Computer Science

Computer Science ›› 2023, Vol. 50 ›› Issue (10): 266-274.doi: 10.11896/jsjkx.221000221

• Computer Network • Previous Articles     Next Articles

Performance Analysis of Multi-server Gated Service System Based on BiLSTM Neural Networks

YANG Zhijun1,2,3, HUANG Wenjie1, DING Hongwei1   

  1. 1 School of Information Science and Technology,Yunnan University,Kunming 650500,China
    2 Educational Instruments and Facilities Service Center,Educational Department of Yunnan Province,Kunming 650223,China
    3 Key Laboratory of Education Informatization for Nationalities of Ministry of Education, Yunnan Normal University,Kunming 650500, China
  • Received:2022-10-25 Revised:2023-02-18 Online:2023-10-10 Published:2023-10-10
  • About author:YANG Zhijun,born in 1968,Ph.D,researcher.His main research interests include computer network and communication,polling control system,and deep learning.
  • Supported by:
    National Natural Science Foundation of China(61461053,61461054) and Industry Innovation Talents Project of Yunnan Xingdian Talents Support Plan(YNWR-CYJS-2020-017).

PDF (PC)

1917

Abstract: In order to meet the requirements of fast operation,low delay,good performance and fairness,a multi-server gated service system is proposed and its predictive analysis is carried out using BiLSTM (bi-directional long short-term memory) neural networks.Multi-server access is used to reduce the network delay and improve system performance.Both synchronous and asynchronous approaches can be used when multiple servers are scheduled.Firstly,the system model of multi-server gated service is investigated.Secondly,the average queue length,average cycle period and average delay of multi-server gated service are solved on the basis of single server using the analytical methods of embedded Markov chain and probabilistic generating function.Meanwhile,simulation experiments are conducted using Matlab to compare the theoretical and simulated values of single server system and multi-server system respectively system analysis,comparing both multi-server synchronous and asynchronous approaches.Finally,a BiLSTM neural network is constructed to predict the performance of the multi-server system.Experiments show that the asynchronous approach of this multi-server system is superior to the synchronous and the single-server system,and the multi-server asynchronous system has better performance,lower delay and higher efficiency.Comparing the three basic multi-server service systems,the gated service system is more stable while ensuring fairness.And the use of BiLSTM neural network prediction algorithm can accurately predict the performance of the system and improve the computational efficiency,which is a guideline for the performance evaluation of the polling system.

Key words: Multi-server, Synchronous mode, Asynchronous mode, Average queue length, Average delay, Fairness, BiLSTM neural network

CLC Number: 

