{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T05:01:56Z","timestamp":1776834116895,"version":"3.51.2"},"reference-count":25,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Task scheduling in cloud computing environments is a complex NP-hard problem that requires maximizing resource utilization while satisfying quality-of-service (QoS) constraints. Traditional meta-heuristic algorithms often become stuck in local optima, while single deep reinforcement learning (DRL) models exhibit instability when exploring large-scale solution spaces. To address this, this paper proposes a hybrid scheduling algorithm based on multi-objective sand cat colony optimization (MoSCO). This algorithm utilizes a D3QN network to extract task features and guide population initialization, followed by a multi-objective Sand Cat Swarm Optimization (SCSO) algorithm for refined local search. Results from 50 independent replicate experiments conducted in a simulated cloud environment, coupled with an analysis of the dynamic convergence process, demonstrate that MoSCO exhibits significant superiority and robustness. Scatter plot convergence analysis further confirms that MoSCO\u2019s knowledge injection mechanism effectively overcomes the blind exploration phase of traditional algorithms and successfully breaks through the local optimum bottleneck in the late iteration stages of single reinforcement learning, achieving higher-quality, denser, and more stable convergence. Furthermore, 3D and 2D Pareto front analyses show that MoSCO generates highly competitive, well-distributed non-dominated solutions, offering flexible trade-off options for conflicting objectives. Compared to PureD3QN, H-SCSO, and NSGA-II, MoSCO exhibits the smallest performance fluctuations in box plots. Specifically, MoSCO elevates the average resource utilization of clusters to 92.20%, while reducing the average maximum Makespan and Tardiness to 528 and 4187, respectively. Experimental data confirm that MoSCO effectively balances global exploration with local exploitation, delivering stable, high-quality solutions for dynamic cloud task scheduling.<\/jats:p>","DOI":"10.3390\/a19040321","type":"journal-article","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T14:53:23Z","timestamp":1776696803000},"page":"321","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["D3QN-Guided Sand Cat Swarm Optimization with Hybrid Exploration for Multi-Objective Cloud Task Scheduling"],"prefix":"10.3390","volume":"19","author":[{"given":"Minghao","family":"Shao","sequence":"first","affiliation":[{"name":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan 250013, China"},{"name":"Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science, Jinan 250103, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Guo","sequence":"additional","affiliation":[{"name":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan 250013, China"},{"name":"Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science, Jinan 250103, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jibin","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan 250013, China"},{"name":"Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science, Jinan 250103, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan 250013, China"},{"name":"Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science, Jinan 250103, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Baloni, D., Bhatt, C., Kumar, S., Patel, P., and Singh, T. (2023, January 23\u201325). The Evolution of Virtualization and Cloud Computing in the Modern Computer Era. Proceedings of the 2023 International Conference on Communication, Security and Artificial Intelligence (ICCSAI), Greater Noida, India.","DOI":"10.1109\/ICCSAI59793.2023.10421611"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"12255","DOI":"10.1109\/ACCESS.2025.3529839","article-title":"Multi-Objective Optimization Techniques in Cloud Task Scheduling: A Systematic Literature Review","volume":"13","author":"Abraham","year":"2025","journal-title":"IEEE Access"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"102144","DOI":"10.1016\/j.simpat.2020.102144","article-title":"Cloud computing simulators: A comprehensive review","volume":"104","author":"Mansouri","year":"2020","journal-title":"Simul. Model. Pract. Theory"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1016\/j.future.2018.09.014","article-title":"Task scheduling techniques in cloud computing: A literature survey","volume":"91","author":"Arunarani","year":"2019","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"104766","DOI":"10.1016\/j.jpdc.2023.104766","article-title":"Task scheduling optimization in heterogeneous cloud computing environments: A hybrid GA-GWO approach","volume":"183","author":"Behera","year":"2024","journal-title":"J. Parallel Distrib. Comput."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1007\/s42979-021-00609-5","article-title":"A multi-objective deadline-constrained task scheduling algorithm with guaranteed performance in load balancing on heterogeneous networks","volume":"2","author":"Chatterjee","year":"2021","journal-title":"SN Comput. Sci."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"10266","DOI":"10.1109\/ACCESS.2022.3163273","article-title":"Multiobjective task scheduling in cloud environment using decision tree algorithm","volume":"10","author":"Mahmoud","year":"2022","journal-title":"IEEE Access"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"3685","DOI":"10.1109\/TCC.2023.3315014","article-title":"Multi-objective cloud task scheduling optimization based on evolutionary multi-factor algorithm","volume":"11","author":"Cui","year":"2023","journal-title":"IEEE Trans. Cloud Comput."