Multi-access Edge Computing (MEC) deploys computation and storage resources at the network edge, enabling devices to process data and requests on nearby edge services. This reduces data transmission latency and network congestion. However, due to edge servers' volatile running status and limited resources, the reliability of edge services deployed on them fluctuates over time. This may lead to concept drifts in edge services' real-time reliability streaming data. A severe negative drift may indicate a runtime reliability anomaly in an edge service, which often impacts users' Quality of Experience (QoE). To ensure edge services' reliability, this paper proposes CS-Detection, a hierarchical approach for detecting runtime reliability anomalies based on concept drift. CS-Detection employs the compressed sensing technique to sample complex and large-scale reliability streaming data. It employs a new technique that combines Variational AutoEncoder and Energy-Based Generative Adversarial Network (E2BGAN) to estimate the anomaly level of edge services by calculating the reconstruction error and discriminant error of compressed real-time reliability streaming data. To demonstrate the usefulness of CS-Detection in ensuring the QoE of MEC systems, we present CPRest, a coordinated checkpoint-based effective rejuvenation approach for restoring the normal operation of edge services affected by runtime reliability anomalies. CPRest classifies detection results into four levels and adjusts the edge services' restart trigger time accordingly. Comprehensive experiments conducted on real-world datasets demonstrate the effectiveness and efficiency of CS-Detection compared to state-of-the-art approaches.

Driven by cloud computing, edge computing, and IoT, crossover service convergence, as a key approach for digital economy, aims to generate new services by means of a service composition technique. Mashup services recommendation, by recommending cooperatable application program interfaces (APIs) for the composite service, has emerged as an indispensable technique for crossover service convergence. However, the users’ requirements for mashup applications are complex and diverse. Traditional mashup services recommendation methods face multiple challenges: 1) user intents often have overlapping semantic boundaries that are difficult to distinguish, 2) interaction data between users and services is sparse, and 3) input features come from heterogeneous sources with inconsistent representations. This article proposes semantic-enhanced and feature-fused recommendation (SEFR), a semantic-enhanced and fusion-based mashup services recommendation approach for cross-domain service integration. First, SEFR employs SimCSE (i.e., simple contrastive learning of sentence embeddings), a Transformer-based unsupervised contrastive learning model, to extract discriminative semantic features from user inputs. Second, K-nearest neighbor (KNN) is utilized to retrieve semantically similar instances to enhance current feature representation. Third, an attention gate mechanism is leveraged to adaptively integrate the enhanced heterogeneous features. Finally, SEFR outputs the API list and category prediction results in parallel through sigmoid-activated linear layers, jointly optimized with a supervised contrastive loss. Experimental results show that SEFR improves NDCG@1 and NDCG@10 by 4.51% and 10.67%, respectively, compared to the best baseline.

By pushing computing resources from the cloud to the network edge close to mobile users, mobile edge computing (MEC) enables low latency for a wide variety of applications. Nevertheless, in dynamic MEC systems, MEC services are challenged by the risks of runtime reliability anomalies. Detecting runtime reliability anomalies for MEC services is challenging yet critical to ensuring the stability of MEC systems. The effectiveness of existing anomaly detection methods suffers from poor performance when handling MEC services’ large-volume, continuous, and volatile reliability streaming data. The key is to identify significant changes in the distribution of MEC services’ current reliability streaming data compared with their historical performance. Inspired by concept drift, this paper proposes B-Detection, a boosting Long Short-Term Memory (LSTM) Autoencoder for detecting MEC services’ runtime reliability anomalies based on distribution dissimilarity evaluation. B-Detection employs a deep learning method named LSTM Autoencoder to characterize the MEC services’ historical reliability data distribution. To cope with the challenge of modeling complex distribution characteristics of MEC services’ historical reliability streaming data and guarantee the real-time performance of B-Detection, we enhance LSTM Autoencoder with a weight-based reservoir sampling technique and an LSTM boosting algorithm. The reconstruction loss of the trained LSTM Autoencoder model is estimated for the up-to-date reliability streaming data, and the result is used to infer MEC services’ runtime reliability anomalies. The performance of B-Detection is verified through a series of experiments conducted on a real-world dataset.

