Quality Of Service Prediction Research Articles

Dynamic QoS Prediction Algorithm Based on Kalman Filter Modification.

With the widespread adoption of service-oriented architectures (SOA), services with the same functionality but the different Quality of Service (QoS) are proliferating, which is challenging the ability of users to build high-quality services. It is often costly for users to evaluate the QoS of all feasible services; therefore, it is necessary to investigate QoS prediction algorithms to help users find services that meet their needs. In this paper, we propose a QoS prediction algorithm called the MFDK model, which is able to fill in historical sparse QoS values by a non-negative matrix decomposition algorithm and predict future QoS values by a deep neural network. In addition, this model uses a Kalman filter algorithm to correct the model prediction values with real-time QoS observations to reduce its prediction error. Through extensive simulation experiments on the WS-DREAM dataset, we analytically validate that the MFDK model has better prediction accuracy compared to the baseline model, and it can maintain good prediction results under different tensor densities and observation densities. We further demonstrate the rationality of our proposed model and its prediction performance through model ablation experiments and parameter tuning experiments.

Web Service QoS Prediction via Collaborative Filtering: A Survey

With the growing number of competing Web services that provide similar functionality, Quality-of-Service (QoS) prediction is becoming increasingly important for various QoS-aware approaches of Web services. Collaborative filtering (CF), which is among the most successful personalized prediction techniques for recommender systems, has been widely applied to Web service QoS prediction. In addition to using conventional CF techniques, a number of studies extend the CF approach by incorporating additional information about services and users, such as location, time, and other contextual information from the service invocations. There are also some studies that address other challenges in QoS prediction, such as adaptability, credibility, privacy preservation, and so on. In this survey, we summarize and analyze the state-of-the-art CF QoS prediction approaches of Web services and discuss their features and differences. We also present several Web service QoS datasets that have been used as benchmarks for evaluating the predition accuracy and outline some possible future research directions.

Topology-Aware Neural Model for Highly Accurate QoS Prediction

With the widespread deployment of various cloud computing and service-oriented systems, there is a rapidly increasing demand for collaborative quality-of-service (QoS) prediction. Existing QoS prediction methods have made great progress in modeling users and services as well as exploiting contexts of service invocations. However, they ignore the completion of service requests/responses relies on the underlying network topology and the complex interactions between Autonomous Systems. To tackle this challenge, we propose a topology-aware neural (TAN) model for collaborative QoS prediction. In the TAN model, the features of users, services, and intermediate nodes on the communication path are projected to a shared latent space as input features. To jointly characterize the invocation process, the path features and end-cross features are captured respectively through an explicit path modeling layer and an implicit cross-modeling layer. After that, a gating layer fuses and transmits these features to the prediction layer for estimating unknown QoS values. In this way, TAN provides a flexible framework that can comprehensively capture the invocation context for making accurate QoS prediction. Experimental results on two real-world datasets demonstrate that TAN significantly outperforms state-of-the-art methods on the tasks of response time, throughput, and reliability prediction. Also, TAN shows better extensibility of using auxiliary information.

HSA-Net: Hidden-State-Aware Networks for High-Precision QoS Prediction

The high-precision QoS (quality of service) prediction is based on the comprehensive perception of state information of users and services. However, the current QoS prediction approaches have limited accuracy, for most state information of users and services (i.e., network speed, latency, network type, and more) are hidden due to privacy protection. Therefore, this article proposes a hidden-state-aware network (HSA-Net) that includes three steps called hidden state initialization, hidden state perception, and QoS prediction. A hidden state initialization approach is developed first based on the latent dirichlet allocation (LDA). After that, a hidden-state perception approach is proposed to abstract the initialized hidden state by fusing the known information (e.g., service ID and user location). The perception approach consists of four hidden-state perception (HSP) modes (i.e., known mode, object mode, hybrid mode and overall mode) implemented to generate explainable and fused features through four adaptive convolutional kernels. Finally, the relationship between the fused features and the QoS is discovered through a fully connected network to complete the high-precision QoS prediction process. The proposed HSA-Net is evaluated on two real-world datasets. According to the results, the HSA-Net's mean absolute error (MAE) index reduced by 3.67% and 28.84%, whereas the root mean squared error (RMSE) index decreased by 3.07% and 7.14% compared with ten baselines on average in the two datasets.

