Search

There is an opportunity in modern power systems to explore the demand flexibility by incentivizing consumers with dynamic prices. In this paper, we quantify demand flexibility using an efficient tool called time-varying elasticity, whose value may change depending on the prices and decision dynamics. This tool is particularly useful for evaluating the demand response potential and system reliability. Recent empirical evidences have highlighted some abnormal features when studying demand flexibility, such as delayed responses and vanishing elasticities after price spikes. Existing methods fail to capture these complicated features because they heavily rely on some predefined (often over-simplified) regression expressions. Instead, this paper proposes a model-free methodology to automatically and accurately derive the optimal estimation pattern. We further develop a two-stage estimation process with Siamese long short-term memory (LSTM) networks. Here, a LSTM network encodes the price response, while the other network estimates the time-varying elasticities. In the case study, the proposed framework and models are validated to achieve higher overall estimation accuracy and better description for various abnormal features when compared with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Distribution system state estimation (DSSE) is a core task for monitoring and control of distribution networks. Widely used algorithms such as Gauss–Newton perform poorly with the limited number of measurements typically available for DSSE, often require many iterations to obtain reasonable results, and sometimes fail to converge. DSSE is a non-convex problem, and working with a limited number of measurements further aggravates the situation, as indeterminacy induces multiple global (in addition to local) minima. Gauss–Newton is also known to be sensitive to initialization. Hence, the situation is far from ideal. It is therefore natural to ask if there is a smart way of initializing Gauss–Newton that will avoid these DSSE-specific pitfalls. This paper proposes using historical or simulation-derived data to train a shallow neural network to “learn to initialize,” that is, map the available measurements to a point in the neighborhood of the true latent states (network voltages), which is used to initialize Gauss–Newton. It is shown that this hybrid machine learning/optimization approach yields superior performance in terms of stability, accuracy, and runtime efficiency, compared to conventional optimization-only approaches. It is also shown that judicious design of the neural network training cost function helps to improve the overall DSSE performance. [ABSTRACT FROM AUTHOR]

Load forecasting is one of the most important and studied topics in modern power systems. Most of the existing research on day-ahead load forecasting try to build a good model to improve the forecasting accuracy. The forecasted load is then used as the input to generation scheduling with the ultimate goal of minimizing the cost of generation schedules. However, existing day-ahead load forecasting models do not consider this ultimate goal at the training/forecasting stage. This paper proposes a task-based day-ahead load forecasting model labeled as LfEdNet that combines two individual layers in one model, including a load forecasting layer based on deep neural network (Lf layer) and a day-ahead stochastic economic dispatch (SED) layer (Ed layer). The training of LfEdNet aims to minimize the cost of the day-ahead SED in the Ed layer by updating the parameters of the Lf layer. Sequential quadratic programming (SQP) is used to solve the day-ahead SED in the Ed layer. The test results demonstrate that the forecasted results produced by LfEdNet can lead to lower cost of day-ahead SED at the expense of slight reduction in forecasting accuracy. [ABSTRACT FROM AUTHOR]

This paper presents a new non-deterministic approach for multiyear distribution network reinforcement planning (DNRP) considering the uncertainty sources pertaining to loads, electricity prices, investment costs, and operation costs. Accordingly, the underlying idea of the information-gap decision theory (IGDT) is used to obtain a robust solution protected against different realizations of each uncertain variable lying in its robust region. The proposed model is capable of adjusting the robustness of the optimal solution in terms of a specific parameter designated as the budget of uncertainty. As the uncertain loads, investment and operation costs competitively tend to maximize their robust regions for a particular value of the budget of uncertainty, the normalized normal constraint (NNC) method as a proficient multi-objective optimization method is exploited in this paper to solve the proposed multiobjective IGDT-based DNRP (IGDT-DNRP) model. Mainly, the NNC method presents a set of Pareto optimal solutions rather than a single optimal solution. Accordingly, a posteriori out-of-sample analysis is introduced in this paper to find the best solution among the set of Pareto optimal solutions. The proposed IGDT-DNRP model is implemented on the IEEE 33-bus distribution network under different circumstances. Simulation results illustrate the effectiveness of the proposed nondeterministic approach. [ABSTRACT FROM AUTHOR]

This paper proposes a market framework to approach economic dispatch as a subproblem in smart distribution systems. Four subproblems are associated with four different submarkets (SMs) in the presented framework. Market participants are eligible to bid in different submarkets based on the type of their distributed generation (DG) unit. To effectively tackle the conflicts among objective functions of different submarkets, the corresponding formulated subproblems are assigned to two different agents, namely distribution system operator (DSO) and a green bank agent (GBA). A communication mechanism is designed within the proposed framework such that DSO and GBA compromise their solutions and find a tradeoff to reasonably address the concerns of the four subproblems within SMs 1-4. The effectiveness of the proposed market framework is validated on a well-known 136-bus distribution system, which is modified to contain wind turbine DG aggregators, photovoltaic DG aggregators, and diesel-engine DG aggregators. [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]