Time synchronization is a fundamental requirement for wireless communication systems to work properly. Most of the existing studies focus on time synchronization among homogeneous devices. This work investigates time synchronization with heterogeneous technologies (e.g., WiFi, ZigBee, and Bluetooth) which is important for the rising Internet of Thing (IoT) scenarios where heterogeneous devices coexist. Recent advances in cross-technology communication (CTC) break the wall between heterogeneous wireless devices. In this work, we propose a new time synchronization strategy based on the CTC technique and provide a technique called TimeBee, which takes the advantage of coordination from a WiFi device to assist ZigBee devices for time synchronization. An effective method is employed so that ZigBee nodes are coordinated for time synchronization based on the received timestamps from WiFi devices. The experimental results show that TimeBee achieves global time synchronization with low time errors.

Federated learning (FL) is a machine learning technique that allows for on-site data collection and processing without sacrificing data privacy and transmission. Heterogeneity is a key challenge in federated settings. Recently, cross-technology communication (CTC) has emerged as a solution for Internet of Things (IoT) heterogeneity, enabling direct communication between different wireless devices without the need for hardware modifications or gateway intervention. For example, a sophisticated WiFi device can serve as a central coordinator for other heterogeneous devices, such as LoRa, ZigBee, Bluetooth, and LTE, leading to more efficient and ubiquitous cross-network information exchange. However, heterogeneous wireless technologies present different data transmission rates and computing resources, making it difficult to achieve high accuracy in predictions due to large amounts of multidimensional data, communication delays, transmission latency, limited processing capacity, and data privacy concerns. In this work, we propose an FL framework based on CTC for heterogeneous IoT applications, called FLCTC. To demonstrate the usability of FLCTC, we implemented FLCTC and a specific solution for forest fire prediction. FLCTC was concretely implemented as a federal deep learning based on long and short-term memory and used for forest fire prediction, addressing the challenge of data characterization in heterogeneous IoT networks. FLCTC promises to improve communication efficiency and prediction accuracy. Our platform-based evaluation results show that FLCTC is feasible, with a recall of 96% and an accuracy of 88%, offering valuable insights into the use of FL with CTC for heterogeneous IoT applications.

To meet the rapidly increasing need of computation-intensive and latency-sensitive applications, mobile edge computing (MEC) has attracted tremendous attention from both academia and industry. However, the runtime reliability of edge services fluctuates over time due to the dynamics in their internal states and the external environment. This causes the distribution of edge services’ reliability data streams to vary in the form of concept drift. Severe negative reliability drifts indicate that an edge service may be suffering from a performance anomaly or a runtime failure. To ensure the stable operation of edge services, we propose A-Detection, a concept drift-based runtime reliability anomaly detection approach for edge services adaptation. We integrate reservoir sampling and singular value decomposition (SVD) for large-scale streaming data sampling and feature extraction. Jensen Shannon (JS) divergence is utilized to develop a dissimilarity metric of data stream distribution, called FDC, for runtime edge service reliability anomaly detection. When an anomaly is detected in a running edge service, checkpoint-retry is combined with computation offloading to implement runtime reliability adaptation. Extensive experimental results verify and demonstrate the effectiveness and efficiency of A-Detection.

