Large-scale Web Services Research Articles

Reducing Mobile Web Latency Through Adaptively Selecting Transport Protocol

To improve the performance of mobile web services, a new transport protocol, QUIC, has been recently proposed as a substitute for TCP. However, with pros and cons of QUIC, it is challenging to decide whether and when to use QUIC in large-scale real-world mobile web services. Complex temporal correlation of network conditions, high user heterogeneity in a nationwide deployment, implementation diversity of QUIC variants limited, and resources on mobile devices all affect the selection of transport protocols. In this paper, we present WiseTrans, an adaptive transport protocol selection mechanism, to switch transport protocols for mobile web services online and improve the completion time of web requests. WiseTrans introduces machine learning techniques to deal with temporal heterogeneity, makes decisions with historical information to handle spatial heterogeneity, adopts an online learning method to keep pace with implementation variation, and switches transport protocols at the request level to reach high performance with acceptable overhead. We implement WiseTrans on two platforms (Android and iOS) in a popular mobile web service application of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Baidu</i> . Comprehensive experiments demonstrate that WiseTrans can reduce request completion time by up to 25.8% on average compared to the usage of a single protocol.

A Kalman-Filter-Incorporated Latent Factor Analysis Model for Temporally Dynamic Sparse Data.

With the rapid development of services computing in the past decade, Quality-of-Service (QoS)-aware selection of Web services has become a hot yet thorny issue. Conducting warming-up tests on a large set of candidate services for QoS evaluation is time consuming and expensive, making it vital to implement accurate QoS-estimators. Existing QoS-estimators barely consider the temporal patterns hidden in QoS data. However, such data are naturally time dependent. For addressing this critical issue, this study presents a Kalman-filter-incorporated latent factor analysis (KLFA)-based QoS-estimator for accurate representation to temporally dynamic QoS data. Its main idea is to make the user latent features (LFs) time dependent, while the service ones time consistent. A novel iterative training scheme is designed, where the user LFs are learned through a Kalman filter for precisely modeling the temporal patterns, and the service ones are alternatively trained via an alternating least squares algorithm for precisely representing the historical QoS data. Empirical studies on large-scale and real Web service QoS datasets demonstrate that the proposed KLFA model significantly outperforms state-of-the-art QoS-estimators in estimation accuracy for dynamic QoS data.

Efficient KPI Anomaly Detection Through Transfer Learning for Large-Scale Web Services

Timely anomaly detection of key performance indicators (KPIs), <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g.</i> , service response time, error rate, is of utmost importance to Web services. Over the years, many unsupervised deep learning-based anomaly detection approaches have been proposed. To achieve good performance, they require a long period of KPI data for model training, which is not easy to guarantee with frequent service changes. Additionally, the training overhead is too significant for the vast number of KPIs in large-scale Web services. To address the problems, we propose an unsupervised KPI anomaly detection approach, named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">AnoTransfer</i> , by combining a novel Variational Auto-Encoder (VAE)-based KPI clustering algorithm with an adaptive transfer learning strategy. Extensive evaluation experiments using real-world data collected from several large-scale Web service providers demonstrate that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">AnoTransfer</i> reduces the average initialization time by 65.71% and improves the training efficiency by 50.62 times, without significantly degrading anomaly detection accuracy.

Improved Hunting Search Algorithm for Web Service Composition Optimization

With the rapid development and application of Web services, the problem of Web service composition optimization based on Quality of Service (QoS) has become a research hotspot in the field of service computing. There are many researches on hunting search algorithm in continuous optimization problems, however, there are few researches using it to solve Web service composition optimization. In this paper, we propose an improvement on the hunting search algorithm (IHuS). It introduces an elite guidance strategy to accelerate the convergence of the algorithm, and at the same time it learns from the mutation strategy in the GA algorithm to improve the diversity of combined services. Compared with the standard HuS and GA algorithms, the experimental results demonstrate that IHuS has faster convergence speed and better optimization performance in solving large-scale Web service composition problems.

