Supervised Learning Approach for State Estimation of Unmeasured Points of Distribution Network

Hong, Gwangpyo; Kim, Yun-Su

doi:10.1109/access.2020.3003049

Cited by 16 publications

(10 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As several datasets were synthetically generated using simulation software, only various studies reported problems with imbalanced datasets and missing items in the data. In this regard, Hong et al [45] analyzed the case in which data were missing from one of the buses, concluding that system performance decreased significantly. Karagiannopoulos et al [46] extrapolated historical data and used information from the public domain or from neighboring systems to deal with missing or noisy data.…”

Section: Discussionmentioning

confidence: 99%

Advances in the Application of Machine Learning Techniques for Power System Analytics: A Survey

et al. 2021

View full text Add to dashboard Cite

The recent advances in computing technologies and the increasing availability of large amounts of data in smart grids and smart cities are generating new research opportunities in the application of Machine Learning (ML) for improving the observability and efficiency of modern power grids. However, as the number and diversity of ML techniques increase, questions arise about their performance and applicability, and on the most suitable ML method depending on the specific application. Trying to answer these questions, this manuscript presents a systematic review of the state-of-the-art studies implementing ML techniques in the context of power systems, with a specific focus on the analysis of power flows, power quality, photovoltaic systems, intelligent transportation, and load forecasting. The survey investigates, for each of the selected topics, the most recent and promising ML techniques proposed by the literature, by highlighting their main characteristics and relevant results. The review revealed that, when compared to traditional approaches, ML algorithms can handle massive quantities of data with high dimensionality, by allowing the identification of hidden characteristics of (even) complex systems. In particular, even though very different techniques can be used for each application, hybrid models generally show better performances when compared to single ML-based models.

show abstract

Section: Discussionmentioning

confidence: 99%

Advances in the Application of Machine Learning Techniques for Power System Analytics: A Survey

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Artificial neural networks or connectionist systems are machine learning tools inspired by biological neural networks and can process the same data as the human brain [22]. ANN can develop linear and nonlinear models for time series.…”

Section: Feed-forward Neural Networkmentioning

confidence: 99%

Atom Search Optimization – Neural Network for Driving Dc Motor

Aribowo

Joko

Isnur

et al. 2021

Sinergi

View full text Add to dashboard Cite

DC motor applications are very widely used because DC motors are very suitable for applications, especially control. Thus, a proper DC motor controller design is required. DC motor speed control is very important to maintain the stability of motor operation. A recent type of metaheuristic algorithm that mimics the motion of atoms is introduced. Atom search optimization (ASO) is a mathematical model and duplicates the behavior of atoms in nature. Atoms intercommunicate with each other via the delivering contact force in the form of the Lennard-Jones potential and the constraint force produced from the potential bond length. The algorithm is simple and easy to be applied. In this study, the atomic search optimization (ASO) algorithm is proposed as a speed controller for the control dc motor. First, the ASO proposed by the algorithm is applied for the optimization of the neural network. Second, the ASO-NN proposal was the result compared to other algorithms. This paper compares the performance of two different control techniques applied to DC motors, namely the ASO-NN and proportional integral derivative (PID) methods. The results show that the proposed method has effectiveness. The calculation of the proposed ASO-NN control shows the best performance in the settling time. The ASO-NN method has the capability of settling time 0.04 seconds faster than the PID method.

show abstract

“…A gradient-based multi-area algorithm is proposed for the distribution network state estimation, and it is expressed through a weighted least squares problem in [10]. The authors of [11], proposed a methodology to estimate the target bus voltage with known bus information using a supervised learning algorithm. A neural network technique that offers robustness for any restructuring in the network topology discussed in [12].…”

Section: Introductionmentioning

confidence: 99%

Voltage Estimation of Active Distribution Network Using PMU Technology

Tangi

Gaonkar

2021

IEEE Access

View full text Add to dashboard Cite

As the Distributed Generation (DG) is evolving, the distribution network has undergone tremendous change. The DG sources like wind and solar are intermittent in nature. Hence to estimate the Active distribution network's (ADN) parameters (Voltage and Current) accurately with the DG variation, the traditional offline method like long-term smart distribution network planning (with off-line variant) method is not feasible in terms of network's reliability and operation. In this work, an online voltage estimation technique using PMU (Phasor Measurement Unit) technology is proposed to enhance a distribution network's reliable operation and real-time monitoring. The proposed estimation method does not require PMU units at all nodes in the network. The estimation of unknown states information can be achieved from available PMU unit's data. The proposed methodology is economical and feasible for voltage estimation, and system observability as the number of PMU units required is less. The standard IEEE Distribution network systems are considered for checking the feasibility of the recommended technique. For the simulation of the case studies, MATLAB programming is used. A Forward and Backward sweep (FBS) load-flow algorithm is used to authenticate the proposed methodology.

show abstract

Supervised Learning Approach for State Estimation of Unmeasured Points of Distribution Network

Cited by 16 publications

References 24 publications

Advances in the Application of Machine Learning Techniques for Power System Analytics: A Survey

Advances in the Application of Machine Learning Techniques for Power System Analytics: A Survey

Atom Search Optimization – Neural Network for Driving Dc Motor

Voltage Estimation of Active Distribution Network Using PMU Technology

Contact Info

Product

Resources

About