Options
A Decision Support System for Photovoltaic Potential Estimation
Hopf, Konstantin; Kormann, Michael; Sodenkamp, Mariya; u. a. (2017): A Decision Support System for Photovoltaic Potential Estimation, in: IML ’17: Proceedings of the 1st International Conference on Internet of Things and Machine Learning, New York: ACM Digital Library, S. 1–10, doi: 10.1145/3109761.3109764.
Faculty/Chair:
Title of the compilation:
IML '17: Proceedings of the 1st International Conference on Internet of Things and Machine Learning
Conference:
IML 2017: International Conference on Internet of Things and Machine Learning, October 17 - 18, 2017 ; Liverpool
Publisher Information:
Year of publication:
2017
Issue:
Article No.: 3
Pages:
ISBN:
978-1-4503-5243-7
Language:
English
Abstract:
With knowledge on the photovoltaic potential of individual residential buildings, solar companies, energy service providers and electric utilities can identify suitable customers for new PV installations and directly address them in renewable energy rollout and maintenance campaigns. However, many currently used solutions for the simulation of energy generation require detailed information about houses (roof tilt, shading, etc.) that is usually not available at scale. On the other hand, the methodologies enabling extraction of such details require costly remote-sensing data from three-dimensional (3D) laser scanners or aerial images. To bridge this gap, we present a decision support system (DSS) that estimates the potential amount of electric energy that could be generated at a given location if a photovoltaic system would be installed. The DSS automatically generates insights about photovoltaic yields of individual roofs by analyzing freely available data sources, including the crowdsourced volunteered geospatial information systems OpenStreetMap and climate databases. The resulting estimates pose a valuable foundation for selecting the most prospective households (e.g., for personal visit and screening by an expert) and targeted solar panel kit offerings, ultimately leading to significant reduction of manual human efforts, and to cost-effective personalized renewables adoption.
GND Keywords: ; ;
Entscheidungsunterstützungssystem
Fotovoltaikanlage
Raumdaten
Keywords: ; ; ; ;
Crowdsourced Data
Solar Potential
Volunteered Geographic Information
Renewable Energy
Photovoltaic
DDC Classification:
RVK Classification:
Type:
Conferenceobject
Activation date:
September 28, 2018
Versioning
Question on publication
Permalink
https://fis.uni-bamberg.de/handle/uniba/43113