Search

This paper proposes a fully data-driven approach for PMU-based pre-fault dynamic security assessment (DSA) with incomplete data measurements. The generative adversarial network (GAN), which is an emerging unsupervised deep learning technique based on two contesting deep neural networks, is used to address the missing data. While the state-of-the-art methods for missing data are dependent on PMU observability, they are limited by the placement of PMU and network topologies. Distinguished from existing methods, the proposed approach is fully data-driven and can fill up incomplete PMU data independent on PMU observability and network topologies. Therefore, it is more generalized and extensible. Simulation results show that, under any PMU missing conditions, the proposed method can maintain a competitively high DSA accuracy with a much less computation complexity. [ABSTRACT FROM AUTHOR]

As power systems are undergoing a significant transformation with more uncertainties, less inertia and closer to operation limits, there is increasing risk of large outages. Thus, there is an imperative need to enhance grid emergency control to maintain system reliability and security. Towards this end, great progress has been made in developing deep reinforcement learning (DRL) based grid control solutions in recent years. However, existing DRL-based solutions have two main limitations: 1) they cannot handle well with a wide range of grid operation conditions, system parameters, and contingencies; 2) they generally lack the ability to fast adapt to new grid operation conditions, system parameters, and contingencies, limiting their applicability for real-world applications. In this paper, we mitigate these limitations by developing a novel deep meta-reinforcement learning (DMRL) algorithm. The DMRL combines the meta strategy optimization together with DRL, and trains policies modulated by a latent space that can quickly adapt to new scenarios. We test the developed DMRL algorithm on the IEEE 300-bus system. We demonstrate fast adaptation of the meta-trained DRL polices with latent variables to new operating conditions and scenarios using the proposed method, which achieves superior performance compared to the state-of-the-art DRL and model predictive control (MPC) methods. [ABSTRACT FROM AUTHOR]

Due to the diversity of power consumption patterns, the false positive rate (FPR) of data-driven electricity theft detection (ETD) methods is too high to meet practical needs, which severely restricts the engineering application of data-based methods. To reduce FPR of ETD methods based on advanced metering infrastructure (AMI), a deep neural network with low FPR (LFPR-DNN) is proposed in this paper. First, a deep model is constructed based on one-dimensional convolution and residual network, which can automatically extract features from consumption data. Then, a two-stage training scheme is used to train the network. In the first stage, the conventional gradient descent algorithm is used to update the network weights. To minimize the impact of data imbalance on detection performance, focal loss is used. Besides, grid search is used to optimize the hyper-parameters of the model. In the second stage, with FPR as the optimization objective, the particle swarm optimization (PSO) algorithm is used to train the network. Finally, the proposed LFPR-DNN is verified by using the open Irish data set. Compared to other state-of-the-art classifiers, LFPR-DNN has the lowest FPR with 0.29% and the highest AUC with 99.42%. The FPR is reduced by an order of magnitude, which verifies the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

With the new feature of multi-energy coupling and the advancement of the energy market, Energy Internet (EI) has higher requirements for the efficiency and applicability of integrated energy response. This paper proposes an indirect multi-energy transaction (IMET) to promote multi-energy collaborative optimization in local energy market (LEM) and improve energy utilization through personalized responses from We-Energies (WEs). Firstly, an indirect customer-to-customer multi-energy transaction is modeled for local multi-energy coupling market which can satisfy privacy, preference and autonomy of users. The efficiency of energy matching can be promoted through the participation of conversion devices. In addition, multi-time scale hybrid trading mechanism is constructed with the consideration of the transmission speed of different energy sources. Meanwhile, energy transaction process is built as a Markov decision process (MDP) with deep reinforcement learning algorithm so that the system modeling error can be successfully avoided. Furthermore, a distributed training structure is utilized to obtain more experience for a wider range of scenarios. The results of numerical simulations demonstrate the performance of the proposed method. [ABSTRACT FROM AUTHOR]

Deep learning (DL) techniques have shown promising performance for designing data-driven power system transient stability assessment (TSA) models. However, due to the deep structure of the DL, the resulting model is always a black-box and hard to explain, which hinders its practical adoption by the industry. This paper proposes an interpretable DL-based TSA model to balance the TSA accuracy and transparency. The proposed method combines the strong nonlinear modelling capability of a deep neural network and the interpretability of a decision tree (DT). Through regularizing DL-based model with the average DT path length in the training process, the proposed interpretable DL-based TSA method can visually explain the TSA decision-making process. Simulation results have shown that the proposed method can deliver highly accurate TSA results and interpretable TSA decision-making rules, which can be used for designing preventive control actions. [ABSTRACT FROM AUTHOR]

This paper proposes a novel data driven framework for detecting topology transitions in a distribution network. The framework analyzes data from phasor measurement units (PMUs) and relies on the fact that changes in network topology results in changes in the structure and admittance of the network. Using voltage and current phasors recorded by PMUs, the proposed method approximates network parameters using an ensemble-based deep learning model and thus, it does not require any knowledge of network parameters and load models. Using the prediction error of the proposed model, a connectivity matrix which shows the status of switches is constructed. In contrast to other methods, this proposed framework does not require a library of voltage and current transients associated with possible network transitions. It can also detect simultaneous switching actions and is robust to noise and load variations. The model yields a lower error detection rate, and its performance is validated using a modified version of the IEEE 33 bus network and a real feeder located in Queensland, Australia, under full and partial observability conditions. The proposed model has also been compared with another data driven method in terms of inference time and error detection rates. [ABSTRACT FROM AUTHOR]

