Extended kernel density estimation for anomaly detection in streaming data

Rosenberger, Julia; Muller, Kristen E.; Selig, Andreas; Bühren, Michael; Schramm, Dieter

doi:10.1016/j.procir.2022.09.065

Cited by 10 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The decisions are made in dependence on the states of the IIoT network, i.e., the current available resources. In the context of this work, a task q can either be a pair of data stream and processing algorithm, e.g., anomaly detection [41] or data compression [42], or only a computing task that does not process data, e.g., a node in a distributed ledger technology network [43]. The proposed system optimizes the usage of multiple resources.…”

Section: Inputmentioning

confidence: 99%

Deep Reinforcement Learning Multi-Agent System for Resource Allocation in Industrial Internet of Things

Rosenberger

Urlaub

Rauterberg

et al. 2022

Sensors

View full text Add to dashboard Cite

The high number of devices with limited computational resources as well as limited communication resources are two characteristics of the Industrial Internet of Things (IIoT). With Industry 4.0 emerges a strong demand for data processing in the edge, constrained primarily by the limited available resources. In industry, deep reinforcement learning (DRL) is increasingly used in robotics, job shop scheduling and supply chain. In this work, DRL is applied for intelligent resource allocation for industrial edge devices. An optimal usage of available resources of the IIoT devices should be achieved. Due to the structure of IIoT systems as well as security aspects, multi-agent systems (MASs) are preferred for decentralized decision-making. In our study, we build a network from physical and virtualized representative IIoT devices. The proposed approach is capable of dealing with several dynamic changes of the target system. Three aspects are considered when evaluating the performance of the MASs: overhead due to the MASs, improvement of the resource usage of the devices as well as latency and error rate. In summary, the agents’ resource usage with respect to traffic, computing resources and time is very low. It was confirmed that the agents not only achieve the desired results in training but also that the learned behavior is transferable to a real system.

show abstract

Section: Inputmentioning

confidence: 99%

Deep Reinforcement Learning Multi-Agent System for Resource Allocation in Industrial Internet of Things

Rosenberger

Urlaub

Rauterberg

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…For evaluation, the exemplary use case of an RL-based MAS for intelligent resource allocation in IIoT with edge computing is examined. It comprises both the MAS as enabler for DSPSs [ 83 ] on the middleware layer as well as different data stream processing algorithms [ 4 , 22 , 88 ] that belong to the logic layer. While the single approaches have already been evaluated individually, the proposed application of simulation is used for a realistic evaluation of the overall system and the interaction of the single approaches in combination with an industrial plant.…”

Section: Simulation Experimentsmentioning

confidence: 99%

“…Three kinds of high-level edge computing algorithms are run on the edge devices: Anomaly detection: The anomaly detection is based on unsupervised learning, i.e., the nonparametric statistic method kernel density estimation. The efficient one-pass algorithm is suited for the detection of different kinds of anomalies in streaming data (for details, see [ 4 ]). DLT and SCs: In a previous work ([ 22 ]), we presented two use cases for DLT in the IIoT.…”

Section: Simulation Experimentsmentioning

confidence: 99%

“…The anomaly detection is based on unsupervised learning, i.e., the nonparametric statistic method kernel density estimation. The efficient one-pass algorithm is suited for the detection of different kinds of anomalies in streaming data (for details, see [ 4 ]).…”

Section: Simulation Experimentsmentioning

confidence: 99%

“…In addition, many end-users still object to transferring critical enterprise and production data to remote service providers. Thus, the shift to edge computing has been recognizable for a few years in industry [ 2 , 3 , 4 , 5 ]. In the context of distributed stream processing systems (DSPSs), this trend is also evident, as the use of edge device resources for (pre)processing tasks is increasing [ 6 , 7 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Virtual Commissioning of Distributed Systems in the Industrial Internet of Things

Rosenberger

Selig

Ristić

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

With the convergence of information technology (IT) and operational technology (OT) in Industry 4.0, edge computing is increasingly relevant in the context of the Industrial Internet of Things (IIoT). While the use of simulation is already the state of the art in almost every engineering discipline, e.g., dynamic systems, plant engineering, and logistics, it is less common for edge computing. This work discusses different use cases concerning edge computing in IIoT that can profit from the use of OT simulation methods. In addition to enabling machine learning, the focus of this work is on the virtual commissioning of data stream processing systems. To evaluate the proposed approach, an exemplary application of the middleware layer, i.e., a multi-agent reinforcement learning system for intelligent edge resource allocation, is combined with a physical simulation model of an industrial plant. It confirms the feasibility of the proposed use of simulation for virtual commissioning of an industrial edge computing system using Hardware-in-the-Loop. In summary, edge computing in IIoT is highlighted as a new application area for existing simulation methods from the OT perspective. The benefits in IIoT are exemplified by various use cases for the logic or middleware layer using physical simulation of the target environment. The relevance for real-life IIoT systems is confirmed by an experimental evaluation, and limitations are pointed out.

show abstract

Estimating streamflow by an innovative rating curve model based on hydraulic parameters

Vatanchi,

Maghrebi

2024

Environ Earth Sci

View full text Add to dashboard Cite

Extended kernel density estimation for anomaly detection in streaming data

Cited by 10 publications

References 10 publications

Deep Reinforcement Learning Multi-Agent System for Resource Allocation in Industrial Internet of Things

Deep Reinforcement Learning Multi-Agent System for Resource Allocation in Industrial Internet of Things

Virtual Commissioning of Distributed Systems in the Industrial Internet of Things

Estimating streamflow by an innovative rating curve model based on hydraulic parameters

Contact Info

Product

Resources

About