Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/76149
Title: Urban data analytics for better power grid management
Authors: Neo, Shannon Si Lin
Keywords: DRNTU::Engineering::Computer science and engineering
Issue Date: 2018
Abstract: Technology advancement has allowed efficient and highly accurate collection of data generated by human activity in space and time. The large amount of data often also known as big data, is essential for uncovering new insights to enable better decision making. Harnessing these human activity data, namely electricity demand and consumption, is greatly beneficial to many societal applications such as urban planning through more effective power grid management. This project will be conducted on a relevant geographical area, Trentino region in Italy, where there is access to their open big data resources. The utilization of a real dataset which contains nearly 1 million rows of electricity consumption records is adaptive to its local electricity demand and provides a more accurate and localized electricity consumption prediction result. The study proposes using a deep learning model, which is a special type of Recurrent Neural Network (RNN), known as Long Short-Term memory (LSTM). The LSTM model is particularly useful for time series datasets and has demonstrate high performance in prediction accuracy.
URI: http://hdl.handle.net/10356/76149
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
ShannonNeo_FYP.pdf
  Restricted Access
1.29 MBAdobe PDFView/Open

Page view(s) 50

77
checked on Oct 24, 2020

Download(s) 50

6
checked on Oct 24, 2020

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.