Open Access Open Access  Restricted Access Subscription or Fee Access

Automation of Control Processes of an Electric Power System with Baseload Nuclear Generation and a High Share of Renewable Energy Sources Based on Artificial Intelligence and Machine Learning

I. Alfimov

Abstract



The study was conducted to assess the possibilities of increasing the frequency stability of an electric power system with baseload nuclear generation and a high share of renewable energy sources by automating control processes based on artificial intelligence algorithms. Methodologically, the work was based on the creation and validation of a digital twin of the electric power system using realistic load and generation profiles, as well as on parameterised modelling of different classes of small modular nuclear reactors and the implementation of adaptive control and forecasting algorithms. The main results showed that with an increase in the share of renewable energy sources to 50-60%, the integration of small modular reactors made it possible to reduce the maximum frequency deviations to the range of 0.07-0.1 Hz compared to 0.12-0.15 Hz in baseline scenarios without such reactors. The frequency change rate decreased to 0.25-0.35 Hz/s versus 0.45-0.6 Hz/s, and the time for the frequency to return to the permissible range was reduced from 18-22 s to 9-13 s. The smallest proportion of intervals with critical deviations above 0.1 Hz was recorded for systems with high thermal inertia of reactors. The critical instability threshold was set at about 40% of renewable generation. Regional analysis for France, the USA, and Canada showed that the greatest stabilisation effect was achieved in decentralised and low-inertia networks. The practical value of the study lies in supporting the configuration of baseload generation, automated frequency control, and stability assessment in power systems with high shares of renewable energy sources.

Keywords


Dynamic stability, frequency stability, power grid inertia, digital twin, rate of change of frequency.

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. Journal never mentioned that we have DOI number. However, to get free DOI, author can register your work which published with Zonodo (https://zenodo.org/signup/). We have no objection for this open access repository.