AI explainability and governance in smart energy systems: A review

Abstract

Traditional electrical power grids have long suffered from operational unreliability, instability, inflexibility, and inefficiency. Smart grids (or smart energy systems) continue to transform the energy sector with emerging technologies, renewable energy sources, and other trends. Artificial intelligence (AI) is being applied to smart energy systems to process massive and complex data in this sector and make smart and timely decisions. However, the lack of explainability and governability of AI is a major concern for stakeholders hindering a fast uptake of AI in the energy sector. This paper provides a review of AI explainability and governance in smart energy systems. We collect 3,568 relevant papers from the Scopus database, automatically discover 15 parameters or themes for AI governance in energy and elaborate the research landscape by reviewing over 150 papers and providing temporal progressions of the research. The methodology for discovering parameters or themes is based on “deep journalism,” our data-driven deep learning-based big data analytics approach to automatically discover and analyse cross-sectional multi-perspective information to enable better decision-making and develop better instruments for governance. The findings show that research on AI explainability in energy systems is segmented and narrowly focussed on a few AI traits and energy system problems. This paper deepens our knowledge of AI governance in energy and is expected to help governments, industry, academics, energy prosumers, and other stakeholders to understand the landscape of AI in the energy sector, leading to better design, operations, utilisation, and risk management of energy systems.

Multi-generational labour markets: Data-driven discovery of multi-perspective system parameters using machine learning

“…This paper is part of our broader work on the use of information and communication technology (ICT) to address challenges facing smart cities and societies. Our work on this topic has included the concept of Deep Journalism, 145 , 146 as well as research on topics such as transportation, 146 tourism, 147 smart families and homes, 148 healthcare services for cancer, 58 mental health, 149 education during the COVID-19 pandemic, 150 energy systems 151 and AI-based event detection. 152 Future work will be directed to improving the methodological approach presented in this paper using advanced deep learning methods and their applications to investigate and improve labour economics and other problems facing our societies.…”

Research on energy consumption in household sector: a comprehensive review based on bibliometric analysis

“…Residential customers as the main users of electrical energy, have a strong influence on electricity demand due to the randomness of their household activities and the flexibility of their appliance usage patterns (Wang et al, 2022). The promotion and application of smart control systems based on energy monitoring, management, and data analysis play a crucial role in optimizing energy utilization and providing personalized recommendations (Alsaigh et al, 2023;Paneru and Tarigan, 2023). The development and diffusion of smart home devices such as smart thermostats, smart lighting and smart appliances support the monitoring and management of energy behavior in the household (Alhussein et al, 2020;Moadab et al, 2021), to better control energy use and improve energy efficiency.…”

Comparison of machine learning and statistical methods in the field of renewable energy power generation forecasting: a mini review

“…Cocchi et al (2018) demonstrated that machine learning methods have higher prediction accuracy than statistical methods in complex power generation prediction problems. Statistical methods have good interpretability, but machine learning methods are often considered to be "black box problems" (Kane et al, 2014;Alsaigh et al, 2023).…”