As a nascent technique, Mobile Edge Computing (MEC) is mushrooming with a broad application prospect. By transferring abundant computing and storage resources from cloud to edge servers close to users, it allows services to be hosted on edge servers, which greatly reduces service latency. However, due to environmental dynamics, the edge services' reliability fluctuates in real-time. When the reliability of an edge service degrades severely, it may be suffering an anomaly, which can seriously impact its real-time performance and users' quality of experience. To ensure the real-time performance of edge services, this paper presents CDCrest, a concept drift-based checkpoint restart approach for edge service rejuvenation. CDCrest employs L-Detection, a concept drift-based approach to detect edge services' runtime reliability anomalies. L-Detection leverages a sliding window and Locality Sensitive Hashing (LSH)-based sampling to extract features from an edge service's real-time and historic reliability data streams. Then, it calculates the real-time Distribution Change Degree (DCD) based on Jensen-Shannon (JS) divergence to infer whether the edge service is suffering a reliability anomaly. Once an anomaly for an edge service is identified, CDCrest employs a checkpoint restart mechanism to ensure the rapid rejuvenation of the edge service. Extensive experiments conducted based on a popular real-world dataset demonstrate the effectiveness and efficiency of CDCrest against the state-of-the-art approaches.

Summary With the development of Internet technology and the cloud service industry, an increasing number of application programming interfaces (APIs) hosted in the cloud has been made publicly available. To facilitate cloud service APIs vendors and buyers, some large‐scale software cloud directory platforms have been established. Nevertheless, it is difficult for users to choose for renting from a massive number of cloud service APIs with similar functionalities in a software cloud directory platform. Recent efforts in building cloud service APIs recommender systems can help address this challenge. Relevant existing recommendation approaches are designed based on requirement election techniques to identify users' preferences to the quality of service (QoS) of the APIs. In particular, users' preferences are mainly obtained through their self‐description, in which users sometimes cannot accurately and completely express their preferences. In this article, we propose SVD‐APIR, a singular value decomposition (SVD)‐based behavior‐aware cloud service APIs recommendation approach for large‐scale software cloud directory platforms. In SVD‐APIR, users' historical behavior information is captured and APIs' association information is analyzed to identify the users' potential preferences to the APIs with specific QoS. A unified SVD model is utilized to prioritize the users preferred APIs. Experimental evaluation results conducted on WS‐Dream dataset demonstrate the effectiveness and efficiency of the proposed approach.

Benefiting from the pay-as-you-go business model, cloud-based software applications are becoming more and more popular. A composite cloud system can be constructed by integrating existing component cloud services available over the internet as its system components. In order to fulfill the service-level agreements (SLAs), as well as users’ quality of experience (QoE), a stable execution of the constructed system is desirable in the long term. To achieve this goal, system components at high risk of failing must be identified and fault-tolerated. This is extremely challenging in the dynamic cloud environment that host the component cloud services. However, existing approaches are constrained by their lack of modeling and analysis of system components’ fluctuating reliability time series. To systematically address these issues, in this article, we propose PARS, a perturbation-aware approach, for measuring the reliability sensitivity of component cloud services. It first analyzes the negative perturbations in component cloud services’ historical reliability time series. Then, it calculates the reliability sensitivity of the component cloud services by analyzing how their reliability perturbations impact the reliability of the entire cloud system. Based on PARS, we propose a proactive adaptation approach for constructing and operating composite cloud systems with 1-out-of-2 N-version Programming fault-tolerance. This approach takes the reliability sensitivity of component cloud services estimated by PARS as input to assure the reliability of the cloud system. The results of experiments conducted on two widely used datasets demonstrate the effectiveness and efficiency of the proposed approaches in ensuring the reliability of composite cloud systems.

