Energies

Research

Jump to: Review

23 pages, 1970 KiB

Open AccessArticle

Generating Energy Data for Machine Learning with Recurrent Generative Adversarial Networks

by Mohammad Navid Fekri, Ananda Mohon Ghosh and Katarina Grolinger

Energies 2020, 13(1), 130; https://doi.org/10.3390/en13010130 - 26 Dec 2019

Cited by 80 | Viewed by 8296

Abstract

The smart grid employs computing and communication technologies to embed intelligence into the power grid and, consequently, make the grid more efficient. Machine learning (ML) has been applied for tasks that are important for smart grid operation including energy consumption and generation forecasting, [...] Read more.

The smart grid employs computing and communication technologies to embed intelligence into the power grid and, consequently, make the grid more efficient. Machine learning (ML) has been applied for tasks that are important for smart grid operation including energy consumption and generation forecasting, anomaly detection, and state estimation. These ML solutions commonly require sufficient historical data; however, this data is often not readily available because of reasons such as data collection costs and concerns regarding security and privacy. This paper introduces a recurrent generative adversarial network (R-GAN) for generating realistic energy consumption data by learning from real data. Generativea adversarial networks (GANs) have been mostly used for image tasks (e.g., image generation, super-resolution), but here they are used with time series data. Convolutional neural networks (CNNs) from image GANs are replaced with recurrent neural networks (RNNs) because of RNN’s ability to capture temporal dependencies. To improve training stability and increase quality of generated data, Wasserstein GANs (WGANs) and Metropolis-Hastings GAN (MH-GAN) approaches were applied. The accuracy is further improved by adding features created with ARIMA and Fourier transform. Experiments demonstrate that data generated by R-GAN can be used for training energy forecasting models. Full article

(This article belongs to the Special Issue Application of Machine Learning and Data Mining in Electrical Engineering)

► Show Figures

Figure 1

19 pages, 6072 KiB

Open AccessArticle

Features Recognition from Piping and Instrumentation Diagrams in Image Format Using a Deep Learning Network

by Eun-Seop Yu, Jae-Min Cha, Taekyong Lee, Jinil Kim and Duhwan Mun

Energies 2019, 12(23), 4425; https://doi.org/10.3390/en12234425 - 21 Nov 2019

Cited by 33 | Viewed by 11037

Abstract

A piping and instrumentation diagram (P&ID) is a key drawing widely used in the energy industry. In a digital P&ID, all included objects are classified and made amenable to computerized data management. However, despite being widespread, a large number of P&IDs in the [...] Read more.

A piping and instrumentation diagram (P&ID) is a key drawing widely used in the energy industry. In a digital P&ID, all included objects are classified and made amenable to computerized data management. However, despite being widespread, a large number of P&IDs in the image format still in use throughout the process (plant design, procurement, construction, and commissioning) are hampered by difficulties associated with contractual relationships and software systems. In this study, we propose a method that uses deep learning techniques to recognize and extract important information from the objects in the image-format P&IDs. We define the training data structure required for developing a deep learning model for the P&ID recognition. The proposed method consists of preprocessing and recognition stages. In the preprocessing stage, diagram alignment, outer border removal, and title box removal are performed. In the recognition stage, symbols, characters, lines, and tables are detected. The objects for recognition are symbols, characters, lines, and tables in P&ID drawings. A new deep learning model for symbol detection is defined using AlexNet. We also employ the connectionist text proposal network (CTPN) for character detection, and traditional image processing techniques for P&ID line and table detection. In the experiments where two test P&IDs were recognized according to the proposed method, recognition accuracies for symbol, characters, and lines were found to be 91.6%, 83.1%, and 90.6% on average, respectively. Full article

(This article belongs to the Special Issue Application of Machine Learning and Data Mining in Electrical Engineering)

► Show Figures

Graphical abstract

13 pages, 5943 KiB

Open AccessArticle

Design of a Chamfering Tool Diagnosis System Using Autoencoder Learning Method

by Chung-Wen Hung, Wei-Ting Li, Wei-Lung Mao and Pal-Chun Lee

Energies 2019, 12(19), 3708; https://doi.org/10.3390/en12193708 - 27 Sep 2019

Cited by 6 | Viewed by 2626

Abstract

In this paper, the autoencoder learning method is proposed for the system diagnosis of chamfering tool equipment. The autoencoder uses unsupervised learning architecture. The training dataset that requires only a positive sample is quite suitable for industrial production lines. The abnormal tool can [...] Read more.