Assessing cloud QoS predictions using OWA in neural network methods

Quality of Service (QoS) is the key parameter to measure the overall performance of service-oriented applications. In a myriad of web services, the QoS data has multiple highly sparse and enormous dimensions. It is a great challenge to reduce computational complexity by reducing data dimensions without losing information to predict QoS for future intervals. This paper uses an Induced Ordered Weighted Average (IOWA) layer in the prediction layer to lessen the size of a dataset and analyse the prediction accuracy of cloud QoS data. The approach enables stakeholders to manage extensive QoS data better and handle complex nonlinear predictions. The paper evaluates the cloud QoS prediction using an IOWA operator with nine neural network methods—Cascade-forward backpropagation, Elman backpropagation, Feedforward backpropagation, Generalised regression, NARX, Layer recurrent, LSTM, GRU and LSTM-GRU. The paper compares results using RMSE, MAE, and MAPE to measure prediction accuracy as a benchmark. A total of 2016 QoS data are extracted from Amazon EC2 US-West instance to predict future 96 intervals. The analysis results show that the approach significantly decreases the data size by 66%, from 2016 to 672 records with improved or equal accuracy. The case study demonstrates the approach's effectiveness while handling complexity, reducing data dimension with better prediction accuracy.

A truncated SVD-based ARIMA model for multiple QoS prediction in mobile edge computing

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.

QoS-Aware Algorithm Based on Task Flow Scheduling in Cloud Computing Environment.

This paper deals with the challenging problem of scheduling users’ tasks, while taking into consideration users’ quality of service (QoS) requirements, with the objective of reducing the energy consumption of physical machines. This paper presents a model to analyze the current state of the running tasks according to the results of the QoS prediction assigned by an ARIMA prediction model optimized with Kalman filter. Then, we calculate a scheduling policy with a combined particle swarm optimization (PSO) and gravitational search algorithm (GSA) algorithms according to the QoS status analysis. Experimental results show that the proposed HPSO algorithm reduces resources consumption 16.51% more than the original hybrid algorithm, and the violation of service-level agreement (SLA) is 0.053% less when the optimized prediction model is used.

QoS Prediction Model of Cloud Services Based on Deep Learning

This letter presents a deep learning-based prediction model for the quality-of-service (QoS) of cloud services. Specifically, to improve the QoS prediction accuracy of cloud services, a new QoS prediction model is proposed, which is based on multi-staged multi-metric feature fusion with individual evaluations. The multi-metric features include global, local, and individual ones. Experimental results show that the proposed model can provide more accurate QoS prediction results of cloud services than several state-of-the-art methods.

Recurrent Neural Network Based Collaborative Filtering for QoS Prediction in IoV

As the emerging paradigm that is believed to be conducive to the development of intelligent transportation systems (ITS), Internet of Vehicles (IoV) is constructed with a number of connected heterogeneous vehicle devices which provide a variety of services. As the number of vehicle devices in IoV is growing fast, selecting the appropriate service from candidate services which are functionally equivalent is becoming an imperative task. Predicting the non-functional attribute of service invocation, namely quality of service (QoS), to ensure the optimal service selection is the mainstream direction. Considering that most of the conventional prediction methods neglect the fact that QoS values change dynamically with some objective factors, this paper proposes a recurrent neural network based collaborative filtering method called RNCF for QoS prediction. Specifically, a multi-layer GRU structure is incorporated in the framework of neural collaborative filtering to model the dynamic state of physical environments or network conditions and share the invocation records across different time slices. We conduct extensive experiments on the WSDream dataset to demonstrate the effectiveness of the proposed QoS prediction model RNCF.

QoS Prediction of Web Services Based on a Two-Level Heterogeneous Graph Attention Network

