基于混沌反向学习改进灰狼算法的移动网络调度运行信息共享方法

doi:10.11959/j.issn.1000-0801.2023164

摘要/Abstract

摘要：

为了提高移动网络调度运行信息的效用程度，提出了基于混沌反向学习改进灰狼算法的移动网络调度运行信息共享方法。在研究信息内部网/省调隔离区（demilitarized zone，DMZ）、网/省调III区之间的信息共享结构的基础上，通过包含共享任务层、信息层以及用户层的三层调度网络模型实现信息共享，并确定信息效用最大化的信息调度优化目标函数，通过灰狼算法求解该目标函数，获取信息调度结果；为获取更佳的目标函数求解结果，创新性地引入混沌反向学习和信息共享搜索策略，优化灰狼算法的初始种群和交流能力，以此获取更佳的求解结果，实现信息最优共享。测试结果显示：该方法具有较好的应用性能，信息效用值均达到20以上，偏差率低于0.12、拟合优度高于0.92，能够完成不同传输模式下的信息共享，并且呈现共享信息详情。

关键词: 混沌反向学习, 改进灰狼算法, 移动网络, 调度运行, 信息共享, 共享搜索策略

Abstract:

In order to improve the effectiveness of mobile network scheduling operation information, a method of mobile network scheduling operation information sharing based on chaos reverse learning improved gray wolf algorithm was proposed.On the basis of studying the information sharing structure between the information intranet/provincial dispatching demilitarized zone (DMZ) and the network/provincial dispatching III area, the information sharing was realized through a three-layer scheduling network model including the sharing task layer, the information layer and the user layer, and the information scheduling optimization objective function to maximize the information utility was determined, and the information scheduling results were obtained by solving the objective function through the grey wolf algorithm.In order to obtain better solution results of the objective function, chaos reverse learning and information sharing search strategy were introduced to optimize the initial population and communication ability of the grey wolf algorithm, so as to obtain better solution results and realize the optimal information sharing.The test results show that the method has good application performance.The information utility values are all above 20, the deviation rate is lower than 0.12, and the goodness of fit is higher than 0.92.It can complete information sharing under different transmission modes and present the details of shared information.

Key words: chaos reverse learning, improved grey wolf algorithm, mobile network, dispatch operation, information sharing, sharing search policy

中图分类号:

TP393

余昕越, 张艺镨, 张勇, 杨林, 高卫东, 郭岩. 基于混沌反向学习改进灰狼算法的移动网络调度运行信息共享方法[J]. 电信科学, 2023, 39(8): 82-90.

Xinyue YU, Yipu ZHANG, Yong ZHANG, Lin YANG, Weidong GAO, Yan GUO. Mobile network scheduling and operation information sharing method based on chaos reverse learning improved grey wolf algorithm[J]. Telecommunications Science, 2023, 39(8): 82-90.