In order to reduce the dependence on accumulated experience that is difficult to replicate for the human dispatchers to make power generation scheduling more automatically, quickly, and intelligently, higher requirements are placed on the level of the auxiliary decision-making system. In this paper, a short-term scheduling problem was treated as a regression task that concentrates on how to learn a reliable statistic model that concludes the intrinsic logic of the dispatching policy from extensive historical dispatching experience. In this way, since Kullback-Leibler distance can better measure the distance between two distributions, we designed a novel GAN-based learning method for the scheduling task. Also, we proposed a feasible framework that combines the stage of learning, decision-making, and deployment to support the practical implementation of the proposed algorithm. In the experiment, a real case that takes short-term scheduling tasks on a regional large-scale power system is considered in our experiments. As a result, the comparison of several methods further shows the superiority of the proposed GAN-based method under our implementations. [ABSTRACT FROM AUTHOR]

This paper proposes a new deep learning (DL) based model-free robust method for bulk system on-line load restoration with high penetration of wind power. Inspired by the iterative calculation of the two-stage robust load restoration model, the deep neural network (DNN) and deep convolutional neural network (CNN) are respectively designed to find the worst-case system condition of a load pickup decision and evaluate the corresponding security. In order to find the optimal result within a limited number of checks, a load pickup checklist generation (LPCG) algorithm is developed to ensure the optimality. Then, the fast robust load restoration strategy acquisition is achieved based on the designed one-line strategy generation (OSG) algorithm. The proposed method finds the optimal result in a model-free way, holds the robustness to handle uncertainties, and provides real-time computation. It can completely replace conventional robust optimization and supports on-line robust load restoration which better satisfies the changeable restoration process. The effectiveness of the proposed method is validated using the IEEE 30-bus system and the IEEE 118-bus system, showing high computational efficiency and considerable accuracy. [ABSTRACT FROM AUTHOR]

With the increasing penetration of renewable energy, frequency response and its security are of significant concerns for reliable power system operations. Frequency-constrained unit commitment (FCUC) is proposed to address this challenge. Despite existing efforts in modeling frequency characteristics in unit commitment (UC), current strategies can only handle oversimplified low-order frequency response models and do not consider wide-range operating conditions. This paper presents a generic data-driven framework for FCUC under high renewable penetration. Deep neural networks (DNNs) are trained to predict the frequency response using real data or high-fidelity simulation data. Next, the DNN is reformulated as a set of mixed-integer linear constraints to be incorporated into the ordinary UC formulation. In the data generation phase, all possible power injections are considered, and a region-of-interest active sampling is proposed to include power injection samples with frequency nadirs closer to the UFLC threshold, which enhances the accuracy of frequency constraints in FCUC. The proposed FCUC is investigated on the IEEE 39-bus system. Then, a full-order dynamic model simulation using PSS/E verifies the effectiveness of FCUC in frequency-secure generator commitments. [ABSTRACT FROM AUTHOR]

Accurate models of power plants play an important role in maintaining the reliable and secure grid operations. In this paper, we propose a synchrophasor measurement-based generator parameter calibration method by a novel deep learning method with high computational efficiency. An elementary effects-based approach is developed to identify the critical parameters from a nonlinear system with much better performance than the widely used trajectory sensitivity-based method. Then, synchrophasor measurement-based conditional variational autoencoder is developed to estimate the parameters’ posterior distributions even in the presence of a high-dimensional case with eighteen critical parameters to be calibrated. The effectiveness of the proposed method is validated for a hydro generator with a very detailed model. The results show that the proposed approach can accurately and efficiently estimate the generator parameters’ posterior distributions even when the parameters true values are not in support of the prior distribution. [ABSTRACT FROM AUTHOR]

Power system control and transient stability analysis play essential roles in secure system operation. Control of power systems typically involves highly nonlinear and complex dynamics. Most of the existing works address such problems with additional assumptions in system dynamics, leading to a requirement for a complete and general solution. This paper, therefore, proposes a novel control framework for various power system control and stability problems leveraging a learning-based approach. The proposed framework includes a two-module structure that iteratively and jointly learns the candidate Lyapunov function and control law via deep neural networks in a learning module. Meanwhile, it guides the learning procedure towards valid results satisfying Lyapunov conditions in a falsification module. The introduced termination criteria ensure provable system stability. This control framework is verified through several studies handling different types of power system control problems. The results show that the proposed framework is generalizable and can simplify the control design for complex power systems with the stability guarantee and enlarged region of attraction. [ABSTRACT FROM AUTHOR]

This paper develops an efficient multi-agent deep reinforcement learning algorithm for cooperative controls in powergrids. Specifically, we consider the decentralized inverter-based secondary voltage control problem in distributed generators (DGs), which is first formulated as a cooperative multi-agent reinforcement learning (MARL) problem. We then propose a novel on-policy MARL algorithm, PowerNet, in which each agent (DG) learns a control policy based on (sub-)global reward but local states and encoded communication messages from its neighbors. Motivated by the fact that a local control from one agent has limited impact on agents distant from it, we exploit a novel spatial discount factor to reduce the effect from remote agents, to expedite the training process and improve scalability. Furthermore, a differentiable, learning-based communication protocol is employed to foster the collaborations among neighboring agents. In addition, to mitigate the effects of system uncertainty and random noise introduced during on-policy learning, we utilize an action smoothing factor to stabilize the policy execution. To facilitate training and evaluation, we develop PGSim, an efficient, high-fidelity powergrid simulation platform. Experimental results in two microgrid setups show that the developed PowerNet outperforms the conventional model-based control method, as well as several state-of-the-art MARL algorithms. The decentralized learning scheme and high sample efficiency also make it viable to large-scale power grids. [ABSTRACT FROM AUTHOR]

