Configuration of the Actor and Critic Network of the Deep Reinforcement Learning controller for Multi-Energy Storage System

The computational burden and the time required to train a deep reinforcement learning (DRL) can be appreciable, especially for the particular case of a DRL control used for frequency control of multi-electrical energy storage (MEESS). This paper presents an assessment of four training configurations of the actor and critic network to determine...

Descriptive Statistical Analysis of Frequency control-related variables of Nordic Power System

This paper presents a descriptive statistical analysis (DSA) of time-series of electro-mechanical quantities related to the frequency control (e.g. kinetic energy (KE), electrical frequency and power demand) of the Nordic power system (NPS). The idea of the DSA is to identify main observables features and patterns between these variables....

Security Assessment of System Frequency Response

Low inertia power systems experience more extreme frequency dynamics immediately after a disturbance. A higher rate of change of frequency (ROCOF) contributes to a lower frequency nadir which could trigger load shedding schemes. Active power injections in a time frame of two seconds or less are necessary to maintain frequency stability. This...