Short-term load forecasts are needed for the efficient management of power systems. Although weather-based modeling is common, univariate models can be useful when the lead time of interest is less than one day. A class of univariate methods that has performed well with intraday data is exponential smoothing. This paper considers five recently developed exponentially weighted methods that have not previously been used for load forecasting. These methods include several exponential smoothing formulations, as well as methods using discount weighted regression, cubic splines, and singular value decomposition (SVD). In addition, this paper presents a new SVD-based exponential smoothing formulation. Using British and French half-hourly load data, these methods are compared for point forecasting up to one day ahead. Although the new SVD-based approach showed some potential, the best performing method was a previously developed exponential smoothing method. A second empirical study showed the better of the univariate methods outperforming a weather-based method up to about five hours ahead, with a combination of these methods producing the best results overall. [ABSTRACT FROM PUBLISHER]

Based on the knowledge accumulated off-line and feature extractions, a novel data-based learning and control method is proposed for the long-term voltage stability problem in this paper. All the spatial-temporal data is considered and the features of different emergency events are extracted by principle component analysis which can reduce the dimension and reveal the significant internal structure of the data. An artificial neural network is used to build a classifier to reinforce the relationship directly between the system dynamics and optimal control actions. With the prepared control knowledge, it is faster to find an optimal control action online with a good system performance. Simulation results on the 6-bus system, New England 39-bus system and Iceland 189-bus system are given to show the potential of this method for on-line control. [ABSTRACT FROM AUTHOR]

Small isolated power systems often experience generator outages, which are responsible for the activation of the under-frequency load shedding scheme with the corresponding negative impact on electricity consumers and, hence, market loss. There are three main causes of this problem: the power system's low inertia, the speed governors' low capacity, and a poor size-ratio between generator and system. The most extensive research line in this area is focused on the optimization of the load shedding scheme, which is a partial solution. Another research line is presented to solve the problem from the point of view of the system operator. This paper proposes an online method to predict and correct possible load shedding by redistributing load dispatching. This proposal uses artificial intelligence techniques, in particular neural networks, and a special-purpose power system simulator. In order to evaluate the proposal, the achieved solution is applied to a real case study: the island of Gran Canaria. This application shows the improvement that might be achieved by implementing this simple method. The method proposed in this paper is strongly recommended for regions that have suitable geographical sites as well as energy problems similar to those of the Canary Islands (see tech. rep. “Map of the Canary Islands Power Systems” by Red Electrica de Espana). [ABSTRACT FROM AUTHOR]

In this paper, a new ensemble forecasting model for short-term load forecasting (STLF) is proposed based on extreme learning machine (ELM). Four important improvements are used to support the ELM for increased forecasting performance. First, a novel wavelet-based ensemble scheme is carried out to generate the individual ELM-based forecasters. Second, a hybrid learning algorithm blending ELM and the Levenberg–Marquardt method is proposed to improve the learning accuracy of neural networks. Third, a feature selection method based on the conditional mutual information is developed to select a compact set of input variables for the forecasting model. Fourth, to realize an accurate ensemble forecast, partial least squares regression is utilized as a combining approach to aggregate the individual forecasts. Numerical testing shows that proposed method can obtain better forecasting results in comparison with other standard and state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Examines a collection of papers that report the application of neural networks (NN) to short-term electric load forecasting. Introduction to NN; Overview of the proposed NN-based forecasting systems; Issues in designing NN-based forecasting systems.

Accurate estimates of network parameters are essential for modeling, monitoring, and control in power distribution systems. In this paper, we develop a physics-informed graphical learning algorithm to estimate network parameters of three-phase power distribution systems. Our proposed algorithm uses only readily available smart meter data to estimate the three-phase series resistance and reactance of the primary distribution line segments. We first develop a parametric physics-based model to replace the black-box deep neural networks in the conventional graphical neural network (GNN). Then we derive the gradient of the loss function with respect to the network parameters and use stochastic gradient descent (SGD) to estimate the physical parameters. Prior knowledge of network parameters is also considered to further improve the accuracy of estimation. Comprehensive numerical study results show that our proposed algorithm yields high accuracy and outperforms existing methods. [ABSTRACT FROM AUTHOR]

