Search

Power system security is the power system’s capability to maintain its stability when a disturbance occurs. Transient instability is a phenomenon that threatens the security of the power system and synchronous generators. When rotor angle instability occurs in a synchronous generator, it is capable of driving the generator O.S. If the O.S operation of a generator sustains even for a brief period of time, it may result to serious mechanical and thermal damages to the machine. Therefore, faster identification of such conditions and in time isolation of the unstable generator from the power system is necessary for keeping the power system safe. Conventional methods for the identification of the generator O.S is based on the use of impedance relays. The purpose of this chapter is the prediction of the generator O.S with dynamic data of generator and power system, which can be gathered by PMUs in the fault and clearance period. Generator dynamic information includes variations of voltage phasor, active and reactive power, rotor angle, and speed of generator as well as the data of voltage and line flows in the adjacency of the generator that are collected in different time intervals. The measured information is continually updated in the moving window and with a special algorithm such as a three-step DT that performs the detection fault occurrence and clearance and prediction of O.S of generators. The proposed algorithm is working constantly as a relay, and the proposed algorithm recognizes the stability of the generator whenever changes occur in the generator parameter according to the severity of variations. Since training data perform an effective role in DT learning or other machine learning methods, to increase the learning ability of DT, training samples are prepared for having complete coverage of almost all load levels and different operation points. The proposed scheme is implemented on the generator of the IEEE 39-bus system with promising results.

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.

Over the past few decades, with the increasing influence of renewable energy sources, power systems have undergone a tremendous transformation, and the management of such systems has become increasingly difficult due to the intermittent nature of their production capacity. The increase in the influence of renewable energy sources has changed the overall behavior of the market. In the off-peak hours, renewable energy sources reduce the price of energy due to their unpredictability. It is necessary to use energy storage systems to add alternating sources to the network and transfer the energy produced by these sources from nonpeak hours to peak hours. Despite the aforementioned, today, due to the uncertainties in energy prices, the issue of profitability of energy storage systems for its owners is debatable. This chapter focuses on the optimal planning of energy storage systems with WT, PV, and dispatchable distributed generation, to participate in the energy market and increase the profitability of its related resources. In this chapter, a model is presented for optimal planning of energy storage systems along with related resources to participate in the energy market and increase their profits. The impact of energy price uncertainty on the profitability of energy storage systems and related resources has also been investigated. Also, the proposed model has been implemented on the IEEE 33-bus network using the Teaching–learning-based optimization algorithm, and the simulation results have been analyzed to evaluate the proposed model.

Operation of power networks requires examining all aspects of the concepts. In recent years, due to the expansion of the power grid and the development of new technologies, some new challenges have appeared, which required study and respect. With the development of technology and a comprehensive change of power systems, problem solutions also changed and led to challenges. These challenges can be explored in two ways. First, it is necessary to examine the new topology created in the configuration and network components. Second, find the interaction between components and problems due to the structural complexity. In future networks, intelligent structures will be activated, and all activities will be performed by these intelligent systems. Even energy exchange contracts will be changed, and smart contracts will be applicable. Also, the volume of data exchanges increase that results in a huge change in communication structures. Big data and neural networks, including machine learning, will be widely used, and control and monitoring systems need to be accurate online and in real time. Therefore, it is necessary to properly examine the new challenges of power networks and analyze the issues accordingly.

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.