|
|
基于改进人工鱼群算法的电商平台AR-ASFA分布式系统
|
Abstract:
数字化、信息化和互联网的普及催生了电子商务的高速发展。面对急速膨胀的用户访问量，电商平台如何承载更多的用户流量并提高服务器响应性能等技术上仍存在瓶颈。本文从软硬件两方面进行系统优化，构建高性能分布式AR-AFSA系统。(1) AR (Application Router)架构配置三台JobManager服务器节点，分别接收三种方式的用户访问请求，运用流量分配机制分散系统的流量承载压力，并将用户请求按不同访问方式划分为四个流量队列进行调度。(2) 改进的人工鱼群算法(AFSA)进行容器调度，重新规划人工鱼的各行为执行顺序，增加对最优解寻找的可能性并加快局部收敛速度。(3) 设计人工鱼的参数与评价指标，为用户请求匹配足够资源的容器同时保证资源节约和系统负载均衡。最后在淘宝用户行为数据集以及多组对照实验下进行验证，AR系统可承载传统服务器三倍的流量压力。改进的人工鱼群算法相比对照算法可收敛至更优解，并且在服务器资源规模更为复杂的情况下，展示出更大的优势。
The popularization of digitalization, informatization and the Internet has given birth to the rapid development of e-commerce. Faced with rapidly expanding user traffic, e-commerce platforms still face technical bottlenecks in carrying more user traffic and improving server response performance. This article optimizes the system from both software and hardware aspects to build a high-performance distributed AR-AFSA system. (1) The AR (Application Router) architecture is configured with three JobManager server nodes, which receive user access requests in three different ways. The traffic allocation mechanism is used to distribute the system’s traffic carrying pressure, and user requests are divided into four traffic queues for scheduling according to different access methods. (2) Improved artificial fish swarm algorithm (AFSA) is used for container scheduling, re planning the execution order of various behaviors of artificial fish, increasing the possibility of finding the optimal solution and accelerating local convergence speed. (3) Parameters and evaluation indicators for artificial fish are designed to match containers with sufficient resources for user requests while ensuring resource conservation and system load balancing. Finally, validation was conducted on the Taobao user behavior dataset and multiple control experiments, and it was found that the AR system can withstand three times the traffic pressure of traditional servers. The improved artificial fish swarm algorithm can converge to a better solution compared to the control algorithm, and demonstrates greater advantages in situations where server resources are more complex.
| [1] | Niu, W. and Li, J. (2022) A Two-Stage Cooperative Evolutionary Algorithm for Energy-Efficient Distributed Group Blocking Flow Shop with Setup Carryover in Precast Systems. Knowledge-Based Systems, 257, Article 109890. https://doi.org/10.1016/j.knosys.2022.109890 |
| [2] | Li, C., Liu, J., Li, W. and Luo, Y. (2021) Adaptive Priority-Based Data Placement and Multi-Task Scheduling in Geo-Distributed Cloud Systems. Knowledge-Based Systems, 224, Article 107050. https://doi.org/10.1016/j.knosys.2021.107050 |
| [3] | Liu, G. (2023) A Q-Learning-Based Distributed Routing Protocol for Frequency-Switchable Magnetic Induction-Based Wireless Underground Sensor Networks. Future Generation Computer Systems, 139, 253-266. https://doi.org/10.1016/j.future.2022.10.004 |
| [4] | Ohi, A.Q., Mridha, M.F., Safir, F.B., Hamid, M.A. and Monowar, M.M. (2020) Autoembedder: A Semi-Supervised DNN Embedding System for Clustering. Knowledge-Based Systems, 204, Article 106190. https://doi.org/10.1016/j.knosys.2020.106190 |
| [5] | Singh, H.J. and Bawa, S. (2022) Lameta: An Efficient Locality Aware Metadata Management Technique for an Ultra-Large Distributed Storage System. Journal of King Saud University-Computer and Information Sciences, 34, 8323-8335. https://doi.org/10.1016/j.jksuci.2022.08.012 |
| [6] | Costa, B., Pires, P.F. and Delicato, F.C. (2020) Towards the Adoption of OMG Standards in the Development of Soa-Based IoT Systems. Journal of Systems and Software, 169, Article 110720. https://doi.org/10.1016/j.jss.2020.110720 |
| [7] | Li, J. (2020) Resource Optimization Scheduling and Allocation for Hierarchical Distributed Cloud Service System in Smart City. Future Generation Computer Systems, 107, 247-256. https://doi.org/10.1016/j.future.2019.12.040 |
| [8] | Yin, L. and Sun, Z. (2022) Distributed Multi-Objective Grey Wolf Optimizer for Distributed Multi-Objective Economic Dispatch of Multi-Area Interconnected Power Systems. Applied Soft Computing, 117, Article 108345. https://doi.org/10.1016/j.asoc.2021.108345 |
| [9] | Moghadam, A.S., Suratgar, A.A., Hesamzadeh, M.R. and Nikravesh, S.K.Y. (2022) Multi-Objective ACOPF Using Distributed Gradient Dynamics. International Journal of Electrical Power & Energy Systems, 141, Article 107934. https://doi.org/10.1016/j.ijepes.2021.107934 |
| [10] | Cinque, M., Della Corte, R. and Pecchia, A. (2022) Micro2vec: Anomaly Detection in Microservices Systems by Mining Numeric Representations of Computer Logs. Journal of Network and Computer Applications, 208, Article 103515. https://doi.org/10.1016/j.jnca.2022.103515 |