Voltage-to-power sensitivities play a key role in the control and operation of distribution networks. To estimate these sensitivities without network information, data-driven estimation methods have been studied. However, conventional methods do not consider mutual dependency (MD) of the sensitivities and thus the estimation can be inaccurate. Thus, this paper proposes a new data-driven estimation method of the sensitivities, which considers MD of the sensitivities in medium voltage distribution networks. In the proposed method, via MD analysis, the sensitivities are estimated by solving nonlinear least square problems and thus the accurate estimation can be achieved. The effectiveness of the proposed method is verified using the real-time platform. [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]

Non-intrusive load monitoring addresses the challenging task of decomposing the aggregate signal of a household's electricity consumption into appliance-level data without installing dedicated meters. By detecting load malfunction and recommending energy reduction programs, cost-effective non-intrusive load monitoring provides intelligent demand-side management for utilities and end users. In this paper, we boost the accuracy of energy disaggregation with a novel neural network structure named scale- and context-aware network, which exploits multi-scale features and contextual information. Specifically, we develop a multi-branch architecture with multiple receptive field sizes and branch-wise gates that connect the branches in the sub-networks. We build a self-attention module to facilitate the integration of global context, and we incorporate an adversarial loss and on-state augmentation to further improve the model's performance. Extensive simulation results tested on open datasets corroborate the merits of the proposed approach, which significantly outperforms state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This paper presents a new methodology to exploit consumers’ flexibility for the provision of ancillary services (AS) in the smart grid era. The proposed framework offers a control-based approach that adopts price signalsas the economic driver to modulate consumers’ response. In this framework, various system operators broadcast price signals independently to fulfil their AS requirements. Appropriate flexibility estimators are developed from the transmission system operator (TSO) and distribution system operator (DSO) perspectives for price generation. An artificial neural network (ANN) controller is used for the TSO to infer the price-consumption reaction from pools of consumers in its territory. A proportional-integral (PI) controller is preferred to represent the consumers’ price-response and generate time-varying electricity prices at the DSO level for voltage management. A multi-timescale simulation model is built in MATLAB to assess the proposed methodology in different operational conditions. Numerical analyses show the applicability of the proposed method for the provision of AS from consumers at different levels of the grid and the interaction between TSO and DSOs through the proposed framework. [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]

Environmental factors, such as weather, trees, and animals, are major causes of power outages in electric utility distribution systems. Of these factors, wind and lightning have the most significant impacts. The objective of this paper is to investigate models to estimate wind and lighting related outages. Such estimation models hold the potential for lowering operational costs and reducing customer downtime. This paper proposes an ensemble learning approach based on a boosting algorithm, AdaBoost^+, for estimation of weather-caused power outages. Effectiveness of the model is evaluated using actual data, which comprised of weather data and recorded outages for four cities of different sizes in Kansas. The proposed ensemble model is compared with previously presented regression, neural network, and mixture of experts models. The results clearly show that AdaBoost^+ estimates outages with greater accuracy than the other models for all four data sets. [ABSTRACT FROM PUBLISHER]

Anomalous data can negatively impact energy forecasting by causing model parameters to be incorrectly estimated. This paper presents two approaches for the detection and imputation of anomalies in time series data. Autoregressive with exogenous inputs (ARX) and artificial neural network (ANN) models are used to extract the characteristics of time series. Anomalies are detected by performing hypothesis testing on the extrema of the residuals, and the anomalous data points are imputed using the ARX and ANN models. Because the anomalies affect the model coefficients, the data cleaning process is performed iteratively. The models are re-learned on “cleaner” data after an anomaly is imputed. The anomalous data are reimputed to each iteration using the updated ARX and ANN models. The ARX and ANN data cleaning models are evaluated on natural gas time series data. This paper demonstrates that the proposed approaches are able to identify and impute anomalous data points. Forecasting models learned on the unclean data and the cleaned data are tested on an uncleaned out-of-sample dataset. The forecasting model learned on the cleaned data outperforms the model learned on the unclean data with 1.67% improvement in the mean absolute percentage errors and a 32.8% improvement in the root mean squared error. Existing challenges include correctly identifying specific types of anomalies such as negative flows. [ABSTRACT FROM PUBLISHER]

Future distributed transactive energy markets are envisioned to integrate multiple entities located mainly at the distribution level of the grid, so that consumers and prosumers can trade power either directly with the upstream wholesale energy market or through local pricing mechanisms (e.g., through “peer-to-peer” contracts or by forming “energy communities”). In such market environments, a transparent loss allocation framework is required to guarantee economic efficiency and fairness. Nevertheless, the unbalanced power flow nature associated with the distribution networks should be fundamentally integrated in the loss allocation process. To this end, this paper presents a graph-based loss allocation framework that harmonizes the physical attributes of the distribution grid with the underlying financial transactions in distributed market settings. The latter is achieved via representing distribution networks as multilayered radial graphs. The proposed loss allocation framework is tested on an actual LV feeder that is experiencing rapid growth in DG applications. [ABSTRACT FROM AUTHOR]

