scholarly journals Time Synchronized State Estimation for Incompletely Observed Distribution Systems Using Deep Learning Considering Realistic Measurement Noise

2021 ◽  
Author(s):  
B. Azimian ◽  
R. Sen Biswas ◽  
A. Pal ◽  
Lang Tong
Keyword(s):  
Deep Learning ◽  
State Estimation ◽  
Distribution Systems ◽  
Measurement Noise

scholarly journals Bayesian State Estimation for Unobservable Distribution Systems via Deep Learning

2019 ◽  
Vol 34 (6) ◽  
pp. 4910-4920 ◽  
Author(s):  
Kursat Rasim Mestav ◽  
Jaime Luengo-Rozas ◽  
Lang Tong
Keyword(s):  
Deep Learning ◽  
State Estimation ◽  
Distribution Systems

An improved unscented Kalman filter based dynamic state estimation algorithm for electric distribution Systems

2017 ◽  
Vol 36 (4) ◽  
pp. 1220-1236 ◽  
Author(s):  
Fiaz Ahmad ◽  
Kabir Muhammad Abdul Rashid ◽  
Akhtar Rasool ◽  
Esref Emre Ozsoy ◽  
Asif Sabanoviç ◽  
...  
Keyword(s):  
Kalman Filter ◽  
State Estimation ◽  
Radial Distribution ◽  
Distribution Systems ◽  
Unscented Kalman Filter ◽  
Distribution Networks ◽  
Measurement Noise ◽  
Content Type ◽  
Load Variations ◽  
Bad Data

Purpose To propose an improved algorithm for the state estimation of distribution networks based on the unscented Kalman filter (IUKF). The performance comparison of unscented Kalman filter (UKF) and newly developed algorithm, termed Improved unscented Kalman Filter (IUKF) for IEEE-30, 33 and 69-bus radial distribution networks for load variations and bad data for two measurement noise scenarios, i.e. 30 and 50 per cent are shown. Design/methodology/approach State estimation (SE) plays an instrumental role in realizing smart grid features like distribution automation (DA), enhanced distribution generation (DG) penetration and demand response (DR). Implementation of DA requires robust, accurate and computationally efficient dynamic SE techniques that can capture the fast changing dynamics of distribution systems more effectively. In this paper, the UKF is improved by changing the way the state covariance matrix is calculated, to enhance its robustness and accuracy under noisy measurement conditions. UKF and proposed IUKF are compared under the cummulative effect of load variations and bad data based on various statistical metrics such as Maximum Absolute Deviation (MAD), Maximum Absolute Per cent Error (MAPE), Root Mean Square Error (RMSE) and Overall Performance Index (J) for three radial distribution networks. All the simulations are performed in MATLAB 2014b environment running on an hp core i5 laptop with 4GB memory and 2.6 GHz processor. Findings An Improved Unscented Kalman Filter Algorithm (IUKF) is developed for distribution network state estimation. The developed IUKF is used to predict network states (voltage magnitude and angle at all buses) and measurements (source voltage magnitude, line power flows and bus injections) in the presence of load variations and bad data. The statistical performance of the coventional UKF and the proposed IUKF is carried out for a variety of simulation scenarios for IEEE-30, 33 and 69 bus radial distribution systems. The IUKF demonstrated superiority in terms of: RMSE; MAD; MAPE; and overall performance index J for two measurement noise scenarios (30 and 50 per cent). Moreover, it is shown that for a measurement noise of 50 per cent and above, UKF fails while IUKF performs. Originality/value UKF shows degraded performance under high measurement noise and fails in some cases. The proposed IUKF is shown to outperform the UKF in all the simulated scenarios. Moreover, this work is novel and has justified improvement in the robustness of the conventional UKF algorithm.

scholarly journals Application of Deep Neural Networks to Distribution System State Estimation and Forecasting

2022 ◽  
Vol 3 ◽  
Author(s):  
James P. Carmichael ◽  
Yuan Liao
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Power System ◽  
State Estimation ◽  
Power Distribution ◽  
Distribution Systems ◽  
System State ◽  
Power Distribution Systems ◽  
Static State ◽  
Power System State Estimation

