Analysis of Smart Meter Data for Energy Waste Management

Djordje Batic (), Lina Stankovic () and Vladimir Stankovic ()
Additional contact information
Djordje Batic: University of Strathclyde
Lina Stankovic: University of Strathclyde
Vladimir Stankovic: University of Strathclyde

Chapter 8 in Artificial Intelligence for Sustainability, 2024, pp 153-173 from Springer

Abstract: Abstract Smart meters enable the high-frequency measurement and wireless communication of energy consumption, facilitating the digitalization of the energy industry, reducing operational costs and lowering carbon emission. Recently, artificial intelligence (AI) has emerged as an important tool for the analysis of smart meter data, supporting the transition to renewable energy sources, optimizing the energy supply through demand-response programs, and offering insights into energy usage patterns in homes through non-intrusive load monitoring (NILM). However, such precise data analysis has the power to reveal sensitive information about behavioral routines and personal activity, raising critical ethical challenges which may hurt public trust in the AI system. Motivated by these challenges, this chapter explores the development of trustworthy AI mechanisms for smart meter data analytics. Trustworthy AI enhances user privacy, adapts to changing usage patterns, and improves system transparency thereby facilitating a smoother transition to energy efficiency. We illustrate how privacy-preserving techniques can be used to protect user data while preserving the utility of AI models. The chapter further investigates how AI robustness can be enhanced to handle varied and dynamic energy usage patterns. Moreover, we emphasize the need for transparency and explainability in AI systems to ensure decision-making processes are understandable and justifiable, a requirement that is rarely fulfilled due to the complexity of AI algorithms. In summary, this chapter will discuss the types of AI approaches that leverage smart meter data, the ethical concerns they raise, and innovative solutions to overcome these difficulties.

Keywords: Non-intrusive load monitoring; NILM; Energy disaggregation; Deep learning; Smart meters; Trustworthy AI (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-031-49979-1_8

Ordering information: This item can be ordered from
http://www.springer.com/9783031499791

DOI: 10.1007/978-3-031-49979-1_8

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().