The advances in distributed renewable generation technologies in recent years have started to cause load balancing issues in power networks. Distributed energy storage (ES) systems, although seen as a tool to mitigate the stress on local networks, tend to be operated only to minimize the energy cost of their direct owner. In this paper, cooperative game theory is used to construct an energy grand coalition, in which ES system operations are optimized to minimize the coalitional energy cost. Case studies then show that forming energy coalitions is effective in reducing the variability of a local network load profile. The resulting cooperative game is mathematically proven to be balanced, which means the energy cost savings from the cooperative ES operation can be allocated to the players within the energy grand coalition in a manner that disincentivizes them from exiting from the grand coalition to form smaller coalitions. [ABSTRACT FROM AUTHOR]

This paper extends previous research on using a Bayesian network model to investigate impacts of time (month) and weather (number of fair weather days in a week) on animal-related outages in distribution systems. Outage history (outages in the previous week) is included as an additional input to the model, and inputs and outputs are classified systematically to reduce errors in estimates of outputs. Conditional probability table obtained from the historical data are used to estimate weekly animal-related outages which is followed by a Monte Carlo simulation to find estimates of mean and confidence limits for monthly animal-related outages. Comparison of results obtained for four cities of different sizes in Kansas with those obtained using a hybrid wavelet/neural network model shows consistency between the two models. The methodology presented in this paper is simple to implement and useful for the utilities for year-end analysis of the outage data to identify specific reliability-related concerns. [ABSTRACT FROM PUBLISHER]

Short-term load forecasting (STLF) is the basis of power system planning and operation. With regard to the fast-growing load in China, a novel two-stage hybrid forecasting method is proposed in this paper. In the first stage, daily load is forecasted by time-series methods; in the second stage, the deviation caused by time-series methods is forecasted considering the impact of relative factors, and then is added to the result of the first stage. Different from other conventional methods, this paper does an in-depth analysis on the impact of relative factors on the deviation between actual load and the forecasting result of traditional time-series methods. On the basis of this analysis, an adaptive algorithm is proposed to perform the second stage which can be used to choose the most appropriate algorithm among linear regression, quadratic programming, and support vector machine (SVM) according to the characteristic of historical data. These ideas make the forecasting procedure more accurate, adaptive, and effective, comparing with SVM and other prevalent methods. The effectiveness has been demonstrated by the experiments and practical application in China. [ABSTRACT FROM PUBLISHER]

The illegal use of electricity, defective meters, and a malfunctioning infrastructure are major causes of Non-technical losses (NTLs) in electric distribution systems. Although the use of supervised machine learning techniques to detect NTLs has been widely studied, further research is needed in order to address some significant challenges. (i) Given that fraudulent consumers remarkably outnumber non-fraudulent ones, the imbalanced nature of the dataset can have a major negative impact on the performance of supervised machine learning methods. (ii) Given the large number of dimensions present in the time series data used for training and testing classifiers, advanced signal processing techniques are required in order to extract the most relevant information. (iii) The effectiveness of classifiers must be evaluated using meaningful performance measures for imbalanced data. This paper proposes a framework that addresses the three previous challenges. The core of the proposed framework is the application of the maximal overlap discrete wavelet-packet transform (MODWPT) for feature extraction from time series data and the random undersampling boosting (RUSBoost) algorithm for NTL detection. Moreover, our framework is evaluated using an extensive list of performance metrics. Experiments show that the MODWPT combined with the RUSBoost algorithm can significantly improve the quality of NTL predictions. [ABSTRACT FROM AUTHOR]

In this paper, an artificial neural network (ANN) based method is developed for quickly estimating the long-term voltage stability margin. The investigation presented in the paper showed that node voltage magnitudes and the phase angles are the best predictors of voltage stability margin. Further, the paper shows that the proposed ANN based method can successfully estimate the voltage stability margin not only under normal operation but also under N-1 contingency situations. If the voltage magnitudes and phase angles are obtained in real-time from phasor measurement units (PMUs) using the proposed method, the voltage stability margin can be estimated in real time and used for initiating stability control actions. Finally, a suboptimal approach to determine the best locations for PMUs is presented. Numerical examples of the proposed techniques are presented using the New England 39-bus test system and a practical power system which consists of 1844 buses, 746 load buses, and 302 generator buses. [ABSTRACT FROM AUTHOR]

