Abstract: In response to the increasing demand for heterogeneous data interaction and cross-disciplinary modeling in aerospace situational awareness simulations, we propose a microservice platform for data–model computing (MP-DMC), which is a high-performance microservice framework built on a container cloud. The proposed MP-DMC framework unifies the control of data and models through a distributed node resource management and scheduling strategy, integrating an election-optimized leader–follower mechanism, a predictive model based on a double-moving-average long short-term memory (DMA-LSTM) network for dynamic elastic scaling, and an intelligent load migration algorithm to address management inefficiencies, prevent node crashes, and mitigate resource oscillations under high-concurrency conditions. Experimental results demonstrate that the proposed MP-DMC framework outperforms mainstream algorithms in terms of election performance, node scaling efficiency, task response time, and load balancing, including consensus algorithms (Paxos, Raft, and PBFT), elastic scaling methods (HPA, DMA-HPA, ProSmart HPA, and RL), and scheduling algorithms (round-robin, purely random, and weighted random), achieving exceptional resource allocation performance and system availability.

面向态势感知仿真的数据–模型融合计算调度策略

[1]Ahmad H, Treude C, Wagner M, et al., 2025. Towards resource-efficient reactive and proactive auto-scaling for microservice architectures. J Syst Softw, 225:112390.

[2]Cui HT, Zhang C, Ding X, et al., 2021. Evaluation framework for development organizations’ adaptability to micro-services architecture. J Softw, 32(5):1256-1283 (in Chinese).

[3]Dayal J, Bratcher D, Eisenhauer G, et al., 2014. Flexpath: type-based publish/subscribe system for large-scale science analytics. 14^th IEEE/ACM Int Symp on Cluster, Cloud and Grid Computing, p.246-255.

[4]Ding TC, Qian SY, Zhu WD, et al., 2020. Comat: an effective composite matching framework for content-based pub/sub systems. IEEE Int Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking, p.236-243.

[5]Ding WH, Ding XH, Xu ZP, et al., 2025. Simulation technology for large-scale satellite cloud network with the integration of digital and reality. Space Integr Ground Inform Netw, 6(1):64-77 (in Chinese).

[6]Dragoni N, Lanese I, Larsen ST, et al., 2017. Microservices: how to make your application scale. http://arxiv.org/abs/1702.07149

[7]Feng ZY, Xu YW, Xue X, et al., 2020. Review on the development of microservice architecture. J Comput Res Dev, 57(5):1103-1122 (in Chinese).

[8]Guo W, 2019. DolphinScheduler. https://dolphinscheduler.apache.org/zh-cn/ [Accessed on Oct. 5, 2025].

[9]Lamport L, 1998. The part-time parliament. ACM Trans Comput Syst, 16(2):133-169.

[10]Larsson M, 2021. Microservices with Spring Boot and Spring Cloud: Build Resilient and Scalable Microservices Using Spring Cloud, Istio, and Kubernetes (2^nd Ed.). Packt Publishing, Birmingham, UK.

[11]Lei X, Yang LM, Zhu YY, et al., 2024. Digital-analog hybrid simulation platform construction and characteristic research of Baihetan-Jiangsu hybrid cascaded UHVDC project. Power Syst Technol, 48(1):434-442 (in Chinese).

[12]Li L, Li HZ, Li T, 2024. Multi-primary-node Byzantine fault-tolerant consensus mechanism based on Raft. J Guangxi Norm Univ (Nat Sci Ed), 42(3):122-130 (in Chinese).

[13]Liang F, 2017. Apache Dubbo. https://github.com/apache/dubbo [Accessed on Oct. 5, 2025].

[14]Liu F, Weissman JB, 2015. Elastic job bundling: an adaptive resource request strategy for large-scale parallel applications. Proc Int Conf for High Performance Computing, Networking, Storage and Analysis, Article 33.

[15]Liu WG, Cui JH, Li TT, et al., 2023. A space-efficient fair cache scheme based on machine learning for NVMe SSDs. IEEE Trans Parall Distrib Syst, 34(1):383-399.

[16]Luo H, Jiang W, Liu MW, et al., 2022. Multi resource load balancing optimization method based on microservice architecture. Sci Technol Eng, 22(5):1965-1971 (in Chinese).

