Broderick, Robert J.; Reno, Matthew J.; Lave, Matthew S.; Azzolini, Joseph A.; Blakely, Logan; Galtieri, Jason; Mather, Barry; Weekley, Andrew; Hunsberger, Randolph; Chamana, Manohar; Li, Qinmiao; Zhang, Wenqi; Latif, Aadil; Zhu, Xiangqi; Grijalva, Santiago; Zhang, Xiaochen; Deboever, Jeremiah; Qureshi, Muhammad U.; Therrien, Francis; Lacroix, Jean-Sebastien; Li, Feng; Belletete, Marc; Hebert, Guillaume; Montenegro, Davis; Dugan, Roger
The rapid increase in penetration of distributed energy resources on the electric power distribution system has created a need for more comprehensive interconnection modeling and impact analysis. Unlike conventional scenario-based studies, quasi-static time-series (QSTS) simulations can realistically model time-dependent voltage controllers and the diversity of potential impacts that can occur at different times of year. However, to accurately model a distribution system with all its controllable devices, a yearlong simulation at 1-second resolution is often required, which could take conventional computers a computational time of 10 to 120 hours when an actual unbalanced distribution feeder is modeled. This computational burden is a clear limitation to the adoption of QSTS simulations in interconnection studies and for determining optimal control solutions for utility operations. The solutions we developed include accurate and computationally efficient QSTS methods that could be implemented in existing open-source and commercial software used by utilities and the development of methods to create high-resolution proxy data sets. This project demonstrated multiple pathways for speeding up the QSTS computation using new and innovative methods for advanced time-series analysis, faster power flow solvers, parallel processing of power flow solutions and circuit reduction. The target performance level for this project was achieved with year-long high-resolution time series solutions run in less than 5 minutes within an acceptable error.
In power grid operation, optimal power flow (OPF) problems are solved several times per day to find economically optimal generator setpoints that balance given load demands. Ideally, we seek an optimal solution that is also “N-1 secure”, meaning the system can absorb contingency events such as transmission line or generator failure without loss of service. Current practice is to solve the OPF problem and then check a subset of contingencies against heuristic values, resulting in, at best, suboptimal solutions. Unfortunately, online solution of the OPF problem including the full N-1 contingencies (i.e., two-stage stochastic programming formulation) is intractable for even modest sized electrical grids. To address this challenge, this work presents an efficient method to embed N-1 security constraints into the solution of the OPF by using Neural Network (NN) models to represent the security boundary. Our approach introduces a novel sampling technique, as well as a tuneable parameter to allow operators to balance the conservativeness of the security model within the OPF problem. Our results show that we are able to solve contingency formulations of larger size grids than reported in literature using non-linear programming (NLP) formulations with embedded NN models to local optimality. Solutions found with the NN constraint have marginally increased computational time but are more secure to contingency events.
Distribution system models play a critical role in the modern grid, driving distributed energy resource integration through hosting capacity analysis and providing insight into critical areas of interest such as grid resilience and stability. Thus, the ability to validate and improve existing distribution system models is also critical. This work presents a method for identifying service transformers which contain errors in specifying the customers connected to the low-voltage side of that transformer. Pairwise correlation coefficients of the smart meter voltage time series are used to detect when a customer is not in the transformer grouping that is specified in the model. The proposed method is demonstrated both on synthetic data as well as a real utility feeder, and it successfully identifies errors in the transformer labeling in both datasets.
Calibrating distribution system models to aid in the accuracy of simulations such as hosting capacity analysis is increasingly important in the pursuit of the goal of integrating more distributed energy resources. The recent availability of smart meter data is enabling the use of machine learning tools to automatically achieve model calibration tasks. This research focuses on applying machine learning to the phase identification task, using a co-association matrix-based, ensemble spectral clustering approach. The proposed method leverages voltage time series from smart meters and does not require existing or accurate phase labels. This work demonstrates the success of the proposed method on both synthetic and real data, surpassing the accuracy of other phase identification research.
Timeseries power and voltage data recorded by electricity smart meters in the US have been shown to provide immense value to utilities when coupled with advanced analytics. However, Advanced Metering Infrastructure (AMI) has diverse characteristics depending on the utility implementing the meters. Currently, there are no specific guidelines for the parameters of data collection, such as measurement interval, that are considered optimal, and this continues to be an active area of research. This paper aims to review different grid edge, delay tolerant algorithms using AMI data and to identify the minimum granularity and type of data required to apply these algorithms to improve distribution system models. The primary focus of this report is on distribution system secondary circuit topology and parameter estimation (DSPE).