Web Service Slicing: Intra and Inter-Operational Analysis to Test Changes

We introduce Web Service Slicing, a technique that captures a functional subset of a large-scale web service using an interface slice captured as a WSDL slice (a subset of a service's WSDL). An interface (WSDL) slice provides access to an interoperable slice, which is a functional subset of the service's code. The technique uses intra-operational and inter-operational analysis to identify web service changes. With the aid of an associative code-test mapping, we leverage the identification of affected operations to reduce the cost of web-service regression testing by extracting a subset of the existing test cases. Used in conjunction with a web service slice, this subset reduces the cost of web-service regression testing by enabling the running of fewer tests. Furthermore, we exploit two approaches: Operationalized Regression Testing of Web Services (ORTWS) and Parameterized Regression Testing of Web Services (PRTWS). ORTWS effectively tests intra-operational changes at the WSDL and WS-code levels, while PRTWS tests inter-operational changes involving inter-operational dependencies due to primary parameters. Finally, we present results obtained using our prototype implementation, AWSCM (Automated Web Service Change Management), in two case-study experiments that serve to illustrate the reduction potential of the technique using eight real-world web services.

Formal foundations of serverless computing

Serverless computing (also known as functions as a service) is a new cloud computing abstraction that makes it easier to write robust, large-scale web services. In serverless computing, programmers write what are called serverless functions, which are programs that respond to external events. When demand for the serverless function spikes, the platform automatically allocates additional hardware and manages load-balancing; when demand falls, the platform silently deallocates idle resources; and when the platform detects a failure, it transparently retries affected requests. In 2014, Amazon Web Services introduced the first serverless platform, AWS Lambda, and similar abstractions are now available on all major cloud computing platforms. Unfortunately, the serverless computing abstraction exposes several low-level operational details that make it hard for programmers to write and reason about their code. This paper sheds light on this problem by presenting λ λ , an operational semantics of the essence of serverless computing. Despite being a small (half a page) core calculus, λ λ models all the low-level details that serverless functions can observe. To show that λ λ is useful, we present three applications. First, to ease reasoning about code, we present a simplified naive semantics of serverless execution and precisely characterize when the naive semantics and λ λ coincide. Second, we augment λ λ with a key-value store to allow reasoning about stateful serverless functions. Third, since a handful of serverless platforms support serverless function composition, we show how to extend λ λ with a composition language and show that our implementation can outperform prior work.

TerrierTail: Mitigating Tail Latency of Cloud Virtual Machines

Large-scale online services parallelize sub-operations of a user’s request across a large number of physical machines (service components) so as to enhance the responsiveness. Even a temporary spike in latency of any service component can notably inflate the end-to-end delay; therefore, the tail of the latency distribution of service components has become a subject of intensive research. The key characteristics of clouds such as elasticity and on-demand resource provisioning have made clouds attractive for hosting large-scale online services wherein VMs are the building blocks of services. However, adherence to traditional hypervisor scheduling policies has led to unpredictable CPU access latencies for virtual CPUs (vCPUs) that are responsible for performing network IO processes. This has resulted in poor and unpredictable performance for network IO, exacerbating VMs’ long tail latencies and discouraging the hosting of large-scale parallel web services on virtualized clouds. This paper presents TerrierTail, a hypervisor CPU scheduler whose primary goal is to trim the tail of the latency distribution of individual VMs in virtualized clouds. In TerrierTail, we have modified the network driver to identify vCPUs that are responsible for performing network IO processes. Leveraging this information, the TerrierTail scheduler mitigates the CPU access latencies of such vCPUs using novel scheduling policies, resulting in a higher and more predictable network IO performance and therefore lower tail latency. TerrierTail’s gains come at no measurable negative impacts on other performance attributes (e.g., fairness) or on the performance of VMs running other types of workloads (e.g., CPU-intensive VMs). A prototype implementation of TerrierTail in the Xen hypervisor substantially outperforms the default Credit scheduler of Xen. For example, TerrierTail mitigates the tail latency of a Memcached server by up to 53 percent and an RPC server by up to 50 percent at 99.9th percentile.

