Papers
Topics
Authors
Recent
Search
2000 character limit reached

Big Data Meet Cyber-Physical Systems: A Panoramic Survey

Published 29 Oct 2018 in cs.LG and stat.ML | (1810.12399v1)

Abstract: The world is witnessing an unprecedented growth of cyber-physical systems (CPS), which are foreseen to revolutionize our world {via} creating new services and applications in a variety of sectors such as environmental monitoring, mobile-health systems, intelligent transportation systems and so on. The {information and communication technology }(ICT) sector is experiencing a significant growth in { data} traffic, driven by the widespread usage of smartphones, tablets and video streaming, along with the significant growth of sensors deployments that are anticipated in the near future. {It} is expected to outstandingly increase the growth rate of raw sensed data. In this paper, we present the CPS taxonomy {via} providing a broad overview of data collection, storage, access, processing and analysis. Compared with other survey papers, this is the first panoramic survey on big data for CPS, where our objective is to provide a panoramic summary of different CPS aspects. Furthermore, CPS {require} cybersecurity to protect {them} against malicious attacks and unauthorized intrusion, which {become} a challenge with the enormous amount of data that is continuously being generated in the network. {Thus, we also} provide an overview of the different security solutions proposed for CPS big data storage, access and analytics. We also discuss big data meeting green challenges in the contexts of CPS.

Citations (187)

Summary

Big Data Meet Cyber-Physical Systems: A Panoramic Survey

The paper presents a comprehensive examination of the integration between big data and cyber-physical systems (CPS). CPS are poised to disrupt traditional industries by offering new services across sectors, including environmental monitoring, transportation systems, and mobile-health applications. This paper provides an extensive survey of the interaction between big data and CPS, focusing on data generation, storage, processing, and security challenges. The purpose of the survey is to offer researchers a centralized overview of the existing literature gaps while providing insight into emerging technologies and approaches.

The discussion begins by detailing the data aggregation mechanisms in CPS, citing sources such as context-aware computing and remote sensing. It highlights the expected surge in raw data collection driven by the prevalence of IoT and sensor networks. The taxonomy elaborates on the intricacies of data lifecycle management within CPS, structuring the data processing into phases such as acquisition, storage, reduction, and analysis. Furthermore, the paper identifies clustering and data mining as key methodologies to manage and interpret the voluminous data generated by CPS. Technologies like MapReduce, and the evolving NoSQL databases are emphasized as necessary tools for managing distributed, unstructured data.

The importance of cybersecurity within CPS is explicitly noted due to potential vulnerabilities arising from CPS's interconnected nature. The expanding breadth of sensor networks and the data generated demands sophisticated security protocols to safeguard against breaches and unauthorized access. The authors survey existing security frameworks, proposing improvements in data deduplication, encryption schemes, and anomaly detection methods as core strategies to enhance CPS security.

In exploring the sustainability challenges posed by CPS, the paper examines how the imposition of big data processing impacts energy consumption. The authors emphasize the need for green and sustainable solutions, proposing energy-efficient strategies for data acquisition, transmission, and processing in CPS. Techniques such as dynamic voltage and frequency scaling, traffic engineering, and optimization of VM placements in cloud environments are mentioned as crucial to reducing energy footprints.

The implications of meeting green challenges with big data are broad, touching upon sectors like power management, transportation, and even social computing applications. The paper suggests that CPS could revolutionize these fields by increasing efficiency and promoting sustainability.

The Future research directions suggested in the paper focus on improving data fusion for analytics, developing robust security solutions, and exploring cross-layer designs to optimize CPS operations. For great advancements, the paper suggests further exploration into integrating heterogeneous data types, improving privacy-preserving analytics protocols such as k-anonymization and homomorphic encryption, and boosting CPS's reliability.

This survey presents an exhaustive perspective on CPS functionalities, assessing the methodologies, challenges, and solutions in a detailed manner. The anticipation of an increased reliance on CPS in various sectors necessitates ongoing research efforts to mitigate challenges, particularly concerning security and sustainability. While revealing the plethora of opportunities in CPS integration with big data, the paper sets the stage for future innovations and interdisciplinary research ventures.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Collections

Sign up for free to add this paper to one or more collections.