This paper proposes the design of two coordinated wide-area damping controllers (CWADCs) for damping low frequency oscillations (LFOs), while accounting for the uncertainties present in the power system. The controllers based on Deep Neural Network (DNN) and Deep Reinforcement Learning (DRL), respectively, coordinate the operation of different local damping controls such as power system stabilizers (PSSs), static VAr compensators (SVCs), and supplementary damping controllers for DC lines (DC-SDCs). The DNN-CWADC learns to make control decisions using supervised learning; the training dataset consisting of polytopic controllers designed with the help of linear matrix inequality (LMI)-based mixed $H_2/H_\infty$ optimization. The DRL-CWADC learns to adapt to the system uncertainties based on its continuous interaction with the power system environment by employing an advanced version of the state-of-the-art deep deterministic policy gradient (DDPG) algorithm referred to as bounded exploratory control-based DDPG (BEC-DDPG). The studies performed on a 33 machine, 127 bus equivalent model of the Western Electricity Coordinating Council (WECC) system-embedded with different types of damping controls demonstrate the effectiveness of the proposed CWADCs. [ABSTRACT FROM AUTHOR]

The uncertain nature of renewable energy resources (RERs) and fast demand response lead to recurring voltage violations in the power systems, which causes frequent transformer tap shifting and capacitor switching. Therefore, this paper resorts to the static var compensators (SVCs) to manage the bus voltages based on the multi-agent deep reinforcement learning (MA-DRL) algorithm. The proposed scheme includes several system agents and SVC agents to collaboratively adjust the injected reactive power to restrict the bus voltages within the normal range. All the agents are trained centrally and executed separately, which requires minimum communication cost. The IEEE 14-bus system, IEEE 300-bus system, and China 157-node urban power grid are used to verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Due to the deregulation of power systems worldwide, bidding behavior simulation research has gained prominence. One crucial element in these studies is accurately defining and modelling the individual reward function (or objective function). Considering the ubiquitous information barriers between market participants and researchers, the common way is to develop reward functions based on theoretical assumptions, which will inevitably cause deviations from the real world. However, since market data have gradually become transparent in recent years, especially data regarding historical bidding behaviors, it is feasible to introduce data-driven methods to identify the individual reward functions that are hidden in raw bidding data. Thus, this paper proposes a data-driven bidding objective function identification framework with three procedures. First, the bidding decision processes of participants are formulated as a standard Markov decision process. Second, a deep inverse reinforcement learning method that is based on maximum entropy is introduced to identify individual reward functions, whose high-dimensional nonlinearity could be saved in multilayer perceptions (MLPs). Third, a deep Q-network method is customized to simulate the individual bidding behaviors based on the obtained MLP-based objective functions. The effectiveness and feasibility of the proposed framework and methods are tested based on real market data from the Australian electricity market. [ABSTRACT FROM AUTHOR]

Fast insecurity early warning is the key technique to resist the dynamic insecurity risk, which becomes intractable due to the strong nonlinearity of hybrid AC/DC grids and the high uncertainty of wind generation. Considering dynamic security constraints and wind power uncertainty, this paper presents an insecurity early warning method based on decision tree (DT) and semi-supervised deep learning. First, semi-supervised deep learning is deployed to estimate the dynamic security limit of the critical interface of hybrid AC/DC grids. The system security is assessed by comparing the actual power transfer of the critical interface with the security limit. Then, operating conditions (OCs) are ranked into different insecure levels according to the type of preventive control actions that is needed to ensure the system security. Finally, oblique DT is utilized to identify insecurity classification boundaries in the wind power injection space. Insecure OC sets are constructed based on these classification boundaries. Simulation results of the real-life Jiangsu-Shanghai interconnected grid in east China demonstrate that the proposed method can fast construct the insecure OC sets corresponding to different insecure levels. [ABSTRACT FROM AUTHOR]

Resilience of a distribution system can be enhanced by efficient restoration of critical load following a major outage. Existing models include optimization approaches that consider available information without incorporating the inherent asynchrony of data arrival during execution of the restoration plan. Failure to consider the asynchronous nature of information arrival can lead to underutilization of critical resources. Moreover, analytical models become computationally inefficient for large scale systems. On the other hand, artificial intelligence (AI)-based tools have demonstrated efficient results for power system applications. In this paper, it is proposed a Reinforcement Learning (RL) model that learns how to efficiently restore a distribution system after a major outage. The proposed approach is based on a Monte Carlo Tree Search to expedite the training process. The proposed model strategy provides a robust decision-making tool for asynchronous and partial information scenarios. The results, validated with the IEEE 13-bus test feeder and IEEE 8500-node distribution test feeder, demonstrate the effectiveness and scalability of the proposed method. [ABSTRACT FROM AUTHOR]

The security-constrained optimal power flow (SCOPF) is fundamental in power systems and connects the automatic primary response (APR) of synchronized generators with the short-term schedule. Every day, the SCOPF problem is repeatedly solved for various inputs to determine robust schedules given a set of contingencies. Unfortunately, the modeling of APR within the SCOPF problem results in complex large-scale mixed-integer programs, which are hard to solve. To address this challenge, leveraging the wealth of available historical data, this paper proposes a novel approach that combines deep learning and robust optimization techniques. Unlike recent machine-learning applications where the aim is to mitigate the computational burden of exact solvers, the proposed method predicts directly the SCOPF implementable solution. Feasibility is enforced in two steps. First, during training, a Lagrangian dual method penalizes violations of physical and operations constraints, which are iteratively added as necessary to the machine-learning model by a Column-and-Constraint-Generation Algorithm (CCGA). Second, another different CCGA restores feasibility by finding the closest feasible solution to the prediction. Experiments on large test cases show that the method results in significant time reduction for obtaining feasible solutions with an optimality gap below 0.1%. [ABSTRACT FROM AUTHOR]

