In recent years, there has been an increasing need for effective voltage controls in power systems due to the growing complexity and dynamic nature of practical power grid operations. Deep reinforcement learning (DRL) techniques now have been widely explored and applied to various electric power operation analyses under different control structures. With massive data available from phasor measurement units (PMU), it is possible to explore the application of DRL to ensure that electricity is delivered reliably.For steady-state power system voltage regulation and control, this study proposed a novel deep reinforcement learning (DRL) based method to provide voltage control that can quickly remedy voltage violations under different operating conditions. Multiple types of devices, adjustable voltage ratio (AVR) and switched shunts, are considered as controlled devices. A modified deep deterministic policy gradient (DDPG) algorithm is applied to accommodate both the continuous and discrete control action spaces of different devices. A case study conducted on the WECC 240-Bus system validates the effectiveness of the proposed method. System dynamic stability and performance after serious disturbances using DRL are further discussed in this study. A real-time voltage control method is proposed based on DRL, which continuously regulates the excitation system in response to system disturbances. Dynamic performance is considered by incorporating historical voltage data, voltage rate of change, voltage deviation, and regulation amount. A versatile transmission-level power system dynamic training and simulation platform is developed by integrating the simulation software PSS/E and a user-written DRL agent code developed in Python. The platform developed facilitates the training and testing of various power system algorithms and power grids in dynamic simulations with all the modeling capabilities available within PSS/E. The efficacy of the proposed method is evaluated based on the developed platform. To enhance the controller's resilience in addressing communication failures, a dynamic voltage control method employing the Multi-agent DDPG algorithm is proposed. The algorithm follows the principle of centralized training and decentralized execution. Each agent has independent actor neural networks and critic neural networks. Simulation outcomes underscore the method’s efficacy, showcasing its capability in providing voltage support and handling communication failures among agents.

Event identification is increasingly recognized as crucial for enhancing the reliability, security, and stability of the electric power system. With the growing deployment of Phasor Measurement Units (PMUs) and advancements in data science, there are promising opportunities to explore data-driven event identification via machine learning classification techniques. This dissertation explores the potential of data-driven event identification through machine learning classification techniques. In the first part of this dissertation, using measurements from multiple PMUs, I propose to identify events by extracting features based on modal dynamics. I combine such traditional physics-based feature extraction methods with machine learning to distinguish different event types.Using the obtained set of features, I investigate the performance of two well-known classification models, namely, logistic regression (LR) and support vector machines (SVM) to identify generation loss and line trip events in two datasets. The first dataset is obtained from simulated events in the Texas 2000-bus synthetic grid. The second is a proprietary dataset with labeled events obtained from a large utility in the USA. My results indicate that the proposed framework is promising for identifying the two types of events in the supervised setting. In the second part of the dissertation, I use semi-supervised learning techniques, which make use of both labeled and unlabeled samples.I evaluate three categories of classical semi-supervised approaches: (i) self-training, (ii) transductive support vector machines (TSVM), and (iii) graph-based label spreading (LS) method. In particular, I focus on the identification of four event classes i.e., load loss, generation loss, line trip, and bus fault. I have developed and publicly shared a comprehensive Event Identification package which consists of three aspects: data generation, feature extraction, and event identification with limited labels using semi-supervised methodologies. Using this package, I generate eventful PMU data for the South Carolina 500-Bus synthetic network. My evaluation confirms that the integration of additional unlabeled samples and the utilization of LS for pseudo labeling surpasses the outcomes achieved by the self-training and TSVM approaches. Moreover, the LS algorithm consistently enhances the performance of all classifiers more robustly.