Quality of Service (QoS) prediction for Web services is a hot research topic in the field of services computing. Recently, representation learning of heterogeneous networks has attracted much attention, and specifically the relationship between users and services, as a typical heterogeneous network in which heterogeneity and rich semantic information provide a new perspective for QoS prediction. This paper proposes a novel QoS Prediction scheme based on a heterogeneous graph attention network. Our method first unitizes the user’s location information to construct an attributed user-service network. Then, considering the difference between nodes and links in the latter network, we model a heterogeneous graph neural network based on a hierarchical attention machine (HGN2HIA) that includes node- and semantic-level attentions. Specifically, node-level attention aims to learn the importance between a node and its meta-path-based neighbors, while semantic-level attention learns the importance of different meta-paths. Finally, user embedding will be generated by aggregating features from meta-path-based neighbors in a hierarchical manner, used for QoS prediction. Experimental results on the public WS-Dream dataset demonstrate the superior performance of the proposed model over the current state-of-the-art methods, with NMAE and RMSE metrics reduced by at least 2.56% and 1.3%, respectively. Furthermore, the experimental results highlight that node-level attention contributes more than semantic-level. Overall, we demonstrate that introducing these attention levels improves the QoS prediction performance.

Proactive Dual Connectivity for Automated Guided Vehicles in Outdoor Industrial Environment

5G communication systems are one of the major enabling technologies to meet the needs of Industry 4.0. This paper focuses on the use case of automated guided vehicles (AGVs) in an outdoor industrial scenario. To meet the communication requirements in these type of use cases, dual connectivity (DC) with resource aggregation in the uplink (UL) is generally proposed. However, uncontrolled use of DC schemes may negatively affect the network causing effects such as reduced network capacity, increased signaling, and increased interference. To overcome these issues, this paper proposes and evaluates the use of a proactive DC activation algorithm based on the instantaneous quality of service (QoS) and network conditions. The proposed algorithm has two phases, a first phase in which the QoS prediction is performed, and a second phase in which the DC activation decision is made. The performance evaluation of the algorithm has been carried out in two different scenarios: a single-frequency (SF) network and a dual-frequency (DF) network; and compared to two baselines. Our results show that our predictive DC algorithm is sufficiently robust and can offer benefits in terms of reduced signaling and increased UL performance, especially in scenarios with low to medium traffic load.

Predictability and Fairness in Social Sensing

We consider the design of distributed algorithms that govern the manner in which agents contribute to a social sensing platform. Specifically, we are interested in situations where fairness among the agents contributing to the platform is needed. A notable example are platforms operated by public bodies, where fairness is a legal requirement. The design of such distributed systems is challenging due to the fact that we wish to simultaneously realise an efficient social sensing platform, but also deliver a predefined quality of service to the agents (for example, a fair opportunity to contribute to the platform). In this paper, we introduce iterated function systems (IFS) as a tool for the design and analysis of systems of this kind. We show how the IFS framework can be used to realise systems that deliver a predictable quality of service to agents, can be used to underpin contracts governing the interaction of agents with the social sensing platform, and which are efficient. To illustrate our design via a use case, we consider a large, high-density network of participating parked vehicles. When awoken by an administrative centre, this network proceeds to search for moving missing entities of interest using RFID-based techniques. We regulate which vehicles are actively searching for the moving entity of interest at any point in time. In doing so, we seek to equalise vehicular energy consumption across the network. This is illustrated through simulations of a search for a missing Alzheimer's patient in Melbourne, Australia. Experimental results are presented to illustrate the efficacy of our system and the predictability of access of agents to the platform independent of initial conditions.

DeepTSQP: Temporal-aware service QoS prediction via deep neural network and feature integration

Quality of service (QoS) has been mostly applied to represent non-functional properties of web services and differentiate those with the same functionality. How to accurately predict unknown service QoS has become a hot research issue. Although existing researches have been investigated on temporal-aware service QoS prediction, conventional approaches are restricted to a couple of limitations. (1) most of them cannot well mine the time-series relationships and the interaction invocation information among users and services. (2) even although some sophisticated approaches make use of recurrent neural networks for temporal service QoS prediction, they mainly focus on the learning of user-service temporal relationship and have paid less attention to more effectively represent implicit features, resulting in low accuracy on service QoS prediction. To deal with the challenges, we propose a novel deep learning based approach called DeepTSQP to perform the task of temporal-aware service QoS prediction by feature integration. In DeepTSQP, we first present an improved temporal feature representation of users and services by integrating binarization feature and similarity feature. Then, we propose a deep neural network with gated recurrent units (GRU), learning and mining temporal features among users and services. Finally, DeepTSQP model can be trained by parameter optimization and applied to predict unknown service QoS. Extensive experiments are conducted on a large-scale real-world temporal QoS dataset WS-Dream with 27,392,643 historical QoS invocation records. The results demonstrate that DeepTSQP significantly outperforms state-of-the-art approaches for temporal-aware service QoS prediction in terms of multiple evaluation metrics.

