Search

Dynamic Security Assessment (DSA) for the future power system is expected to be increasingly complicated with the higher level penetration of renewable energy sources (RES) and the widespread deployment of power electronic devices, which drive new dynamic phenomena. As a result, the increasing complexity and the severe computational bottleneck in real-time operation encourage researchers to exploit machine learning to extract offline security rules for the online assessment. However, traditional machine learning methods lack in providing information on the confidence of their corresponding predictions. A better understanding of confidence of the prediction is of key importance for Transmission System Operators (TSOs) to use and rely on these machine learning methods. Specifically, from the perspective of topological changes, it is often unclear whether the machine learning model can still be used. Hence, being aware of the confidence of the prediction supports the transition to using machine learning in real-time operation. In this paper, we propose a novel Conditional Bayesian Deep Auto-Encoder (CBDAC) based security assessment framework to compute a confidence metric of the prediction. This informs not only the operator to judge whether the prediction can be trusted, but it also allows for judging whether the model needs updating. A case study based on IEEE 68-bus system demonstrates that CBDAC outperforms the state-of-the-art machine learning-based DSA methods and the models that need updating under different topologies can be effectively identified. Furthermore, the case study verifies that effective updating of the models is possible even with very limited data. [ABSTRACT FROM AUTHOR]

This paper presents a novel, unified approach for generating high-quality datasets for training machine-learned models for real-time security assessment in power systems. Synthetic data generation methods that extrapolate beyond historical data can be inefficient in generating feasible and rare operating conditions (OCs). The proposed approach balances the trade-off between historically relevant OCs and rare but feasible OCs. Unlike conventional methods that rely on historical records or generic sampling, our approach results in datasets that generalise well beyond similar distributions. The proposed approach is validated through experiments on the IEEE 118-bus system, where a decision tree model trained on data generated using our approach achieved 97 % accuracy in predicting the security label of rare OCs, outperforming baseline approaches by 41 % and 20 %. This work is crucial for deploying reliable machine-learned models for real-time security assessment in power systems undergoing decarbonisation and integrating renewable energy sources. • Machine-learned models as surrogates to predict real-time security of power systems. • Quality datasets are crucial to train high performing Machine Learning (ML) models. • Method trades-off historically relevant operating conditions (OCs) and 'rare' feasible OCs. • Method generates datasets that generalise well beyond similar distributions. • Studies carried out on the IEEE 118-bus validate the proposed method. [ABSTRACT FROM AUTHOR]

Machine learning (ML) for real-time security assessment requires a diverse training database to be accurate for scenarios beyond historical records. Generating diverse operating conditions is highly relevant for the uncertain future of emerging power systems that are completely different to historical power systems. In response, for the first time, this work proposes a novel split-based sequential sampling approach based on optimisation that generates more diverse operation scenarios for training ML models than state-of-the-art approaches. This work also proposes a volume-based coverage metric, the convex hull volume (CHV), to quantify the quality of samplers based on the coverage of generated data. This metric accounts for the distribution of samples across multidimensional space to measure coverage within the physical network limits. Studies on IEEE test cases with 6, 68 and 118 buses demonstrate the efficiency of the approach. Samples generated using the proposed split-based sampling cover 37.5% more volume than random sampling in the IEEE 68-bus system. The proposed CHV metric can assess the quality of generated samples (standard deviation of 0.74) better than a distance-based coverage metric which outputs the same value (standard deviation of < 0. 001) for very different data distributions in the IEEE 68-bus system. As we demonstrate, the proposed split-based sampling is relevant as a pre-step for training ML models for critical tasks such as security assessment. • Database generation is pivotal in machine learning for Dynamic Security Assessment • GAPSPLIT ∗ approach sequentially samples pre-fault operating conditions • Convex hull volume (CHV) assesses the quality of a generic sampler • Studies carried out on the IEEE test systems with 6 , 68 , and 118 buses • Gapsplit samples cover 37.5 % more volume than random sampling [ABSTRACT FROM AUTHOR]

Weather forecast models are essential for sustainable energy systems. However, forecast accuracy may not be the best metric for developing forecast models. A more or less conservative forecast may be preferred over pure accuracy. For example, forecasting accurately in times of energy-deprived situations may be more important than in times of excess wind power generation. This is not accounted for when learning a wind power forecast without system knowledge. Wind power forecasts directly impact system energy schedules. Therefore, to optimise system costs, our paper proposes a neural network structure for wind power forecasts directly considering varying energy system conditions. To train this neural network optimally, this paper models the system dispatch and their costs as an optimisation problem. Then, this paper connects the neural network with the optimisation model. In this connection, the implicit function theorem and the Karush–Kuhn–Tucker (KKT) conditions provide the system cost gradients during the training of the neurons. A case study using onshore and offshore weather data from Germany and The Netherlands showed forecast errors of system costs reduced by up to 10 % with high wind capacity. Wind curtailment was reduced by more than 20 % for individual cases but increased overall. Modified cases of the optimal power flow (OPF) with tighter line constraints led to a higher advantage of the proposed method. The approach led to more consistent forecast performance and reduced error variance by up to 70 %. • Neural networks for wind power forecasts considering varying energy system conditions • System dispatch and costs as an optimisation during the neural network training • The implicit function theorem and KKT conditions provide the system cost gradients • German and Dutch studies confirmed trained forecasts reduced system costs up to 10 % • More consistent forecast performance with reduced error variance by up to 70 %. [ABSTRACT FROM AUTHOR]