Machine Learning for Real-time Data Reduction in Cloud of Things

Alahmed, Atheer; Alrasheedi, A. F.; Alharbi, Maha; Alrebdi, Norah; Aleasa, Marwan; Moulahi, Tarek

doi:10.1109/iccis49240.2020.9257645

Cited by 3 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing literature has shown that feature encoding through dimensionality reduction on the edge or mobile side can help achieve the goals of real-time stream data analytics [25], [26] and transmissions optimization [27], [28], [29], [30]. However, many dimensionality reduction methods suffer from high information loss and data distortion, making it difficult to have a true representation of the data.…”

Section: Feature Encodingmentioning

confidence: 99%

Edge-Enhanced QoS Aware Compression Learning for Sustainable Data Stream Analytics

Amaizu

Ali

Anjum

et al. 2023

IEEE Trans. Sustain. Comput.

View full text Add to dashboard Cite

In conventional cloud systems, large volumes of data streams are sent to the data centres for monitoring, storage, and analytics. However, migrating all the data to the cloud is often not feasible due to cost, privacy, and performance concerns. Deep neural network (DNN) based applications typically require a tremendous amount of computation, hence cannot be directly deployed on resource-constrained edge devices for learning and analytics. Edge-enhanced compressive offloading becomes a sustainable solution that allows data to be compressed at the edge and offloaded to the cloud for further analytics, therefore reducing bandwidth consumption and communication latency. However, it poses a unique challenge to decode the data and perform inference at the server-side within an acceptable quality of service (QoS) limit. This paper makes the first contribution to address the gaps by designing and implementing a principled compression learning method for discovering the compression models that offer the right QoS for an application. It works by a novel modularisation approach that maps features to models and classifies them for a range of quality of service models. An automated QoS-aware orchestrator has been designed to select the best autoencoder model in real-time for compressive offloading in edge-enhanced clouds based on changing QoS requirements. The orchestrator has been designed to have diagnostic capabilities to search appropriate parameters that give the best compression. To our knowledge, this is one of the first attempts at harnessing the capabilities of autoencoders for edge-enhanced compressive offloading based on portable encodings, latent space splitting, and fine-tuning network weights. Due to the discoverable pool of features offering variety of QoS models, the system is capable of processing a large number of QoS requests in a given time. The search strategy, based on a narrowed search over the entire neural architectural space, reduces the computational cost of searching through the entire space by up to 89%. When deployed on an edge-enhanced cloud in Azure IoT testbed, the approach saves up to 70% data transfer costs and takes 32% less time for job completion. It eliminates the additional computational cost of decompression, thereby reducing the processing cost by up to 30%.

show abstract

Section: Feature Encodingmentioning

confidence: 99%

Edge-Enhanced QoS Aware Compression Learning for Sustainable Data Stream Analytics

Amaizu

Ali

Anjum

et al. 2023

IEEE Trans. Sustain. Comput.

View full text Add to dashboard Cite

show abstract

An overview of data reduction solutions at the edge of IoT systems: a systematic mapping of the literature

et al. 2022

View full text Add to dashboard Cite

Internet of Things (IoT) is a technology that connects devices of different types and characteristics through a network. The massive quantity of the heterogeneous generated data by the sensors imposes many challenges in making these data available to IoT applications. Data reduction and preprocessing are promising concepts that help to handle these data efficiently before storing them. Applying data reduction methods at the edge has emerged as an efficient solution. In such context, this systematic mapping is intended to investigate the data reduction solutions performed exclusively at the edge through a set of research questions. To reach this objective, we performed a Systematic Literature Mapping (SLM) in which 35 papers were strictly analyzed among a total of 853 articles. Finally, we present the results of these analyses answering questions that relate to the researcher’s used techniques, hardware technologies, used data type, and contributed objects to perform the data reduction techniques on the edge of the IoT systems.

show abstract

A Novel Negative and Positive Selection Algorithm to Detect Unknown Malware in the IoT

Alrubayyi

Goteng

Jaber

et al. 2021

IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)

View full text Add to dashboard Cite

Machine Learning for Real-time Data Reduction in Cloud of Things

Cited by 3 publications

References 14 publications

Edge-Enhanced QoS Aware Compression Learning for Sustainable Data Stream Analytics

Edge-Enhanced QoS Aware Compression Learning for Sustainable Data Stream Analytics

An overview of data reduction solutions at the edge of IoT systems: a systematic mapping of the literature

A Novel Negative and Positive Selection Algorithm to Detect Unknown Malware in the IoT

Contact Info

Product

Resources

About