Renewable energy and carbon reduction policies are creating new challenges for electricity markets. To achieve carbon-free goals, large-scale battery energy storage systems (BESSs) are necessary to ensure grid reliability and flexibility. The impact of BESSs on market and grid operation, as well as the optimal portfolio across the energy and ancillary services markets, must be analyzed to guide their operation. At the same time, the expansion of renewable and storage resources and the adoption of carbon reduction policies have introduced new complexities to the bidding behavior of market participants, which cannot be easily described by cost-based bidding objectives. In response to these challenges, this dissertation aims to achieve two research objectives: (I) enable BESS participation in energy and ancillary services markets under uncertainties, considering the battery's degradation cost; (II) identify robust bidding objectives for electricity market participants based on their historical bidding data. Three optimization frameworks are proposed in Part I to model a BESS as a price-maker in energy markets, evaluating its impact on market outcomes. The preliminary framework models automatic generation control signals, while the detailed framework proposes a participation factor for dispatching AGC signals and accounts for battery degradation costs. The stochastic framework models spinning reserve deployment with uncertainty and propose an optimization-based approximation method based on reinforcement learning. Case studies on proposed frameworks validate operational models for Battery Energy Storage Systems (BESS) and markets, showing the accuracy and efficiency of the approximation approach. Key findings include that accurate degradation cost modeling is essential, and participation in ancillary services markets is more profitable. Part II proposes a data-driven approach using Adversarial Inverse Reinforcement Learning to identify robust bidding objectives for electricity market participants. It introduces a tailored reinforcement learning model for bidding objective identification without data discretization, and a special policy structure compliant with multi-segment bidding rules. Two approaches are suggested for electricity market environment modeling in RL/IRL problems, ensuring the robustness of the identified bidding objective. Three case studies validated the accuracy and robustness of the proposed bidding objective identification method in various application scenarios.

Fault detection is an integral part for power systems as without its proper study, analysis and mitigation, people will not be able to power the various appliances and equipment required in all aspects of life. One such type of fault which is very criticalin an electrical cable but very difficult to spot is incipient fault. These momentary faults are observed for very short periods however, if it persists, this would lead to consequences like insulation wear-off and even, power outages. With the advent of machine learning in the power systems fraternity, this paper also uses a new and updated Active Learning algorithm to detect incipient fault data from a simulated test case. The objective of the paper is to detect the fault data accurately using this new and precise method. For purposes of data collection and training of the model, MATLAB Simulink and Python programming has been used respectively.

This report studies the optimal mechanisms for the vertically integrated utility to dispatch and incentivize the third-party demand response (DR) providers in its territory. A framework is proposed, with three-layer coupled Stackelberg and simultaneous games, to study the interactions and competitions among the pro t-seeking process of the utility, the third-party DR providers, and the individual end users (EUs) in the DR programs. Two coupled single-leader-multiple-followers Stackelberg games with a three-layer structure are proposed to capture the interactions among the utility (modeled in the upper layer), the third-party DR providers (modeled in the middle layer), and the EUs in each DR program (modeled in the lower layer). The competitions among the EUs in each DR program is captured through a non-cooperative simultaneous game. An inconvenience cost function is proposed to model the DR provision willingness and capacity of different EUs. The Stackelberg game between the middle-layer DR provider and the lower-layer EUs is solved by converting the original bi-level programming to a single level programming. This converted single level programming is embedded in an iterative algorithm toward solving the entire coupled games framework. Case studies are performed on IEEE 34-bus and IEEE69-bus test systems to illustrate the application of the proposed framework.