This paper discusses common types of errors that are frequently present in utility distribution system models and which can significantly influence distribution planning and operational assessments that rely on the model accuracy. Based on Google Earth imagery and analysis of correlation coefficients, this paper also illustrates some common error types and demonstrates methods to correct the errors. Error types include misla-beled interconnections between customers and service transformers, three-phase customers labeled as single-phase, unmarked transformers, and customers lacking coordinates. Identifying and correcting for these errors is critical for accurate distribution planning and operational assessments, such as load flow and hosting capacity analysis.
Spectral clustering is applied to the problem of phase identification of electric customers to investigate the data needs (resolution and accuracy) of advanced metering infrastructure (AMI). More accurate models are required to accurately interconnect high penetrations of PV/DER and for optimal electric grid operations. This paper demonstrates the effects of different data collection implementations and common errors in AMI datasets on the phase identification task. This includes measurement intervals, data resolution, collection periods, time synchronization issues, noisy measurements, biased meters, and mislabeled phases. High quality AMI data is a critical consideration to model correction and accurate hosting capacity analyses.
Smart grid technologies and wide-spread installation of advanced metering infrastructure (AMI) equipment present new opportunities for the use of machine learning algorithms paired with big data to improve distribution system models. Accurate models are critical in the continuing integration of distributed energy resources (DER) into the power grid, however the low-voltage models often contain significant errors. This paper proposes a novel spectral clustering approach for validating and correcting customer electrical phase labels in existing utility models using the voltage timeseries produced by AMI equipment. Spectral clustering is used in conjunction with a sliding window ensemble to improve the accuracy and scalability of the algorithm for large datasets. The proposed algorithm is tested using real data to validate or correct over 99% of customer phase labels within the primary feeder under consideration. This is over a 94% reduction in error given the 9% of customers predicted to have incorrect phase labels.
High-resolution, quasi-static time series (QSTS) simulations are essential for modeling modern distribution systems with high-penetration of distributed energy resources (DER) in order to accurately simulate the time-dependent aspects of the system. Presently, QSTS simulations are too computationally intensive for widespread industry adoption. This paper proposes to simulate a portion of the year with QSTS and to use decision tree machine learning methods, random forests and boosting ensembles, to predict the voltage regulator tap changes for the remainder of the year, accurately reproducing the results of the time-consuming, brute-force, yearlong QSTS simulation. This research uses decision tree ensemble machine learning, applied for the first time to QSTS simulations, to produce high-accuracy QSTS results, up to 4x times faster than traditional methods.
Rapid and accurate quasi-static time series (QSTS) analysis is becoming increasingly important for distribution system analysis as the complexity of the distribution system intensifies with the addition of new types, and quantities, of distributed energy resources (DER). The expanding need for hosting capacity analysis, control systems analysis, photovoltaic (PV) and DER impact analysis, and maintenance cost estimations are just a few reasons that QSTS is necessary. Historically, QSTS analysis has been prohibitively slow due to the number of computations required for a full-year analysis. Therefore, new techniques are required that allow QSTS analysis to rapidly be performed for many different use cases. This research demonstrates a novel approach to doing rapid QSTS analysis for analyzing the number of voltage regulator tap changes in a distribution system with PV components. A representative portion of a yearlong dataset is selected and QSTS analysis is performed to determine the number of tap changes, and this is used as training data for a machine learning algorithm. The machine learning algorithm is then used to predict the number of tap changes in the remaining portion of the year not analyzed directly with QSTS. The predictions from the machine learning algorithms are combined with the results of the partial year simulation for a final prediction for the entire year, with the goal of maintaining an error <10% on the full-year prediction. Five different machine learning techniques were evaluated and compared with each other; a neural network ensemble, a random forest decision tree ensemble, a boosted decision tree ensemble, support vector machines, and a convolutional neural network deep learning technique. A combination of the neural network ensemble together with the random forest produced the best results. Using 20% of the year as training data, analyzed with QSTS, the average performance of the technique resulted in ~2.5% error in the yearly tap changes, while maintaining a <10% 99.9th percentile error bound on the results. This is a 5x speedup compared to a standard, full-length QSTS simulation. These results demonstrate the potential for applying machine learning techniques to facilitate modern distribution system analysis and further integration of distributed energy resources into the power grid.