Smart grids (SGs) revolutionize existing power grids by using a wide range of developing disruptive technologies to generate clean, efficient, and predictable energy. Our study uses an action research method and focuses solely on the first two stages of the action research process, diagnosis and action planning, to evaluate ways to adopt artificial intelligence (AI) applications in SGs for predictive analytics in practice. The diagnosis stage of the study entails conducting a systematic literature review on AI applications in SGs, highlighting four areas of potential for predictive analytics: power outage prediction, demand response, control and coordination, and AI-enabled security to optimize decision-making, diagnose faults, and improve grid stability and security. The action planning step included a document analysis to devise methods to enable the practical implementation of AI in smart grids for predictive analytics. Finally, we address practical ways for implementing transparent AI for predictive analytics, followed by a conclusion and future research direction. The study’s key conclusion is that more research is needed to complete the action taking (implementing the solution), evaluation (assessing the results), and learning (reflecting on lessons learned) phases of the action research cycle.

The rapid proliferation of IoT devices has increased security and privacy vulnerabilities due to device resource restrictions and a lack of edge intelligence. To better understand how Supervised Machine Learning (ML) may be used at edge devices, this study examined how industry actors can use ML to improve IoT edge security. Despite the interest in ML for intrusion detection in IoT, edge device security is in demand as IoT devices spread. The current technique is computationally costly, and resource-limited IoT devices struggle to run ML algorithms. Using a mixed-method approach, this study uses EuX testbed and UNSW-NB 15 network datasets to train, assess, and finetune ML models for edge deployment. The study's findings present the model's performance, best features, compute time, and resource needs from an exploratory examination of the data sets. This study concludes that ML models can improve IoT real-time anomaly and intrusion detection by boosting edge device intelligence. However, ML deployments also require algorithm optimization and computational reduction.

The shift toward decentralised energy generation, driven by the rapid expansion of renewable energy sources, is redefining traditional consumers as active co-creators of electricity generation. This study examines the role of predictive analytics in supporting resilience and co-creation within distributed energy resources (DERs). It employs semi-structured qualitative interviews to explore stakeholder perspectives on how predictive analytics is envisioned and applied. Our preliminary findings show that predictive analytics could be used across diverse applications, such as forecasting, maintenance, and load optimisation. These diverse applications actively shape energy management systems while influencing decision-making and operational design. The application of predictive analytics is shaped by both enabling and constraining conditions. We conclude that predictive analytics functions not only as a technical tool but also aligns stakeholders and promotes collaborative and adaptive energy management among distributed energy resources.

Smart grids (SG) transform a traditional electricity energy grid by incorporating many emergingdisruptive technologies to produce clean, efficient, and dependable energy. This review focusesexclusively on one instance of AI application in SG - predictive analytics. We conducted asystematic literature review on AI applications in SG, which resulted in a review of 18 articlespublished after 2015. In the first part of the review, it is concluded that integrating AI into SGcould address many challenges in SGs and transform traditional grids. The second part focuseson the predictive analytic capability enabled through AI in SG. Predictive analytics can be appliedin many contexts to optimize decision-making, diagnose faults, and enhance grid stability. Thelast part presents two use cases for AI-enabled predictive analytics: energy outage prediction andsecurity enhancement. AI, especially the predictive analytic technique, is a future avenue for SGenhancement. The main conclusion from the review is that more research describing empiricalexamples of the adoption and deployment of AI predictive analytics in SG is needed.

The new paradigm in clean, sustainable, dependable, and efficient energy generation, and delivery, hasled to the transformation and innovation of traditional grid to smart grid. The transformation andinnovation use advanced technologies such as AI and IoT to monitor and control power generation,transmission, and distribution processes in a smart grid (SG). AI applications in SG have emerged as aninnovation that guarantees effective, flexible, reliable, sustainable, decentralized, secure, and cost-effective distribution and management of energy in SG. This study is a research proposal for AIApplications in SG for Reliability, Security, and Stability. It begins by introducing the SG and its relatedchallenges, followed by AI applications in SG and its implementation challenges. The study identifiesresearch problems in AI applications in SG to be AI interpretability and formulates three researchquestions that can help address the problem identified. Also, this paper presents the results of theliterature review conducted to provide a sufficient grounding for this study and discusses the followingconcepts of AI application in SG. Predictive Analytics in SG, AI-enabled Demand Response in SG, AI-enabled Control and Coordination in SG, AI-enabled security, stability, and reliability analysis in SG, andImplementation challenges of AI applications in SG. The study proceeds to discuss the proposedtheoretical approach and the chosen research methodology and then concludes with the expectedstudy contribution to research and practice.