Power distribution systems play an important role in modern society. When distribution system outages occur, fast and proper restorations are crucial to improve the quality of services and customer satisfaction. Proper usages of outage root cause identification tools are often essential for effective outage restorations. This paper reports on the investigation and results of two popular classification methods: logistic regression (LR) and artificial neural network (ANN) applied on power distribution fault cause identification. LR is seldom used in power distribution fault diagnosis, while ANN has been extensively used in power system reliability researches. This paper discusses the practical application problems, including data insufficiency, imbalanced data constitution, and threshold setting that are often faced in power distribution fault cause identification problems. Two major distribution fault types, tree and animal contact, are used to illustrate the characteristics and effectiveness of the investigated techniques. [ABSTRACT FROM AUTHOR]

Prediction and shaping of dynamic response of the demand will enable advanced control algorithms for active demand management as well as improved stability assessment of the power system. Based on previously developed demand disaggregation approach, this paper develops a methodology for day-ahead prediction and shaping of dynamic response of the demand at bulk supply points without having to perform field measurements. The methodology is broadly based on application of artificial neural network and Monte Carlo simulations and incorporates multiple approaches namely, load forecasting, load disaggregation and the component-based load modelling approach. The input data include standard rms measurements at bulk supply points and actual and day-ahead forecasted weather data and does not rely on having access to detailed customer surveys or high-resolution load signatures. Measured dynamic responses of the demand from the substations of the local utility are used for validation. Load shifting and shaping of dynamic response of the demand are also illustrated. [ABSTRACT FROM PUBLISHER]

In order to support an appropriate level of resource adequacy in the long term and also to achieve a reliable operation in the short term, a new pricing design and mechanism is needed as a key success factor of real-time energy-only market. This paper proposes optimization-based mathematical models to explore operating reserve demand curves (ORDCs) and two price adders in real-time energy-only market, including dispatch correction and extended security-constrained economic dispatch. The Lagrangian multipliers of the dispatch correction problem are used to construct the ORDCs. Then, the derivative of the ORDCs’ social welfare is formulated as real-time online reserve price adders such as the scarcity adder and the price-lift adder. In case studies, we justify the effectiveness of the proposed ORDCs and two price adders by a simple example with two aggregated units and the Electric Reliability Council of Texas data. [ABSTRACT FROM AUTHOR]

Demand decomposition (disaggregation) presents the process of assessing time-varying participation of different load categories within the total active or reactive load. Information on load composition is highly beneficial for different demand side management applications. In order to decompose total forecasted load of aggregated households where only some are monitored by smart meters (SMs) with submetering capabilities, a two-level methodology is proposed. At the first level, load disaggregation of the load monitored by SMs is done based on measurements of power consumed by each home appliance, and at the second, the disaggregation of the total forecasted load is performed using artificial neural network. This paper investigates the required percentage of users in an aggregation that should be equipped with a SM with submetering capabilities in order to forecast (within certain confidence level) the load composition of the overall aggregated demand. The methodology was first tested on a UK statistics-based load model, and then validated on a real pilot site's consumption dataset. The results show that even with 5% SM coverage, one can forecast, with high confidence, the composition of the load at the substation (aggregation point). In other words, there is no techno-economic justification for submetering technologies to be installed at every user's premise; a limited installation of such devices would suffice. [ABSTRACT FROM AUTHOR]

The ever-increasing number of wind farms has brought both challenges and opportunities in the development of wind power forecasting techniques to take advantage of interdependencies between tens or hundreds of spatially distributed wind farms, e.g., over a region. In this paper, a sparsity-controlled vector autoregressive (SC-VAR) model is introduced to obtain sparse model structures in a spatio-temporal wind power forecasting framework by reformulating the original VAR model into a constrained mixed integer nonlinear programming (MINLP) problem. It allows controlling the sparsity of the coefficient matrices in direct manner. However this original SC-VAR is difficult to implement due to its complicated constraints and the lack of guidelines for setting its parameters. To reduce the complexity of this MINLP and to make it possible to incorporate prior expert knowledge to benefit model building and forecasting, the original SC-VAR is modified and a correlation-constrained SC-VAR (CCSC-VAR) is proposed based on spatial correlation information about wind farms. Our approach is evaluated based on a case study of very-short-term forecasting for 25 wind farms in Denmark. Comparison is performed with a set of traditional local methods and spatio-temporal methods. The results obtained show the proposed CCSC-VAR has better overall performance than both the original SC-VAR and other benchmark methods, taking into account all evaluation indicators, including sparsity-control ability, sparsity, accuracy, and efficiency. [ABSTRACT FROM AUTHOR]