With the continued increase in the amount of renewable generation in the formof distributed energy resources, reliability planning has progressively become a more challenging task for the modern power system. This is because with higher penetration of renewable generation, the system has to bear a higher degree of variability and uncertainty. One way to address this problem is by generating realistic scenarios that complement and supplement actual system conditions. This thesis presents a methodology to create such correlated synthetic scenarios for load and renewable generation using machine learning. Machine learning algorithms need to have ample amounts of data available to them for training purposes. However, real-world datasets are often skewed in the distribution of the different events in the sample space. Data augmentation and scenario generation techniques are often utilized to complement the datasets with additional samples or by filling in missing data points. Datasets pertaining to the electric power system are especially prone to having very few samples for certain events, such as abnormal operating conditions, as they are not very common in an actual power system. A recurrent generative adversarial network (GAN) model is presented in this thesis to generate solar and load scenarios in a correlated manner using an actual dataset obtained from a power utility located in the U.S. Southwest. The generated solar and load profiles are verified both statistically and by implementation on a simulated test system, and the performance of correlated scenario generation vs. uncorrelated scenario generation is investigated. Given the interconnected relationships between the variables of the dataset, it is observed that correlated scenario generation results in more realistic synthetic scenarios, particularly for abnormal system conditions. When combined with actual but scarce abnormal conditions, the augmented dataset of system conditions provides a better platform for performing contingency studies for a more thorough reliability planning. The proposed scenario generation method is scalable and can be modified to work with different time-series datasets. Moreover, when the model is trained in a conditional manner, it can be used to synthesise any number of scenarios for the different events present in a given dataset. In summary, this thesis explores scenario generation using a recurrent conditional GAN and investigates the benefits of correlated generation compared to uncorrelated synthesis of profiles for the reliability planning problem of power systems.

The past few years have witnessed a significant growth of distributed energy resources (DERs) in power systems at the customer level. Such growth challenges the traditional centralized model of conventional synchronous generation, making a transition to a decentralized network with a significant increase of DERs. This decentralized network requires a paradigm change in modeling distribution systems in more detail to maintain the reliability and efficiency while accommodating a high level of DERs. Accurate models of distribution feeders, including the secondary network, loads, and DER components must be developed and validated for system planning and operation and to examine the distribution system performance. In this work, a detailed model of an actual feeder with high penetration of DERs from an electrical utility in Arizona is developed. For the primary circuit, distribution transformers, and cables are modeled. For the secondary circuit, actual conductors to each house, as well as loads and photovoltaic (PV) units at each premise are represented. An automated tool for secondary network topology construction for load feeder topology assignation is developed. The automated tool provides a more accurate feeder topology for power flow calculation purposes. The input data for this tool consists of parcel geographic information system (GIS) delimitation data, and utility secondary feeder topology database. Additionally, a highly automated, novel method to enhance the accuracy of utility distribution feeder models to capture their performance by matching simulation results with corresponding field measurements is presented. The method proposed uses advanced metering infrastructure (AMI) voltage and derived active power measurements at the customer level, data acquisition systems (DAS) measurements at the feeder-head, in conjunction with an AC optimal power flow (ACOPF) to estimate customer active and reactive power consumption over a time horizon, while accounting for unmetered loads. The method proposed estimates both voltage magnitude and angle for each phase at the unbalanced distribution substation. The accuracy of the method developed by comparing the time-series power flow results obtained from the enhancement algorithm with OpenDSS results and with the field measurements available. The proposed approach seamlessly manages the data available from the optimization procedure through the final model verification.

The penetration of renewable energy in the power system has grown considerably in the past few years. While this use may come with an abundance of advantages, it also introduces new challenges in operating the 100+ years old electrical network. Fundamentally, the power system relies on a real-time balance of generation and demand. However, renewable resources such as solar and wind farms are not available throughout the day. Furthermore, they introduce temporal variability to the generation process due to metrological factors, making the balance of generation and demand precarious. Utilities use standby units with reserve power and high ramp-up, ramp-down capabilities to ensure balance. However, such solutions can be very costly. An accurate scenario generation and forecasting of the stochastic variables (load and renewable resources) can help reduce the cost of these solutions. The goal of this research is to solve the scenario generation and forecasting problems using state-of-the-art machine learning techniques and algorithms. The training database is created using publicly available data obtained from NREL and the Texas-2000 bus system. The IEEE-30 bus system is used as the test system for the analysis conducted here. The conventional generators of this system are replaced with solar farms and wind farms. The ability of four machine learning algorithms in addressing the scenario generation and forecasting problems are investigated using appropriate metrics. The first machine learning algorithm is the convolutional neural network (CNN). It is found to be well-suited for the scenario generation problem. However, its inability to capture certain intricate details about the different variables was identified as a possible drawback. The second algorithm is the long-short term memory-variational auto-encoder (LSTM-VAE). It generated scenarios that are very similar to the actual scenarios indicating that it is suitable for solving the forecasting problem. The third algorithm is the conditional generative adversarial network (C-GAN). It was extremely effective in generating scenarios when the number of variables were small. However, its scalability was found to be a concern. The fourth algorithm is the spatio-temporal graph convolutional network (STGCN). It was found to generate representative correlated scenarios effectively.

