基于特征深度融合的Web服务QoS联合预测

doi:10.11959/j.issn.1000-436x.2022107

通信学报 ›› 2022, Vol. 43 ›› Issue (7): 215-226.doi: 10.11959/j.issn.1000-436x.2022107

• 学术通信 • 上一篇

基于特征深度融合的Web服务QoS联合预测

刘建勋¹^,², 丁领航¹^,², 康国胜¹^,², 曹步清¹^,², 肖勇¹^,²

¹ 湖南科技大学服务计算与软件新技术湖南省重点实验室，湖南湘潭 411201
² 湖南科技大学计算机科学与工程学院，湖南湘潭 411201

修回日期:2022-05-07 出版日期:2022-07-25 发布日期:2022-06-01
作者简介:刘建勋（1970- ），男，湖南衡阳人，博士，湖南科技大学教授，主要研究方向为工作流管理、服务计算、云计算、语义和知识网格等
丁领航（1994- ），男，湖南湘潭人，湖南科技大学硕士生，主要研究方向为服务计算与云计算
康国胜（1985- ），男，湖南郴州人，博士，湖南科技大学讲师，主要研究方向为服务计算和云计算、以数据为中心的业务流程管理、业务流程配置、数据挖掘和社交网络
曹步清（1979- ），男，湖南湘潭人，博士，湖南科技大学教授，主要研究方向为服务计算、社交网络和软件工程
肖勇（1995- ），男，湖南湘潭人，湖南科技大学博士生，主要研究方向为服务推荐、服务集群和网络表示学习
基金资助:
国家自然科学基金资助项目(61872139);湖南省教育厅基金资助项目(20B244)

Joint QoS prediction for Web services based on deep fusion of features

Jianxun LIU¹^,², Linghang DING¹^,², Guosheng KANG¹^,², Buqing CAO¹^,², Yong XIAO¹^,²

¹ Hunan Provincial Key Lab for Services Computing and Novel Software Technology, Hunan University of Science and Technology, Xiangtan 411201, China
² School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan 411201, China

Revised:2022-05-07 Online:2022-07-25 Published:2022-06-01
Supported by:
The National Natural Science Foundation of China(61872139);Educational Commission of Hunan Prov-ince of China(20B244)

摘要/Abstract

摘要：

为了解决Web服务QoS预测准确度不够的问题，针对QoS中隐藏的环境偏好信息和多类QoS隐藏的共同特征，提出一种基于特征深度融合的Web服务QoS联合预测方法。考虑QoS数据可以建模为用户-服务二部图，采用多组件图卷积神经网络进行特征提取和映射，采用加权融合方法对多类QoS特征进行同维映射。使用注意力因子分解机对映射后的特征向量进行一阶特征、二阶交互特征和高阶交互特征的提取，并结合各部分结果实现QoS联合预测。实验结果表明，所提方法在均方根误差和平均绝对误差方面优于现有QoS预测方法。

关键词: 联合预测, 服务质量, 偏好特征, 深度融合

Abstract:

In order to solve the problem of insufficient accuracy of Web service QoS prediction, a joint QoS prediction method for Web services based on the deep fusion of features was proposed with considering of the hidden environmental preference information in QoS and the common features of multi-class QoS.First, QoS data was modeled as a user-service bipartite graph and multi-component graph convolution neural network was used for feature extraction and mapping, and the weighted fusion method was used for the same dimensional mapping of multi-class of QoS features.Subsequently, the attention factor decomposition machine was used to extract the first-order features, second-order interactive features, and high-order interactive features of the mapped feature vector.Finally, the results of each part were combined to achieve the joint QoS prediction.The experimental results show that the proposed method is superior to the existing QoS prediction methods in terms of root mean square error (RMSE) and average absolute error (MAE).

Key words: joint prediction, quality of service, preference feature, deep fusion

中图分类号:

TN92

刘建勋, 丁领航, 康国胜, 曹步清, 肖勇. 基于特征深度融合的Web服务QoS联合预测[J]. 通信学报, 2022, 43(7): 215-226.

Jianxun LIU, Linghang DING, Guosheng KANG, Buqing CAO, Yong XIAO. Joint QoS prediction for Web services based on deep fusion of features[J]. Journal on Communications, 2022, 43(7): 215-226.

