Search

Machine learning (ML) methods and their applications are among the most innovative and attractive engineering topics. The advent of artificial intelligence has given birth to various tools widely used in science and engineering. ML is utilized in solving various problems in the power system engineering community, such as power system planning and operation. In this chapter, the authors will investigate different machine learning methods, and we will discuss their applications in solving power system planning problems, including load forecasting. The authors will discuss different ML methods used in the power engineering field, and other ML applications in planning problems such as optimization problems will be studied. This chapter’s main objective is to serve as an introduction to ML for power system planning and the basic concepts of the ML methods commonly used in this field.

The expansion of electric power systems and increasing energy demand leads to operating close stability margins and an increase in the risk of voltage collapse. In such a situation, a fast and accurate assessment of voltage stability is necessary to prevent large-scale blackouts. Machine learning techniques are widely applied in the voltage stability assessment according to their ability to train offline and predict results online. This paper presents a novel machine learning framework employed in the online voltage stability assessment. The framework consists of four main stages: database generation, training model, performance evaluation, and online application. For the determined operating conditions, the database is constructed using random sampling based on the continuation power flow. Randomly generated samples are labeled as “secure” or “insecure” using the WECC voltage security criteria. Various machine learning methods are trained using several training sets that are obtained by applying importance sampling and dimensionality reduction. Also, hyperparameters tuning is employed to obtain the best performance; subsequently, the performance is evaluated using different measures such as accuracy and the CPU time. The framework robustness is demonstrated by adding noisy and missing data to the dataset. The proposed framework was tested on the IEEE 39-bus and IEEE 118-bus test. The results confirm the applicability of the proposed framework in the online voltage stability assessment.

Frequency Disturbance Events (FDEs) occur due to various events such as Generator Trip (GT), Line Outage (LO), and Load Disconnection (LD), which affect the stability of power systems. Depending on disturbance severity, it has small to severe effects on an integrated system's performance. Accurate and fast detection and classification of the event and its location are crucial in monitoring resource adequacy, preventing economic losses and blackouts. This paper, focusing on an online cutting-edge hierarchical methodology, first detects the event, then identifies its classification. Eventually, the exact location of FDE is found based on Phasor Measurement Units (PMUs) data. Compared to other counterparts, which focused only on classifying or locating events separately, in this paper, both aims are achieved using the suggested novel hierarchical framework. This research employs Deep Learning (DL) advances to develop a Recurrent Neural Network (RNN) model and a Long Short-Term Memory (LSTM) model to distinguish and locate FDEs with significant accuracy. In the research, only a few time-series of Rate-Of-Change-Of-Frequency (ROCOF) received from a limited number of PMUs is used as the DL algorithm's inputs. This hierarchical methodology is tested in New England 39-bus, IEEE 14 bus systems, and modified IEEE 118-bus system. The evaluation results demonstrate the potential application of the proposed models to detect and classify FDEs compared to conventional algorithms and the frequency-based DL model. The proposed models have achieved significant classification accuracy. Simultaneously, the models locate the events with competitive performance in terms of precision, recall, accuracy, and F1-score. © 2017 Elsevier Inc. All rights reserved.