Brushless DC (BLDC) motors are becoming increasingly common in various industrial and commercial applications such as micromobility and robotics due to their high torque density and efficiency. A BLDC Motor is a three-phase synchronous motor that is very similar to a non-salient Permanent Magnet Synchronous Motor (PMSM) with key differences lying in the non-ideal characteristics of the motor; the most prominent of these is BLDC motors have trapezoidal-shaped Back-Electromotive Force (BEMF). Despite their advantages, a present weakness of BLDC motors is the difficulty controlling these motors at standstill and low-speed conditions that require high torque. These operating conditions are common in the target applications and almost always necessitate the use of external sensors which introduce additional costs and points of failure. As such, sensorless based methods of position estimation would serve to improve system reliability, cost, and efficiency. High Frequency (HF) pulsating voltage injection in the direct axis is a popular method of sensorless control of salient-pole Interior-mount Permanent Magnet Synchronous Motors (IPMSM); however, existing methods are not sufficiently robust for use in BLDC and small Surface-mount Permanent Magnet Synchronous Motors (SPMSM) and are accompanied by other issues, such as acoustic noise. This thesis proposes novel improvements to the method of High Frequency Voltage Injection to allow for practical use in BLDC Motors and small SPMSM. Proposed improvements include 1) a hybrid frequency generator which allows for dynamic frequency scaling to improve tracking and eliminate acoustic noise, 2) robust error calculation that is stable despite the non-ideal characteristics of BLDC Motors, 3) gain engineering of Proportional-Integral (PI) type Phase-Locked-Loop (PLL) trackers that further lend stability, 4) observer decoupling mechanism to allow for seamless transition into state-of-the-art BEMF sensing methods at high speed, and 5) saliency boosting that allows for continuous tracking of saliency under high torque load. Experimental tests with a quadrature encoder and torque efficiency calculations on a dynamometer verify the practicality of the proposed algorithm and improvements.

In order to meet the world’s growing energy need, it is necessary to create a reliable, robust, and resilient electric power grid. One way to ensure the creation of such a grid is through the extensive use of synchrophasor technology that is based on devices called phasor measurement units (PMUs), and their derivatives, such as μPMUs. Global positioning system (GPS) time-synchronized wide-area monitoring, protection, and control enabled by PMUs has opened up new ways in which the power grid can tackle the problems it faces today. However, with implementation of new technologies comes new challenges, and one of those challenges when it comes to PMUs is the misuse of GPS as a method to obtain a time reference.The use of GPS in PMUs is very intuitive as it is a convenient method to time stamp electrical signals, which in turn helps provide an accurate snapshot of the performance of the PMU-monitored section of the grid. However, GPS is susceptible to different types of signal interruptions due to natural (such as weather) or unnatural (jamming, spoofing) causes. The focus of this thesis is on demonstrating the practical feasibility of GPS spoofing attacks on PMUs, as well as developing novel countermeasures for them. Prior research has demonstrated that GPS spoofing attacks on PMUs can cripple power system operation. The research conducted here first provides an experimental evidence of the feasibility of such an attack using commonly available digital radios known as software defined radio (SDR). Next, it introduces a new countermeasure against such attacks using GPS signal redundancy and low power long range (LoRa) spread spectrum modulation technique. The proposed approach checks the integrity of the GPS signal at remote locations and compares the data with the PMU’s current output. This countermeasure is a steppingstone towards developing a ready-to-deploy system that can provide an instant solution to the GPS spoofing detection problem for PMUs already placed in the power grid.