图/表 7

图1

图2

表1

表2

表3

图3

图4

参考文献 15

[1]	刘尧, 邓晓衡, 桂劲松 ,等. 弱链路下基于全对等模式和相关性检测的资源信息共享[J]. 湖南科技大学学报(自然科学版), 2021,36(3): 88-96.
	LIU Y , DENG X H , GUI J S ,et al. Resource information sharing based on full peer mode and correlation detection for weak-link-oriented communication environments[J]. Journal of Hunan University of Science ＆ Technology (Natural Science Edition), 2021,36(3): 88-96.
[2]	包空军, 张新敬 . 基于粒子群优化的数据库信息远程共享仿真[J]. 计算机仿真, 2022,39(2): 487-490,495.
	BAO K J , ZHANG X J . Remote sharing simulation of database information based on particle swarm optimization[J]. Computer Simulation, 2022,39(2): 487-490,495.
[3]	席嫣娜, 张宏宇, 高鑫 ,等. 基于区块链的能源互联网大数据知识共享模型[J]. 电力建设, 2022,43(3): 123-130.
	XI Y N , ZHANG H Y , GAO X ,et al. Knowledge sharing model based on blockchain for big data of energy Internet[J]. Electric Power Construction, 2022,43(3): 123-130.
[4]	王泽曦, 张敏情, 柯彦 ,等. 基于图像秘密共享的密文域可逆信息隐藏算法[J]. 计算机应用, 2022,42(5): 1480-1489.
	WANG Z X , ZHANG M Q , KE Y ,et al. Reversible data hiding algorithm in encrypted domain based on secret image sharing[J]. Journal of Computer Applications, 2022,42(5): 1480-1489.
[5]	吴昌友, 付熙松, 裴均珂 . 基于信息共享搜索策略的自适应灰狼算法研究[J]. 电光与控制, 2022,29(7): 22-28.
	WU C Y , FU X S , PEI J K . Research on adaptive grey wolf algorithm based on information sharing search strategy[J]. Electronics Optics ＆ Control, 2022,29(7): 22-28.
[6]	夏凯文, 颜超, 冯径 ,等. 基于改进拜占庭容错算法的区块链气象数据共享系统[J]. 科学技术与工程, 2022,22(13): 5312-5321.
	XIA K W , YAN C , FENG J ,et al. Blockchain meteorological data sharing system based on improved Byzantine-fault tolerance algorithm[J]. Science Technology and Engineering, 2022,22(13): 5312-5321.
[7]	刘晶, 董志红, 张喆语 ,等. 基于联邦增量学习的工业物联网数据共享方法[J]. 计算机应用, 2022,42(4): 1235-1243.
	LIU J , DONG Z H , ZHANG Z Y ,et al. Data sharing method of industrial Internet of Things based on federal incremental learning[J]. Journal of Computer Applications, 2022,42(4): 1235-1243.
[8]	李永强, 刘兆伟 . 基于区块链的车联网安全信息共享机制设计[J]. 郑州大学学报(工学版), 2022,43(1): 103-110.
	LI Y Q , LIU Z W . Blockchain-based secure data sharing mechanism design in the vehicular networks[J]. Journal of Zhengzhou University (Engineering Science), 2022,43(1): 103-110.
[9]	FERRAIOLO D F , DEFRANCO J F , KUHN D R ,et al. A new approach to data sharing and distributed ledger technology:a clinical trial use case[J]. IEEE Network, 2021,35(1): 4-5.
[10]	SINGH C , SUNITHA C A . Chaotic and Paillier secure image data sharing based on blockchain and cloud security[J]. Expert Systems with Applications, 2022,198(7): 116874.1-116874.13.
[11]	李开言, 王亚刚, 张涛 . 基于改进灰狼优化算法的边缘计算任务调度方法[J]. 信息与控制, 2022,51(4): 489-497,512.
	LI K Y , WANG Y G , ZHANG T . Edge computing task scheduling method based on an improved grey wolf optimization algorithm[J]. Information and Control, 2022,51(4): 489-497,512.
[12]	刘炼, 付绍昌, 黄辉先 . 基于醉汉漫步和反向学习的灰狼优化算法[J]. 计算机工程与科学, 2021,43(9): 1558-1566.
	LIU L , FU S C , HUANG H X . A grey wolf optimization algorithm based on drunkard strolling and reverse learning[J]. Computer Engineering and Science, 2021,43(9): 1558-1566.
[13]	蔡娟 . 混沌映射与精英高斯扰动的非线性灰狼优化算法[J]. 计算机工程与设计, 2022,43(1): 186-195.
	CAI J . Non-linear grey wolf optimization algorithm based on chaotic Tent mapping and elite Gauss perturbation[J]. Computer Engineering and Design, 2022,43(1): 186-195.
[14]	徐雪敏, 张秀国, 肖媛元 ,等. 基于优化的灰狼算法的大规模Web服务组合[J]. 计算机应用, 2022,42(10): 3162-3169.
	XU X M , ZHANG X G , XIAO Y Y ,et al. Large-scale Web service composition based on optimized grey wolf optimizer[J]. Journal of Computer Applications, 2022,42(10): 3162-3169.
[15]	丁雨, 李晨凯, 韩会梅 ,等. 基于5G无人机通信的多智能体异构网络选择方法[J]. 电信科学, 2022,38(8): 28-36.
	DING Y , LI C K , HAN H M ,et al. Multi-agent heterogeneous network selection method based on 5G UAV communication[J]. Telecommunications Science, 2022,38(8): 28-36.

用户数量/人	信息不共享	本文方法共享后	文献[7]方法共享后	文献[8]方法共享后
10	5.74	21.36	16.14	15.33
20	6.08	21.79	16.33	15.45
30	5.97	21.68	16.39	15.57
40	8.66	22.44	17.03	16.23
50	9.74	22.39	17.15	16.38
60	10.22	24.56	18.36	16.52
70	12.36	25.52	19.12	17.04
80	13.37	25.98	19.52	17.38
90	14.48	26.76	20.12	17.56
100	15.52	26.88	20.27	17.86
110	17.71	26.86	20.34	18.31
120	18.85	27.02	21.44	19.67
130	18.96	26.87	20.91	19.98

信息数量/条	偏差率
信息数量/条	本文方法	灰狼算法	文献[7]方法	文献[8]方法
2 000	0.033	0.056	0.058	0.049
4 000	0.041	0.063	0.064	0.058
6 000	0.058	0.073	0.068	0.069
8 000	0.062	0.079	0.074	0.073
12 000	0.055	0.089	0.079	0.085
14 000	0.074	0.097	0.084	0.094
16 000	0.092	0.112	0.096	0.102
18 000	0.087	0.127	0.117	0.107
20 000	0.101	0.131	0.122	0.126

信息数量/条	拟合优度
信息数量/条	本文方法	灰狼算法	文献[7]方法	文献[8]方法
2 000	0.927	0.858	0.856	0.853
4 000	0.936	0.864	0.863	0.866
6 000	0.947	0.868	0.873	0.862
8 000	0.952	0.874	0.879	0.878
12 000	0.962	0.879	0.889	0.872
14 000	0.986	0.884	0.907	0.888
16 000	0.981	0.896	0.882	0.846
18 000	0.976	0.857	0.827	0.813
20 000	0.927	0.842	0.831	0.825