QoS Prediction for Reliable Service Composition in IoT

White, Gary; Palade, Andrei; Clarke, Siobhán

doi:10.1007/978-3-319-91764-1_12

Cited by 22 publications

(17 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In such settings, collaborative approaches like Matrix Factorization (MF) are used to predict missing values in the Quality of Service (QoS) vectors of various services. Some of the main contributions include [8,21,23,26,27,30]. All these works predict missing values for Response Time (RT) and THP, under various matrix densities and dimensionalities of learning algorithms.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Parametric Analysis of Reliability and Energy Consumption in IoT: A Deep Learning Approach

Ateeq

Ishmanov

Afzal

et al. 2019

Sensors

View full text Add to dashboard Cite

Small-to-medium scale smart buildings are an important part of the Internet of Things (IoT). Wireless Sensor Networks (WSNs) are the major enabler for smart control in such environments. Reliability is among the key performance requirements for many loss-sensitive IoT and WSN applications, while Energy Consumption (EC) remains a primary concern in WSN design. Error-prone links, traffic intense applications, and limited physical resources make it challenging to meet these service goals—not only that these performance metrics often conflict with one another, but also require solving optimization problems, which are intrinsically NP-hard. Correctly forecasting Packet Delivery Ratio (PDR) and EC can play a significant role in different loss-sensitive application environments. With the ever-increasing availability of performance data, data-driven techniques are becoming popular in such settings. It is observed that a number of communication parameters like transmission power, packet size, etc., influence metrics like PDR and EC in diverse ways. In this work, different regression models including linear, gradient boosting, random forest, and deep learning are used for the purpose of predicting both PDR and EC based on such communication parameters. To evaluate the performance, a public dataset of the IEEE 802.15.4 network, containing measurements against more than 48,000 combinations of parameter configurations, is used. Results are evaluated using root mean square error and it turns out that deep learning achieves up to 98% accuracy for both PDR and EC predictions. These prediction results can help configure communication parameters taking into account the performance goals.

show abstract

Section: Related Workmentioning

confidence: 99%

“…MF is used in Refs. [21,23], whereas Ref. [27] proposes long short-term memory for the same purpose.…”

Section: Related Workmentioning

confidence: 99%

Multi-Parametric Analysis of Reliability and Energy Consumption in IoT: A Deep Learning Approach

Ateeq

Ishmanov

Afzal

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…The population of such solutions form the Pareto-optimal set (Pareto-front) [14,23], and are generally identified using non-dominated sorting techniques [15]. While the QoS values of each service in the graph can generally be estimated using existing QoS prediction mechanisms [27], finding valid paths in this dynamic graph is challenging. The QoS values of services may be time-dependent, or services may become un-available because of the mobility of service providers.…”

Section: Problem Descriptionmentioning

confidence: 99%

Stigmergic Service Composition and Adaptation in Mobile Environments

Palade

Cabrera

White

et al. 2018

Service-Oriented Computing

Self Cite

View full text Add to dashboard Cite

Users within a limited geographic area can form servicesharing communities using the services deployed on their mobile devices. Creating Quality of Service (QoS) optimal service compositions in such decentralised and dynamic environments is challenging because of the service providers' mobility and the inherent dynamism in the available services. Existing proposals for mobile environments either use templatematching composition or require a-priori knowledge about the QoS objectives' weights, which limits the composition's flexibility in such environments. This paper presents a stigmergic-based approach to model the decentralised, flexible and dynamic service interactions of providers in a mobile environment. A nature-inspired optimisation mechanism is used to approximate the set of QoS optimal compositions that result from these interactions. To facilitate adaptation of the composite during execution, we introduce a procedure that encourages the exploration of service composition configurations that emerge as a result of providers' mobility. We evaluate the performance of the proposed approach with a no-adaptation variant, a Dijkstra-based, a Greedy and a Random approach. The results show that the proposed approach can obtain superior solutions compared with current optimisation methods for flexible service composition in mobile environments at the cost of increased overhead.

show abstract

“…In edge computing, the edge servers and many third-party service providers are required to provide intelligent and personalized services for the unprecedented growth of IoT end-devices and data [24]. Recommender systems boost to more easily identify relevant association between users and items then finishing personalized services for meeting the functional and non-functional requirements [25], [26]. Edge caching a primary and indispensable technique in edge computing, which caches some popular contents at the edge servers in advance to reduce latency and network traffic, thereby improving the QoS [27], [28].…”

Section: Introductionmentioning

confidence: 99%

Convergence of Recommender Systems and Edge Computing: A Comprehensive Survey

Sun

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Under the explosive growth of information available on the Web, recommender systems have been used as an effective technology to filter useless information and attempt to recommend the most useful items. The proliferation of smart phones, smart wearable devices and other Internet of Thing (IoT) devices has gradually driven many novel emerging services which are latency-sensitive and computation-intensive with a higher quality-of-service. Under such circumstances, the data sources contain four key characteristics (i.e., sparsity, heterogeneity, mobility, volatility). The conventional recommender systems based on cloud computing are incapable of digging the information of user demands. Mobile edge computing is a novel computing paradigm via pushing computation/storage resource from the remote cloud servers to the network edge servers to provide more intelligent and personalized service. This paper comprehensively reviews the state of the art literature on the convergence of recommender systems and edge computing, and identify the future directions along this dimension. This paper can provide an array of new perspectives on the convergence for researchers, practitioners, and tap into the richness of this interdisciplinary research area.

show abstract

QoS Prediction for Reliable Service Composition in IoT

Cited by 22 publications

References 25 publications

Multi-Parametric Analysis of Reliability and Energy Consumption in IoT: A Deep Learning Approach

Multi-Parametric Analysis of Reliability and Energy Consumption in IoT: A Deep Learning Approach

Stigmergic Service Composition and Adaptation in Mobile Environments

Convergence of Recommender Systems and Edge Computing: A Comprehensive Survey

Contact Info

Product

Resources

About