Classical neural networks such as feedforward multi-layer perceptron models (MLPs) are well established as universal approximators and as such, show promise in applications such as static state estimation in power transmission systems. The dynamic nature of distributed generation (i.e. solar and wind), vehicle to grid technology (V2G) and false data injection attacks (FDIAs), may pose significant challenges to the application of classical MLPs to state estimation (SE) and state forecasting (SF) in power distribution systems. This paper investigates the application of conventional neural networks (MLPs) and deep learning based models such as convolutional neural networks (CNNs) and long-short term networks (LSTMs) to mitigate the aforementioned challenges in power distribution systems. The ability of MLPs to perform regression to perform power system state estimation will be investigated. MLPs are considered based upon their promise to learn complex functional mapping between datasets with many features. CNNs and LSTMs are considered based upon their promise to perform time-series forecasting by learning the correlation of the dataset being predicted. The performance of MLPS, CNNs, and LSTMs to perform state estimation and state forecasting will be presented in terms of average root-mean square error (RMSE) and training execution time. An IEEE standard 34-bus test system is used to illustrate the proposed conventional neural network and deep learning methods and their effectiveness to perform power system state estimation and power system state forecasting.

scholarly journals Full-Observable Three-Phase State Estimation Algorithm Applied to Electric Distribution Grids

Energies ◽  
2019 ◽  
Vol 12 (7) ◽  
pp. 1327 ◽  
Author(s):  
Thiago Soares ◽  
Ubiratan Bezerra ◽  
Maria Tostes
Keyword(s):  
State Estimation ◽  
Real Time ◽  
Distribution Systems ◽  
Phase State ◽  
Reactive Power ◽  
Estimation Algorithm ◽  
Load Flow ◽  
Electrical Network ◽  
The Real ◽  
Three Phase

This paper proposes the development of a three-phase state estimation algorithm, which ensures complete observability for the electric network and a low investment cost for application in typical electric power distribution systems, which usually exhibit low levels of supervision facilities and measurement redundancy. Using the customers´ energy bills to calculate average demands, a three-phase load flow algorithm is run to generate pseudo-measurements of voltage magnitudes, active and reactive power injections, as well as current injections which are used to ensure the electrical network is full-observable, even with measurements available at only one point, the substation-feeder coupling point. The estimation process begins with a load flow solution for the customers´ average demand and uses an adjustment mechanism to track the real-time operating state to calculate the pseudo-measurements successively. Besides estimating the real-time operation state the proposed methodology also generates nontechnical losses estimation for each operation state. The effectiveness of the state estimation procedure is demonstrated by simulation results obtained for the IEEE 13-bus test network and for a real urban feeder.

Robust high-degree cubature information filter and its application to trajectory estimation for ballistic missile

2017 ◽  
Vol 232 (12) ◽  
pp. 2364-2377 ◽  
Author(s):  
Xiaogang Wang ◽  
Wutao Qin ◽  
Naigang Cui ◽  
Yu Wang
Keyword(s):  
State Estimation ◽  
Estimation Algorithm ◽  
Ballistic Missile ◽  
Measurement Noise ◽  
Estimation Accuracy ◽  
Trajectory Estimation ◽  
Information Filter ◽  
Non Gaussian ◽  
Time Update ◽  
High Degree

This paper presents a new recursive filter algorithm, the robust high-degree cubature information filter, which can provide reliable state estimation in the presence of non-Gaussian measurement noise. The novel algorithm is developed in the framework of the conventional information filter. The fifth-degree Cubature rule is utilized to improve the estimation accuracy and numerical stability during the time update, while the Huber technique is adopted in the measurements update stage. As the Huber technique is a combined minimum l1 and l2 norm estimation algorithm, the proposed algorithm could exhibit robustness to the non-Gaussian measurement noise, especially the glint noise. In addition, Monte Carlo simulation and the trajectory estimation for ballistic missile experiments demonstrate that the robust high-degree cubature information filter can provide improved state estimation performance over extended information filter and high-degree cubature information filter.

Sign in / Sign up

Export Citation Format

Share Document