Benefiting from the pay-as-you-go business model, cloud computing has significantly promoted service computing techniques in real-world industrial applications. Software applications based on cloud computing are becoming more and more popular. By integrating existing component cloud services through the internet, composite cloud systems can be built to meet sophisticated application logic. Stable execution of such systems is desirable in the long term so that the service-level agreements (SLAs), as well as users’ quality of experience (QoE), can be fulfilled. To achieve this goal, it is critical to identify and fault-tolerate system components at high risks of failing. This is extremely challenging due to the dynamic and uncertainty of the cloud environment that hosts the component cloud services. Nevertheless, existing approaches pay little attention to the modeling and analysis of system components’ reliability time series. To address the above issues, we first present a reliability evaluation method for component cloud services based on the reliability model and their failure probability under continuous client-side invocation tests. Then, we propose a perturbation-aware reliability sensitivity measurement approach (named PARS) for measuring the reliability sensitivity of component cloud services. It first analyzes the negative perturbations in component cloud services’ historical reliability time series based on the Markov chain rule. Then, it calculates the reliability sensitivity of component cloud services by analyzing how their reliability perturbations impact the reliability of the entire cloud system. To guarantee the execution quality of the composite cloud system, we further propose a proactive adaptation approach named PA-PARS that enables 1-out-of-2 N-version Programming fault-tolerance for composite cloud systems based on PARS. PA-PARS takes the reliability sensitivity of component cloud services estimated by PARS as input to assure the reliability of the cloud system. It consists of four parts: 1) risky system component identification; 2) adaptation trigger; 3) candidate component cloud service selection; and 4) NVP-based system construction as the proactive adaptation for the composite cloud system. The results of experiments conducted on two widely-used datasets demonstrate the effectiveness and efficiency of the proposed approaches in ensuring the reliability of composite cloud systems.

Mobile-edge computing (or MEC) has aroused a wide attention at the 5th generation mobile networks (5G) communication era. Different edge servers (such as cloudlets, micro data centers, and base stations) have been proposed to support the MEC architecture paradigm. For the diverse loading capacities of different edge servers, computation offloading for the edge services loaded in neighboring edge servers is desired for assuring the overall serve performance as well as the Quality of Experience of users for MEC applications. To dynamically balance the computation load for neighboring edge servers, we model the optimal edge services computation offloading destination determination issue as an optimal transport distances problem in this article. We propose computation offloading via Sinkhorn's matrix scaling (COSIMS) to determine the optimal offloading destination. Experimental evaluations conducted on real-world edge computing data sets indicate that COSIMS can guarantee that the neighboring edge servers cooperatively provide effective services to mobile users with least extra communication hops.

The widespread adoption of service computing allows software to be developed by outsourcing open cloud services (i.e., SOAP-based or RESTful Web APIs) through mashup or service composition techniques. Fault tolerance for the purpose of assuring the stable execution for cloud-based software (or CBS) application has attracted great attention in coping with a loosely coupled CBS operating under dynamic and uncertain running environments. It is too expensive to rent massively redundant cloud services for CBS fault tolerance application. To reduce budget but guarantee the effectiveness of CBS fault tolerance, identifying critical components within a CBS composite system is of significant importance. We integrate CBS composite system architecture analysis and reliability sensitivity analysis approaches and propose an Architecture-based Reliability-sensitive Criticality Measure (or ARCMeas) method in this paper. We verify ARCMeas application through a cost-effective fault tolerance CBS by presenting a particle swarm optimization (PSO)-based cost-effective fault tolerance strategy determination (or PSO-CFTD) algorithm. Experimental results suggest the effectiveness of the approach.

Service computing is an emerging technology in System of Systems Engineering (SoS Engineering or SoSE), which regards a System as a Service, and aims at constructing a robust and value-added complex system by outsourcing external component systems through service composition. The burgeoning Big Service computing just covers the significant challenges in constructing and maintaining a stable service-oriented SoS. A service-oriented SoS runs under a volatile and uncertain environment. As a step toward big service, service fault tolerance (FT) can guarantee the run-time quality of a service-oriented SoS. To successfully deploy FT in an SoS, online reliability time series prediction, which aims at predicting the reliability in near future for a service-oriented SoS arises as a grand challenge in SoS research. In particular, we need to tackle a number of big data related issues given the large and fast increasing size of the historical data that will be used for prediction purpose. The decision-making of prediction solution space be more complex. To provide highly accurate prediction results, we tackle the prediction challenges by identifying the evolution regularities of component systems' running states via different machine learning models. We present in this paper the motifs-based Dynamic Bayesian Networks (or m_DBNs) to perform one-step-ahead online reliability time series prediction. We also propose a multi-steps trajectory DBNs (or multi_DBNs) to further improve the accuracy of future reliability prediction. Finally, a Convolutional Neural Networks (CNN)-based prediction approach is developed to deal with the big data challenges. Extensive experiments conducted on real-world Web services demonstrate that our models outperform other well-known approaches consistently.