A prior knowledge of residential load demand is critical for power system operations at the distribution level, such as economic dispatch, demand response and energy storage schedule. However, as residential customers perform more casual and active consumption behaviors, prediction of such highly volatile loads can be much harder. Owing to the development of sensor technology, micrometeorological data can be sampled with a high geographic resolution. Those data that represent the weather condition on the land surface show a strong relationship to the residential load evidently, whereas it remains unsolved on how to fully utilize those great number of datasets. This paper proposes a day-ahead probabilistic residential load forecasting method based on a novel deep learning model, named convolutional neural network with squeeze-and-excitation modules (CNN-SE), and micrometeorological data. The model can employ multi-channel input data with dissimilar weights, suitable for analyzing massive relevant input factors. A feature extraction method is adopted for customer consumption pattern based on sparse auto-encoder (SAE), which can help correct probabilistic forecasting results. A case study that covers 8 residential communities and 18 micrometeorological sites is conducted to validate the feasibility and accuracy of the proposed hybrid method. [ABSTRACT FROM AUTHOR]

Accurate and speedy detection of power system events is critical to enhancing the reliability and resiliency of power systems. Although supervised deep learning algorithms show great promise in identifying power system events, they require a large volume of high-quality event labels for training. This paper develops a bidirectional anomaly generative adversarial network (GAN)-based algorithm to detect power system events using streaming PMU data, which does not rely on a huge amount of event labels. By introducing conditional entropy constraint in the objective function of GAN and graph signal processing-based PMU sorting technique, our proposed algorithm significantly outperforms state-of-the-art event detection algorithms in terms of accuracy. To facilitate the adoption of the proposed algorithm, a prototype online platform is also developed using Apache Hadoop, Kafka, and Spark to enable real-time event detection. The accuracy and computational efficiency of the proposed algorithm are validated using a large-scale real-world PMU dataset from the Eastern Interconnection of the United States. [ABSTRACT FROM AUTHOR]

Faults are extreme events that canadversely affect the voltages in islanded microgrids. This paper provides a new data-driven methodology for timely prediction of the post-fault voltage stability in hybrid AC/DC microgrids. The proposed method performs a binary classification with delay constraints by processing sequences of the short-time mean squared deviations using a deep learning system. The deep learning system consists of a bidirectional long short-term memory network whose output is a probabilistic voltage instability indicator. When the value of the indicator is non-zero, persistent voltage disturbances are most likely to occur even after the fault clearance. The proposed method enables the microgrid to carry out remedial or preventive actions, such as event-triggered protection and control of distributed energy resources (DERs), which are advantageous to the resilient operation of the microgrids. Extensive and detailed electromagnetic transient (EMT) simulations of a low-voltage hybrid AC/DC microgrid benchmark are analyzed, and the results confirm the effectiveness of the proposed method for online prediction and fast voltage regulation. [ABSTRACT FROM AUTHOR]

This paper proposes a data-driven cooperative method for load frequency control (LFC) of the multi-area power system based on multi-agent deep reinforcement learning (MA-DRL) in continuous action domain. The proposed method can nonlinearly and adaptively derive the optimal coordinated control strategies for multiple LFC controllers through centralized learning and decentralized implementation. The centralized learning is achieved by MA-DRL based on a global action-value function to quantify overall LFC performance of the power system. To solve the MA-DRL problem, multi-agent deep deterministic policy gradient (DDPG) is derived to adjust control agents’ parameters considering the nonlinear generator behaviors. For implementation, each individual controller only needs local information in its control area to deliver optimal control signals. Numerical simulations on a three-area power system and the fully-modeled New-England 39-bus system demonstrate that the proposed method can effectively minimize control errors against stochastic frequency variations caused by load and renewable power fluctuations. [ABSTRACT FROM AUTHOR]

This paper proposes a multi-agent deep reinforcement learning-based approach for distribution system voltage regulation with high penetration of photovoltaics (PVs). The designed agents can learn the coordinated control strategies from historical data through the counter-training of local policy networks and centric critic networks. The learned strategies allow us to perform online coordinated control. Comparative results with other methods show the enhanced control capability of the proposed method under various conditions. [ABSTRACT FROM AUTHOR]

This paper develops a hierarchical deep learning machine (HDLM) to efficiently achieve both quantitative and qualitative online transient stability prediction (TSP). For the sake of improving its online efficiency, multiple generators’ fault-on trajectories as well as the two closest data-points in pre-/post-fault stages are acquired by PMUs to form its raw inputs. An anti-noise graphical transient characterization technique is tactfully designed to transform multiplex trajectories into 2-D images, within which system-wide transients are concisely described. Then, following the divide-and-conquer philosophy, the HDLM trains a two-level convolutional neural network (CNN) based regression model. With stability margin regressions hierarchically refined, it manages to perform reliable and adaptive online TSP almost immediately after fault clearance. Test results on the IEEE 39-bus test system and the real-world Guangdong Power Grid in South China demonstrate the HDLM's superior performances on both stability status and stability margin predictions. [ABSTRACT FROM AUTHOR]

