Mariya Sodenkamp
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mariya Sodenkamp has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Thorsten Staake
Chair of Information Systems and Energy Efficient Systems, University of Bamberg, Bamberg, Germany and Chair of Information Management, ETH Zurich, Zurich, Switzerland
4 shared publications - Konstantin Hopf
University of Bamberg
3 shared publications - Debora Di Caprio
Department of Economics and Management, University of Trento, Trento, Italy
1 shared publication - Ilya Kozlovkiy
University of Bamberg
1 shared publication Ilya Kozlovskiy
Energy Efficient Systems Group, University of Bamberg, Bamberg, Germany
1 shared publication- Jürgen Wenig
University of Bamberg
1 shared publication
Latest Publications
- Open Access
- 1 October 2018
- Published by Elsevier in Applied Soft Computing
- Vol. 71, 715-727
An aggregation method for solving group multi-criteria decision-making problems with single-valued neutrosophic sets
- 1 October 2018
- Published by Elsevier in Applied Soft Computing
- Vol. 71, 715-727
Open AccessAn aggregation method for solving group multi-criteria decision-making problems with single-valued neutrosophic sets
- Open Access
- 14 September 2018
- Published by MDPI AG in Applied Sciences
- Vol. 8 (9) , 1654
Revealing Household Characteristics from Electricity Meter Data with Grade Analysis and Machine Learning Algorithms
In this article, the Grade Correspondence Analysis (GCA) with posterior clustering and visualization is introduced and applied to extract important features to reveal households’ characteristics based on electricity usage data. The main goal of the analysis is to automatically extract, in a non-intrusive way, number of socio-economic household properties including family type, age of inhabitants, employment type, house type, and number of bedrooms. The knowledge of specific properties enables energy utilities to develop targeted energy conservation tariffs and to assure balanced operation management. In particular, classification of the households based on the electricity usage delivers value added information to allow accurate demand planning with the goal to enhance the overall efficiency of the network. The approach was evaluated by analyzing smart meter data collected from 4182 households in Ireland over a period of 1.5 years. The analysis outcome shows that revealing characteristics from smart meter data is feasible, and the proposed machine learning methods were yielding for an accuracy of approx. 90% and Area Under Receiver Operating Curve (AUC) of 0.82.
- 14 September 2018
- Published by MDPI AG in Applied Sciences
- Vol. 8 (9) , 1654
Open AccessRevealing Household Characteristics from Electricity Meter Data with Grade Analysis and Machine Learning Algorithms
In this article, the Grade Correspondence Analysis (GCA) with posterior clustering and visualization is introduced and applied to extract important features to reveal households’ characteristics based on electricity usage data. The main goal of the analysis is to automatically extract, in a non-intrusive way, number of socio-economic household properties including family type, age of inhabitants, employment type, house type, and number of bedrooms. The knowledge of specific properties enables energy utilities to develop targeted energy conservation tariffs and to assure balanced operation management. In particular, classification of the households based on the electricity usage delivers value added information to allow accurate demand planning with the goal to enhance the overall efficiency of the network. The approach was evaluated by analyzing smart meter data collected from 4182 households in Ireland over a period of 1.5 years. The analysis outcome shows that revealing characteristics from smart meter data is feasible, and the proposed machine learning methods were yielding for an accuracy of approx. 90% and Area Under Receiver Operating Curve (AUC) of 0.82.
- Open Access
- 1 January 2018
- Published by Universitatsbibliothek Bamberg
Predictive Customer Data Analytics : The Value of Public Statistical Data and the Geographic Model Transferability
Companies pay high prices for detailed customer information (e.g., income, household type) for gaining insights and conducting targeted marketing campaigns. We argue that companies can utilize predictive analytics artifacts to derive such information from existing customer data in combination with freely available data sources, such as open government data. In this study, we use a machine learning artifact for a specific yet highly relevant case from the utility industry, trained on data of 7,504 energy customers and investigate two important aspects for predictive business analytics: First, we identified the sparsely available open government statistics and found that even that limited amount of open data can increase our artifact's performance. Second, we applied the predictive models, trained with a regional customer dataset, on households in other geographic regions with acceptable performance loss. The results support the development of systems aiding managerial decision-making, predictive marketing and showcase the value of open data.
- 1 January 2018
- Published by Universitatsbibliothek Bamberg
Open AccessPredictive Customer Data Analytics : The Value of Public Statistical Data and the Geographic Model Transferability
Companies pay high prices for detailed customer information (e.g., income, household type) for gaining insights and conducting targeted marketing campaigns. We argue that companies can utilize predictive analytics artifacts to derive such information from existing customer data in combination with freely available data sources, such as open government data. In this study, we use a machine learning artifact for a specific yet highly relevant case from the utility industry, trained on data of 7,504 energy customers and investigate two important aspects for predictive business analytics: First, we identified the sparsely available open government statistics and found that even that limited amount of open data can increase our artifact's performance. Second, we applied the predictive models, trained with a regional customer dataset, on households in other geographic regions with acceptable performance loss. The results support the development of systems aiding managerial decision-making, predictive marketing and showcase the value of open data.
- Open Access
- 1 January 2018
- Published by Universitatsbibliothek Bamberg
A Decision Support System for Photovoltaic Potential Estimation
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.
- 1 January 2018
- Published by Universitatsbibliothek Bamberg
Open AccessA Decision Support System for Photovoltaic Potential Estimation
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.
- Open Access
- 27 January 2016
- Published by Springer Nature in Decision Analytics
- Vol. 3 (1) , 1-22
Supervised classification with interdependent variables to support targeted energy efficiency measures in the residential sector
- 27 January 2016
- Published by Springer Nature in Decision Analytics
- Vol. 3 (1) , 1-22
Open AccessSupervised classification with interdependent variables to support targeted energy efficiency measures in the residential sector
- 1 January 2015
- Published by Springer Nature
- p. 115-126
Data-Based Assessment of Plug-in Electric Vehicle Driving
- 1 January 2015
- Published by Springer Nature
- p. 115-126
Data-Based Assessment of Plug-in Electric Vehicle Driving
- 26 November 2014
- Published by Springer Nature in Computer Science - Research and Development
- Vol. 31 (3) , 141-148
Feature extraction and filtering for household classification based on smart electricity meter data
- 26 November 2014
- Published by Springer Nature in Computer Science - Research and Development
- Vol. 31 (3) , 141-148
Feature extraction and filtering for household classification based on smart electricity meter data
- 1 January 2014
- Published by IGI Global Scientific Publishing
- p. 108-138
A Multi-Criteria Vendor Selection and Order Allocation GDSS using a Mixed Alternative and Value Focused Thinking Approach
A Multi-Criteria Vendor Selection and Order Allocation GDSS using a Mixed Alternative and Value Focused Thinking Approach: 10.4018/978-1-4666-5958-2.ch007: Vendor selection and order quantity assignment plays a central role in the purchasing activity of manufacturing and trading companies. Evaluation of product
- 1 January 2014
- Published by IGI Global Scientific Publishing
- p. 108-138
A Multi-Criteria Vendor Selection and Order Allocation GDSS using a Mixed Alternative and Value Focused Thinking Approach
A Multi-Criteria Vendor Selection and Order Allocation GDSS using a Mixed Alternative and Value Focused Thinking Approach: 10.4018/978-1-4666-5958-2.ch007: Vendor selection and order quantity assignment plays a central role in the purchasing activity of manufacturing and trading companies. Evaluation of product