As the number of Cloud services is growing at a tremendous speed, there is an increasing number of service providers offering similar functionalities. Selecting services with user desired non-functional properties (NFPs) becomes of significant importance but triggers a number of Big Data related research issues. First, the selection decision should deal with a large volume of service NFPs data. Second, service selection needs to reflect diverse user preferences, including both qualitative and quantitative ones. Third, the uncertainty of the network and service load leads to high variability in NFPs. Fourth, as the trust values of service NFPs are collected via historic user's feedbacks,it brings the veracity dimension to the NFPs of services. Fifth, multiple and sometimes conflicting decision objectives for optimal service selection should be balanced. An effective service selection mechanism is in demand that can tackle all the above Big Data challenges in an integrated way to handle the highly diverse QoS with significant variability along with the trust related issues giving rise to data veracity. Existing investigations focus on either users' QoS preferences or their trust concerns but fail to provide a systematic solution to integrate both criteria in the selection process. In this paper, we tackle heterogeneous preference- and trust-based service selection by developing a novel multi-objective optimization approach to make trade-off decision between service's trust value and user's QoS preference to rank candidate Cloud services based on their match degrees with users' requirements. We conduct extensive experiments to evaluate the effectiveness and efficiency of the proposed approach.

A service-oriented System of Systems (SoS) considers a system as a service and constructs a robust and value-added SoS by outsourcing external component systems through service composition techniques. Online reliability prediction for the component systems for the purpose of assuring the overall Quality of Service (QoS) is often a major challenge in coping with a loosely coupled SoS operating under dynamic and uncertain running environments. It is also a prerequisite for guaranteeing runtime QoS of a SoS through optimal service selection for reliable system construction. We propose a novel online reliability time series prediction approach for the component systems in a service-oriented SoS. We utilize Probabilistic Graphical Models (PGMs) to yield near-future, time series predictions. We assess the approach via invocation records collected from widely used real Web services. Experimental results have confirmed the effectiveness of the approach.

Cloud computing is a new computing paradigm which features renting the computation devices instead of buying them. In a typical cloud computing environment, there will always be different kinds of cloud resources and a number of cloud services making use of cloud resources to run on. As we can see, these cloud services usually have different performance traits. Some may be I/O-intensive, like those data querying services, while others might demand more CPU cycles, like 3D image processing services. Meanwhile, cloud resources also have different kinds of capabilities such as data processing, I/O throughput, 3D image rendering, etc. A simple fact is that allocating a suitable resource will greatly improve the performance of the cloud service, and make the cloud resource itself more efficient as well. In this paper, a new cloud resource allocating algorithm via fitness-enabled auction is proposed to guarantee the fitness of performance traits between cloud resources (sellers) and cloud services (buyers). We study the allocating algorithm in terms of economic efficiency and system performance, and experiments show that the allocation is far more efficient in comparison with the continuous double auction in which the idea of fitness is not introduced.

Service composition is an emerging technology in System of Systems Engineering (SoS Engineering or SoSE), which aims to construct a robust and value-added complex system by outsourcing external component systems. A serviceoriented SoS runs under a dynamic and uncertain environment. To assure the overall Quality of Service (QoS), online reliability time series prediction, which aims to predict the reliability in near future for service-oriented SoS arises as a grand challenge in SoS research. In this paper, we tackle the prediction challenge by exploiting two Markov independence assumptions resulted from the special system dynamics of a SoS environment. A novel motifs-based Dynamic Bayesian Networks model is proposed that supports the independence assumptions. Experimental results conducted on real Web services demonstrate the effectiveness of our approach.