Accurate and reliable low-voltage load forecasting is critical to optimal operation and control of distribution network and smart grid. However, compared to traditional regional load forecasting at high-voltage level, it faces tough challenges due to the inherent high uncertainty of the low-capacity load and distributed renewable energy integrated in the demand side. This paper proposes a novel hybrid ensemble deep learning (HEDL) approach for deterministic and probabilistic low-voltage load forecasting. The deep belief network (DBN) is applied to low-voltage load point prediction with the strong ability of approximating nonlinear mapping. A series of ensemble learning methods including bagging and boosting variants are introduced to improve the regression ability of DBN. In addition, the differencing transformation technique is utilized to ensure the stationarity of load time series for the application bagging and boosting methods. On the basis of the integrated thought of ensemble learning, a new hybrid ensemble algorithm is developed via integrating multiple separate ensemble methods. Considering the diversity in various ensemble algorithms, an effective K nearest neighbor classification method is utilized to adaptively determine the weights of sub-models. Furthermore, HEDL based probabilistic forecasting is proposed by taking advantage of the inherent resample idea in bagging and boosting. The effectiveness of the HEDL method for both deterministic and probabilistic forecasting has been systematically verified based on realistic load data from East China and Australia, indicating its promising prospective for practical applications in distribution networks. [ABSTRACT FROM AUTHOR]

Demand-side management (DSM) increases the complexity of forecasting environment, which makes traditional forecasting methods difficult to meet the firm's need for predictive accuracy. Since deep learning can comprehensively consider various factors to improve prediction results, this paper improves the deep belief network from three aspects of input data, model and performance, and uses it to solve the short-term load forecasting problem in DSM. In the data optimization stage, the Hankel matrix is constructed to increase the input weight of DSM data, and the gray relational analysis is used to select strongly correlated data from the data set. In the model optimization stage, the Gauss-Bernoulli restricted Boltzmann machine is used as the first restricted Boltzmann machine of the deep network to convert the continuity feature of input data into binomial distribution feature. In the performance optimization stage, a pre-training method combining error constraint and unsupervised learning is proposed to provide good initial parameters, and the global fine-tuning of network parameters is realized based on the genetic algorithm. Based on the actual data of Tianjin Power Grid in China, the experimental results show that the proposed method is superior to other methods. [ABSTRACT FROM AUTHOR]

Non-technical losses (NTL) in electricity utilities are responsible for major revenue losses. In this paper, we propose a novel end-to-end solution to self-learn the features for detecting anomalies and frauds in smart meters using a hybrid deep neural network. The network is fed with simple raw data, removing the need of handcrafted feature engineering. The proposed architecture consists of a long short-term memory network and a multi-layer perceptrons network. The first network analyses the raw daily energy consumption history whilst the second one integrates non-sequential data such as its contracted power or geographical information. The results show that the hybrid neural network significantly outperforms state-of-the-art classifiers as well as previous deep learning models used in NTL detection. The model has been trained and tested with real smart meter data of Endesa, the largest electricity utility in Spain. [ABSTRACT FROM AUTHOR]

Decarbonization of electricity systems drives significant and continued investments in distributed energy sources to support the cost-effective transition to low-carbon energy systems. However, the rapid integration of distributed photovoltaic (PV) generation presents great challenges in obtaining reliable and secure grid operations because of its limited visibility and intermittent nature. Under this reality, net load forecasting is facing unprecedented difficulty in answering the following question: How can we accurately predict the net load while capturing the massive uncertainties arising from distributed PV generation and load, especially in the context of high PV penetration? This paper proposes a novel probabilistic day-ahead net load forecasting method to capture both epistemic uncertainty and aleatoric uncertainty using Bayesian deep learning, which is a new field that combines Bayesian probability theory and deep learning. The proposed methodological framework employs clustering in subprofiles and considers residential rooftop PV outputs as input features to enhance the performance of aggregated net load forecasting. Numerical experiments have been carried out based on fine-grained smart meter data from the Australian grid with separately recorded measurements of rooftop PV generation and loads. The results demonstrate the superior performance of the proposed scheme compared with a series of state-of-the-art methods and indicate the importance and effectiveness of subprofile clustering and high PV visibility. [ABSTRACT FROM AUTHOR]

Diverse fault types, fast reclosures, and complicated transient states after a fault event make real-time fault location in power grids challenging. Existing localization techniques in this area rely on simplistic assumptions, such as static loads, or require much higher sampling rates or total measurement availability. This paper proposes a faulted line localization method based on a convolutional neural network (CNN) classifier using bus voltages. Unlike prior data-driven methods, the proposed classifier is based on features with physical interpretations that improve the robustness of the location performance. The accuracy of our CNN-based localization tool is demonstrably superior to other machine learning classifiers in the literature. To further improve the location performance, a joint phasor measurement units placement strategy are proposed and validated against other methods. A significant aspect of our methodology is that under very low observability (${7\%}$ of buses), the algorithm is still able to localize the faulted line to a small neighborhood with high probability. The performance of our scheme is validated through simulations of faults of various types in the IEEE 39-bus and 68-bus power systems under varying uncertain conditions, system observability, and measurement quality. [ABSTRACT FROM AUTHOR]

Accurate modeling is an important method for dynamic response analysis and control strategy verification of high photovoltaic (PV) penetration distribution networks. This paper proposes a precise dynamic modeling framework for the two-staged PV station cluster, namely as deep learning clustering hybrid modeling framework. It includes clustering-based equivalent model and error correction model (ECM). A long short-term memory network is used to form the ECM, which models the dynamic response error between the existing equivalent model and the detailed model. The competence of this framework is validated by numerous case studies based on a practical PV cluster construction. The simulation results reveal that the proposed method is featured of low complexity and fast response speed as the equivalent model but has much higher accuracy. [ABSTRACT FROM AUTHOR]