图/表 9

图1

图2

图3

表1

表2

基于响应时间数据集的所有QoS预测评价结果"

方法	DoT=5%		DoT=10%		DoT=15%		DoT=20%		DoT=25%		DoT=30%
方法	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE
UIPCC	0.197 1	0.086 1	0.184 9	0.079 8	0.177 4	0.073 2	0.166 1	0.068 9	0.158 1	0.066 5	0.152 8	0.058 6
PMF	0.154 8	0.069 7	0.152 4	0.066 7	0.147 5	0.064 8	0.142 6	0.061 9	0.134 1	0.058 5	0.129 3	0.052 1
DNM	0.142 8	0.061 9	0.139 6	0.060 5	0.136 7	0.059 3	0.130 8	0.056 9	0.129 5	0.052 2	0.123 5	0.051 2
MLP-ANFM	0.142 2	0.061 1	0.139 3	0.059 4	0.135 8	0.059 1	0.128 0	0.054 4	0.127 5	0.050 2	0.122 0	0.050 3
MGCN-MLP	0.141 4	0.060 4	0.138 7	0.058 5	0.134 6	0.057 8	0.128 5	0.053 8	0.124 7	0.049 9	0.120 8	0.488 0
Single-MGCN	0.140 8	0.059 9	0.138 8	0.057 7	0.134 4	0.057 2	0.128 2	0.056 5	0.123 0	0.0500	0.118 6	0.047 9
JQSP	$0 . 1357$	$0 . 0587$	$0 . 1335$	$0 . 0554$	$0 . 1296$	$0 . 0525$	$0 . 1220$	$0 . 0504$	$0 . 1126$	$0 . 0477$	$0 . 0988$	$0 . 0452$
Gains	4.97%	5.17%	4.37%	8.43%	5.19%	11.47%	6.73%	11.42%	13.05%	8.62%	20.00%	11.72%

表2

表3

基于吞吐量数据集的所有QoS预测评价结果"

方法	DoT=5%		DoT=10%		DoT=15%		DoT=20%		DoT=25%		DoT=30%
方法	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE
UIPCC	0.216 2	0.117 8	0.200 5	0.101 6	0.198 4	0.096 9	0.190 3	0.088 3	0.179 2	0.084 7	0.164 1	0.076 4
PMF	0.180 2	0.086	0.176 4	0.075 6	0.168 5	0.069 2	0.160 2	0.061 6	0.158 5	0.059 4	0.154 3	0.058 8
DNM	0.184 4	0.082 2	0.179 8	0.075 8	0.170 9	0.064 3	0.162 9	0.060 5	0.155 7	0.054 7	0.151 0	0.052 9
MLP-ANFM	0.182 3	0.083 6	0.177 0	0.073 8	0.168 8	0.066 3	0.161 1	0.060 0	0.154 8	0.053 8	0.147 7	0.051 1
MGCN-MLP	0.180 3	0.080 5	0.177 2	0.071 6	0.165 8	0.064 2	0.160 3	0.059 9	0.150 2	0.053 8	0.142 8	0.051 5
Single-MGCN	0.179 8	0.080 4	0.175 9	0.072 8	0.162 5	0.061 7	0.158 9	0.059 2	0.148 8	0.052 9	0.137 9	0.051 6
JQSP	$0 . 1725$	$0 . 0788$	$0 . 1659$	$0 . 0701$	$0 . 1524$	$0 . 0602$	$0 . 1465$	$0 . 0575$	$0 . 1333$	$0 . 0510$	$0 . 1073$	$0 . 0502$
Gains	6.45%	4.14%	7.73%	7.52%	10.83%	6.38%	10.07%	4.96%	14.39%	6.76%	28.96%	5.10%