GAIN-QoS: A Novel QoS Prediction Model for Edge Computing

With recent increases in the number of network-connected devices, the number of edge computing services that provide similar functions has increased. Therefore, it is important to recommend an optimal edge computing service, based on quality-of-service (QoS). However, in the real world, there is a cold-start problem in QoS data: highly sparse invocation. Therefore, it is difficult to recommend a suitable service to the user. Deep learning techniques were applied to address this problem, or context information was used to extract deep features between users and services. However, edge computing environment has not been considered in previous studies. Our goal is to predict the QoS values in real edge computing environments with improved accuracy. To this end, we propose a GAIN-QoS technique. It clusters services based on their location information, calculates the distance between services and users in each cluster, and brings the QoS values of users within a certain distance. We apply a Generative Adversarial Imputation Nets (GAIN) model and perform QoS prediction based on this reconstructed user service invocation matrix. When the density is low, GAIN-QoS shows superior performance to other techniques. In addition, the distance between the service and user slightly affects performance. Thus, compared to other methods, the proposed method can significantly improve the accuracy of QoS prediction for edge computing, which suffers from cold-start problem.

QoS prediction for smart service management and recommendation based on the location of mobile users

Quality of Service (QoS) directly reflects the degree to which services offered by providers satisfy the non-functional requirements of users. QoS information is not usually available as a priori to providers when recommending services to user queries, this creates uncertainty in offering right services to right queries. Recent researches in service recommendation and management mainly address the issues of sparse data prediction and user personalized recommendation. Recommendation systems require smart strategies of recommending and managing services in accordance with the user queries. Predicting the QoS requirements of user queries before recommending the services can potentially aid in offering the most suitable services to users. This paper proposes a hybrid mobile service recommendation and management model based on semantic recommendation along with location-based quality preference analysis for emerging 5G mobile networks. The proposed model can effectively predict the QoS by exploiting previously invoked services to identify the best matching mobile services based on the similarity between users and services. Performance evaluation based on a published web services dataset demonstrates an enhanced prediction accuracy with an effective reduction in time overheads when compared to other related methods.

A new QoS prediction model using hybrid IOWA-ANFIS with fuzzy C-means, subtractive clustering and grid partitioning

Quality of Service (QoS) is one of the key indicators to measure the overall performance of cloud services. The quantitative measurement of the QoS enables the service provider to manage its Service Level Agreement (SLA) in a viable way. It also supports a consumer in service selection and allows measuring the received services to comply with agreed services. There is much existing literature that tries to predict the QoS and assist stakeholders in their decision-making process. However, it is tricky to deal with multidimensional data in time series prediction methods. The computational complexity increases with an increase in data dimension, and it is a challenging task to give precise weights to each time interval. Existing prediction methods could not deal with the intricate reordering of input weights. To address this problem, we propose a novel Clustered Induced Ordered Weighted Averaging (IOWA) Adaptive Neuro-Fuzzy Inference System (ANFIS), (CI-ANFIS) model. This fuzzy time series prediction model reduces data dimension and handles the nonlinear relationship of the cloud QoS dataset. The proposed method uses an intelligent sorting mechanism that regulates uncertainty in prediction while incorporating a fuzzy neural network structure for optimal prediction results. The proposed method employs the IOWA operator to sort input arguments based on associated order-inducing variables and assign customised weights accordingly. The inputs are further classified using three fuzzy clustering methods - fuzzy c-means (FCM), subtractive clustering and grid partitioning. The inputs further pass to the ANFIS structure that takes the benefits of both the fuzzy and neural networks. The fuzzy structure in ANFIS builds understandable rules for cloud stakeholders and deals with uncertain occurrences of data. The model uses a real cloud QoS dataset extracted from the Amazon Elastic Compute Cloud (EC2) US-West instance and predict its behaviour every five minutes for the next 24 h. The proposed method is further compared with the existing twelve methods. The comparative results show that the proposed CI-ANFIS model outperforms all current techniques. The proposed approach opens a new area of research in various complex prediction problems such as stock trading, big data, complex IoT sensors, and other social computing problems.

