Live Webinar Events

The Smart Grid describes a next-generation electrical power system that is typified by the increased use of communications and information technology in the generation, delivery, and consumption of electrical energy worldwide.

IEEE Smart Grid hosts a series of complimentary webinars on varying aspects of global grid modernization.

Application of Machine Learning in Power Systems - Part 1
Presented by: Qiuhua Huang, Pacific Northwest National Laboratory
Thursday, October 25, 2018 1:00PM EDT 
In Part I, this webinar will begin with a short tutorial of machine learning, then provide an overview of application of machine learning in power generation, transmission and distribution systems, including the history, recent applications and lessons learned. Lastly, future work and research directions will be discussed. Read more. 
Click Here to Register NOW 

Application of Machine Learning in Power Systems - Part 2

Presented by: Qiuhua Huang & Jason Hou- Pacific Northwest National Laboratory
Thursday, Nov 1, 2018 1:00PM EDT 
Part II of this webinar will focus on the-state-of-the-art applications with some R&D work from Pacific Northwest National Laboratory as examples. These include PMU data analytics, uncertainty quantification(UQ), tie-line exchange prediction, adaptive Remedial Action Scheme (RAS) settings using machine learning, power system emergency control using deep reinforcement learning, which powered AlphaGo to beat human Go champions. The ultimate goal of these projects is to leverage state-of-the-art machine learning technologies to make decision-makings in power system control centers—the “brain” of the grid— adaptive, robust and smart. Read more. 
Click Here to Register NOW

Next-Generation Smart Grids --- Synchronized and Democratized Smart Grids
Presented by: Qing-Chang Zhong, Illinois Institute of Technology & Syndem LLC
Thursday, November 15, 2018 1:00PM ET 
Power systems are going through a paradigm change. Centralized generating facilities are being replaced by millions of widely dispersed non-synchronous relatively small renewable or alternative power plants, plug-in EVs, and energy storage units. Moreover, the majority of loads are expected to actively take part in the grid regulation. In this webinar, it will be shown that the synchronization mechanism of conventional synchronous machines, which has underpinned the power systems for over 100 years, can continue playing its fundamental role in power systems. All power electronics-interfaced suppliers and loads can be equipped with this fundamental mechanism to behave like virtual synchronous machines. As a result, they can take part in the regulation of system frequency and voltage, in a synchronized and democratized (SYNDEM) manner. This leads to a unified grid architecture (called the SYNDEM grid architecture) that unifies the integration and interaction of all players with the grid and harmonizes power systems players. It also releases the communication infrastructure from low-level control and opens up the prospect of achieving autonomous operation for power systems. This holistic solution will considerably enhance the stability, scalability, operability, security, reliability and resiliency of the next-generation smart grid. Read more. 
Click Here to Register NOW

Application of Adaptive Hybrid Deep Learning for Power System State Estimation
Presented by: Qun Zhou, University of Central Florida
Thursday, November 29, 2018 1:00PM ET 
Deep learning is powerful in data-driven applications, such as computer vision and natural language processing. Power system applications such as state estimation are data-driven in nature as the amount of measurement data is rapidly increasing with emerging sensing technology. Nevertheless, conventional state estimation is considered as single-snapshot, which estimates system variables by only using the measurement data at the moment. In fact, power system states are intrinsically correlated in time, but the true dynamics are very challenging to model. In this research, deep learning is employed to learn this dynamics and temporal correlations are explored among historical measurements. The proposed state estimation method takes into account the physical power flow model, and estimate system variables in an online manner. We investigate the two most recent deep learning networks – convolutional neural net and long short-term memory net, and compare the results with the traditional approach in terms of accuracy and robustness on the IEEE 118-bus system. The results demonstrate that deep learning is indeed capable to capture the temporal correlations and improve the estimation performance. Read more. 
Click Here to Register NOW