In this paper, a wavelet ridge technique based approach is applied to analyze wide area measurement systems data representing power system dynamic behavior. When used to extract the oscillating trend from the measured network frequency signal, it efficiently tracks the oscillations in the presence of significant noise. Using multivariate signal analysis, a novel disturbance contribution index for individual generator is proposed to estimate how much a generator's contribution is in a severely disturbed power system, as recorded by various phasor measurement units. In other words, this index helps in quantifying how severely affected a particular machine is following a system-wide disturbance. It is shown that any control action applied on the most disturbed generator as identified by the disturbance contribution index, stabilizes the overall system more quickly, compared to the cases where control action is applied on other generators. When the analytic wavelet is used to extract the dynamic pattern from the signal, the recovered signal is also analytic. A new coherency index is also proposed, based on the properties of analytic signal, to indicate how similar two measured signals are. The proposed technique is demonstrated using synthetic signals, signals obtained from time-domain simulation of various power systems and actual phasor measurement units data. [ABSTRACT FROM AUTHOR]

Online identification of postcontingency transient stability is essential in power system control, as it facilitates the grid operator to decide and coordinate system failure correction control actions. Utilizing machine learning methods with synchrophasor measurements for transient stability assessment has received much attention recently with the gradual deployment of wide-area protection and control systems. In this paper, we develop a transient stability assessment system based on the long short-term memory network. By proposing a temporal self-adaptive scheme, our proposed system aims to balance the trade-off between assessment accuracy and response time, both of which may be crucial in real-world scenarios. Compared with previous work, the most significant enhancement is that our system learns from the temporal data dependencies of the input data, which contributes to better assessment accuracy. In addition, the model structure of our system is relatively less complex, speeding up the model training process. Case studies on three power systems demonstrate the efficacy of the proposed transient stability as sessment system. [ABSTRACT FROM PUBLISHER]

With rapid increase in wind power penetration into the power grid, wind power forecasting is becoming increasingly important to power system operators and electricity market participants. The majority of the wind forecasting tools available in the literature provide deterministic prediction, but given the variability and uncertainty of wind, such predictions limit the use of the existing tools for decision-making under uncertain conditions. As a result, probabilistic forecasting, which provides information on uncertainty associated with wind power forecasting, is gaining increased attention. This paper presents a novel hybrid intelligent algorithm for deterministic wind power forecasting that utilizes a combination of wavelet transform (WT) and fuzzy ARTMAP (FA) network, which is optimized by using firefly (FF) optimization algorithm. In addition, support vector machine (SVM) classifier is used to minimize the wind power forecast error obtained from WT+FA+FF. The paper also presents a probabilistic wind power forecasting algorithm using quantile regression method. It uses the wind power forecast results obtained from the proposed hybrid deterministic WT+FA+FF+SVM model to evaluate the probabilistic forecasting performance. The performance of the proposed forecasting model is assessed utilizing wind power data from the Cedar Creek wind farm in Colorado. [ABSTRACT FROM PUBLISHER]

The distribution system state estimation problem seeks to determine the network state from available measurements. Widely used Gauss-Newton approaches are very sensitive to the initialization and often not suitable for real-time estimation. Learning approaches are very promising for real-time estimation, as they shift the computational burden to an offline training stage. Prior machine learning approaches to power system state estimation have been electrical model-agnostic, in the sense that they did not exploit the topology and physical laws governing the power grid to design the architecture of the learning model. In this paper, we propose a novel learning model that utilizes the structure of the power grid. The proposed neural network architecture reduces the number of coefficients needed to parameterize the mapping from the measurements to the network state by exploiting the separability of the estimation problem. This prevents overfitting and reduces the complexity of the training stage. We also propose a greedy algorithm for phasor measuring units placement that aims at minimizing the complexity of the neural network required for realizing the state estimation mapping. Simulation results show superior performance of the proposed method over the Gauss-Newton approach. [ABSTRACT FROM AUTHOR]

Recent breakthroughs in transmission network expansion planning (TNEP) have demonstrated that the use of robust optimization, as opposed to stochastic programming methods, renders the expansion planning problem considering uncertainties computationally tractable for real systems. However, there is still a yet unresolved and challenging problem as regards the resolution of the dynamic TNEP problem, which considers the year-by-year representation of uncertainties and investment decisions in an integrated way. This problem has been considered to be a highly complex and computationally intractable problem, and most research related to this topic focuses on very small case studies or used heuristic methods and has lead most studies about TNEP in the technical literature to take a wide spectrum of simplifying assumptions. In this paper, an adaptive robust TNEP formulation is proposed for keeping the full dynamic complexity of the problem. The method overcomes the problem size limitations and computational intractability associated with dynamic TNEP for realistic cases. Numerical results from an illustrative example and the IEEE 118-bus system are presented and discussed, demonstrating the benefits of this dynamic TNEP approach with respect to classical methods. [ABSTRACT FROM AUTHOR]