CTS: An operating system CPU scheduler to mitigate tail latency for latency-sensitive multi-threaded applications

Large-scale interactive Web services break a user’s request to many sub-requests and send them to a large number of independent servers so as to consult multi-terabyte datasets instantaneously. Service responsiveness hinges on the slowest server, making the tail of the latency distribution of individual servers a matter of great concern. A large number of latency-sensitive applications hosted on individual servers use thread-driven concurrency model wherein a thread is spawned for each user connection. Threaded applications rely on the operating system CPU scheduler for determining the order of thread execution. Our experiments show that the default Linux scheduler (CFS) idiosyncrasies result in LCFS (Last Come First Served) scheduling of threads belonging to the same application. On the other hand, studies have shown that FCFS (First Come First Served) scheduling yields the lowest response time variability and tail latency, making the default scheduler of Linux a source of long tail latency for multi-threaded applications. In this paper, we present CTS, an operating system CPU scheduler to trim the tail of the latency distribution for latency-sensitive multi-threaded applications while maintaining the key characteristics of the default Linux scheduler (e.g., fairness). By adding new data structures to the Linux kernel, CTS tracks threads belonging to an application in a timely manner and schedules them in FCFS manner, mitigating the tail latency. To keep the existing features of the default Linux scheduler intact, CTS keeps CFS responsible for system-wide load balancing and core level process scheduling; CTS merely schedules threads of the CFS chosen process in FCFS order, ensuring tail latency mitigation without sacrificing the default Linux scheduler properties. Experiments with a prototype implementation of CTS in the Linux kernel demonstrate that CTS significantly outperforms the Linux default scheduler. For example, CTS mitigates the tail latency of a Null RPC server by up to 96%, a Thrift server by up to 90% and an Apache Web server by up to 51% at 99.9th percentile.

A Web service search engine for large-scale Web service discovery based on the probabilistic topic modeling and clustering

With the ever increasing number of Web services, discovering an appropriate Web service requested by users has become a vital yet challenging task. We need a scalable and efficient search engine to deal with the large volume of Web services. The aim of this approach is to provide an efficient search engine that can retrieve the most relevant Web services in a short time. The proposed Web service search engine (WSSE) is based on the probabilistic topic modeling and clustering techniques that are integrated to support each other by discovering the semantic meaning of Web services and reducing the search space. The latent Dirichlet allocation (LDA) is used to extract topics from Web service descriptions. These topics are used to group similar Web services together. Each Web service description is represented as a topic vector, so the topic model is an efficient technique to reduce the dimensionality of word vectors and to discover the semantic meaning that is hidden in Web service descriptions. Also, the Web service description is represented as a word vector to address the drawbacks of the keyword-based search system. The accuracy of the proposed WSSE is compared with the keyword-based search system. Also, the precision and recall metrics are used to evaluate the performance of the proposed approach and the keyword-based search system. The results show that the proposed WSSE based on LDA and clustering outperforms the keyword-based search system.

GACRM: A dynamic multi-Attribute decision making approach to large-Scale Web service composition

The problem of QoS-aware Web service composition (QWSC), i.e., how to select from a pool of candidate services to construct a composite service with the best overall QoS performance, is an NP-hard problem. To address a large-scale QWSC problem, a novel method is proposed based on information theory, multi-attribute decision making (MADM) and genetic algorithm. To capture complex judgments, the QWSC problem is formulated into a MADM representation which aims to find acceptable solutions assessed by multiple QoS attributes with varying distributions. To solve the MADM problem for QWSC, each QoS attribute is weighted in both a priori, subjective perspective and a posteriori, information-based perspective based on the discriminative capability of QoS attributes for a dynamic pool of candidate services. Furthermore, to solve the large-scale QWSC problem that conventional MADM methods cannot navigate, we develop a GACRM algorithm by integrating genetic algorithm (GA) with Compromise Ratio Method (CRM). Experiments demonstrate that GACRM obtains nearly the same solution ranking by the CRM but scales much better in terms of computation time for large-scale QWSC problems.

