Jin Wei, The University of Akron
Pirathayini Srikantha, Western University
SCOPE AND MOTIVATION
Recent years have witnessed the rapid evolution of Artificial Intelligence (AI) techniques, such as machine learning, computer vision, and natural language processing, and their dramatically increased applications in modern industrial systems such as energy systems and transportation systems. For smart energy systems, AI technology provides intelligent and effective tools for electricity generation and delivery, marketing management, and emergency response. For example, AI has been applied to produce ultra-accurate forecasts making it feasible to integrate much more renewable energy into the power grids. Various machine learning-based security assessment tools have been designed for power grids. Additionally, computer vision techniques have been exploited for remote power monitoring and control. Therefore, although AI is in its early stages of implementation, it is poised to revolutionize the way we produce, transmit, and consume energy. It also paves the path to a self-healing and resilient power grid that can adapt to any changes in the system. This is especially important in today’s grid into which highly fluctuating power components like distributed generation sources, electric vehicles and storage systems are present. These introduce significant vulnerabilities due to the inherent infrastructure limitations in the grid which will otherwise result in exorbitant costs to upgrade. In addition to being more responsive, applying artificial intelligence in the power grid will also enable the operators to plan resources based on demand/supply trends and identify vulnerabilities. Thus, artificial intelligence in the energy systems is highly promising with a wide range of rich and exciting research opportunities.
The goal of this workshop is to solicit high-quality research articles proposing the state-of-the-art AI-based solutions to improve the stability, efficiency, security and resilience of the energy systems. Prospective authors are invited to submit manuscripts for possible publications in this special issue. Original research as well as high-quality review articles are all welcome.
WORKSHOP DATE: October 31st , 2018
14: 00 to 14:30 pm: Pirathayini Srikantha, “Pareto Optimality based Appliance Disaggregation via Hybrid Hidden Markov Model”
14:30 to 14:50 pm: Reinforcement Learning Control Algorithm for a PV-Battery-System Providing Frequency Containment Reserve Power
14:50 to 15:10 pm: Day-ahead electricity consumption prediction of a population of households: analyzing different machine learning techniques based on real data from RTE in France
15:10 to 15:30 pm: A Cost-efficient Software Testbed for Cyber-Physical Security in IEC 61850-based Substations
15:30 to 15: 50 pm: Break
15:50 to 16:10 pm: Synchronization Games in P2P Energy Trading
16:10 to 16:30 pm: Online Power Quality Disturbance Classification with Recurrent Neural Network
16:30 to 16:50 pm: Stand-Alone Distributed PV Systems: Maximizing Self Consumption and User Comfort using ANNs
16:50 to 17:10 pm: Is Machine Learning in Power Systems Vulnerable?
17:10 to 17:30 pm: Residential Short-Term Load Forecasting Using Convolutional Neural Networks
Dr. Islam S. Bayram, Academia, Hamad Bin Khalifa University and Qatar Environment and Energy Research Institute
Dr. Abiodun Iwayemi, Industry, Vermont Energy Investment Corporation
Dr. Francois Fouquet, Academia, University of Luxembourg
Dr. Jinsub Kim, Academia, Oregon State University
Dr. Miao He, Academia, Texas Tech University
Dr. Rakesh Bobba, Oregon State University
Dr. Amin Khodaei, Academia, University of Denver