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...

Optimal UFLS Settings: An Assessment of Frequency System Response Indicators

This paper investigates the positive changes in the system frequency response indicators caused by the implementation of a set of optimal settings of an under-frequency load shedding (UFLS) scheme. The optimal UFLS scheme is optimised by minimising the total amount of load shedding and considering the recovery process of the system frequency...

Frequency Support of Fast-Multi-Energy Storage Systems in Low Rotational Inertia Scenarios

Modern power systems are increasing the connection of power electronic converters (PECs), and new inertia-less technologies displace the synchronous generation units. Therefore, the total rotational system inertia is reduced, creating new problems related to the system frequency control and stability. Several mechanisms to enable the PECs with...

Under-Frequency Load Shedding in Mongolia: Simulation Assessment Considering Inertia Scenarios

Mongolia power system (MPS) is evolving quite fast, and the integration of renewable resources (mainly wind power and solar photovoltaic) reached 20% by 2019. The MPS is interconnected to Russia in order to cover local energy deficits, especially during freezing winters. However, the interconnection to Russia is a sensible element of the MPS,...

Improvement of the Frequency Response Indicators by Optimal UFLS Scheme Settings

This research investigates the positive changes in the system frequency response indicators caused by the implementation of a set of optimal settings of an under-frequency load shedding (UFLS) scheme. The optimal under-frequency load shedding (UFLS) scheme is optimised by minimising the total amount of load shedding and taking into account...

Assessment of Under-Frequency Load Shedding in Mongolia Considering Inertia Scenarios

The Mongolian power system (MPS) has been changing in recent years mainly by the integration of wind power and solar photovoltaic sources which until 2019 has been reached a 20% of the total generation sources. The interconnection with the Russian power system is crucial from the frequency control and stability point of view, especially during...