PHash: A memory-efficient, high-performance key-value store for large-scale data-intensive applications

Abstract Large-scale data-intensive web services are evolving faster than ever, accelerating global growth in data usage and traffic at a rapid rate. This rapid growth is demanding the expansion of high-cost data infrastructures, which also underscores the industry’s need for cost-effective, high-performance distributed key-value stores. Designing key-value stores often involves a trade-off between performance and memory usage. For example, many previous studies focusing on minimizing the memory usage have developed on-disk indexing schemes, leading to lower performance. An alternative design based on in-memory indexing allows better performance, but at the expense of greater memory usage. This paper proposes a novel key-value store called PHash (Packed Hash) based on an advanced design of index and data structures that ensures both high performance and small memory usage. These advantages make the proposed scheme a better fit for processing demanding workloads in large-scale data-intensive applications. Compared to the best-performing competitor, FAWN-DS, the proposed scheme significantly reduces the memory consumption (bytes per key-value) by 83% and improves the GET throughput by up to 27.3% while the PUT throughput decreases by 12.6%. In particular, the GET performance of the proposed scheme reaches up to 99.4% of the optimal performance of the raw SSD (Solid State Drive).

RProtoBuf: Efficient Cross-Language Data Serialization inR

Modern data collection and analysis pipelines often involve a sophisticated mix of applications written in general purpose and specialized programming languages. Many formats commonly used to import and export data between different programs or systems, such as CSV or JSON, are verbose, inefficient, not type-safe, or tied to a specific programming language. Protocol Buffers are a popular method of serializing structured data between applications - while remaining independent of programming languages or operating systems. They offer a unique combination of features, performance, and maturity that seems particularly well suited for data-driven applications and numerical computing. The RProtoBuf package provides a complete interface to Protocol Buffers from the R environment for statistical computing. This paper outlines the general class of data serialization requirements for statistical computing, describes the implementation of the RProtoBuf package, and illustrates its use with example applications in large-scale data collection pipelines and web services.

Correlation consistency constrained matrix completion for web service tag refinement

With the permeation of web 2.0, large-scale web services with tags are easily available on websites. However, the noisy and incomplete correspondence between web services and tags impedes the tag related web service applications. To address this challenge, a Matrix Completion based Web Service Tag Refinement (MCWSTR) framework is proposed. Firstly, the MCWSTR framework naturally formulates the web service tag refinement problem as a Correlation Consistency Constrained Matrix Completion (C3MC) problem, which jointly model content correlation consistency and tag correlation consistency among web services and tags. Secondly, the MCWSTR framework employs an efficient Fixed Point Iterative algorithm based on Operator Splitting technique to solve the C3MC problem, Experimental results on the real-world web services collection show the encouraging performance of our proposed MCWSTR framework.

Face hallucination and recognition in social network services

Due to the rapid growth of social network services such as Facebook and Twitter, incorporation of face recognition in these large-scale web services is attracting much attention in both academia and industry. The major problem in such applications is that visual data provided are in general noisy, low resolution, prone to degradation due to lighting and other adverse effects. This paper proposes a novel face hallucination method with an aim of improving face recognition performance with the photography in social media data, which is modeled as a progressive process which explores the specific face characteristics and priors based on frequency bands analysis. In the first stage of our algorithm, initially estimated middle-resolution images are generated based on a patch-based learning method in discrete cosine transformation (DCT) domain as the first-scale restoration image. According to the relationship between the high-resolution face images and their lower resolution ones, the DC coefficients and AC coefficients are estimated separately. In the second stage, aiming at generating more refined high-resolution face images, a DCT up-sample algorithm emphasizing on low-frequency bands preserving is applied. Meanwhile, an interpolation-based method is presented in spatial domain to obtain high-frequency bands. Extensive experiments show that the proposed algorithm effectively helps improving the recognition performance of low-resolution faces.

Dynamic composition of Web services using efficient planners in large-scale service repository

Web services as independent software components are published by service providers over the Internet and invoked by service requesters for their desired functionalities. In many cases, however, there is no single service in a Web service repository satisfying a service request. So how to design an efficient method for composing a chain of connected services has become an important research issue. Recently, much research has been done into the search time reduction when finding a composite service. However, most methods take a long time for traversing all of the Web services in a service repository, thus it makes their response time significantly overrun a user’s waiting patience. This paper develops an efficient approach for automatic composition of Web services using the state-of-the-art Artificial Intelligence (AI) planners, where a Web service composition (WSC) problem is regarded as a WSC planning problem. Unlike most traditional WSC methods that traverse a Web service repository many times, our approach converts a Web service repository into a planning domain in PDDL just once, which will only be regenerated when the Web service repository changes. This treatment substantially reduces the response time and improves the scalability of solving WSC problems. We have implemented a prototype system and conducted extensive experiments on large-scale Web service repositories. The experimental results demonstrate that our proposed approach outperforms the state-of-the-art.