In this paper, the autoencoder learning method is proposed for the system diagnosis of chamfering tool equipment. The autoencoder uses unsupervised learning architecture. The training dataset that requires only a positive sample is quite suitable for industrial production lines. The abnormal tool can be diagnosed by comparing the output and input of the autoencoder neural network. The adjustable threshold can effectively improve accuracy. This method can effectively adapt to the current environment when the data contain multiple signals. In the experimental setup, the main diagnostic signal is the current of the motor. The current reflects the torque change when the tool is abnormal. Four-step conversions are developed to process the current signal, including (1) current-to-voltage conversion, (2) analog-digital conversion, (3) downsampling rate, and (4) discrete Fourier transform. The dataset is used to find the best autoencoder parameters by grid search. In training results, the testing accuracy, true positive rate, and precision approach are 87.5%, 83.33%, and 90.91%, respectively. The best model of the autoencoder is evaluated by online testing. The online test means loading the diagnosis model in the production line and evaluating the model. It is shown that the proposed tool can effectively detect abnormal conditions. The online assessment accuracy, true positive rate, and precision are 75%, 90%, and 69.23% in the original threshold, respectively. The accuracy can be up to 90% after adjusting the threshold, and the true positive rate and precision are up to 80% and 100%, respectively. Full article

(This article belongs to the Special Issue Application of Machine Learning and Data Mining in Electrical Engineering)

► Show Figures

Figure 1

20 pages, 3585 KiB

Open AccessArticle

A Hierarchical Self-Adaptive Method for Post-Disturbance Transient Stability Assessment of Power Systems Using an Integrated CNN-Based Ensemble Classifier

by Ruoyu Zhang, Junyong Wu, Yan Xu, Baoqin Li and Meiyang Shao

Energies 2019, 12(17), 3217; https://doi.org/10.3390/en12173217 - 21 Aug 2019

Cited by 21 | Viewed by 2438

Abstract

Data-driven approaches using synchronous phasor measurements are playing an important role in transient stability assessment (TSA). For post-disturbance TSA, there is not a definite conclusion about how long the response time should be. Furthermore, previous studies seldom considered the confidence level of prediction [...] Read more.

Data-driven approaches using synchronous phasor measurements are playing an important role in transient stability assessment (TSA). For post-disturbance TSA, there is not a definite conclusion about how long the response time should be. Furthermore, previous studies seldom considered the confidence level of prediction results and specific stability degree. Since transient stability can develop very fast and cause tremendous economic losses, there is an urgent need for faster response speed, credible accurate prediction results, and specific stability degree. This paper proposed a hierarchical self-adaptive method using an integrated convolutional neural network (CNN)-based ensemble classifier to solve these problems. Firstly, a set of classifiers are sequentially organized at different response times to construct different layers of the proposed method. Secondly, the confidence integrated decision-making rules are defined. Those predicted as credible stable/unstable cases are sent into the stable/unstable regression model which is built at the corresponding decision time. The simulation results show that the proposed method can not only balance the accuracy and rapidity of the transient stability prediction, but also predict the stability degree with very low prediction errors, allowing more time and an instructive guide for emergency controls. Full article

(This article belongs to the Special Issue Application of Machine Learning and Data Mining in Electrical Engineering)

► Show Figures

Figure 1

26 pages, 376 KiB

Open AccessArticle

Proton Exchange Membrane Fuel Cell Stack Design Optimization Using an Improved Jaya Algorithm

by Uday K. Chakraborty

Energies 2019, 12(16), 3176; https://doi.org/10.3390/en12163176 - 19 Aug 2019

Cited by 12 | Viewed by 3407

Abstract

Fuel cell stack configuration optimization is known to be a problem that, in addition to presenting engineering challenges, is computationally hard. This paper presents an improved computational heuristic for solving the problem. The problem addressed in this paper is one of constrained optimization, [...] Read more.

