基于特征深度融合的Web服务QoS联合预测

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，所提出的方法在均方根误差和平均绝对误差方面优于现有 QoS 预

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 is proposeproposed with considering of the hidden environmental
preference information in QoS and the common feature s of multi multi-class QoS QoS. First, QoS data is modeled as a useruser-servicservice bipartite graph graph; then , multi multi-component graph convolution neural network is used for feature extraction and mapping, and
the weighted fusion method is used for the same dimensional mapping of multi multi-cl ass of QoS features. Subsequently, t he
attention factor decomposition machine is used to extract the first first-order features, second second-order interactive features features, and
highhigh-order interactive features of the mapped feature vector . the results of each par part ar e 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 ( and average absolute error ( MAE).

Key words: joint predi ction, quality of serviceervice, preference feature, deep fusion

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.

LIU Jianxun , , DING Linghang , , KANG Guosheng , , CAO Buqing , , XIAO Yong , . Joint QoS prediction for Web services based on deep fusion of features[J]. Journal on Communications.

参考文献

[1] 方晨, 张恒巍, 张铭, et al. 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(01): 147-58.
FANG C, ZHANG H, ZHANG M, et al. Trust expansion and listwise
learning-to-rank based service recommendation method[J]. Journal on
Communications, 2018, 39(01): 147-58.
[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(09): 61-73.
ZHAO C, WANG J. Service recommendation method based on
context-embedded support vector machine[J]. Journal on
Communications, 2019, 40(09): 61-73.
[3] YIN Y, CHEN L, XU Y, et al. QoS prediction for service
recommendation with deep feature learning in edge computing
environment [J]. Mobile Networks and Applications, 2019: 1-11.
[4] WANG X, WANG R, SHI C, et al. Multi-component graph
convolutional collaborative filtering; proceedings of the Proceedings of
the AAAI Conference on Artificial Intelligence, F, 2020 [C].
[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; proceedings of the 2021
IEEE International Conference on Web Services (ICWS), F, 2021 [C].
IEEE.
[6] SHAO L, ZHANG J, WEI Y, et al. Personalized qos prediction forweb
services via collaborative filtering; proceedings of the Ieee international
conference on web services (icws 2007), F, 2007 [C]. IEEE.
[7] CHEN L, FENG Y, WU J, et al. An enhanced QoS prediction approach
for service selection; proceedings of the 2011 IEEE International
Conference on Services Computing, F, 2011 [C]. IEEE.
[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(06): 1176-81.
REN L, WANG W. Method for QoS Prediction in Mobile Edge
Computing Environment[J]. Journal of Chinese Computer Systems, vol.
41, no. 06, pp. 1176-1181, 2020.
[9] WANG S, ZHAO Y, HUANG L, et al. QoS prediction for service
recommendations in mobile edge computing [J]. Journal of Parallel and
Distributed Computing, 2019, 127: 134-44.
[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): 99-100+3.
DENG X, LV S, Research on Web Service QoS prediction based on
reputation perception and embedded learning [J]. Internet of Things
Technologies, 2021, vol. 11, no. 12, pp. 99-100+103.
[11] SALAKHUTDINOV R, MNIH A, HINTON G. Restricted Boltzmann
machines for collaborative filtering; proceedings of the Proceedings of
the 24th international conference on Machine learning, F, 2007 [C].
[12] LUO X, ZHOU M, WANG Z, et al. An effective scheme for QoS
estimation via alternating direction method-based matrix factorization
[J]. IEEE Transactions on Services Computing, 2016, 12(4): 503-18.
[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(02): 63-75.
LU C, KOU J, Personalized web service quality prediction based on
user and service area information [J]. Journal of Management Science,
2020, vol. 33, no. 02, pp. 63-75.
[14] CHEN L, XIE F, ZHENG Z, et al. Predicting quality of service via
《通信学报》
·96· 通信学报第 41 卷
leveraging locatio
leveraging location information [J]. Complexity, 2019, 2019.n information [J]. Complexity, 2019, 2019.
[15]
[15] TANG M, LIANG W, YANG Y, et al. A factorization machineTANG M, LIANG W, YANG Y, et al. A factorization machine-based based QoS prediQoS prediction approachction approach for mobile service selection [J]. IEEE Access, for mobile service selection [J]. IEEE Access, 2019, 7: 329612019, 7: 32961-70.70.
[16]
[16] 夏会 , 高旻, 邹淑 . 时空感知下基于结构相似度的时空感知下基于结构相似度的WebWeb服务质量预服务质量预测 [J]. [J]. 重庆大学学报重庆大学学报, 202, 2021, 44(01): 881, 44(01): 88-96.96. XIA H, GAO M, et al, Web service quality predict, et al, Web service quality prediction based on ion based on structural similarity under spatiostructural similarity under spatio-temptemporal perceptiooral perception [J]. Journal of n [J]. Journal of Chongqing University, Chongqing University, 20212021, vol. 44, no. 01, pp. 88vol. 44, no. 01, pp. 88-96 .