Performance evaluation of NoSQL big-data applications using multi-formalism models

Starting with the birth of Web 2.0, the quantity of data managed by large-scale web services has grown exponentially, posing new challenges and infrastructure requirements. This has led to new programming paradigms and architectural choices, such as map-reduce and NoSQL databases, which constitute two of the main peculiarities of the specialized massively distributed systems referred to as Big Data architectures. The underlying computer infrastructures usually face complexity requirements, resulting from the need for efficiency and speed in computing over huge evolving data sets. This is achieved by taking advantage from the features of new technologies, such as the automatic scaling and replica provisioning of Cloud environments. Although performances are a key issue for the considered applications, few performance evaluation results are currently available in this field. In this work we focus on investigating how a Big Data application designer can evaluate the performances of applications exploiting the Apache Hive query language for NoSQL databases, built over a Apache Hadoop map-reduce infrastructure.This paper presents a dedicated modeling language and an application, showing first how it is possible to ease the modeling process and second how the semantic gap between modeling logic and the domain can be reduced, by means of vertical multiformalism modeling.

Web service execution model for cloud environment

Web services describe a standardized way of integrating Web-based applications. In recent days, with the advancement of cloud computing, web services play pivoting roles towards meeting complex business objectives on a large scale. However, engineering dynamic web services is a complex task as they can be added, modified and deleted on the fly and even without any prior notification. Executing a large scale business process using dynamic web services is very challenging. This paper proposes an execution machine, called Web Service Dynamic Execution Machine ( WSDE machine), which works in the execution layer of the three layered architecture for web service dynamics [23]. The proposed machine is capable of executing business processes having both deterministic and non-deterministic flows, where the related web services are represented using a graph-based semantic based formal model. The generic nature of the WSDE machine is useful in improving performance, scalability and maintainability of large scale web service based information systems. In this paper, the proposed WSDE machine is also illustrated with a suitable case study.

On Internet Resources Service System Based on SN-Network Service Mmodel and SOA Framework

In recent years, the number and size of Web services on the Internet have a rapid development. Industry and academia start to study the web service. In Internet resources, if the web cannot be found, the web service will become meaningless. So for web services, large-scale managements and problems are the keys of the study of Internet service resources. This paper studies large-scale distributed web services in network resources based on SOA architecture ideas. It also designs the unified management and organization system of ideological and political education which treat the ideological and political education as the content. It proposes SN network resource service model of ideological and political education. With the development and popularization of the Internet today, the study on Internet resources of ideological and political education in this paper provides a theoretical reference for the innovation of the ideological and political education.

A Community Based Algorithm for Large Scale Web Service Composition

Web service composition is the process of synthesizing a new composite service using a set of available Web services in order to satisfy a client request that cannot be treated by any available Web services. The Web services space is a dynamic environment characterized by a huge number of elements. Furthermore, many Web services are offering similar functionalities. In this paper we propose a model for Web service composition designed to address the scale effect and the redundancy issue. The Web services space is represented by a two-layered network architecture. A concrete similarity network layer organizes the Web services operations into communities of functionally similar operations. An abstract interaction network layer represents the composition relationships between the sets of communities. Composition synthesis is performed by a two-phased graph search algorithm. First, the interaction network is mined in order to discover abstract solutions to the request goal. Then, the abstract compositions are instantiated with concrete operations selected from the similarity network. This strategy allows an efficient exploration of the Web services space. Furthermore, operations grouped in a community can be easily substituted if necessary during the composition's synthesis's process.

The tail at scale

Software techniques that tolerate latency variability are vital to building responsive large-scale Web services.