Fuel cell stack configuration optimization is known to be a problem that, in addition to presenting engineering challenges, is computationally hard. This paper presents an improved computational heuristic for solving the problem. The problem addressed in this paper is one of constrained optimization, where the goal is to seek optimal (or near-optimal) values of (i) the number of proton exchange membrane fuel cells (PEMFCs) to be connected in series to form a group, (ii) the number of such groups to be connected in parallel, and (iii) the cell area, such that the PEMFC assembly delivers the rated voltage at the rated power while the cost of building the assembly is as low as possible. Simulation results show that the proposed method outperforms four of the best-known methods in the literature. The improvement in performance afforded by the proposed algorithm is validated with statistical tests of significance. Full article

(This article belongs to the Special Issue Application of Machine Learning and Data Mining in Electrical Engineering)

► Show Figures

Figure 1

15 pages, 2173 KiB

Open AccessArticle

Edge Computing Approach for Vessel Monitoring System

by Joao C. Ferreira and Ana Lucia Martins

Energies 2019, 12(16), 3087; https://doi.org/10.3390/en12163087 - 10 Aug 2019

Cited by 8 | Viewed by 2808

Abstract

A vessel monitoring system (VMS) is responsible for real-time vessel movement tracking. At sea, most of the tracking systems use satellite communications, which have high associated costs. This leads to a less frequent transmission of data, which reduces the reliability of the vessel [...] Read more.

A vessel monitoring system (VMS) is responsible for real-time vessel movement tracking. At sea, most of the tracking systems use satellite communications, which have high associated costs. This leads to a less frequent transmission of data, which reduces the reliability of the vessel location. Our research work involves the creation of an edge computing approach on a local VMS, creating an intelligent process that decides whether the collected data needs to be transmitted or not. Only relevant data that can indicate abnormal behavior is transmitted. The remaining data is stored and transmitted only at ports when communication systems are available at lower prices. In this research, we apply this approach to a fishing control process increasing the data collection process from once every 10 min to once every 30 s, simultaneously decreasing the satellite communication costs, as only relevant data is transmitted in real-time to the competent central authorities. Findings show substantial communication savings from 70% to 90% as only abnormal vessel behavior is transmitted. Even with a data collection process of once every 30 s, findings also show that the use of more stable fishing techniques and fishing areas result in higher savings. The proposed approach is assessed as well in terms of the environmental impact of fishing and potential fraud detection and reduction. Full article

(This article belongs to the Special Issue Application of Machine Learning and Data Mining in Electrical Engineering)

► Show Figures

Figure 1

18 pages, 1872 KiB

Open AccessArticle

Identification of Low Frequency Oscillations Based on Multidimensional Features and ReliefF-mRMR

by Shuang Feng, Jianing Chen and Yi Tang

Energies 2019, 12(14), 2762; https://doi.org/10.3390/en12142762 - 18 Jul 2019

Cited by 5 | Viewed by 2485

Abstract

Low frequency oscillations (LFOs) in power systems usually fall into two types, i.e., forced oscillations and natural oscillations. Waveforms of the two are similar, but the suppression methods are different. Therefore, it is important to accurately identify LFO type. In this paper, a [...] Read more.