This paper proposes a novel high-performance deep learning framework for load recognition. The framework consists of a deep-shallow model and a fast backpropagation (FBP) algorithm. In the deep-shallow model, power-related wave patterns are perceived by a convolutional neural network (CNN), and feature statistics of the power consumption data are analyzed by a sparse feed-forward neural network. The new architecture improves model interpretability and prevents information loss problems in CNNs. The architecture also greatly boosts the convergence speed and significantly enhances the test set accuracy of a neural network. Compared with conventional CNN models utilized by many load recognition applications, the FBP algorithm consisting of four sub-algorithms converges faster at the start of the training process and reduces at least 87.5% of the filter gradient computations on average. The deep-shallow-fast model that combines the deep-shallow model and the FBP algorithm attains 97.62% accuracy on the test set in the load recognition task. To fully utilize the training data, a data augmentation technique is invented that transforms the voltage and current time series into an image-like 4-D tensor. Experiments illustrate that the proposed framework is much more accurate and converges considerably faster than the conventional CNN model that many deep-learning-based load recognition applications are based upon. [ABSTRACT FROM AUTHOR]

Electricity market participants rely on data-driven methods using public market data to predict locational marginal prices (LMPs) and determine optimal bidding strategies, since they cannot access confidential power system models and operating details. In this paper, system-wide heterogeneous public market data are organized into a 3-dimensional (3D) tensor, which can store their spatio-temporal correlations. A generative adversarial network (GAN)-based approach is proposed to predict real-time locational marginal prices (RTLMPs) by learning the spatio-temporal correlations stored in the historical market data tensor. An autoregressive moving average (ARMA) calibration method is adopted to improve the prediction accuracy. Case studies using public market data from Midcontinent Independent System Operator (MISO) and Southwest Power Pool (SPP) demonstrate that the proposed method is able to learn spatio-temporal correlations among RTLMPs and perform accurate RTLMP prediction. [ABSTRACT FROM AUTHOR]

This paper proposes a holistic framework of data-driven distributionally robust joint chance constrained economic dispatch (ED) optimization, which seamlessly incorporates deep learning-based optimization for effective utilization of renewable energy in power systems. By leveraging a deep generative adversarial network (GAN), an f-divergence-based ambiguity set of wind power distributions is constructed as a ball centered around the probability distribution induced by a generator neural network. In particular, the GAN is well suited for capturing complicated spatial and temporal correlations of wind power. Based upon this ambiguity set, a distributionally robust joint chance constrained ED model is developed to hedge against distributional uncertainty present in multiple constraints, without assuming a perfectly known probability distribution. The proposed deep learning based ED optimization framework greatly mitigates the conservatism inflicting on distributionally robust individual chance constrained optimization. Theoretical a priori bound on the required number of synthetic wind power data generated by GAN is explicitly derived for the multi-period ED problem to guarantee a predefined risk level. The effectiveness and scalability of the proposed approach are demonstrated in the six-bus and IEEE 118-bus systems by comparing with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This paper introduces a network topology identification (TI) method based on deep neural networks (DNNs) for online applications. The proposed TI DNN utilizes the set of measurements used for state estimation to predict the actual network topology and offers low computational times along with high accuracy under a wide variety of testing scenarios. The training process of the TI DNN is duly discussed, and several deep learning heuristics that may be useful for similar implementations are provided. Simulations on the IEEE 14-bus and IEEE 39-bus test systems are reported to demonstrate the effectiveness and the small computational cost of the proposed methodology. [ABSTRACT FROM AUTHOR]

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]

In practical power systems, it is still very challenging to figure out a cost-effective undervoltage load shedding (UVLS) scheme that can reliably and adaptively react to the short-term voltage stability (SVS) problem. Faced with this challenge, this paper develops an intelligent data-driven predictive UVLS scheme for online SVS enhancement. Inspired by valuable ideas in model predictive control and supplementary excitation control in power systems, a novel deep feedback learning machine (DFLM) is designed to precisely predict future voltage violations after UVLS execution. With the help of the DFLM, the UVLS scheme is aware of potential effects of various candidate UVLS actions. Owing to this desirable nature, it can adaptively respond to diverse SVS conditions and optimize UVLS decisions in a non-iterative way. Further, two well-designed strategies, i.e., stepwise constraint relaxation and incremental DFLM adaptation, are introduced to enhance the scheme's reliability and adaptability during online application. Numerical test results on the Nordic test system and the realistic North GZ Power Grid in China showcase the excellent performances of the proposed scheme. [ABSTRACT FROM AUTHOR]

Highly wind penetrated future power system will couple to the variabilities and nonlinear correlations of wind. Reliable wind power forecasting (WPF) for a region is critical to the security and economics of the power system operation. Therefore, this paper proposes a multiscale WPF method by establishing a multi-to-multi (m2m) mapping network and the use of stacked denoising autoencoder (SDAE). The concerned forecast time horizon is 24–72 hours. First, multi-NWPs in a region are corrected based on SDAE to generate better inputs for the following regional WPF. Second, a number of SDAEs with diverse model parameters and input features are integrated into ensemble SDAE for predicting the wind power generated from various wind farms in a region. Two sets of data are utilized in this case study to validate the proposed method. The results show that the proposed m2m mapping and SDAE are able to capture the real correlations of wind at multiple sites, and outperform the other counterparts in terms of multi-NWPs correction as well as the WPF for both the region and individual concerned wind farm. Moreover, the ensemble SDAE performs better than any other individual regional WPF model. [ABSTRACT FROM PUBLISHER]

