A Probability Distribution and Location-aware ResNet Approach for QoS Prediction

Abstract

In recent years, the number of online services has grown rapidly, invoking the required services through the cloud platform has become the primary trend. How to help users choose and recommend high-quality services among huge amounts of unused services has become a hot issue in research. Among the existing QoS prediction methods, the collaborative filtering (CF) method can only learn low-dimensional linear characteristics, and its effect is limited by sparse data. Although existing deep learning methods could capture high-dimensional nonlinear features better, most of them only use the single feature of identity, and the problem of network deepening gradient disappearance is serious, so the effect of QoS prediction is unsatisfactory. To address these problems, we propose an advanced probability distribution and location-aware ResNet approach for QoS Prediction (PLRes). This approach considers the historical invocations probability distribution and location characteristics of users and services, and first uses the ResNet in QoS prediction to reuses the features, which alleviates the problems of gradient disappearance and model degradation. A series of experiments are conducted on a real-world web service dataset WS-DREAM. At the density of 5%–30%, the experimental results on both QoS attribute response time and throughput indicate that PLRes performs better than the existing five state-of-the-art QoS prediction approaches.

Web Information Systems Engineering – WISE 2023

“…The problem of QoS prediction has been widely studied in the literature [11,21,14,9,18]. We distinguish particularly two categories: 1-CF-based and 2-DNNbased approaches.…”

“…Then, the values of the next temporal QoS matrice are predicted. In [18], the authors proposed a model based on ResNet. A user and a service are represented by a multidimensional vector through an embedding layer.…”

“…With the proliferation of IoT devices and their services, this remains a challenging concern. QoS prediction presents an interesting alternative to cope with this issue [21,14,9,18]. Mainly, the existing approaches use Collaborative Filtering (CF) method.…”

“…In recent years, Deep Neural Network (DNN) based models have been explored [5,17,18]. Mainly, they combine DNN with CF-based methods.…”

“…Despite such hybrid methods enhance the efficiency of the classical CF-based approaches, they remain limited to making real-time QoS prediction for large-scale systems. The fully DNN-based models address these drawbacks [18]. Despite their advancements and performance, they require to inventory beforehand all the services for which it could be necessary to predict their QoS values.…”