Disaggregation of energy demand profiles with GeoAI methods based on sparse Smart Meter data, Socio-demographic data and mobile phone data

 Suggested by: Johannes Scholz 

Keywords: GeoAI, Energy Demand Disaggregation, Smart Meter Data, Socio-Demographic Data, Mobile Phone Data, Machine Learning, Spatial Data Analysis, Electricity Consumption Modeling 

 

Objective: Develop a methodology for disaggregating electricity demand profiles from local supply transformers to individual households using GeoAI methods. The approach will leverage sparse Smart Meter data, socio-demographic information, and mobile phone data to enhance estimation accuracy. 

 

Short Description: This thesis focuses on using GeoAI techniques to refine the disaggregation of energy demand profiles at a granular level. By integrating Smart Meter readings with socio-demographic and mobile phone data, the research aims to model electricity consumption patterns with high spatial accuracy. The study will develop and validate machine learning-based methodologies to infer household-level demand from aggregated transformer-level data, enabling better grid management and energy planning. 

 

Start: 

As soon as possible 

 

Prerequisites/qualification: 

• Knowledge in GIS and spatial data processing 

• Interest/Knowledge in GeoAI