Part of Grid Network »

The Grid Professionals Group covers electric current from its transmission step down to each customer's home. 

WARNING: SIGN-IN

You need to be a member of Energy Central to access some features and content. Please or register to continue.

Post

Self-Learning Power Grids

In recent past, we saw evolution of the Smart Grid that led to the Gird Modernization which is taking place now. This trend seems to be continuing and hopefully very soon latest technologies such as Machine Learning enabled by Big Data and Advance Analytics will help in Self-Learning Grids.

Integration of ICT (Information and Communication Technology) in Power Systems led to the emergence of the Smart Grid

In recent past, we saw evolution of the Smart Grid that led to the Gird Modernization which is taking place now. This trend seems to be continuing and hopefully very soon latest technologies such as Machine Learning enabled by Big Data and Advance Analytics will help in Self-Learning Grids.

Integration of ICT (Information and Communication Technology) in Power Systems led to the emergence of the Smart Grid1. The main objectives of the Smart Grid such as Grid resilience and increased market participation require system wide upgrades and improvements.

Modern Gird systems produce various types of data which can now be analyzed effectively using latest analytical technologies. These technologies can provide an immediate ROI based on optimized models for power generation, predicting consumption demand, pricing, and predictive maintenance of physical assets. However, looking at a longer horizon, the abundance of available data compounded by recent trends in the field of machine learning driven by advance algorithms and big data technologies are creating the possibilities for Self-Learning Grids of tomorrow.

These Self-Learning Grids will result in enhanced reliability and energy savings - with little to no human intervention. For example, Self-Learning Grids will predict the disturbances and abnormalities more accurately and timely by processing various kind of large data simultaneously, enabled by Big Data technologies.

Further, ‘Self-Learning Grids’ can optimize failover switching and minimize downtime or at least the scale of blackouts. However, we will need to develop the right algorithms and a lot of data & examples to train the grids for Self-Learning.

 

“There is an increasing interdependence of information technology and energy technology, with smarter grids opening pathways to greater functionality (e.g., situational awareness) and active management of more diverse sets of resources providing a range of services that can be monetized in energy markets.”2

 

The current trends in the industry are installing lot of sensors, automatic switching devices and inserting data capable devices with real time communication capabilities. All this data, produced by distribution devices and substation devices needs to be crunched by various systems such as DMS (Distribution Management System) and EMS (Energy Management System) for the reliable and economic operation of the Grid. Thus, a new Grid is evolving and the main trends that are driving the grid evolution come from Innovation in Data (such as Big Data) and advanced analytical techniques that help in System Optimization. The data Generated by main Power System domains can be categorized and identified as described below.

Above data sources generate and transmit data from billions of points in terabytes with some up to nano seconds accuracy.

“Granular data on power system performance and big data analytics can reveal investment needs for grid enhancement and inform the locational value of distributed energy resources such as distributed generation and storage”.2

How to store and analyze this voluminous data simultaneously, as described in above table, of different variety and accuracy that is being generated and transmitted at lightning speed is the subject matter for the article. And this is where Advance Analytics and Big Data Technology comes into the picture.

Voluminous & Speedy data from PMUs for Transmission Grid Operations and Variety of data such as circuit and customer data including customer behavior data for Distribution Operations are being stored and analyzed by different systems at different speed and frequency currently. However, we are exploring the scenarios where this data can be analyzed simultaneously at a much faster speed and correlated for more meaningful business insight.

 

References –

1.     https://energy.gov/oe/services/technology-development/smart-grid

2.     http://www.nrel.gov/docs/fy15osti/62611.pdf

 

Shailesh Jain's picture

Thank Shailesh for the Post!

Energy Central contributors share their experience and insights for the benefit of other Members (like you). Please show them your appreciation by leaving a comment, 'liking' this post, or following this Member.

Discussions

Ben Schultz's picture
Ben Schultz on Dec 1, 2019 7:45 am GMT

Further, ‘Self-Learning Grids’ can optimize failover switching and minimize downtime or at least the scale of blackouts. However, we will need to develop the right algorithms and a lot of data & examples to train the grids for Self-Learning.

Could you please explain how this training is initiated and what it entails? Sounds interesting, but I'm a bit unclear. Is this a matter of automated load distribution based on machine learning?

Cheers! 

Get Published - Build a Following

The Energy Central Power Industry Network is based on one core idea - power industry professionals helping each other and advancing the industry by sharing and learning from each other.

If you have an experience or insight to share or have learned something from a conference or seminar, your peers and colleagues on Energy Central want to hear about it. It's also easy to share a link to an article you've liked or an industry resource that you think would be helpful.

                 Learn more about posting on Energy Central »