In this paper, we introduce a deep learning aided constraint encoding method to tackle the frequency-constraint microgrid scheduling problem. The nonlinear function between system operating condition and frequency nadir is approximated by using a neural network, which admits an exact mixed-integer formulation (MIP). This formulation is then integrated with the scheduling problem to encode the frequency constraint. With the stronger representation power of the neural network, the resulting commands can ensure adequate frequency response in a realistic setting in addition to islanding success. The proposed method is validated on a modified 33-node system. Successful islanding with a secure response is simulated under the scheduled commands using a detailed three-phase model in Simulink. The advantages of our model are particularly remarkable when the inertia emulation functions from wind turbine generators are considered. [ABSTRACT FROM AUTHOR]

Unsteady motion of the atmosphere incurs nonlinear and spatiotemporally coupled uncertainties in the wind power prediction (WPP) of multiple wind farms. This brings both opportunities and challenges to wind power probabilistic forecasting (WPPF) of a wind farm cluster or region, particularly when wind power is highly penetrated within the power system. This paper proposes an Improved Deep Mixture Density Network (IDMDN) for short-term WPPF of multiple wind farms and the entire region. In this respect, a deep multi-to-multi (m2m) mapping Neural Network model, which adopts the beta kernel as the mixture component to avoid the density leakage problem, is established to produce probabilistic forecasts in an end-to-end manner. A novel modified activation function and several general training procedures are then introduced to overcome the unstable behavior and NaN (Not a Number) loss issues of the beta kernel function. Verification of IDMDN is based on an open-source dataset collected from seven wind farms, and comparison results show that the proposed model improves the WPPF performance at both wind farm and regional levels. Furthermore, a laconic and accurate probabilistic expression of predicted power at each time step is produced by the proposed model. [ABSTRACT FROM AUTHOR]

As the number of smart meters increases, compression of metering data becomes essential for data transmission, storing and processing perspectives. Specifically, feature extraction can be used for the compression of metering data and further be utilized for smart grid applications such as customer clustering. So far, there are many studies for compression and clustering based on daily load profiles. However, in order to account for long-term characteristics of electricity load, utilizing yearly load profiles (YLPs) is vital for customer load clustering and analysis. In this paper, we propose a deep learning-based YLP feature extraction that jointly captures daily and seasonal variations. By leveraging convolutional autoencoder (CAE), YLPs in 8,640-dimensional space are compressed to 100-dimensional vectors. We apply the proposed CAE framework to YLPs of 1,405 residential customers and verify that the proposed CAE outperforms other dimensionality reduction methods in terms of reconstruction errors, e.g., by 19–40%, or the compression ratio is increased by 130% or higher than other methods for the same reconstruction error. In addition, clustering analysis is performed on the encoded YLPs. Our results confirm that year-round characteristics are well captured during the clustering process and also clearly visualized with load images. [ABSTRACT FROM AUTHOR]

As residential photovoltaic (PV) system installations continue to increase rapidly, utilities need to identify the locations of these new components to manage the unconventional two-way power flow and maintain sustainable management of distribution grids. But, historical records are unreliable and constant re-assessment of active residential PV locations is resource-intensive. To resolve these issues, we propose to model the solar detection problem in a machine learning setup based on labeled data, e.g., supervised learning. However, the challenge for most utilities is limited labels or labels on only one type of users. Therefore, we design new semi-supervised learning and one-class classification methods based on autoencoders, which greatly improve the nonlinear data representation of human behavior and solar behavior. The proposed methods have been tested and validated not only on synthetic data based on a publicly available data set but also on real-world data from utility partners. The numerical results show robust detection accuracy, laying down the foundation for managing distributed energy resources in distribution grids. [ABSTRACT FROM AUTHOR]

In the current competition framework governing the electricity sector, complex dependencies exist between electrical and market data, which complicates the decision-making procedure of energy actors. These must indeed operate within a complex, uncertain environment, and consequently need to rely on accurate multivariate, multi-step ahead probabilistic predictions. This paper aims to take advantage of recent breakthroughs in deep learning, while exploiting the structure of the problem to design prediction tools with tailored architectural alterations that improve their performance. The method can provide prediction intervals and densities, but is here extended with the objective to generate predictive scenarios. It is achieved by sampling the predicted multivariate distribution with a copula-based strategy so as to embody both temporal information and cross-variable dependencies. The effectiveness of the proposed methodology is emphasized and compared with several other architectures in terms of both statistical performance and impact on the quality of decisions optimized within a dedicated stochastic optimization tool of an electricity retailer participating in short-term electricity markets. [ABSTRACT FROM AUTHOR]

The increased penetration of wind power introduces more operational changes of critical corridors and the traditional time-consuming transient stability constrained total transfer capability (TTC) operational planning is unable to meet the real-time monitoring need. This paper develops a more computationally efficient approach to address that challenge via the analytical deep learning-based surrogate model. The key idea is to resort to deep learning for developing a computationally cheap surrogate model to replace the original time-consuming differential-algebraic constraints related to TTC. However, the deep learning-based surrogate model introduces implicit rules that are difficult to handle in the optimization process. To this end, we derive the Jacobian and Hessian matrices of the implicit surrogate models and finally transfer them into an analytical formulation that can be easily solved by the interior point method. Surrogate modeling and problem reformulation allow us to achieve significantly improved computational efficiency and the yielded solutions can be used for operational planning. Numerical results carried out on the modified IEEE 39-bus and 68-bus systems demonstrate the effectiveness of the proposed method in dealing with complicated TTC constraints while balancing the computational efficiency and accuracy. [ABSTRACT FROM AUTHOR]