The challenge of grid security assessment with $N- k$ contingencies lies in a huge amount of transmission security constraints and even for the modest values of N and k, the computational complexity would be very high. A new method for fast grid security assessment is presented in this paper for DC grid. The key idea is to construct a small number of representative constraints to equivalently “represent” the huge number of original security constraints. It is proved that applying the representative constraints is sufficient to assess grid security as the original security constraints do. An important feature of the new method is that the representative constraints need to be constructed only once offline. They are only related to the parameters of transmission network and do not change with power injections. Numerical testing is performed for IEEE-RTS 24-bus system, IEEE 118-bus system, and the Polish 2383-bus system. The number of representative constraints to be assessed is only 1.1%, 0.32%, and 0.27% of that of the original constraints, respectively, and the computational time of security assessment is greatly reduced. [ABSTRACT FROM AUTHOR]

This paper presents a model for breaker status identification and power system topology estimation based on a mosaic of local auto-associative neural networks. The approach extracts information from values of the analog electric variables and allows the recovery of missing sensor signals or the correction of erroneous data about breaker status. The results are confirmed by extensive tests conducted on an IEEE benchmark network. [ABSTRACT FROM PUBLISHER]

Wind generator (WG) output is a function of wind speed and three-phase terminal voltage. Distribution systems are predominantly unbalanced. A WG model that is purely a function of wind speed is simple to use with unbalanced three-phase power flow analysis but the solution is inaccurate. These errors add up and become pronounced when a single three-phase feeder connects several WGs. Complete nonlinear three-phase WG models are accurate but are slow and unsuitable for power flow applications. This paper proposes artificial neural network (ANN) models to represent type-3 doubly-fed induction generator and type-4 permanent magnet synchronous generator. The proposed approach can be readily applied to any other type of WGs. The main advantages of these ANN models are their mathematical simplicity, high accuracy with unbalanced systems and computational speed. These models were tested with the IEEE 37-bus test system. The results show that the ANN WG models are computationally ten times faster than nonlinear accurate models. In addition, simplicity of the proposed ANN WG models allow easy integration into commercial software packages such as PSS®E and PSS®SINCAL and implementations are also shown in this paper. [ABSTRACT FROM PUBLISHER]

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]

Price forecasting in competitive electricity markets is critical for consumers and producers in planning their operations and managing their price risk, and it also plays a key role in the economic optimization of the electric energy industry. This paper explores a technique of artificial neural network (ANN) model based on similar days (SD) method in order to forecast day-ahead electricity price in the PJM market. To demonstrate the superiority of the proposed model, publicly available data acquired from the PJM Interconnection were used for training and testing the ANN. The factors impacting the electricity price forecasting, including time factors, load factors, and historical price factors, are discussed. Comparison of forecasting performance of the proposed ANN model with that of forecasts obtained from similar days method is presented. Daily and weekly mean absolute percentage error (MAPE) of reasonably small value and forecast mean square error (FMSE) of less than 7$/MWh were obtained for the PJM data, which has correlation coefficient of determination (R²) of 0.6744 between load and electricity price. Simulation results show that the proposed ANN model based on similar days method is capable of forecasting locational marginal price (LMP) in the PJM market efficiently and accurately. [ABSTRACT FROM AUTHOR]

An optimal wide area controller is designed in this paper for a 12-bus power system together with a Static Compensator (STATCOM). The controller provides auxiliary reference signals for the automatic voltage regulators (AVR) of the generators as well as the line voltage controller of the STATCOM in such a way that it improves the damping of the rotor speed deviations of the synchronous machines. Adaptive critic designs theory is used to implement the controller and enable it to provide nonlinear optimal control over the infinite horizon time of the problem and at different operating conditions of the power system. Simulation results are provided to indicate that the proposed wide area controller improves the damping of the rotor speed deviations of the generators during large scale disturbances. Moreover, a robust radial basis function network based identifier is presented in this paper to predict the states of a multimachine power system in real-time. This wide area state predictor (WASP) compensates for transport lags associated with the present communication technology for wide area monitoring of the electric power grid. The WASP is also robust to partial loss of information caused by larger than expected transport lags or even failed sensors throughout the network. [ABSTRACT FROM AUTHOR]

This paper proposes a novel technique that combines orthogonal least-squares (OLS) and enhanced particle swarm optimization (EPSO) algorithms to construct the radial basis function (RBF) network for real-time power dispatch (RTPD). The goals considered are fuel cost, power wheeling cost, and NOx/CO2 emissions. The RBF network is composed of three-layer structures, which contain the input, hidden, and output layer. To simplify the network, the OLS algorithm is used first to determine the number of centers in the hidden layer. With an appropriate network structure, the EPSO algorithm is then used to tune the parameters in the network, including the dilation and translation of RBF centers and the weights between the hidden and output layer. The proposed approach has been tested on the IEEE 30-bus six-generator and practical Taiwan Power Company (Taipower) systems. Testing results indicate that the proposed approach can make a quick response and yield accurate RTPD solutions as soon as the inputs are given. Comparisons of learning performance are made to the existing artificial neural network (ANN), conventional REF network, and basic particle swarm optimization (PSO) methods. [ABSTRACT FROM AUTHOR]

