The Scale2 Multi-Network Architecture for IoT-Based Resilient Communities

Uddin, Yusuf Sarwar; Nelson, Alexander; Benson, Kyle; Wang, Guoxi; Zhu, Qiuxi; Han, Qing; Alhassoun, Nailah Saleh; Chakravarthi, P; Stamatakis, Julien; Hoffman, Daniel; Darcy, Luke; Venkatasubramanian, Nalini

doi:10.1109/smartcomp.2016.7501722

Cited by 20 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SCALE2 [62] leveraged MINA and implemented a multi-tier and multi-network approach to drive data flow from IoT devices to cloud platforms. The authors implemented a local Software-defined networking (SDN)-enabled the network, which is adaptive to the network changes to which IoT client devices are connected.…”

Section: Related Workmentioning

confidence: 99%

Resilient Edge: Building an Adaptive and Resilient Multi-Communication Network for IoT Edge Using LPWAN and WiFi

Kumar

Yadav

Indrusiak

2023

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

Resilient Edge: Building an Adaptive and Resilient Multi-Communication Network for IoT Edge Using LPWAN and WiFi

Kumar

Yadav

Indrusiak

2023

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

show abstract

“…In counterpart, they may involve a significant learning curve for large and complex models. Furthermore, they are difficult to train well and may suffer from local minima problems [17] even after carefully tuning the backpropagation algorithm. The second issue is that RNNs might actually produce worse results than linear models if the data has a significant linear component [31].…”

Section: Related Workmentioning

confidence: 99%

Predictive Anomaly Detection

Berriche

Sailhan

2023

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Cyber attacks are a significant risk for cloud service providers and to mitigate this risk, near real-time anomaly detection and mitigation plays a critical role. To this end, we introduce a statistical anomaly detection system that includes several auto-regressive models tuned to detect complex patterns (e.g. seasonal and multi-dimensional patterns) based on the gathered observations to deal with an evolving spectrum of attacks and a different behaviours of the monitored cloud. In addition, our system adapts the observation period and makes predictions based on a controlled set of observations, i.e. over several expanding time windows that capture some complex patterns, which span different time scales (e.g. long term versus short terms patterns). We evaluate the proposed solution using a public dataset and we show that our anomaly detection system increases the accuracy of the detection while reducing the overall resource usage.

show abstract

“…In [Uddin et al 2016], Uddin et al propose SCALE2 which engages a multi-network approach to drive data flow from IoT devices to cloud platforms where the analytics are executed. The system is organized in a hierarchical approach for managing a community of IoT devices while focusing on resilience methods that can be employed at different tiers in the hierarchical architecture.…”

Section: Distributed Integrated Architecturementioning

confidence: 99%

ADMITS: Architecting Distributed Monitoring and Analytics in IoT-based Disaster Scenarios

Pasquini¹,

Miani²,

Coelho³

et al. 2020

Anais Do Simpósio Brasileiro De Computação Ubíqua E Pervasiva (SBCUP 2020)

View full text Add to dashboard Cite

The ADMITS project aims to develop algorithms, protocols and architectures to enable a distributed computing environment to provide support for monitoring, failure detection, and analytics in IoT disaster scenarios. We face a context where, every year, millions of people are affected by natural and man-made disasters, whereby governments all around the world spend huge amounts of resources on preparation, immediate response, and reconstruction. Recently, the Internet of Things (IoT) paradigm has been extensively used for efficiently managing disaster scenarios, such as volcanic disasters, floods, forest fire, land- slides, earthquakes, urban disasters, industrial and terrorists attacks, and so on. However, in a disaster scenario the communication/processing infrastructure and the devices themselves may fail, producing either temporary or permanent network partitions and loss of information. Moreover, it is expected that in the years to come, IoT will generate large amounts of data, making processing and analysis challenging in time-critical applications. Considering such challenges, ADMITS targets the development of a architecture in which IoT, Fog, and Cloud computing technologies participate to provide required capabilities for IoT data analytics, real-time stream processing, and failure monitoring for environments potentially subject to disasters. In this positional paper, we discuss the motivation, objectives, architecture, research challenges (and how to overcome them) and initial efforts for the ADMITS project.

show abstract

The Scale2 Multi-Network Architecture for IoT-Based Resilient Communities

Cited by 20 publications

References 7 publications

Resilient Edge: Building an Adaptive and Resilient Multi-Communication Network for IoT Edge Using LPWAN and WiFi

Resilient Edge: Building an Adaptive and Resilient Multi-Communication Network for IoT Edge Using LPWAN and WiFi

Predictive Anomaly Detection

ADMITS: Architecting Distributed Monitoring and Analytics in IoT-based Disaster Scenarios

Contact Info

Product

Resources

About