IEM special seminar series in energy storage systems: Online Battery Control in Active Distribution Grids Using Lyapunov Optimization and Reinforcement Learning
Event details
| Date | 22.03.2022 |
| Hour | 10:00 › 11:00 |
| Speaker | Eleni Stai, (Post-doctoral Researcher, ETHZ, Zurich, Switzerland) |
| Location | Online |
| Category | Conferences - Seminars |
| Event Language | English |
Abstract: Energy storage in the form of batteries will likely play a crucial role in the operation of distribution grids that are characterized by a continuously growing integration of uncertain distributed energy resources. In this talk, we present computationally efficient real-time control schemes for batteries in active distribution grids with lookahead state-of-energy constraints. The goal is to follow a previously computed dispatch plan or to optimize a monetary cost from buying and selling power at the point of common coupling. However, the lookahead constraints render the battery decisions non-trivial. The common practice in literature to solve this problem is Model Predictive Control (MPC), which does not scale for large grids.
We first propose iterative Lyapunov Real-time Control (iLypRC), a fast online algorithm, which does not need forecasts. ILypRC is designed via Lyapunov optimization and requires only bounds on the uncertain quantities for each real-time interval. It efficiently accounts for grid losses, battery efficiency and grid constraints via iterative linearizations of the power flow equations. We compute a theoretical upper bound on the difference between the cost of iLypRC with the cost of an oracle. We show via numerical examples that iLypRC achieves a cost very close to that of MPC with good forecast, but iLypRC needs no forecast and has much lower run time complexity. In addition, when the MPC forecast is inaccurate, iLypRC outperforms MPC.
Second, we investigate a reinforcement learning approach based on the Deep Deterministic Policy Gradient (DDPG) algorithm. To satisfy the lookahead battery constraints we adapt the experience replay technique used in DDPG. To guarantee the satisfaction of the hard grid constraints, we introduce a safety layer that performs constrained optimization. We show that it can achieve costs close to MPC and Lyapunov, while reducing the computational time by multiple orders of magnitude.
Bio: Eleni Stai is a Postdoctoral researcher with the Power Systems Laboratory at ETHZ. She received the Diploma in Electrical and Computer Engineering from the National Technical University of Athens (NTUA), Greece, in 2009, the B.Sc. in Mathematics from the National and Kapodistrian University of Athens, Greece, in 2013, the M.Sc. in Applied Mathematical Sciences from NTUA in 2014 and the Ph.D. in Electrical Engineering from NTUA in 2015. From 2016 to 2020, she was a Postdoctoral researcher with the Laboratory for Communications & Applications 2 at EPFL. She has received the Chorafas Foundation Best Ph.D. Thesis award, the Thomaidis Foundation Best M.Sc. Thesis award and a Best Paper Award in ICT 2016. Her main research interests include battery management and control in active distribution grids, smart-grid control and applications, network design and optimization. She has co-authored the book “Evolutionary Dynamics of Complex Communications Networks” (Taylor and Francis Group, CRC Press).
We first propose iterative Lyapunov Real-time Control (iLypRC), a fast online algorithm, which does not need forecasts. ILypRC is designed via Lyapunov optimization and requires only bounds on the uncertain quantities for each real-time interval. It efficiently accounts for grid losses, battery efficiency and grid constraints via iterative linearizations of the power flow equations. We compute a theoretical upper bound on the difference between the cost of iLypRC with the cost of an oracle. We show via numerical examples that iLypRC achieves a cost very close to that of MPC with good forecast, but iLypRC needs no forecast and has much lower run time complexity. In addition, when the MPC forecast is inaccurate, iLypRC outperforms MPC.
Second, we investigate a reinforcement learning approach based on the Deep Deterministic Policy Gradient (DDPG) algorithm. To satisfy the lookahead battery constraints we adapt the experience replay technique used in DDPG. To guarantee the satisfaction of the hard grid constraints, we introduce a safety layer that performs constrained optimization. We show that it can achieve costs close to MPC and Lyapunov, while reducing the computational time by multiple orders of magnitude.
Bio: Eleni Stai is a Postdoctoral researcher with the Power Systems Laboratory at ETHZ. She received the Diploma in Electrical and Computer Engineering from the National Technical University of Athens (NTUA), Greece, in 2009, the B.Sc. in Mathematics from the National and Kapodistrian University of Athens, Greece, in 2013, the M.Sc. in Applied Mathematical Sciences from NTUA in 2014 and the Ph.D. in Electrical Engineering from NTUA in 2015. From 2016 to 2020, she was a Postdoctoral researcher with the Laboratory for Communications & Applications 2 at EPFL. She has received the Chorafas Foundation Best Ph.D. Thesis award, the Thomaidis Foundation Best M.Sc. Thesis award and a Best Paper Award in ICT 2016. Her main research interests include battery management and control in active distribution grids, smart-grid control and applications, network design and optimization. She has co-authored the book “Evolutionary Dynamics of Complex Communications Networks” (Taylor and Francis Group, CRC Press).
Practical information
- General public
- Free
Organizer
- Electrical and Micro Engineering Institute (IEM)
Contact
- Prof. Jean-Philippe Thiran, IEM Director