Medium-term electric energy demand forecasting is an essential tool for power system planning and operation, mainly in those countries whose power systems operate in a deregulated environment. This paper proposes a novel approach to monthly electric energy demand time series forecasting, in which it is split into two new series: the trend and the fluctuation around it. Then two neural networks are trained to forecast them separately. These predictions are added up to obtain an overall forecasting. Several methods have been tested to find out which of them provides the best performance in the trend extraction. The proposed technique has been applied to the Spanish peninsular monthly electric consumption. The results obtained are better than those reached when only one neural network was used to forecast the original consumption series and also than those obtained with the ARIMA method. [ABSTRACT FROM AUTHOR]

This paper aims to develop a load forecasting method for short-term load forecasting, based on an adaptive two-stage hybrid network with self-organized map (SOM) and support vector machine (SVM). In the first stage, a SOM network is applied to cluster the input data set into several subsets in an unsupervised manner. Then, groups of 24 SVMs for the next day's load profile are used to fit the training data of each subset in the second stage in a supervised way. The proposed structure is robust with different data types and can deal well with the nonstationarity of load series. In particular, our method has the ability to adapt to different models automatically for the regular days and anomalous days at the same time. With the trained network, we can straight-forwardly predict the next-day hourly electricity load. To confirm the effectiveness, the proposed model has been trained and tested on the data of the historical energy load from New York Independent System Operator. [ABSTRACT FROM AUTHOR]

Determination of feeder configuration involving the switch statuses is important for the operation in the distribution system. Minimization of the megawatt loss is crucial if the system is in a normal condition; the voltage drop is expected to be as low as possible while a fault occurs in the system. This paper presents a method based on genetic algorithms (GAs) to determine the network configuration. The proposed method, formulated as a fuzzy multiobjective problem, takes both the normal condition and the contingencies (faults) into account. The switch statuses are considered as preventive controls for multiple individual balanced faults. A vertex encoding based on the Prufer number is used in GA for encoding the chromosomes (strings). The Prufer number ensures that the system structure will be radial for the distribution system. The simulation results from two distribution systems are used to show the applicability of the proposed method. [ABSTRACT FROM AUTHOR]

This paper presents an artificial neural network (ANN)-based coordination control scheme for under load tap changing (ULTC) transformer and STATCOM. The objective of the coordination controller is to minimize both the amount of tap changes of the transformer and STATCOM output while maintaining an acceptable voltage magnitude at the substation bus. The coordination controller is designed to substitute for a classical ULTC mechanism by utilizing active and reactive powers, tap position, and STATCOM output. A competitive ANN is used as a classifier for tap positions and trained by a proposed iterative condensed nearest neighbor (ICNN) rule. [ABSTRACT FROM AUTHOR]

This paper presents an approach for short-term load forecast problem, based on hybrid correction method. Conventional artificial neural network based short-term load forecasting techniques have limitations especially when weather changes are seasonal. Hence, we propose a load correction method by using fuzzy logic approach in which a fuzzy logic, based on similar days, corrects the neural network output to obtain the next day forecasted load. An Euclidean norm with weighted factors is used for the selection of similar days. The load correction method for the generation of new similar days is also proposed. The neural network has an advantage of dealing with the nonlinear parts of the forecasted load curves, whereas, the fuzzy rules are constructed based on the expert knowledge. Therefore, by combining these two methods, the test results show that the proposed forecasting method could provide a considerable improvement of the forecasting accuracy especially as it shows how to reduce neural network forecast error over the test period by 23 % through the application of a fuzzy logic correction. The suitability of the proposed approach is illustrated through an application to actual load data of the Okinawa Electric Power Company in Japan. [ABSTRACT FROM AUTHOR]

The paper addresses practical capabilities of artificial neural networks (ANNs) in developing measurement-based continuous-time dynamic equivalents for power systems. Our method is based on a set of measurements at boundary nodes between a subsystem that is to be modeled in detail ("retained" portion of the system) and the part that is to be replaced by a simplified ("equivalent") model. We are particularly interested in combining standard physics-based models with signal-based models derived from measurements. We utilize a color-coding scheme to distinguish between physics-based models (clear or white box) at one end, the signal-based models (opaque or black box) at the opposite end, and mixed (gray box) models in the middle. The paper also proposes a way for combining classical and ANN-based equivalents in a hybrid model implemented in a standard software environment for transient analysis (in this case, ETMSP). Our conclusions are based on simulations performed on a model of a benchmark multimachine power system derived from the WSCC system. [ABSTRACT FROM AUTHOR]