Data analytics provide very effective tools to solve complex problems; however they are typically constrained where the computing system infrastructure lacks the ability to provide reliable data and is prone to data retrieval delays. This project will seek to provide guarantees of data reliability with new tools for failure detection, diagnosis, and recovery, while minimising delays caused by data communication and processing. This will allow decision makers to better react to real-time changes that currently reduce sustainability in infrastructures, and processes, causing system inefficiencies.
Explaining the science
Sensing, processing and actuation, are the three main steps adopted by recent cyber-physical systems (CPS), where data are usually collected with Internet of Things (IoT) devices. These devices are typically constrained to limited resources, such as small battery and low computation capacity. State-of-the-art machine learning (ML) and artificial intelligence (AI) can aid complex CPS problems, but are heavily dependent on the quality of data they receive.
Fault discovery, diagnosis and recovery for IoT networks
To ensure the quality of data collected by ubiquitous sensing networks, where the devices therein are typically fault prone and the communications between devices are unreliable, an online system is needed which can help to identify and diagnose failures and recover from a faulty state. Different mathematical tools such as statistics, machine learning, and graph theory can be exploited to build such systems. However, these IoT networks are typically constrained by limited resources such as battery and computational capacity. Therefore, lightweight approaches are required to replace traditional methodologies.
Mining time series streams in real time
Most data collected in CPSs are in the form of time series, which is a series of data points indexed (or listed or graphed) in time order. However this time series data usually includes noise and trivial information which may cause bias in post analysis even with state-of-the-art ML and AI solutions. To improve the quality of analytic results, meaningful information can be extracted from their raw format by using analytic tools such as motif discovery, feature extraction and visualisation. By extending these approaches, new solutions, which can handle data in an adaptive manner, are proposed to support mining tasks on time series streams.
This work seeks to provide reliable tools that allow decision makers to effectively understand the behaviour of infrastructures, such as bridges, gas pipes etc, and to enable them to react to changes or failures in the infrastructure in real time. The work will explore how sensing devices embedded in the infrastructure can provide this information.
The following research questions will be tackled:
- Can advice be given for efficient and effective sensor placement that better captures phenomena while maintaining overall system reliability?
- Can data quality be ensured with reliable and fault tolerant sensing systems, that provide guarantees of their quality of services?
- Can informative patterns be accurately extracted from big and complex raw data (typically in the form of time series data) in real-time?
- Can the extracted information be interfaced with other real-time analysis tools, such as life cycle analysis (LCA), and provide insights that improve infrastructure sustainability and efficiency?
The project aims to develop approaches that can be generalised across different scales and industrial settings (e.g. from small factory operations to supply chains), and fulfil the requirements of real-world applications which will engage users and stakeholders.
The contribution to sensor systems, failure management, time series analytics, and design engineering disciplines will be evidenced by outputs in international research conferences and journals.
This project is part of the Data-centric engineering programme's Grand Challenge of 'Resilient and robust infrastructure'.
This work is applied to and can benefit real-time sustainable infrastructure, such as water supply networks, smart grids, transportation and precision farming. By providing reliable data and analytic tools in real-time, decision makers can better understand the interdependencies between relevant processes, discover potential impacts caused by the changes in these processes and react accordingly.
- Working with NIAB/EMR to deploy test precision farming solution
- A new paper ‘Antilizer: Run Time Self-Healing Security for Wireless Sensor Networks’, accepted to Proc. MobiQuitous 2018.
- Co organised the UK’s first The Internet of Agri Things Workshop with Harper-Adams University.
- Working with Ridgeview Winery to deploy test precision farming solution.
EPSRC Water-Energy-Food Nexus Networking Event, London.