表3

图4

图5

图6

参考文献 30

[1]	方晨, 张恒巍, 张铭 ,等. 基于信任扩展和列表级排序学习的服务推荐方法[J]. 通信学报, 2018,39(1): 147-158.
	FANG C , ZHANG H W , ZHANG M ,et al. Trust expansion and listwise learning-to-rank based service recommendation method[J]. Journal on Communications, 2018,39(1): 147-158.
[2]	赵晨阳, 王俊岭 . 基于隐含上下文支持向量机的服务推荐方法[J]. 通信学报, 2019,40(9): 61-73.
	ZHAO C Y , WANG J L . Service recommendation method based on context-embedded support vector machine[J]. Journal on Communications, 2019,40(9): 61-73.
[3]	YIN Y Y , CHEN L , XU Y S ,et al. QoS prediction for service recommendation with deep feature learning in edge computing environment[J]. Mobile Networks and Applications, 2020,25(2): 391-401.
[4]	WANG X , WANG R J , SHI C ,et al. Multi-component graph convolutional collaborative filtering[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020,34(4): 6267-6274.
[5]	DING L , KANG G , LIU J ,et al. QoS prediction for Web services via combining multi-component graph convolutional collaborative filtering and deep factorization machine[C]// IEEE International Conference on Web Services. Piscataway:IEEE Press, 202: 551-559.
[6]	SHAO L S , ZHANG J , WEI Y ,et al. Personalized QoS prediction forWeb services via collaborative filtering[C]// Proceedings of IEEE International Conference on Web Services. Piscataway:IEEE Press, 2007: 439-446.
[7]	CHEN L , FENG Y P , WU J ,et al. An enhanced QoS prediction approach for service selection[C]// Proceedings of 2011 IEEE International Conference on Services Computing. Piscataway:IEEE Press, 2011: 727-728.
[8]	任丽芳, 王文剑 . 一种移动边缘计算环境中服务QoS的预测方法[J]. 小型微型计算机系统, 2020,41(6): 1176-1181.
	REN L F , WANG W J . Method for QoS prediction in mobile edge computing environment[J]. Journal of Chinese Computer Systems, 2020,41(6): 1176-1181.
[9]	WANG S G , ZHAO Y L , HUANG L ,et al. QoS prediction for service recommendations in mobile edge computing[J]. Journal of Parallel and Distributed Computing, 2019,127: 134-144.
[10]	邓璇, 吕晟凯 . 基于信誉感知与嵌入式学习的Web服务QoS预测研究[J]. 物联网技术, 2021,11(12): 99-103.
	DENG X , LYU S K . Research on Web service QoS prediction based on reputation perception and embedded learning[J]. Internet of Things Technologies, 2021,11(12): 99-103.
[11]	SALAKHUTDINOV R , MNIH A , HINTON G . Restricted Boltzmann machines for collaborative filtering[C]// Proceedings of the 24th International Conference on Machine Learning. New York:ACM Press, 2007: 791-798.
[12]	LUO X , ZHOU M C , WANG Z D ,et al. An effective scheme for QoS estimation via alternating direction method-based matrix factorization[J]. IEEE Transactions on Services Computing, 2019,12(4): 503-518.
[13]	鲁城华, 寇纪淞 . 基于用户和服务区域信息的个性化 Web 服务质量预测[J]. 管理科学, 2020,33(2): 63-75.
	LU C H , KOU J S . Personalized QoS prediction for Web services based on the region information of users and services[J]. Journal of Management Science, 2020,33(2): 63-75.
[14]	CHEN L , XIE F F , ZHENG Z B ,et al. Predicting quality of service via leveraging location information[J]. Complexity,2019, 2019:4932030.
[15]	TANG M D , LIANG W , YANG Y T ,et al. A factorization machine-based QoS prediction approach for mobile service selection[J]. IEEE Access, 2019,7: 32961-32970.
[16]	夏会, 高旻, 邹淑 . 时空感知下基于结构相似度的Web服务质量预测[J]. 重庆大学学报, 2021,44(1): 88-96.
	XIA H , GAO M , ZOU S . A structure similarity based quality prediction approach for Web service in the spatial-temporal scenario[J]. Journal of Chongqing University, 2021,44(1): 88-96.
[17]	陈蕾, 杨庚, 陈正宇 ,等. 基于结构化噪声矩阵补全的 Web 服务QoS预测[J]. 通信学报, 2015,36(6): 53-63.
	CHEN L , YANG G , CHEN Z Y ,et al. Web services QoS prediction via matrix completion with structural noise[J]. Journal on Communications, 2015,36(6): 53-63.
[18]	LUO X , WU H , YUAN H Q ,et al. Temporal pattern-aware QoS prediction via biased non-negative latent factorization of tensors[J]. IEEE Transactions on Cybernetics, 2020,50(5): 1798-1809.
[19]	KANG G S , LIU J X , XIAO Y ,et al. Neural and attentional factorization machine-based Web API recommendation for mashup development[J]. IEEE Transactions on Network and Service Management, 2021,18(4): 4183-4196.
[20]	GAO H H , XU Y S , YIN Y Y ,et al. Context-aware QoS prediction with neural collaborative filtering for Internet-of-things services[J]. IEEE Internet of Things Journal, 2020,7(5): 4532-4542.
[21]	王安迪 . 基于QoS的Web服务质量预测方法研究[D]. 北京:华北电力大学(北京), 2020.
	WANG A D . Research on prediction method of web services quality based on QoS[D]. Beijing:North China Electric Power University, 2020.
[22]	CHEN D , GAO M , LIU A ,et al. A recurrent neural network based approach for Web service QoS prediction[C]// Proceedings of 2019 2nd International Conference on Artificial Intelligence and Big Data(ICAIBD). Piscataway:IEEE Press, 2019: 350-357.
[23]	ELIF A , CANBERK B . Forecasting quality of service for next- generation data-driven WiFi6 campus networks[J]. IEEE Transactions on Network and Service Management, 2021,18(4): 4744-4755.
[24]	ZHANG X W , LI L . Attentional neural factorization machines for knowledge tracing[C]// Knowledge Science,Engineering and Management. Berlin:Springer, 2021: 319-330.
[25]	RENDLE S . Factorization machines with libFM[J]. ACM Transactions on Intelligent Systems and Technology, 2012,3(3): 1-22.
[26]	VASWANI A , SHAZEER N , PARMAR N ,et al. Attention is all you need[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Massachusetts:MIT Press, 2017: 6000-6010.
[27]	ZHENG Z , MA H , LYU M R ,et al. QoS-aware Web service recommendation by collaborative filtering[J]. IEEE Transactions on services computing, 2011,4(2): 140-52.
[28]	ZHENG Z B , MA H , LYU M R ,et al. Collaborative Web service QoS prediction via neighborhood integrated matrix factorization[J]. IEEE Transactions on Services Computing, 2013,6(3): 289-299.
[29]	WU H , ZHANG Z X , LUO J C ,et al. Multiple attributes QoS prediction via deep neural model with contexts[J]. IEEE Transactions on Services Computing, 2021,14(4): 1084-1096.
[30]	LOUIZOS C , WELLING M , KINGMA D P . Learning sparse neural networks through L₀regularization[J]. arXiv Preprint,arXiv:171201312, 2017.

