Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Faculty of Engineering | en_US |
| dc.contributor.advisor | Chan, Kevin K. W. (EE) | - |
| dc.creator | Hu, Yifei | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/8509 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | Big data and advanced analysis for smart grid applications | en_US |
| dcterms.abstract | As modern electric power systems are combining with Information Communication Technology (ICT), big data technology would become an essential tool for power system operation and monitoring, especially for large and complicated system. Although many big data technologies have been applied in other industries in recent years, their practicality is often limited in electrical utilities since real time processing and advanced analysis are still a challenge in power systems. Therefore, it is imperative for big data and advanced analysis in smart grid applications. This thesis strives to review and investigate the application of big data technologies and its effective data analysis methods in three power system problems. Transient information files are always difficult to store in traditional relational database due to its limitation of data size and format. In this thesis, adopted a distributed collection and storage system based on Hadoop Distributed File System (HDFS) and other Hadoop technologies is therefore designed. HDFS is responsible for the collection and storage of large dataset in smart grid applications, and it supports the integration of high efficient Hbase data management and Hive retrieval technology in the proposed system. Furthermore, a small file storage solution is proposed to avoiding the production of lots of Mappers, and hence lead to a high efficient processing speed. In the evaluation of I/O performance on different cases, it has been revealed that the transmission rate of HDFS is higher for large dataset as compared to scp and the overall performance of transmission rate can be improved with the increased number of DataNodes. Also, the downloading speed is faster than uploading speed. | en_US |
| dcterms.abstract | With increasingly deployment of sensors in power system equipment, a large amount of information will be produced in timely, such abundant historical data are useful for fault diagnosing of power equipment, such as transformer. This thesis proposes a parallel K-means algorithm using the MapReduce model to classify transformer fault with large set of historical Dissolved Gas Analysis (DGA) data samples. This algorithm is performed on a 4-nodes Hadoop cluster to evaluate its performance with limited training DGA samples. The result shows a good performance for transformer fault diagnosing. In addition, cases with different number of nodes and datasets are studied and compared to evaluate the speedup, scaleup and sizeup performance, and a relatively good performance is found in all these aspects. Mathematically, state estimation is a complicated nonlinear estimation problem with high dimensionality, which has requirements of highly accuracy, robust and real time. In this thesis, a review on traditional state estimation method is conducted, and a comparison study on five different cases in a 7-bus system is made using a traditional Weighted Least Squares (WLS) estimator. The results show that, high penetration of PMUs would greatly improve the performance of power system state estimation (PSSE). Moreover, a theoretical study on novel big data-driven method has also been made for processing large and complicated PSSE. The proposed estimation approach is based on the idea that the close-by states usually indicate similar measurements in power system with the same topology. While the proposed MapReduce k-nearest-neighbors (MRKNNs) is responsible for data preprocessing and bagging, the support vector regression (SVR) algorithm is used for the state estimation. | en_US |
| dcterms.extent | xii, 85 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2016 | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.LCSH | Smart power grids. | en_US |
| dcterms.LCSH | Big data. | en_US |
| dcterms.LCSH | Electric power distribution. | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b28945669.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 2.22 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/8509