  • TN911
[1]TRAN T X,POMPILI D.Joint Task Offloading and ResourceAllocation for Multi-Server Mobile Edge Computing Networks[C]//IEEE Transactions on Vehicular Technology.2019:856-868.
[2]TEYMOORI P,SOHRABY K,KIM K.A Fair and Efficient Re-source Allocation Scheme for Multi-Server Distributed Systems and Networks[C]//IEEE Transactions on Mobile Computing.2016:2137-2150.
[3]BOON M A A,WINANDS E M M,ADAN I J B F,et al.Closed-form waiting time approximations for polling systems[J].Performance Evaluation,2011,68(3):290-306.
[4]LI H F,LING Z G,DING H W,et al.Mixed Service Policy Po-lling Feature Analysis and Access Control System for Energy Saving Design[J].Journal of Internet Technology,2019,9(6):37-40,43.
[5]BAO L Y,ZHAO D F,DING H W.Research on Load Balance Strategy of the Double Server in the Synchronous Dispatch Mecha-nism of Polling[J].Journal of Yunnan University(Natural Sciences Edition),2009,31(s1)1-4,8.
[6]BAO L Y,ZHAO D F,DING H W.An Approximate Algorithm Analysis of Dual-server Asynchronous Control Policy Polling System Performance[C]//Proceedings of 2009 China University Communication Academic Conference.2009:401-405.
[7]HUANG W H,MA Z,DAI X F,et al.Fuzzy Clustering Based Load Balancing Algorithm with Feature Weighted[J].Journal of Xidian University,2017,44(2):127-132.
[8]TAO X L,WEI Y,WANG Y.A Load Balancing Method Based on Hierarchy and Multi-agent for Cloud Computing Platform[J].Acta Electronica Sinica,2016,44(9):2106-2113.
[9]ZHAO Z H,LI Q,YANG S P,et al.Based on BiLSTM and Attention Mechanism of Residual Service Life Prediction Research[J].Journal of Vibration and Shock,2022,41(6):44-50,196.
[10]ZHU L J,XUN Z H,WANG Y X,et al.Short-term Power Load Forecasting Based on CNN-BiLSTM[J].Power Grid Techno-logy,2021,45(11):4532-4539.
[11]LIU Q L,ZHAO D F,DING H W,et al.The Evolution and Development of Polling System[J].Wireless Communication Technology,2013,39(2):55-59.
[12]YANG Z J,ZHENG H Y,DING H W.Wireless LAN Multi-robot System Polling MAC Protocol Study[J].Computer Application Researh,2022,39(4)6:1178-1182.
[13]CHEN C L.Research on MAC enhancement technology of low delay and high reliability wireless LAN[D].Xi'an University of Electronic Science and Technology,2019.
[14]EDIRISINGHE S,RANAWEERA C,LIM C,et al.Universaloptical network architecture for future wireless LANs[J].Journal of Optical Communications and Networking,2021,13(9):D93-D102.
[15]HAYAKAWA M,ITO Y.Study on an Appropriate Value of the Maximum Transmission Rate over Congested IEEE802.11g Wireless LAN Based on Web QoE[C]//2019 IEEE 8th Global Conference on Consumer Electronics (GCCE).2019.
[16]YANG Z J,MAO L,DING H W.Analysis of Dual-server Pol-ling Access Control Protocol[C]//2020 IEEE 4th Information Technology,Networking,Electronic and Automation Control Conference(ITNEC),2020:2607-2612.
[17]CHEN B,WU L,ZEADALLY S,et al.Dual-server Public-KeyAuthenticated Encryption with Keyword Search[C]//IEEE Transactions on Cloud Computing.2022:322-333.
[18]YANG Z J,MAO L DING H W,et al.Analysis of Continuous-time Two-level Complete Polling Access MAC Protocol[J].Computer Engineering and Applications,2022,58(9):136-143.
[19]YANG Z J,MAO L,YAN B,et al.Performance analysis and prediction of asymmetric two-level priority polling system based on BP neural network[J].Applied Soft Computing,2021,29(6):1046-1053.
[20]YANG Z J,LIU Z,DING H W.Research on Performance ofContinuous-time Exhaustive Service and Gated Service Two-le-vel Polling System[J].Journal of Computer Applications,2019,39(7):2019-2023.
[21]XIE X Y,ZHOU J H,ZHANG Y J,et al.An Ultra-short-term Power Generate on Forecasting Method Based on W-BiLSTM[J].Automation of Electric Power Systems,2021,45(8):175-184.
[1] XU Xia, ZHANG Hui, YANG Chunming, LI Bo, ZHAO Xujian. Fair Method for Spectral Clustering to Improve Intra-cluster Fairness [J]. Computer Science, 2023, 50(2): 158-165.
[2] WEI Hong-ru, LI Si-yue, GUO Yong-hao. Secret Reconstruction Protocol Based on Smart Contract [J]. Computer Science, 2022, 49(6A): 469-473.
[3] PENG Dong-yang, WANG Rui, HU Gu-yu, ZU Jia-chen, WANG Tian-feng. Fair Joint Optimization of QoE and Energy Efficiency in Caching Strategy for Videos [J]. Computer Science, 2022, 49(4): 312-320.
[4] REN Yi. Design of Network Multi-server SIP Information Encryption System Based on Block Chain and Artificial Intelligence [J]. Computer Science, 2020, 47(6A): 634-638.
[5] JIANG Rui, YIN Hui, XU You-yun. Millimeter-wave Beamforming Scheme Based on Location Fairness Guarantee for HSR Communications [J]. Computer Science, 2020, 47(10): 269-274.
[6] DU Hao-rui, CHEN Jian-hua, QI Ming-ping, PENG Cong, FAN Qing. Forward-secure RSA-based Multi-server Authentication Protocol [J]. Computer Science, 2019, 46(11A): 409-413.
[7] GUO Li-juan, LV Xiao-lin. Optimistic Certified Email for Line Topology [J]. Computer Science, 2018, 45(8): 156-159.
[8] WANG Zhen-chao,ZHAO Yun,XUE Wen-ling. Power Control Based on Fairness in D2DUnderlaid Cellular Networks [J]. Computer Science, 2018, 45(7): 104-109.
[9] YUAN Bo-ao, LIU Jun. Reliable Logic Analysis Method of Multi-party Non-repudiation Protocol [J]. Computer Science, 2018, 45(7): 143-149.
[10] YIN Qiu-shi, CHEN Jian-hua. Improved Identity Authentication Protocol Based on Elliptic Curve Cryptographyin Multi-server Environment [J]. Computer Science, 2018, 45(6): 111-116.
[11] YANG Yu-qi, ZHANG Guo-an and JIN Xi-long. Dual-cluster-head Routing Protocol Based on Vehicle Density in VANETs [J]. Computer Science, 2018, 45(4): 126-130.
[12] LU Zheng-fu, PU Yan-hong, NI Sheng-bin, XU Chen-ming, YANG Chun-yao. Design and Simulation of Fair Data Exchange Protocol with Bounded Rationality [J]. Computer Science, 2018, 45(11): 115-123.
[13] GUO Zi-rong, ZENG Hua-xin and DOU Jun. Simple and Smoothed Fair Round Robin Scheduling Algorithm [J]. Computer Science, 2016, 43(1): 122-127.
[14] LIU Hai, PENG Chang-gen, ZHANG Hong and REN Zhi-jing. Game Logic Formal Model of Rational Secure Protocol [J]. Computer Science, 2015, 42(9): 118-126.
[15] SHI Zhou-qi,DING Zhi-jun and CHEN Hong-zhong. Further Study of Relationship between Weak Fairness and Fairness of Petri Nets [J]. Computer Science, 2014, 41(7): 49-51.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
Add:18# Honghu West Rd., Yubei ,Chongqing,China    Post Code: 401121
Tel: 023-63500828/023-67039612/023-67039623
E-mail: jsjkx12@163.com
Powered by Beijing Magtech Co., Ltd.