参数	值
转换矩阵数量	3
优化器	Adam
神经网络嵌入维度	64
自注意力嵌入维度	64
Dropout	0.5
正则化系数	3.3×10^-5
激活函数	ReLU
神经网络层	2
学习率	0.0001

基于特征深度融合的Web服务QoS联合预测

Joint QoS prediction for Web services based on deep fusion of features

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 30

相关文章 15

Metrics

推荐阅读 0

[1]	李元诚, 秦永泰. 基于深度强化学习的软件定义安全中台QoS实时优化算法[J]. 通信学报, 2023, 44(5): 181-192.
[2]	张达敏, 王义, 邹诚诚, 赵沛雯, 张琳娜. 认知异构蜂窝网络中改进蜉蝣算法的资源分配策略[J]. 通信学报, 2022, 43(6): 156-167.
[3]	李俊娥, 陆秋余, 刘剑, 袁凯, 田薇, 彭弼君. 智能变电站通信业务优先级及其队列调度方法[J]. 通信学报, 2021, 42(7): 25-40.
[4]	汪硕, 黄玉栋, 黄韬, 霍如, 刘韵洁. 基于软件定义的时间敏感网络跨域调度机制[J]. 通信学报, 2021, 42(10): 1-9.
[5]	卢毅,徐梦颖,周杰. 基于改进的免疫克隆蛙跳算法的多约束QoS路由优化研究[J]. 通信学报, 2020, 41(5): 141-149.
[6]	李罡,吴志军. 基于多QoS约束条件的广域信息管理系统任务调度算法[J]. 通信学报, 2019, 40(7): 27-37.
[7]	苏命峰,王国军,李仁发. 基于利益相关视角的多维QoS云资源调度方法[J]. 通信学报, 2019, 40(6): 102-115.
[8]	黄韬,汪硕,黄玉栋,郑尧,刘江,刘韵洁. 确定性网络研究综述[J]. 通信学报, 2019, 40(6): 160-176.
[9]	兰巨龙,张学帅,胡宇翔,孙鹏浩. 基于深度强化学习的软件定义网络QoS优化[J]. 通信学报, 2019, 40(12): 60-67.
[10]	陈亮,王军,陈蓉,顾翔,王进,万杰. 车载自组织网视频流媒体协助下载研究[J]. 通信学报, 2019, 40(1): 51-63.
[11]	夏玮玮,丁兆明,沈连丰. 异构网络中基于负载传递的联合接纳控制算法[J]. 通信学报, 2018, 39(5): 34-47.
[12]	裴卓雄,李兴华,刘海,雷凯跃,马建峰,李晖. LBS隐私保护中基于查询范围的匿名区构造方案[J]. 通信学报, 2017, 38(9): 125-132.
[13]	赵志远,孟相如,苏玉泽,李振涛. 多控制器条件下区分QoS的虚拟SDN映射方法[J]. 通信学报, 2017, 38(8): 101-110.
[14]	孙志,陈鸣. PriQoS：基于SDN的区分优先权流控机制[J]. 通信学报, 2017, 38(2): 115-124.
[15]	胡焰智,章锋斌,甘志春,田田,尹才华. 基于场景的移动应用服务QoS建模与评估[J]. 通信学报, 2015, 36(Z1): 110-117.