College of Economic and Management, Shandong University of Science and Technology, Qingdao266590, China
Weifang Key Laboratory of Blockchain on Agricultural Vegetables, Weifang University of Science and Technology, Weifang262700, China
School of Computer Science, Qufu Normal University, Rizhao276826, China
Show Author Information
Hide Author Information
Abstract
In the mobile edge computing environments, Quality of Service (QoS) prediction plays a crucial role in web service recommendation. Because of distinct features of mobile edge computing, i.e., the mobility of users and incomplete historical QoS data, traditional QoS prediction approaches may obtain less accurate results in the mobile edge computing environments. In this paper, we treat the historical QoS values at different time slots as a temporal sequence of QoS matrices. By incorporating the compressed matrices extracted from QoS matrices through truncated Singular Value Decomposition (SVD) with the classical ARIMA model, we extend the ARIMA model to predict multiple QoS values simultaneously and efficiently. Experimental results show that our proposed approach outperforms the other state-of-the-art approaches in accuracy and efficiency.
G. E. P.Box and G. M.Jenkins, Some recent advances in forecasting and control: Part I, J. Roy. Statist. Soc. Ser. C (Appl. Statist.), vol. 17, no. 2, pp. 91-109, 1968.
C. H.Liu, S. C. H.Hoi, P. L.Zhao, and J. L.Sun, Online ARIMA algorithms for time series prediction, in Proc. 13th AAAI Conf. Artificial Intelligence, Phoenix, AZ, USA, 2016, pp. 1867-1873.
[4]
Q. Q.Shi, J. M.Yin, J. J.Cai, A.Cichocki, T.Yokota, L.Chen, M. X.Yuan, and J.Zeng, Block hankel tensor ARIMA for multiple short time series forecasting, Proc. AAAI Conf. Artif. Intell., vol. 34, no. 4, pp. 5758-5766, 2020.
S. G.Wang, Y. L.Zhao, L.Huang, J. L.Xu, and C. H.Hsu, QoS prediction for service recommendations in mobile edge computing, J. Parallel Distrib. Comput., vol. 127, pp. 134-144, 2019.
G.White, A.Palade, C.Cabrera, and S.Clarke, Autoencoders for QoS prediction at the edge, in Proc. of 2019 IEEE Int. Conf. Pervasive Computing and Communications, Kyoto, Japan, 2019, pp. 1-9.
Y. Y.Yin, L.Chen, Y. S.Xu, J.Wan, H.Zhang, and Z. D.Mai, QoS prediction for service recommendation with deep feature learning in edge computing environment, Mobile Netw. Appl., vol. 25, no. 2, pp. 391-401, 2020.
Y. W.Liu, A. X.Pei, F.Wang, Y. H.Yang, X. Y.Zhang, H.Wang, H. N.Dai, L. Y.Qi, and R.Ma, An attention-based category-aware GRU model for the next POI recommendation, Int. J. Intell. Syst., vol. 36, no. 7, pp. 3174-3189, 2021.
Y.Hu, Q. M.Peng, X. H.Hu, and R.Yang, Time aware and data sparsity tolerant web service recommendation based on improved collaborative filtering, IEEE Trans. Serv. Comput., vol. 8, no. 5, pp. 782-794, 2015.
L. Y.Qi, C. H.Hu, X. Y.Zhang, M. R.Khosravi, S.Sharma, S. N.Pang, and T.Wang, Privacy-aware data fusion and prediction with spatial-temporal context for smart city industrial environment, IEEE Trans. Ind. Inform., vol. 17, no. 6, pp. 4159-4167, 2021.
X. L.Fan, Y. K.Hu, R. S.Zhang, W. B.Chen, P.Brézillon, and X. L.Fan, Modeling temporal effectiveness for context-aware web services recommendation, in Proc. 2015 IEEE Int. Conf. Web Services, New York, NY, USA, 2015, pp. 225-232.
X. Y.Wang, J. K.Zhu, Z. B.Zheng, W. J.Song, Y. H.Shen, and M. R.Lyu, A spatial-temporal QoS prediction approach for time-aware web service recommendation, ACM Trans. Web, vol. 10, no. 1, p. 7, 2016.
X.Chen, Z. B.Zheng, X. D.Liu, Z. C.Huang, and H. L.Sun, Personalized QoS-aware web service recommendation and visualization, IEEE Trans. Serv. Comput., vol. 6, no. 1, pp. 35-47, 2013.
H. F.Sun, Z. B.Zheng, J. L.Chen, and M. R.Lyu, Personalized web service recommendation via normal recovery collaborative filtering, IEEE Trans. Serv. Comput., vol. 6, no. 4, pp. 573-579, 2013.
W.Lo, J. W.Yin, S. G.Deng, Y.Li, and Z. H.Wu, Collaborative web service QoS prediction with location-based regularization, in Proc. 2012 IEEE 19th Int. Conf. Web Services, Honolulu, HI, USA, 2012, pp. 464-471.
C. Y.Yu and L. P.Huang, A web service QoS prediction approach based on time- and location-aware collaborative filtering, Serv. Orient. Comput. Appl., vol. 10, no. 2, pp. 135-149, 2016.
L. Y.Qi, R. L.Wang, C. H.Hu, S. C.Li, Q.He, and X. L.Xu, Time-aware distributed service recommendation with privacy-preservation, Inform. Sci., vol. 480, pp. 354-364, 2019.
A.Amin, A.Colman, and L.Grunske, An approach to forecasting QoS attributes of web services based on ARIMA and GARCH models, in Proc. 2012 IEEE 19th Int. Conf. Web Services, Honolulu, HI, USA, 2012, pp. 74-81.
P. G.Jing, Y. T.Su, X.Jin, and C. Q.Zhang, High-order temporal correlation model learning for time-series prediction, IEEE Trans. Cybern., vol. 49, no. 6, pp. 2385-2397, 2019.
Y. L.Zhang, Z. B.Zheng, and M. R.Lyu, WSPred: A time-aware personalized QoS prediction framework for web services, in Proc. IEEE 22nd Int. Symp. Software Reliability Engineering, Hiroshima, Japan, 2011, pp. 210-219.
J. S.Breese, D.Heckerman, and C.Kadie, Empirical analysis of predictive algorithms for collaborative filtering, in Proc. 14th Conf. Uncertainty in Artificial Intelligence, Madison, WI, USA, 1998, pp. 43-52.
[25]
P.Resnick, N.Iacovou, M.Suchak, P.Bergstrom, and J.Riedl, GroupLens: An open architecture for collaborative filtering of netnews, in Proc. 1994 ACM Conf. Computer Supported Cooperative Work, Chapel Hill North, CA, USA, 1994, pp. 175-186.
A.Guezzaz, Y.Asimi, M.Azrour, and A.Asimi, Mathematical validation of proposed machine learning classifier for heterogeneous traffic and anomaly detection, Big Data Mining and Analytics, vol. 4, no. 1, pp. 18-24, 2021.
H. M.Huang, J. H.Lin, L. Y.Wu, B.Fang, Z. K.Wen, and F. C.Sun, Machine learning-based multi-modal information perception for soft robotic hands, Tsinghua Science and Technology, vol. 25, no. 2, pp. 255-269, 2020.
L.Wang, X. Y.Zhang, T.Wang, S. H.Wan, G.Srivastava, S. N.Pang, and L. Y.Qi, Diversified and scalable service recommendation with accuracy guarantee, IEEE Trans. Comput. Soc. Syst., .
J.Mabrouki, M.Azrour, G.Fattah, D.Dhiba, and S. ElHajjaji, Intelligent monitoring system for biogas detection based on the Internet of Things: Mohammedia, Morocco City landfill case, Big Data Mining and Analytics, vol. 4, no. 1, pp. 10-17, 2021.
L. Y.Qi, X. K.Wang, X. L.Xu, W. C.Dou, and S. C.Li, Privacy-aware cross-platform service recommendation based on enhanced locality-sensitive hashing, IEEE Trans. Netw. Sci. Eng., vol. 8, no. 2, pp. 1145-1153, 2021.
N.Bhardwaj and P.Sharma, An advanced uncertainty measure using fuzzy soft sets: Application to decision-making problems, Big Data Mining and Analytics, vol. 4, no. 2, pp. 94-103, 2021.
Y.Khazbak, J. Y.Fan, S. C.Zhu, and G. H.Cao, Preserving personalized location privacy in ride-hailing service, Tsinghua Science and Technology, vol. 25, no. 6, pp. 743-757, 2020.
L. N.Wang, X. Y.Zhang, R. L.Wang, C.Yan, H. Z.Kou, and L. Y.Qi, Diversified service recommendation with high accuracy and efficiency, Knowl.-Based Syst., vol. 204, p. 106196, 2020.
Y. P.Fu, Y. S.Hou, Z. F.Wang, X. W.Wu, K. Z.Gao, and L.Wang, Distributed scheduling problems in intelligent manufacturing systems, Tsinghua Science and Technology, vol. 26, no. 5, pp. 625-645, 2021.
J.Mabrouki, M.Azrour, D.Dhiba, Y.Farhaoui, and S. E.Hajjaji, IoT-based data logger for weather monitoring using arduino-based wireless sensor networks with remote graphical application and alerts, Big Data Mining and Analytics, vol. 4, no. 1, pp. 25-32, 2021.
N. J.Chen, Z.Wang, R. X.He, J. H.Jiang, F.Cheng, and C. H.Han, Efficient scheduling mapping algorithm for row parallel coarse-grained reconfigurable architecture, Tsinghua Science and Technology, vol. 26, no. 5, pp. 724-735, 2021.
Yan C, Zhang Y, Zhong W, et al. A Truncated SVD-Based ARIMA Model for Multiple QoS Prediction in Mobile Edge Computing. Tsinghua Science and Technology, 2022, 27(2): 315-324. https://doi.org/10.26599/TST.2021.9010040
The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).
10.26599/TST.2021.9010040.F001
QoS prediction in an edge computing environment: An intuitive example.
10.26599/TST.2021.9010040.F002
QoS data representation as a sequence of QoS matrices.
4.2 Matricized ARIMA with truncated SVD
We aim to predict all the QoS values at time slots simultaneously. Here, we formulate the problem as a TSF problem. can be considered as a sequence of matrices , where represents the historical QoS matrix at time slot . Letting denote the -order differencing of , then
As a user only invokes a tiny proportion of services, the QoS data of a user are very sparse. To reduce the computational and storage cost, we compress the columns of through the truncated SVD method, which can be represented as
where is an orthogonal factor matrix, and . is the compressed matrix of , which represents the most important feature of , but has many fewer elements than . can be recovered by and ,
The first goal of our optimization is to minimize the difference between and .
To reduce the computational cost, we incorporate the compressed matrix instead of the original QoS matrix into the ARIMA model. Therefore, the generalized ARIMA model is defined as follows:
where and are the parameters of AR and MA respectively, and is the random error terms of the past observations, which are assumed to be independent, identically distributed variables with zero mean. is the prediction error at the current time slot. Therefore, our second goal is to minimize to zero. On the basis of the two goals of our optimization, the objective function can be defined as follows:
where , which is the minimum number of time slots.
We adopt the augmented Lagrangian method, which is widely used in mathematical optimization problems, to minimize the above objective function. We first fix and , compute the partial derivation of the objective function (
11
) with respect to , and equate it to zero. Then, we can obtain the updated formulation of as follows:
Formula (
11
) with respect to is
which is equivalent to the orthogonal Procrustes problem[
22
]. Then the global optimal solution of Formula (
13
) is . and are the left and right singular vectors of the singular value decomposition of , respectively, which is calculated as
The parameters of AR and MA are typically minimized using Yule-Walker method in classical ARIMA. Calculate the partial derivation of Formula (
11
) with respect to , and equate it to zero. Then, can be updated by
Formally, we summarize the pseudo-code of the model learning process in Algorithm 1.
Then, we reconstruct the new according to Eq. (
9
). Finally, we perform inverse d-order differencing for and obtain . The pseudo-code of the prediction process can be described in Algorithm 2.
10.26599/TST.2021.9010040.F003
Convergence curves of on (a) response time and (b) throughput datasets.
10.26599/TST.2021.9010040.F004
Prediction accuracy comparison with respect to data sparsity on different datasets.
10.26599/TST.2021.9010040.F005
Time cost comparison with respect to data sparsity. The time cost of IPCC method is too large, so we truncate its bar.
10.26599/TST.2021.9010040.F006
Prediction accuracy comparison with respect to the number of time slots on different datasets.
10.26599/TST.2021.9010040.F007
Time cost comparison with respect to the number of time slots. The time cost of the IPCC method is too high, so we truncate its bar.