Fault detection is essential in microgrid control and operation, as it enables the system to perform fast fault isolation and recovery. The adoption of inverter-interfaced distributed generation in microgrids makes traditional fault detection schemes inappropriate due to their dependence on significant fault currents. In this paper, we devise an intelligent fault detection scheme for microgrid based on wavelet transform and deep neural networks. The proposed scheme aims to provide fast fault type, phase, and location information for microgrid protection and service recovery. In the scheme, branch current measurements sampled by protective relays are pre-processed by discrete wavelet transform to extract statistical features. Then all available data is input into deep neural networks to develop fault information. Compared with previous work, the proposed scheme can provide significantly better fault type classification accuracy. Moreover, the scheme can also detect the locations of faults, which are unavailable in previous work. To evaluate the performance of the proposed fault detection scheme, we conduct a comprehensive evaluation study on the CERTS microgrid and IEEE 34-bus system. The simulation results demonstrate the efficacy of the proposed scheme in terms of detection accuracy, computation time, and robustness against measurement uncertainty.

Intelligent Fault Detection Scheme for Microgrids With Wavelet-Based Deep Neural Networks

State estimation is critical to the operation and control of modern power systems. However, many cyber-attacks, such as false data injection attacks, can circumvent conventional detection methods and interfere the normal operation of grids. While there exists research focusing on detecting such attacks in dc state estimation, attack detection in ac systems is also critical, since ac state estimation is more widely employed in power utilities. In this paper, we propose a new false data injection attack detection mechanism for ac state estimation. When malicious data are injected in the state vectors, their spatial and temporal data correlations may deviate from those in normal operating conditions. The proposed mechanism can effectively capture such inconsistency by analyzing temporally consecutive estimated system states using wavelet transform and deep neural network techniques. We assess the performance of the proposed mechanism with comprehensive case studies on IEEE 118- and 300-bus power systems. The results indicate that the mechanism can achieve a satisfactory attack detection accuracy. Furthermore, we conduct a preliminary sensitivity test on the control parameters of the proposed mechanism.

Online False Data Injection Attack Detection With Wavelet Transform and Deep Neural Networks

There are both economic and environmental urges for transition from the current outdated power grid to a sensor-embedded smart grid that monitors system stability, integrates distributed energy and schedules energy consumption for household users. Especially with the proliferation of intelligent measurement devices, exponential growth of data empowers this transition and brings new tools for the development of different applications in power system. Under this context, this paper presents a holistically overview on the state-of-the-art of big data technology in smart grid integration. First, the features of smart grid and the multisource of energy data are discussed. Then, this paper comprehensive summarizes the applications leveraged by big data in smart grid, which also contains some brand new applications with the latest big data technologies. Furthermore, some mainstream platforms and knowledge extraction techniques are looked to promote the big data insights. Finally, challenges and opportunities are pointed out in this paper as well.

Big data issues in smart grid – A review

Data analytics are now playing a more important role in the modern industrial systems. Driven by the development of information and communication technology, an information layer is now added to the conventional electricity transmission and distribution network for data collection, storage and analysis with the help of wide installation of smart meters and sensors. This paper introduces the big data analytics and corresponding applications in smart grids. The characterizations of big data, smart grids as well as huge amount of data collection are firstly discussed as a prelude to illustrating the motivation and potential advantages of implementing advanced data analytics in smart grids. Basic concepts and the procedures of the typical data analytics for general problems are also discussed. The advanced applications of different data analytics in smart grids are addressed as the main part of this paper. By dealing with huge amount of data from electricity network, meteorological information system, geographical information system etc., many benefits can be brought to the existing power system and improve the customer service as well as the social welfare in the era of big data. However, to advance the applications of the big data analytics in real smart grids, many issues such as techniques, awareness, synergies, etc., have to be overcome.

/pdf/big-data-analytics-in-smart-grids-a-review-4g4lfx70ug.pdf

Big data analytics in smart grids: a review

This paper presents a semisupervised machine learning approach based on co-training of two classifiers for fault classification in both the transmission and the distribution systems with consideration of microgrids. Unlike previous work in which only labeled data are treated using supervised machine learning approaches, this study uses a semisupervised machine learning approach to handle both labeled and unlabeled data. In order to extract the hidden features in the current and voltage waveforms, the discrete wavelet transform is applied, while the harmony search algorithm is utilized to identify the optimal parameters of the wavelets. The performance of the proposed method was examined on both transmission and distribution test systems in a simulation environment, and also using experimental hardware. The results have shown that the proposed approach provides flexibility and adaptability in dealing with various system conditions/configurations with high accuracy. The results also have demonstrated that the proposed semisupervised approach can improve the fault classification accuracy compared to that obtained using other machine learning approaches (i.e., supervised and unsupervised) in the case of utilizing unlabeled data to build and train the classifier's model.

Fault Detection and Classification Based on Co-training of Semisupervised Machine Learning

This paper presents an intelligent protection scheme for microgrid using combined wavelet transform and decision tree. The process starts at retrieving current signals at the relaying point and preprocessing through wavelet transform to derive effective features such as change in energy, entropy, and standard deviation using wavelet coefficients. Once the features are extracted against faulted and unfaulted situations for each-phase, the data set is built to train the decision tree (DT), which is validated on the unseen data set for fault detection in the microgrid. Further, the fault classification task is carried out by including the wavelet based features derived from sequence components along with the features derived from the current signals. The new data set is used to build the DT for fault detection and classification. Both the DTs are extensively tested on a large data set of 3860 samples and the test results indicate that the proposed relaying scheme can effectively protect the microgrid against faulty situations, including wide variations in operating conditions.

A Combined Wavelet and Data-Mining Based Intelligent Protection Scheme for Microgrid

This paper presents an intelligent protection scheme for microgrid using combined wavelet transform and decision tree. The process starts at retrieving current signals at the relaying point and preprocessing through wavelet transform to derive effective features such as change in energy, entropy, and standard deviation using wavelet coefficients. Once the features are extracted against faulted and unfaulted situations for each-phase,the data set is built to train the decision tree (DT), which is validated on the unseen data set for fault detection in the microgrid. Further, the fault classification task is carried out by including the wavelet based features derived from sequence components along with the features derived from the current signals. The new data set is used to build the DT for fault detection and classifi- cation. Both the DTs are extensively tested on a large data set of 3860 samples and the test results indicate that the proposed relaying scheme can effectively protect the microgrid against faulty situations, including wide variations in operating conditions.

Debi Prasad Mishra

Papers

A Combined Wavelet and Data-Mining Based Intelligent Protection Scheme for Microgrid

A Combined Wavelet and Data-Mining Based Intelligent Protection Scheme for Microgrid