Low frequency oscillations (LFOs) in power systems usually fall into two types, i.e., forced oscillations and natural oscillations. Waveforms of the two are similar, but the suppression methods are different. Therefore, it is important to accurately identify LFO type. In this paper, a method for discriminating LFO type based on multi-dimensional features and a feature selection algorithm combining ReliefF and minimum redundancy maximum relevance algorithm (mRMR) is proposed. Firstly, 53 features are constructed from six aspects—time domain, frequency domain, energy, correlation, complexity, and modal analysis—which comprehensively characterize the multidimensional features of LFO. Then, the optimal feature subset with greater relevance and less redundancy is extracted by ReliefF-mRMR. In order to improve the classification performance, a modified Support Vector Machine (SVM) with Genetic Algorithm (GA) optimizing the key parameters is adopted, which is conducted in MATLAB. Finally, in 179-bus system, the samples of LFOs are generated by the Power System Analysis Toolbox (PSAT) and the accuracy of the LFO type identification model is verified. In ISO New England and East China power grid, it is proven that the proposed method can accurately identify LFO type considering the influences of noise, oscillation mode, and data incompletion. Hence, it has good robustness, noise immunity, and practicability. Full article

(This article belongs to the Special Issue Application of Machine Learning and Data Mining in Electrical Engineering)

► Show Figures

Figure 1

14 pages, 1133 KiB

Open AccessArticle

Research on Predicting Line Loss Rate in Low Voltage Distribution Network Based on Gradient Boosting Decision Tree

by Mengting Yao, Yun Zhu, Junjie Li, Hua Wei and Penghui He

Energies 2019, 12(13), 2522; https://doi.org/10.3390/en12132522 - 30 Jun 2019

Cited by 31 | Viewed by 3475

Abstract

Line loss rate plays an essential role in evaluating the economic operation of power systems. However, in a low voltage (LV) distribution network, calculating line loss rate has become more cumbersome due to poor configuration of the measuring and detecting device, the difficulty [...] Read more.

Line loss rate plays an essential role in evaluating the economic operation of power systems. However, in a low voltage (LV) distribution network, calculating line loss rate has become more cumbersome due to poor configuration of the measuring and detecting device, the difficulty in collecting operational data, and the excessive number of components and nodes. Most previous studies mainly focused on the approaches to calculate or predict line loss rate, but rarely involve the evaluation of the prediction results. In this paper, we propose an approach based on a gradient boosting decision tree (GBDT), to predict line loss rate. GBDT inherits the advantages of both statistical models and AI approaches, and can identify the complex and nonlinear relationship while computing the relative importance among variables. An empirical study on a data set in a city demonstrates that our proposed approach performs well in predicting line loss rate, given a large number of unlabeled examples. Experiments and analysis also confirmed the effectiveness of our proposed approach in anomaly detection and practical project management. Full article

(This article belongs to the Special Issue Application of Machine Learning and Data Mining in Electrical Engineering)

► Show Figures

Figure 1

17 pages, 4041 KiB

Open AccessArticle

Electric Load Data Compression and Classification Based on Deep Stacked Auto-Encoders

by Xiaoyao Huang, Tianbin Hu, Chengjin Ye, Guanhua Xu, Xiaojian Wang and Liangjin Chen

Energies 2019, 12(4), 653; https://doi.org/10.3390/en12040653 - 18 Feb 2019

Cited by 33 | Viewed by 3742

Abstract

With the development of advanced metering infrastructure (AMI), electrical data are collected frequently by smart meters. Consequently, the load data volume and length increase dramatically, which aggravates the data storage and transmission burdens in smart grids. On the other hand, for event detection [...] Read more.

With the development of advanced metering infrastructure (AMI), electrical data are collected frequently by smart meters. Consequently, the load data volume and length increase dramatically, which aggravates the data storage and transmission burdens in smart grids. On the other hand, for event detection or market-based demand response applications, load service entities (LSEs) want smart meter readings to be classified in specific and meaningful types. Considering these challenges, a stacked auto-encoder (SAE)-based load data mining approach is proposed. First, an innovative framework for smart meter data flow is established. On the user side, the SAEs are utilized to compress load data in a distributed way. Then, centralized classification is adopted at remote data center by softmax classifier. Through the layer-wise feature extracting of SAE, the sparse and lengthy raw data are expressed in compact forms and then classified based on features. A global fine-tuning strategy based on a well-defined labeled subset is embedded to improve the extracted features and the classification accuracy. Case studies in China and Ireland demonstrate that the proposed method is more capable to achieve the minimum of error and satisfactory compression ratios (CR) than benchmark compressors. It also significantly improves the classification accuracy on both appliance and house level datasets. Full article

