Javascript must be enabled for the correct page display

Prediction of Energy Consumption Using Historical Data and Twitter

Stavast, P. (2014) Prediction of Energy Consumption Using Historical Data and Twitter. Master's Thesis / Essay, Computing Science.

thesis.pdf - Published Version

Download (1MB) | Preview
[img] Text
akkoord_StavastP.pdf - Other
Restricted to Registered users only

Download (23kB)


One of the visions for the smart grid is the creation of a dynamic energy market with multiple active buyers and sellers of energy. Renewables will be more widespread and generated energy may be traded in small to large energy markets. This entails a systems that rely on the buying and selling of energy at the right time in any amount. These systems benefit from having accurate predictions of future energy use. This thesis proposes a system that uses historical data to predict electrical load on the network using several machine learning algorithms: Decision tree learning, Artificial Neural Networks and Support Vector Machines. An attempt to predict energy usage by mining social media is explored and is shown to be unreliable. The results of the application are made available by a web service that provides data in JSON or XML format.

Item Type: Thesis (Master's Thesis / Essay)
Degree programme: Computing Science
Thesis type: Master's Thesis / Essay
Language: English
Date Deposited: 15 Feb 2018 07:56
Last Modified: 15 Feb 2018 07:56

Actions (login required)

View Item View Item