Smart Grid - Artificial Intelligence, Machine Learning and Data Mining Applications in Smart Grid

For a downloadable copy of this eNewsletter, please visit the IEEE Smart Grid Resource Center.

Resource Center Update: Improved user experience for IEEE members! Access/Download free products without a checkout process.

By Tao Ding and Mohammad Shahidehpour

Machine learning methods, which include deep learning, reinforcement learning, neural networks, etc., have been successfully applied to smart grid studies. These methods are used to (1) forecast load curves, photovoltaic and wind power outputs, spot electricity prices, voltage collapse, and power system vulnerabilities; (2) schedule midterm events like fuel purchases, and preventive maintenance outages; and (3) maintain the security, enhance the economics, and optimize decisions in electricity markets. Machine learning applications to contingency analyses have included a fuzzy inference data fusion technique that is not affected by fault types and severity and asynchronous data processing which is applied to improve the fault location accuracy. Machine learning was also applied to resilience analyses and power system hardening to determine the impact of hurricanes and other severe weather conditions, where power system components were divided into damaged and operable and a single classifier was trained as input to the machine learning algorithm using the transient energy function to obtain decision boundaries. Deep reinforcement learning applications included adaptive emergency control schemes to manage data variations and uncertainties in power systems.

By Vishu Gupta, Rajesh Kumar, Akash Saxena, and B.K. Panigrahi

Few challenges are ever present with the power grid. While covering a vast area, the grid transfers the electricity at a certain frequency. An important aspect of this is the inertia of the grid. Inertia, in the simplest terms, is the resistance to change.  When looking at inertia from the aspect of the grid and electricity, the inertia is related to the kinetic energy present in the grid. Where does this kinetic energy come from? The production of electricity at the power plants involves rotating generators and motors. The mass of these machines produces the inertia while rotating at the same or close to the same frequency as that of the electricity grid. In other words, the stored energy in the rotating generators gives them the tendency to remain rotating and this is the grid inertia. 

By Vishalya Sooriarachchi

With the increased application of renewable energy in the energy market and the continuous variations undertaken to implement a highly controllable and interactive power system, the present energy systems are becoming extremely complex. The development of deep learning and core technologies such as multicore processors and math accelerators for neural networks, has made Artificial Intelligence (AI) a massively industrialized component in the modern technological arena. To support the existing systems, and to extend the flexibility and applicability of Smart Grids, AI has been therefore naturally adapted. However, though the adaptation of such technologies is highly recommended by the developed countries, the prospect of the developing countries in terms of redefining the existing energy system and adapting AI and other such technologies to provide improved flexibility in the system is yet at a considerably low level. Although the implementation of AI related technologies in the existing energy grids of developing countries is constituted with a number of complications due to the lack of data samples, imperfections in the available infrastructure, and reliability issues, an AI enabled smart grids can enable the optimization of the power supply, analysis of behavior in the power usage by the users, and predetermined diagnosis of faults.

By Ramon Gallart Fernandez

RESOLvD is a research project under the H2020 program (2017/20, Ref. 773715, LCE-01-2016-2017) whose main objective is using machine learning and data mining to demonstrate intelligent and efficient operations in Spanish low voltage distribution network to improve management and maximize renewable generation capacity.


Past Issues

To view archived articles, and issues, which deliver rich insight into the forces shaping the future of the smart grid. Older Bulletins (formerly eNewsletter) can be found here. To download full issues, visit the publications section of the IEEE Smart Grid Resource Center.

IEEE Smart Grid Bulletin Editors

IEEE Smart Grid Bulletin Compendium

The IEEE Smart Grid Bulletin Compendium "Smart Grid: The Next Decade" is the first of its kind promotional compilation featuring 32 "best of the best" insightful articles from recent issues of the IEEE Smart Grid Bulletin and will be the go-to resource for industry professionals for years to come. Click here to read "Smart Grid: The Next Decade"