(This article belongs to the Special Issue Application of Machine Learning and Data Mining in Electrical Engineering)

► Show Figures

Figure 1

Review

Jump to: Research

16 pages, 3451 KiB

Open AccessReview

Partial Discharge Classification Using Deep Learning Methods—Survey of Recent Progress

by Sonia Barrios, David Buldain, María Paz Comech, Ian Gilbert and Iñaki Orue

Energies 2019, 12(13), 2485; https://doi.org/10.3390/en12132485 - 27 Jun 2019

Cited by 76 | Viewed by 6650

Abstract

This paper examines the recent advances made in the field of Deep Learning (DL) methods for the automated identification of Partial Discharges (PD). PD activity is an indication of the state and operational conditions of electrical equipment systems. There are several techniques for [...] Read more.

This paper examines the recent advances made in the field of Deep Learning (DL) methods for the automated identification of Partial Discharges (PD). PD activity is an indication of the state and operational conditions of electrical equipment systems. There are several techniques for on-line PD measurements, but the typical classification and recognition method is made off-line and involves an expert manually extracting appropriate features from raw data and then using these to diagnose PD type and severity. Many methods have been developed over the years, so that the appropriate features expertly extracted are used as input for Machine Learning (ML) algorithms. More recently, with the developments in computation and data storage, DL methods have been used for automated features extraction and classification. Several contributions have demonstrated that Deep Neural Networks (DNN) have better accuracy than the typical ML methods providing more efficient automated identification techniques. However, improvements could be made regarding the general applicability of the method, the data acquisition, and the optimal DNN structure. Full article

(This article belongs to the Special Issue Application of Machine Learning and Data Mining in Electrical Engineering)

► Show Figures

Figure 1

42 pages, 7268 KiB

Open AccessReview

A Review on Hybrid Empirical Mode Decomposition Models for Wind Speed and Wind Power Prediction

by Neeraj Bokde, Andrés Feijóo, Daniel Villanueva and Kishore Kulat

Energies 2019, 12(2), 254; https://doi.org/10.3390/en12020254 - 15 Jan 2019

Cited by 122 | Viewed by 7130

Abstract

Reliable and accurate planning and scheduling of wind farms and power grids to ensure sustainable use of wind energy can be better achieved with the use of precise and accurate prediction models. However, due to the highly chaotic, intermittent and stochastic behavior of [...] Read more.

Reliable and accurate planning and scheduling of wind farms and power grids to ensure sustainable use of wind energy can be better achieved with the use of precise and accurate prediction models. However, due to the highly chaotic, intermittent and stochastic behavior of wind, which means a high level of difficulty when predicting wind speed and, consequently, wind power, the evolution of models capable of narrating data of such a complexity is an emerging area of research. A thorough review of literature, present research overviews, and information about possible expansions and extensions of models play a significant role in the enhancement of the potential of accurate prediction models. The last few decades have experienced a remarkable breakthrough in the development of accurate prediction models. Among various physical, statistical and artificial intelligent models developed over this period, the models hybridized with pre-processing or/and post-processing methods have seen promising prediction results in wind applications. The present review is focused on hybrid empirical mode decomposition (EMD) or ensemble empirical mode decomposition (EEMD) models with their advantages, timely growth and possible future in wind speed and power forecasting. Over the years, the practice of EEMD based hybrid models in wind data predictions has risen steadily and has become popular because of the robust and accurate nature of this approach. In addition, this review is focused on distinct attributes including the evolution of EMD based methods, novel techniques of treating Intrinsic Mode Functions (IMFs) generated with EMD/EEMD and overview of suitable error measures for such studies. Full article

(This article belongs to the Special Issue Application of Machine Learning and Data Mining in Electrical Engineering)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Application of Machine Learning and Data Mining in Electrical Engineering

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (11 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI