A Missing QoS Prediction Approach via Time-Aware Collaborative Filtering
Endong Tong, Wenjia Niu, Jiqiang Liu · IEEE Transactions on Services Computing · 2021
Quality of Service (QoS) guarantee is an important issue in building service-oriented applications. Generally, someQoSvalues of a service are unknown to its users who have never invoked the service before. Fortunately, collaborative filtering (CF)-based methods are proved feasible for missingQoSprediction and have been widely used. However, these methods seldom took the temporal factors into consideration. Indeed, historicalQoSvalues contain more information about user (or service) similarity. Furthermore, as the application environment is dynamic, obtainedQoSvalues usually have short timeliness. Hence, using outdatedQoSvalues will largely decrease the prediction accuracy. In order to resolve this issue, we proposed a time-aware collaborative filtering approach. First, we proposed aQoSmodel to filter out outdatedQoSvalues, and divided the obtainedQoSvalues into several time slices. Then, we computed the average value of historicalQoSas temporalQoSforecast. In addition, by introducing time-aware similarity computation mechanism, we succeeded to select real similar neighbor users (or services) and further predict theCF-basedQoSbased onCFtechnology. Finally, we can predict the final missingQoSby combining temporalQoSforecast andCF-basedQoSprediction. Experiment results show that our approach can receive better prediction precision.