Big Data Challenges in Industrial Automation

Obitko, Marek; Jirkovský, Václav; BezdíăźEk, Jan

doi:10.1007/978-3-642-40090-2_27

Cited by 32 publications

(26 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Physical properties of the process are constantly monitored, often polling data every few milliseconds in the case of critical variables, which with large, continuous processes can lead to a scenario where it is necessary to use Big Data Analytics (BDA), covered in Section 1, in order to process field and control data. This is further confirmed by proposals that, outside the field of security research, point to this need and propose several BDA solutions focused on industrial applications, such as process monitoring [51][52][53][54], maintenance [55], fault detection [56], and fault diagnosis [57,58].…”

Section: Anomaly Detection Systemsmentioning

confidence: 66%

Towards Large-Scale, Heterogeneous Anomaly Detection Systems in Industrial Networks: A Survey of Current Trends

Iturbe

Garitano

Zurutuza

et al. 2017

Security and Communication Networks

View full text Add to dashboard Cite

Industrial Networks (INs) are widespread environments where heterogeneous devices collaborate to control and monitor physical processes. Some of the controlled processes belong to Critical Infrastructures (CIs), and, as such, IN protection is an active research field. Among different types of security solutions, IN Anomaly Detection Systems (ADSs) have received wide attention from the scientific community. While INs have grown in size and in complexity, requiring the development of novel, Big Data solutions for data processing, IN ADSs have not evolved at the same pace. In parallel, the development of Big Data frameworks such as Hadoop or Spark has led the way for applying Big Data Analytics to the field of cyber-security, mainly focusing on the Information Technology (IT) domain. However, due to the particularities of INs, it is not feasible to directly apply IT security mechanisms in INs, as IN ADSs face unique characteristics. In this work we introduce three main contributions. First, we survey the area of Big Data ADSs that could be applicable to INs and compare the surveyed works. Second, we develop a novel taxonomy to classify existing IN-based ADSs. And, finally, we present a discussion of open problems in the field of Big Data ADSs for INs that can lead to further development.

show abstract

Section: Anomaly Detection Systemsmentioning

confidence: 66%

Towards Large-Scale, Heterogeneous Anomaly Detection Systems in Industrial Networks: A Survey of Current Trends

Iturbe

Garitano

Zurutuza

et al. 2017

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…However, in the industrial environment, big data techniques have not been adopted so quickly [10]. In [11], big data techniques are used for analyzing data in industrial processes, but with a limited scope for remote sensing.…”

Section: Related Workmentioning

confidence: 99%

Multilayer Big Data Architecture for Remote Sensing in Eolic Parks

Moguel

Preciado

et al. 2015

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Due to their nature, Eolic parks are situated in zones with difficult access. As a result, management of Eolic parks using remote sensing techniques is of great importance. In addition, the huge amount of data managed by Eolic parks, together with their nature (distributed, heterogeneous, produced, consumed at different times, etc.) makes them ideal to apply big data techniques. In this paper, we present a multilayer hardware/software architecture that applies cloud computing techniques for managing big data from Eolic parks. This architecture allows tackling the processing of large, distributed, and heterogeneous data sets in a remote sensing context. An innovative contribution of this work is the combination of different techniques at three different layers of the proposed hardware/software architecture for Eolic park big data management and processing.

show abstract

“…In this sense, the data from smart machines and products has a great value, which can be further increased when integrated and combined with other data, e.g., from historical and others external, contextual and enterprise information [2]. Additionally, the high volume of data, which some years ago was underused, mainly because of the lack of tools and expertise to process and analyze it, nowadays can have its fully value extracted through the use of Big Data and advanced analytics approaches [5,6].…”

Section: Introductionmentioning

confidence: 99%

“…Among them, the data management (e.g., retrieval, integration and analysis) comprises an essential requirement to support the smart capabilities and features, which pose several challenges, regarding mechanisms to integrate distributed, heterogeneous, dynamic and stream data sources [6]. Also, a cloud-based infrastructure can support all the remote and local software features, such as the monitoring of health and performance, diagnostic, remote control, optimization and reconfiguration strategies and algorithms, as well as to enable the autonomy of smart products and machines, enabling them to learn and adapt to their environment, user preferences and operate on their own, which are essential requirements to achieve Industrie 4.0 goals [9,10].…”

Section: Introductionmentioning

confidence: 99%

Industrial Cyber Physical Systems Supported by Distributed Advanced Data Analytics

Queiroz

Leitão

Oliveira

2017

Service Orientation in Holonic and Multi-Agent Manufacturing

View full text Add to dashboard Cite

Abstract. The industry digitization is transforming its business models, organizational structures and operations, mainly promoted by the advances and the mass utilization of smart methods, devices and products, being leveraged by initiatives like Industrie 4.0. In this context, the data is a valuable asset that can support the smart factory features through the use of Big Data and advanced analytics approaches. In order to address such requirements and related challenges, Cyber Physical Systems (CPS) promote the development of more intelligent, adaptable and responsiveness supervisory and control systems capable to overcome the inherent complexity and dynamics of industrial environments. In this context, this work presents an agent-based industrial CPS, where agents are endowed with data analysis capabilities for distributed, collaborative and adaptive process supervision and control. Additionally, to address the different industrial levels' requirements, this work combines two main data analysis scopes, at operational level, applying distributed data stream analysis for rapid response monitoring and control, and at supervisory level, applying big data analysis for decision-making, planning and optimization. Some experiments have been performed in the context of an electric micro grid where agents were able to perform distributed data analysis to predict the renewable energy production.

show abstract

Big Data Challenges in Industrial Automation

Cited by 32 publications

References 7 publications

Towards Large-Scale, Heterogeneous Anomaly Detection Systems in Industrial Networks: A Survey of Current Trends

Towards Large-Scale, Heterogeneous Anomaly Detection Systems in Industrial Networks: A Survey of Current Trends

Multilayer Big Data Architecture for Remote Sensing in Eolic Parks

Industrial Cyber Physical Systems Supported by Distributed Advanced Data Analytics

Contact Info

Product

Resources

About