Power system structure optimization based on reinforcement learning and sparse constraints under DoS attacks in cloud environments

In this paper we explain how to design intelligent agents able to process the information acquired from interaction with a system to learn a good control policy and show how the methodology can be applied to control some devices aimed to damp electrical power oscillations. The control problem is formalized as a discrete-time optimal control problem and the information acquired from interaction with the system is a set of samples, where each sample is composed of four elements: a state, the action taken while being in this state, the instantaneous reward observed and the successor state of the system. To process this information we consider reinforcement learning algorithms that determine an approximation of the so-called Q-function by mimicking the behavior of the value iteration algorithm. Simulations are first carried on a benchmark power system modeled with two state variables. Then we present a more complex case study on a four-machine power system where the reinforcement learning algorithm controls a Thyristor Controlled Series Capacitor (TCSC) aimed to damp power system oscillations.

Download Full-text

Marginal Value of Vehicle-to-Grid Ancillary Service in a Power System with Variable Renewable Energy Penetration and Grid Side Flexibility

Energies ◽

10.3390/en14227577 ◽

2021 ◽

Vol 14 (22) ◽

pp. 7577

Author(s):

Ryosuke Kataoka ◽

Kazuhiko Ogimoto ◽

Yumiko Iwafune

Keyword(s):

Renewable Energy ◽

Power System ◽

Ancillary Services ◽

Load Frequency Control ◽

System Structure ◽

System Operation ◽

Power System Operation ◽

Vehicle To Grid ◽

Marginal Value ◽

Partial Load

Regulating the frequencies of power grids by controlling electric vehicle charging and discharging, known as vehicle-to-grid (V2G) ancillary services, is a promising and profitable means of providing flexibility that integrates variable renewable energy (VRE) into traditional power systems. However, the ancillary services market is a niche, and the scale, saturation, and time-dependency are unclear when assuming future changes in the power system structure. We studied the marginal value of V2G ancillary services as a balancing capacity of the power system operation on the load-frequency control (LFC) timescale and evaluated the reasonable maximum capacity of the LFC provided by V2G. As a case study, we assumed that the Japanese power system would be used under various VRE penetration scenarios and considered the limited availability time of V2G, based on the daily commuter cycle. The power system operation was modeled by considering pumped storage, interconnection lines, and thermal power–partial load operations. The results show that the marginal value of V2G was greater during the daytime than overnight, and the maximum cost saving (USD 705.6/EV/year) occurred during the daytime under the high-VRE scenario. Improving the value and size of V2G ancillary services required coordination with energy storage and excess VRE generation.

Download Full-text