Loading...

A Data Mining Approach to Efficiently Improve Data Analysis in Energy Management Systems

Joshaghani, Mohammad | 2018

409 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 51129 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Bagheri Shouraki, Saeed
  7. Abstract:
  8. In Energy Management Systems, data analysis is done based on the information gathered from the electricity utility. The closer the information is to its real value, the better the data analysis in EMS becomes. Hence, improving the accuracy of the collected information leads to an improvement in data analysis in EMS. The information collected from the network consists of the measured values of voltage phasor at each bus, the generation or load power at each bus, and the power flow in branches. Since the total number of sensors are usually less than the total network’s parameters, it is not possible to precisely determine the values of Network’s parameters, and only an estimation of them can be provided. The act of estimating these parameters is called State Estimation. In this research, by taking advantage of supervised learning methods, which performs the learning act based on the historical data of the Network, a database consists of the past measurement values and related states, the relationship between the current measurements and the corresponding state is figured and its accuracy is evaluated. The effectiveness of the utilized algorithms is then compared with WLS method, a primitive method in state estimation. Providing comprehensive results of the investigated algorithms, the simulation of the algorithms is performed on a variety of IEEE standard networks. The result of the simulations is provided in the report
  9. Keywords:
  10. State Estimation ; Data Mining ; Data Analysis ; Supervised Learning ; Energy Management

 Digital Object List

 Bookmark

No TOC