We develop DeepOPF as a Deep Neural Network (DNN) approach for solving security-constrained direct current optimal power flow (SC-DCOPF) problems, which are critical for reliable and cost-effective power system operation. DeepOPF is inspired by the observation that solving SC-DCOPF problems for a given power network is equivalent to depicting a high-dimensional mapping from the load inputs to the generation and phase angle outputs. We first train a DNN to learn the mapping and predict the generations from the load inputs. We then directly reconstruct the phase angles from the generations and loads by using the power flow equations. Such a predict-and-reconstruct approach reduces the dimension of the mapping to learn, subsequently cutting down the size of the DNN and the amount of training data needed. We further derive a condition for tuning the size of the DNN according to the desired approximation accuracy of the load-generation mapping. We develop a post-processing procedure based on ℓ1-projection to ensure the feasibility of the obtained solution, which can be of independent interest. Simulation results for IEEE test cases show that DeepOPF generates feasible solutions with less than 0.2% optimality loss, while speeding up the computation time by up to two orders of magnitude as compared to a state-of-the-art solver. [ABSTRACT FROM AUTHOR]

The problem of state estimation for unobservable distribution systems is considered. A deep learning approach to Bayesian state estimation is proposed for real-time applications. The proposed technique consists of distribution learning of stochastic power injection, a Monte Carlo technique for the training of a deep neural network for state estimation, and a Bayesian bad-data detection and filtering algorithm. Structural characteristics of the deep neural networks are investigated. Simulations illustrate the accuracy of Bayesian state estimation for unobservable systems and demonstrate the benefit of employing a deep neural network. Numerical results show the robustness of Bayesian state estimation against modeling and estimation errors and the presence of bad and missing data. Comparing with pseudo-measurement techniques, direct Bayesian state estimation via deep learning neural network outperforms existing benchmarks. [ABSTRACT FROM AUTHOR]

Scenario generation is an important step in the operation and planning of power systems with high renewable penetrations. In this work, we proposed a data-driven approach for scenario generation using generative adversarial networks, which is based on two interconnected deep neural networks. Compared with existing methods based on probabilistic models that are often hard to scale or sample from, our method is data-driven, and captures renewable energy production patterns in both temporal and spatial dimensions for a large number of correlated resources. For validation, we use wind and solar times-series data from NREL integration data sets. We demonstrate that the proposed method is able to generate realistic wind and photovoltaic power profiles with full diversity of behaviors. We also illustrate how to generate scenarios based on different conditions of interest by using labeled data during training. For example, scenarios can be conditioned on weather events (e.g., high wind day, intense ramp events, or large forecasts errors) or time of the year (e.g., solar generation for a day in July). Because of the feedforward nature of the neural networks, scenarios can be generated extremely efficiently without sophisticated sampling techniques. [ABSTRACT FROM PUBLISHER]

The stochastic cloud cover on photovoltaic (PV) panels affects the solar power outputs, producing high instability in the integrated power systems. It is an effective approach to track the cloud motion during short-term PV power forecasting based on data sources of satellite images. However, since temporal variations of these images are noisy and non-stationary, pixel-sensitive prediction methods are critically needed in order to seek a balance between the forecast precision and the huge computation burden due to a large image size. Hence, a graphical learning framework is proposed in this study for intra-hour PV power prediction. By simulating the cloud motion using bi-directional extrapolation, a directed graph is generated representing the pixel values from multiple frames of historical images. The nodes and edges in the graph denote the shapes and motion directions of the regions of interest (ROIs) in satellite images. A spatial-temporal graph neural network (GNN) is then proposed to deal with the graph. Comparing with conventional deep-learning-based models, GNN is more flexible for varying sizes of input, in order to be able to handle dynamic ROIs. Referring to the comparative studies, the proposed method greatly reduces the redundancy of image inputs without sacrificing the visual scope, and slightly improves the prediction accuracy. [ABSTRACT FROM AUTHOR]

Increasing renewable penetration in distribution grids calls for improved monitoring and control, where power flow (PF) model is the basis for many advanced functionalities. However, unobservability makes the traditional way infeasible to construct PF analysis via admittance matrix for many distribution grids. While data-driven approaches can approximate PF mapping, direct machine learning (ML) applications may suffer from several drawbacks. First, complex ML models like deep neural networks lack the degradability and explainability to the true system model, leading to overfitting. There are also asynchronization issues among different meters without GPS chips. Last but not least, bad data is quite common in the distribution grids. To resolve these problems all at once, we propose a variational support matrix regression (SMR). It provides structural learning to (1) embed kernels to regularize physical form in observable area while achieving good approximation at unobservable area, (2) integrate temporal information into matrix regression for asynchronized data imputation, and (3) define support matrix for margins to be robust against bad data. We test the performance for mapping rule learning via IEEE test systems and a utility distribution grid. Simulation results show high accuracy, degradability from data-driven model to physical model, and robustness to data quality issues. [ABSTRACT FROM AUTHOR]

A distribution service restoration algorithm as a fundamental resilient paradigm for system operators provides an optimally coordinated, resilient solution to enhance the restoration performance. The restoration problem is formulated to coordinate distribution generators and controllable switches optimally. A model-based control scheme is usually designed to solve this problem, relying on a precise model and resulting in low scalability. To tackle these limitations, this work proposes a graph-reinforcement learning framework for the restoration problem. We link the power system topology with a graph convolutional network, which captures the complex mechanism of network restoration in power networks and understands the mutual interactions among controllable devices. Latent features over graphical power networks produced by graph convolutional layers are exploited to learn the control policy for network restoration using deep reinforcement learning. The solution scalability is guaranteed by modeling distributed generators as agents in a multi-agent environment and a proper pre-training paradigm. Comparative studies on IEEE 123-node and 8500-node test systems demonstrate the performance of the proposed solution. [ABSTRACT FROM AUTHOR]