[17]Ma HC, Si L, Tan C, 2023. Research on VR system of shearer based on fusion of sensor data and model. Coal Mine Mach, 44(6):200-204 (in Chinese).

[18]Ma Y, Yan RY, Sun JW, et al., 2017. A MQTT protocol message push server based on RocketMQ. 10^th Int Conf on Intelligent Computation Technology and Automation, p.295-298.

[19]Mesbahi MR, Rahmani AM, Hosseinzadeh M, 2019. Dependability analysis for characterizing Google cluster reliability. Int J Commun Syst, 32(16):e4127.

[20]Nguyen TT, Yeom YJ, Kim T, et al., 2020. Horizontal pod autoscaling in Kubernetes for elastic container orchestration. Sensors, 20(16):4621.

[21]Pathak A, Kalaiarasan C, 2021. RabbitMQ queuing mechanism of publish subscribe model for better throughput and response. 4^th Int Conf on Electrical, Computer and Communication Technologies, p.1-7.

[22]Pivotal Software, Inc., 2018. Spring Cloud Scheduler. https://github.com/spring-attic/spring-cloud-scheduler [Accessed on Oct. 5, 2025].

[23]Rossi F, Cardellini V, Presti FL, 2020. Self-adaptive threshold-based policy for microservices elasticity. 28^th Int Symp on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, p.1-8.

[24]Shona M, Sharma R, 2023. Implementation and comparative analysis of static and dynamic load balancing algorithms in SDN. Int Conf for Advancement in Technology, p.1-7.

[25]Shrimal M, Sharma AK, Patel M, 2024. A novel hybrid load balancing method to achieve quality of service (QoS) in cloud-based environments. 3^rd Int Conf on Sentiment Analysis and Deep Learning, p.325-328.

[26]Tsenos M, Kalogeraki V, 2021. Dynamic rate control for topic-based pub/sub systems. 22^nd IEEE Int Conf on Mobile Data Management, p.272-273.

[27]Ullah MH, Park SS, No J, et al., 2013. A collaboration mechanism between wireless sensor network and a cloud through a pub/sub-based middleware service. 5^th Int Conf on Evolving Internet, p.38-42.

[28]Wang YZ, Yu JQ, Yu ZB, 2023. Resource scheduling techniques in cloud from a view of coordination: a holistic survey. Front Inform Technol Electron Eng, 24(1):1-40.

[29]Wei MD, Li YF, Wang YY, et al., 2025. Optimizing real-time e-commerce data streams: a comparative analysis of serialization and topic design patterns in Apache Kafka. Int Conf on Computing, Networking and Communications, p.334-339.

[30]Xu XL, 2015. XXL-JOB, a Distributed Task Scheduling Framework. https://github.com/xuxueli/xxl-job [Accessed on Oct. 5, 2025].

[31]Xu ZC, Zhao DP, Liang WF, et al., 2023. HierFedML: aggregator placement and UE assignment for hierarchical federated learning in mobile edge computing. IEEE Trans Parall Distrib Syst, 34(1):328-345.

[32]Yang T, Zhou XS, Lin Y, 2004. A publish–subscribe system based on CORBA. Comput Eng, 30(10):77-78 (in Chinese).

[33]Yin JB, He SJ, Zhao F, et al., 2015. Design and implementation of intelligent load-balancing heterogeneous data source middleware based on ActiveMQ and XML. Int Conf on Industrial Informatics—Computing Technology, Intelligent Technology, Industrial Information Integration, p.255-258.

[34]Zhang CY, Chen WY, Chen Q, et al., 2021. Distributed intelligent reflecting surfaces-aided device-to-device communications system. J Commun Inform Netw, 6(3):197-207.

[35]Zhang Y, 2023. Research on Fault Diagnosis of Piston Pump Based on Digital Analog Fusion. MS Thesis, North University of China, Taiyuan, China (in Chinese).

[36]Zheng BY, Gao YH, Guo XK, 2025. BE-Raft: a Raft consensus algorithm with enhanced election determinism. Comput Simul, 42(11):326-330, 396 (in Chinese).

Similar articles