[17]
[17] 陈蕾 , 杨庚 , 陈正宇 , et al. , et al. 基于结构化噪声矩阵补全的基于结构化噪声矩阵补全的WebWeb服务 QoSQoS预测 [J]. [J]. 通信学报通信学报, 2015, 36(06): 53, 2015, 36(06): 53-63.63. CHEN CHEN L, YANGL, YANG G, CHENG, CHEN Z, et al. Z, et al. Web services QoS prediction via Web services QoS prediction via matrixmatrix compcompletion with sletion with structural noistructural noise[J]. Journal on CommunicationsJournal on Communications, 2015, 36(06): 532015, 36(06): 53-63.63.
[18]
[18] LUO X, WU H, YUAN H, et al. Temporal PatternLUO X, WU H, YUAN H, et al. Temporal Pattern-Aware QoS Aware QoS Prediction via Biased NonPrediction via Biased Non-Negative Latent FactorizatNegative Latent Factorization of Tensors [J]. ion of Tensors [J]. IEEE Trans Cybern, 2020, 5IEEE Trans Cybern, 2020, 50(5): 17980(5): 1798-809.809.
[19]
[19] KANG G, LKANG G, LIU J, XIAO Y, IU J, XIAO Y, et al. Neural and Attentional Factorization et al. Neural and Attentional Factorization MachineMachine-Based Web API Recommendation for Mashup Development Based Web API Recommendation for Mashup Development [J]. IEEE Transactions on Network and Service Management, 2021[J]. IEEE Transactions on Network and Service Management, 2021, 18(4): 418318(4): 4183-96.96.
[20]
[20] GAO H, XU Y, YIN Y, et GAO H, XU Y, YIN Y, et al. Contextal. Context-aware QoS predictiaware QoS prediction with neuralon with neural collaborative filtering for Internetcollaborative filtering for Internet-of -Things services [J]. IEEE Internet Things services [J]. IEEE Internet of Things Journal, 2019, 7(5): 4532of Things Journal, 2019, 7(5): 4532-42.
[21]
[21] 王安迪 . 基于 QoSQoS的 WebWeb服务质量预测方法研究服务质量预测方法研究 [D]; [D]; 华北电力大华北电力大学(北京 ), 202), 2020. WANG WANG A. Research on Web service quality prediction method based on Research on Web service quality prediction method based on QoS [QoS [D]; North ChinD]; North China Electric Power University (Beijing), 2020.a Electric Power University (Beijing), 2020.
[22]
[22] CHEN D, GAO M, LIU A, et al. A RecurreCHEN D, GAO M, LIU A, et al. A Recurrent Neural Network Based nt Neural Network Based Approach for Web Service QoS Prediction; proceedings of the 2019 Approach for Web Service QoS Prediction; proceedings of the 2019 2nd International Conference on Artificial Intelligence and Big D2nd International Conference on Artificial Intelligence and Big Data ata (ICAIBD), (ICAIBD), F, 2019 [C]. IEEE.F, 2019 [C]. IEEE.
[23]
[23] AK E, CANBERK B. FAK E, CANBERK B. Forecasting Quality of Service for orecasting Quality of Service for NextNext-GeneratGeneration Dataion Data-Driven WiFi6 Campus Networks [J]. IEEE Driven WiFi6 Campus Networks [J]. IEEE Transactions on Network and Service Management, 2021.Transactions on Network and Service Management, 2021.
[24]
[24] ZHANG X, LI L. Attentional Neural FactorizationZHANG X, LI L. Attentional Neural Factorization Machines for Machines for Knowledge Tracing [M]. Knowledge Science, Knowledge Tracing [M]. Knowledge Science, Engineering and Engineering and Management. 2021: 319Management. 2021: 319-30.30.
[25]
[25] RENDLE S. Factorization machines with libfm [J]. ACM Transactions RENDLE S. Factorization machines with libfm [J]. ACM Transactions on Intelligent Systems and Technology (TIST), 2012, 3(3): 1on Intelligent Systems and Technology (TIST), 2012, 3(3): 1-22.22.
[26]
[26] VASWANI A, SHAZEERVASWANI A, SHAZEER N, PARMAR N, N, PARMAR N, et al. Attention is all you et al. Attention is all you need [J]. Advaneed [J]. Advances in neural information processing systems,nces in neural information processing systems, 2017, 30.2017, 30.
[27]
[27] ZHENG Z, MA H, LYU M R, et al. QoSZHENG Z, MA H, LYU M R, et al. QoS-aware web service aware web service recommendation by collaborative filtering [J]. IEEE Transactions on recommendation by collaborative filtering [J]. IEEE Transactions on services computinservices computing, 2010, 4(2):g, 2010, 4(2): 140140-52.52.
[28]
[28] ZHENG Z, MA H, LYU M R, et aZHENG Z, MA H, LYU M R, et al. Collaborative web service qos l. Collaborative web service qos prediction viprediction via neighborhood integrated matrix factorization [J]. IEEE a neighborhood integrated matrix factorization [J]. IEEE Transactions on Services Computing, 2012, 6(3): 289Transactions on Services Computing, 2012, 6(3): 289-99.99.
[29]
[29] WU H, ZHANG Z, LUO J, et al. MultiplWU H, ZHANG Z, LUO J, et al. Multiple attributes Qe attributes QoS prediction via oS prediction via deep neural model deep neural model with contexts [J]. IEEE Transactions on Services with contexts [J]. IEEE Transactions on Services ComComputing, 2018, 14(4): 1084puting, 2018, 14(4): 1084-96.96.
[30]
[30] LOUIZOS C, WELLING M, KINGMA D P. Learning sparse neural LOUIZOS C, WELLING M, KINGMA D P. Learning sparse neural networks through networks through L0 regularization [J]. arXiv preprint regularization [J]. arXiv preprint arXiv:1arXiv:171201312, 201771201312, 2017.