volume":"11","author":"J Zhang","year":"2024","unstructured":"Zhang J, Lyu L (2024) A spacecraft onboard autonomous task scheduling method based on hierarchical task network-timeline. Aerospace 11(5):350. https:\/\/doi.org\/10.3390\/aerospace11050350","journal-title":"Aerospace"},{"issue":"6","key":"392_CR27","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1007\/s10489-010-0234-3","volume":"35","author":"N Zhang","year":"2011","unstructured":"Zhang N, Feng Z, Ke L (2011) Guidance-solution based ant colony optimization for satellite control resource scheduling problem. Appl Intell 35(6):436\u2013444. https:\/\/doi.org\/10.1007\/s10489-010-0234-3","journal-title":"Appl Intell"},{"issue":"4","key":"392_CR28","doi-asserted-by":"publisher","first-page":"1069","DOI":"10.3390\/s25041069","volume":"25","author":"Z Zhang","year":"2025","unstructured":"Zhang Z, Dong T, Yin J, Xu Y, Luo Z, Jiang H, Wu J (2025) A particle swarm optimization-based queue scheduling and optimization mechanism for large-scale low-earth-orbit satellite communication networks. Sensors 25(4):1069. https:\/\/doi.org\/10.3390\/s25041069","journal-title":"Sensors"},{"issue":"3","key":"392_CR29","doi-asserted-by":"publisher","first-page":"2264","DOI":"10.1109\/TNSM.2025.3539865","volume":"22","author":"J Zhang","year":"2025","unstructured":"Zhang J, Zhang D-G, Qiao M, Hong-Lin E, Zhang T, Zhang P (2025) New offloading method of computing task based on gray wolf hunting optimization mechanism for the iov. IEEE Trans Netw Serv Manage 22(3):2264\u20132277. https:\/\/doi.org\/10.1109\/TNSM.2025.3539865","journal-title":"IEEE Trans Netw Serv Manage"},{"key":"392_CR30","doi-asserted-by":"publisher","unstructured":"Li Y, Li J, Lv Z, Li H, Wang Y, Xu Z (2023) Gasto: A fast adaptive graph learning framework for edge computing empowered task offloading. IEEE Trans Netw Serv Manag 20(2):932\u2013944. https:\/\/doi.org\/10.1109\/TNSM.2023.3250395","DOI":"10.1109\/TNSM.2023.3250395"},{"issue":"1","key":"392_CR31","doi-asserted-by":"publisher","first-page":"823","DOI":"10.1016\/j.asr.2021.09.001","volume":"69","author":"C Zhou","year":"2022","unstructured":"Zhou C, Jia Y, Liu J et al (2022) Scientific objectives and payloads of the lunar sample return mission\u2014chang\u2019e-5. Adv Space Res 69(1):823\u2013836. https:\/\/doi.org\/10.1016\/j.asr.2021.09.001","journal-title":"Adv Space Res"},{"issue":"6","key":"392_CR32","doi-asserted-by":"publisher","first-page":"3640","DOI":"10.1109\/TSC.2024.3433579","volume":"17","author":"H Zhou","year":"2024","unstructured":"Zhou H, Wang H, Yu Z, Bin G, Xiao M, Wu J (2024) Federated distributed deep reinforcement learning for recommendation-enabled edge caching. IEEE Trans Serv Comput 17(6):3640\u20133656. https:\/\/doi.org\/10.1109\/TSC.2024.3433579","journal-title":"IEEE Trans Serv Comput"},{"issue":"5","key":"392_CR33","doi-asserted-by":"publisher","first-page":"1115","DOI":"10.1109\/JSAC.2024.3365902","volume":"42","author":"Y Zhou","year":"2024","unstructured":"Zhou Y, Lei L, Zhao X, You L, Sun Y, Chatzinotas S (2024) Decomposition and meta-drl based multi-objective optimization for asynchronous federated learning in 6g-satellite systems. IEEE J Sel Areas Commun 42(5):1115\u20131129. https:\/\/doi.org\/10.1109\/JSAC.2024.3365902","journal-title":"IEEE J Sel Areas Commun"},{"issue":"2","key":"392_CR34","doi-asserted-by":"publisher","first-page":"812","DOI":"10.1016\/j.asr.2020.11.005","volume":"67","author":"Y Zou","year":"2021","unstructured":"Zou Y, Jia Y, Bai Y et al (2021) Scientific objectives and payloads of tianwen-1, china\u2019s first mars exploration mission. Adv Space Res 67(2):812\u2013823. https:\/\/doi.org\/10.1016\/j.asr.2020.11.005","journal-title":"Adv Space Res"}],"container-title":["Journal of King Saud University Computer and Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-025-00392-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44443-025-00392-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-025-00392-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T09:50:56Z","timestamp":1770285056000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44443-025-00392-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,27]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["392"],"URL":"https:\/\/doi.org\/10.1007\/s44443-025-00392-w","relation":{},"ISSN":["1319-1578","2213-1248"],"issn-type":[{"value":"1319-1578","type":"print"},{"value":"2213-1248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,27]]},"assertion":[{"value":"29 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest\/Competing interests"}}],"article-number":"6"}}