HAP: A Hybrid QoS Prediction Approach in Cloud Manufacturing Combining Local Collaborative Filtering and Global Case-Based Reasoning

With the rapid development of cloud manufacturing (CMfg), a large number of functionally equivalent cloud services are available on the Internet, thus quality of service (QoS) prediction has become a hot issue. Since the QoS of service varies widely among users, many Collaborative Filtering (CF) approaches are recently proposed to predict the unknown QoS by extending the Pearson Correlation Coefficient (PCC) similarity. However, most existing approaches either enhance the similarity computation inadequately or ignore the data sparsity problem, and are thus vulnerable to the unreliable result. To address this problem, we propose a hybrid approach HAP for QoS prediction. First, to achieve high prediction accuracy, we employ a similarity-enhanced CF (L-CF) for local QoS prediction, in which the personalized influence of similar users and services are considered when computing PCC similarity. Second, to overcome the data sparsity problem, we propose a global QoS prediction approach based on the case-based reasoning (G-CBR) which could make full use of both user and service information. Finally, we establish an ensemble model to combine the results of two approaches. Comprehensive real-world experiments are conducted to demonstrate the effectiveness of our approach compared with other state-of-the-arts approaches, particularly when the QoS data is very sparse.

Predictive Quality of Service: The Next Frontier for Fully Autonomous Systems

Recent advances in software, hardware, computing, and control have fueled significant prog-ress in the field of autonomous systems. Notably, autonomous machines should continuously estimate how the scenario in which they move and operate will evolve within a predefined timeframe, and foresee whether or not the network will be able to fulfill the agreed quality of service (QoS). If not, appropriate countermea-sures should be taken to satisfy the application requirements. Along these lines, in this article we present possible methods to enable predictive QoS (PQoS) in autonomous systems, and discuss which use cases will particularly benefit from network prediction. Then we shed light on the challenges in the field that are still open for future research. As a case study, we demonstrate whether machine learning can facilitate PQoS in a teleoperated-driving-like use case as a function of different measurement signals.

Context and auto-interaction are all you need: Towards context embedding based QoS prediction via automatic feature interaction for high quality cloud API delivery

Cloud application programming interface (API) is a software intermediary that enables data exchange, business logic or functionality delivery between applications, infrastructures and IoT devices for supporting service oriented architecture. Currently, the number of cloud API in the Web is increasing and the number of cloud API with similar functionality is very large. Since quality of service (QoS) can well differentiate the performance of similar cloud API, QoS prediction has become the critical base for fast, personalized and high-quality cloud API selection and recommendation. However, contexts are used indirectly through context aware neighbors in most existing researches and the combined feature interactions are treated equally in previous factorization machine based methods, which together hinder the accurate QoS prediction. To address the above concerns, we first conduct data analysis on real-world QoS datasets and provide conclusive evidence to verify the necessity of incorporating contextual information and differentiating feature interaction. Then, we propose a context-aware QoS prediction approach via automatic feature interaction named CAFI. Contextual information of both user and cloud API sides are directly fed into CAFI through feature embedding. Moreover, the importance weights of feature interactions are learned by a generalized regularized dual averaging optimizer, so as to reward effective feature interaction and penalize noise feature interaction automatically. Lastly, final QoS prediction is obtained in an ensemble way by balancing the results of linear regression, automatic feature interaction and non-linear interaction. Extensive experiments on two public real-world QoS datasets demonstrate that CAFI can significantly improve QoS prediction accuracy. And the proposed CAFI approach is promising to encourage service providers provide high quality APIs and enable developer get desired cloud APIs quickly, thereby promoting the development of API economy.

QoS Prediction for 5G Connected and Automated Driving

A 5G communication system can support the demanding quality of service (QoS) requirements of many advanced vehicle-to-everything (V2X) use cases. However, safe and efficient driving, especially of automated vehicles, may be affected by sudden changes of the provided QoS. For that reason, the prediction of QoS changes and early notification of these predicted changes to vehicles recently have been enabled by 5G communication systems. This solution enables the vehicles to avoid or mitigate the effect of sudden QoS changes at the application level. This article describes how QoS prediction could be generated by a 5G communication system and delivered to a V2X application. The tele-operated driving use case is used as an example to analyze the feasibility of a QoS prediction scheme. Useful recommendations for the development of a QoS prediction solution are provided, while open research topics are identified.