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"8252","DOI":"10.1007\/s11227-020-03606-2","article-title":"Multi-objective heuristics algorithm for dynamic resource scheduling in the cloud computing environment","volume":"77","author":"Devi","year":"2021","journal-title":"J. Supercomput."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"26977","DOI":"10.1007\/s11042-024-19887-1","article-title":"Adaptive Tasmanian Devil Optimization algorithm based efficient task scheduling for big data application in a cloud computing environment","volume":"84","author":"Mishra","year":"2025","journal-title":"Multimed. Tools Appl."},{"key":"ref_11","first-page":"279","article-title":"Energy-Aware Cloud Task Scheduling algorithm in heterogeneous multi-cloud environment","volume":"16","author":"Pradhan","year":"2022","journal-title":"Intell. Decis. Technol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1016\/j.future.2022.11.031","article-title":"Multi-search-routes-based methods for minimizing makespan of homogeneous and heterogeneous resources in Cloud computing","volume":"141","author":"Zhou","year":"2023","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Hemanth, S.V., Kirubha, D., Reddy, S.R., Chelladurai, T., Soundari, A.G., and Amirthayogam, G. (2024, January 4\u20136). Multi objective Ant Colony Optimization Technique for Task Scheduling in Cloud Computing. Proceedings of the 2024 3rd International Conference on Applied Artificial Intelligence and Computing (ICAAIC), Salem, India.","DOI":"10.1109\/ICAAIC60222.2024.10575423"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2525","DOI":"10.1007\/s10586-023-04099-3","article-title":"A new hybrid multi-objective optimization algorithm for task scheduling in cloud systems","volume":"27","author":"Malti","year":"2024","journal-title":"Clust. Comput."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1799","DOI":"10.1007\/s10586-023-04018-6","article-title":"An efficient multi-objective scheduling algorithm based on spider monkey and ant colony optimization in cloud computing","volume":"27","author":"Amer","year":"2024","journal-title":"Clust. Comput."},{"key":"ref_16","first-page":"59","article-title":"A Hybrid Multi-Swarm Particle Swarm Optimization Algorithm for Solving Agent-Based Epidemiological Model","volume":"25","author":"Akopov","year":"2025","journal-title":"Cybern. Inf. Technol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"100356","DOI":"10.1016\/j.dajour.2023.100356","article-title":"A Crossover-Based Multi-Objective Discrete Particle Swarm Optimization Model for Solving Multi-Modal Routing Problems","volume":"9","author":"Afrasyabi","year":"2023","journal-title":"Decis. Anal. J."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"53448","DOI":"10.1109\/ACCESS.2025.3554054","article-title":"Evolutionary Synthesis of High-Capacity Reconfigurable Multilayer Road Networks Using a Multiagent Hybrid Clustering-Assisted Genetic Algorithm","volume":"13","author":"Akopov","year":"2025","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"111366","DOI":"10.1016\/j.knosys.2024.111366","article-title":"A learning and evolution-based intelligence algorithm for multi-objective heterogeneous cloud scheduling optimization","volume":"286","author":"Hao","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"11354","DOI":"10.1109\/ACCESS.2024.3355092","article-title":"Multi-objective Prioritized Task Scheduler using improved Asynchronous advantage actor critic (a3c) algorithm in multi cloud environment","volume":"12","author":"Mangalampalli","year":"2024","journal-title":"IEEE Access"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"8359","DOI":"10.1007\/s11042-023-16008-2","article-title":"DRLBTSA: Deep Reinforcement Learning Based Task-Scheduling Algorithm in Cloud Computing","volume":"83","author":"Mangalampalli","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"3416","DOI":"10.1109\/TNSE.2025.3560402","article-title":"Dual-Agent DRL-Based Service Placement, Task Scheduling, and Resource Allocation for Multi-Sensor and Multi-User Edge Computing Networks","volume":"12","author":"Fan","year":"2025","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Cui, D., Peng, Z., Li, K., Li, Q., He, J., and Deng, X. (2025). An Novel Cloud Task Scheduling Framework Using Hierarchical Deep Reinforcement Learning for Cloud Computing. PLoS ONE, 20.","DOI":"10.1371\/journal.pone.0329669"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zhang, M., Wang, D., Cai, Z., Huang, Y., Yu, H., Qin, H., and Zeng, J. (2025). EGLight: Enhancing deep reinforcement learning with expert guidance for traffic signal control. Transp. A Transp. Sci., 1\u201327.","DOI":"10.1080\/23249935.2025.2486263"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1109\/TSC.2025.3528346","article-title":"TF-DDRL: A transformer-enhanced distributed DRL technique for scheduling IoT applications in edge and cloud computing environments","volume":"18","author":"Wang","year":"2025","journal-title":"IEEE Trans. Serv. Comput."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/4\/321\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T04:20:53Z","timestamp":1776831653000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/4\/321"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":25,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["a19040321"],"URL":"https:\/\/doi.org\/10.3390\/a19040321","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,20]]}}}