Kategorisering av fjärrvärmekunder utifrån användarmönster
(2013) In LUTMDN/TMHP--13/5281--SEDepartment of Energy Sciences
- Abstract
- The possibility to analyze district heating customers has increased in recent times. This is mainly because of the fact that hourly measured values for each customer now are available for the energy companies. This master thesis aims to categorize Lunds Energi’s district heat customers according to their consumption patterns. The result should be presented in such a way that all the categories could be easily recognized and also contribute to further dynamic network analysis.
The result is accessible in the form of 48 different customer categories, each more or less with unique characteristics. In addition, all the categories are further arranged into four seasons, each including twelve categories. This arrangement is primarily done due... (More) - The possibility to analyze district heating customers has increased in recent times. This is mainly because of the fact that hourly measured values for each customer now are available for the energy companies. This master thesis aims to categorize Lunds Energi’s district heat customers according to their consumption patterns. The result should be presented in such a way that all the categories could be easily recognized and also contribute to further dynamic network analysis.
The result is accessible in the form of 48 different customer categories, each more or less with unique characteristics. In addition, all the categories are further arranged into four seasons, each including twelve categories. This arrangement is primarily done due to the fact that the heat consumption varies over the seasons of the year. The outdoor temperature and the diversity of the customer’s behavior are other factors that affect the heat consumption greatly. A few methods for categorizing the customers are evaluated and an artificial neural network-method called self-organizing maps is chosen to identify customers with similar consumption patterns and place them in the same category. Due to the fact that customers during the winter season consume more heat related to physical needs and have more continuous heat consumption, the categories found within this season are more accurate than the ones during the summer. With the information gained from the presented categories, small houses clearly stands out as the one type of customer that varies most when it comes to consumption patterns. Customer types like apartment blocks, public administrations and offices fit in to fewer categories in general. All the results are made available for Lunds Energi by a Microsoft Excel file containing data useful for further network analysis. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/3994147
- author
- Nilsson, Christoffer and Tengqvist, Henrik
- supervisor
- organization
- year
- 2013
- type
- H1 - Master's Degree (One Year)
- subject
- keywords
- district heating, self-organizing maps, consumption pattern, heat consumption, categorization
- publication/series
- LUTMDN/TMHP--13/5281--SE
- report number
- 5281
- ISSN
- 0282-1990
- language
- Swedish
- id
- 3994147
- date added to LUP
- 2013-08-22 10:06:40
- date last changed
- 2013-08-22 10:06:40
@misc{3994147,
abstract = {{The possibility to analyze district heating customers has increased in recent times. This is mainly because of the fact that hourly measured values for each customer now are available for the energy companies. This master thesis aims to categorize Lunds Energi’s district heat customers according to their consumption patterns. The result should be presented in such a way that all the categories could be easily recognized and also contribute to further dynamic network analysis.
The result is accessible in the form of 48 different customer categories, each more or less with unique characteristics. In addition, all the categories are further arranged into four seasons, each including twelve categories. This arrangement is primarily done due to the fact that the heat consumption varies over the seasons of the year. The outdoor temperature and the diversity of the customer’s behavior are other factors that affect the heat consumption greatly. A few methods for categorizing the customers are evaluated and an artificial neural network-method called self-organizing maps is chosen to identify customers with similar consumption patterns and place them in the same category. Due to the fact that customers during the winter season consume more heat related to physical needs and have more continuous heat consumption, the categories found within this season are more accurate than the ones during the summer. With the information gained from the presented categories, small houses clearly stands out as the one type of customer that varies most when it comes to consumption patterns. Customer types like apartment blocks, public administrations and offices fit in to fewer categories in general. All the results are made available for Lunds Energi by a Microsoft Excel file containing data useful for further network analysis.}},
author = {{Nilsson, Christoffer and Tengqvist, Henrik}},
issn = {{0282-1990}},
language = {{swe}},
note = {{Student Paper}},
series = {{LUTMDN/TMHP--13/5281--SE}},
title = {{Kategorisering av fjärrvärmekunder utifrån användarmönster}},
year = {{2013}},
}