Machine Learning Applications to Energy Forecasting and Analytics

Data analytics is a core technology of power system operation, and smart cities specifically, rely heavily on data collection from numerous sensors, data streaming and data analytics to make their decisions. However, Network congestion is a major technological challenge for smart cities. Distributed computing which enables sensors to talk with other local sensors may avoid network congestion and reduce cloud cost. As author Don Reeves states in the article “How to create smart city”, networking platforms that deliver reliable connectivity must be established for smart cities to be successful to connect sensors and actuators.
To help our members keep up with the latest and best thinking in machine learning, IEEE Power & Energy Society has created a number of resources on this subject. This email is intended to highlight a few of those resources, as well as upcoming events and content focused on this subject:
PES Resources and Content
Machine Learning and Big Data Analytics in Smart Grid
2020 PES General Meeting Tutorial Series
This multi-presenter tutorial provides background information, real-world development experience, and in-depth discussions of big data analytics and machine learning in smart grid. Topics of discussion include: the value, velocity, volume, and variety of big data in the smart grid; the basics of machine learning algorithms such as unsupervised learning, supervised learning, and reinforcement learning algorithms.
- Session 1: Data-driven Analytics for Power System Dynamics
- Session 2: Overview & Reinforcement learning-based Control in Power Distribution Systems
- Session 3: Estimation of System State and Behind-the-Meter Solar Generation
- Session 4: Streaming Analytics and Machine Learning Design for Smart Grid and Power Systems
Artificial Intelligence in Power System Operations and Planning
Panel Session: Feb 2019
Authors: Z. Wang, A. Santos, and D. Deka
This panel will discuss how the recent advancement in AI, especially in machine learning, can be used to help a number of fundamental optimization problems in the operations and planning in power systems.
Deep Learning and Its Application to Power System Analysis
Webinar: Nov 2017
Author: Mike Zhou
This Webinar will give a general overview of Deep Learning in artificial intelligence and its potential application to power system analysis.
Machine Learning to Estimate Energy Demands and User Behavior Related to Buildings in the Smart Grid Context
Panel Session: Aug 2015
Author: Elena Mocanu
This panel session, sponsored by the Energy Development and Power Generation focuses on energy efficient and smart cities.
Modeling of Solar Energy Using AI Technique
Panel Session: Jun 2014
Authors: Professor Dr. Wilfried Elmenreich and Dr. Tamer Khatib
Available PES GM 2020 Panel Sessions
Did you register for the 2020 PES General Meeting? If so, you have access to the following sessions as part of your registration:
- Machine Learning for Power System Planning and Operation
- Application of Machine Learning in Emergency Control for Resilient System Operation
- Big Data and Machine Learning Applications in Power Systems
- Machine Learning Applications to Energy Forecasting and Analytics
- Artificial Intelligence and the Future of Distribution Management Systems
Additional Groups
This topic is one being worked on by a variety of different groups both inside and outside of IEEE PES.
If you are really interested in machine learning applications to energy forecasting and analytics check out this committee for even more info:
Upcoming Events
- Education Tue. 19 Jan, 2021 Live Tutorial - Introduction to Artificial Intelligence and Machine Learning, Session 1: Fundamentals and Selected Applications
- Webinars Wed. 20 Jan, 2021 Live Webinar - What Is in the IEEE PES Resource Center for You?
- Technical Committees Mon. 25 Jan, 2021 2021 IEEE PES Energy Storage and Stationary Battery (ESSB) Committee - Winter Meeting
- Education Tue. 26 Jan, 2021 Live Tutorial - Introduction to Machine Learning, Session 2: Fundamental Algorithms on Concept Learning with Data Mining Applications