Use Case 3: Investigate the role of big data in assessing the impact of behavioural insights in energy consumption
Rationale
With the increasing penetration of sensing and measurement technology, communication network technology, as well as cloud computing and big data storage and analytics, traditional energy systems are being digitized. Large amounts of energy production and consumption data are generated, collected and stored. This provides the possibility to implement energy big data mining and analysis. A set of socioeconomic, demographic and the real time energy consumption data can been combined to assess the impact of behavioral insights on energy consumption patterns. This high level of understanding of energy usage provides knowledge of good and secure investments for bridging the energy efficiency gap and means for verification of investment results. For the third use case we will make use of the following methods:
Machine learning models
For the estimation of the buildings’ energy consumption, ML models such as support vector machines (SVM) and random forests (RF) will be trained and evaluated upon a set of socioeconomic, demographic, and behavioral variables.
Econometric software
Econometric software such as STATA and programming languages for data science like python and R will be used for the analysis of the data.
Analysis of heterogeneous data
Machine learning approaches will be used to create models of the relationship between inputs and outputs. Other validation methods will be employed to select the models’ complexity and to provide valid confidence levels.
Goal setting interfaces
Interfaces based on users’ desire of fulfilling a given objective, either induced by the interface or self imposed by home inhabitants.
Direct feedback
Timely updated in home displays (IHDs) showing the home current energy consumption.
Timely updated in home displays (IHDs) showing the home current energy consumption.
Showing how home consumption evolves over time and highlighting temporal correlations.
Rationale
Goal setting interfaces
Interfaces based on users’ desire of fulfilling a given objective, either induced by the interface or self imposed by home inhabitants.
Direct feedback
Timely updated in home displays (IHDs) showing the home current energy consumption.
Timely updated in home displays (IHDs) showing the home current energy consumption.
Showing how home consumption evolves over time and highlighting temporal correlations.
With the increasing penetration of sensing and measurement technology, communication network technology, as well as cloud computing and big data storage and analytics, traditional energy systems are being digitized. Large amounts of energy production and consumption data are generated, collected and stored. This provides the possibility to implement energy big data mining and analysis. The energy consumption behavior of households can be described in three dimensions, namely time dimension, user dimension and spatial dimension and the existence of real time individual data provide an opportunity of robust analysis. A set of socioeconomic, demographic and the real time energy consumption data can been combined to assess the impact of behavioral insights on energy consumption pat terns. This high level of understanding of current energy usage situation provide knowledge of good and secure investments for bridging the energy efficiency gap and means for verification of expected results of investments. For the third use case we will make use of the following methods:
Machine learning models
For the estimation of the building energy consumption, ML models such as support vector machines (SVM) and random forests (RF) will be trained and evaluated upon a set of socioeconomic, demographic, and behavioral variables.
Econometric software
Econometric software such as STATA and programming languages for data science like python and R will be leveraged for the analysis of the data.
Analysis of heterogeneous data
Regarding the estimation of heterogeneity in treatment effects, ML approaches based on regression trees, RF, LASSO and SVMs will be used to create models of the relationship between attributes and outcomes. Validation methods such as cross-validation will be used to select the optimal level of the models’ complexity and enable the construction of models that provide valid confidence intervals for treatment effects.
Research Questions
Design & Impact
Real time energy consumption data will be collected in the apartment buildings as well as the adjacent EV chargers. Socioeconomic and demographic variables will be collected through public census data and a survey will estimate the existence of specific behavioral biases regarding energy consumption. The goal is to estimate consumer propensities, by using modeling tools over the set of socioeconomic, demographic, and behavioral variables. Statistical results will show whether housing type, number of inhabitants, age, and user behavior are strong characteristics for choosing energy efficient appliances. Based on these project’s results, policy measures will be suggested to increase energy efficiency and information campaigns will be held by targeting key demographics.
Key Performance Indicators
Design & Impact
Real time energy consumption data will be collected at a disaggregated level in the apartment buildings as well as the adjacent EV chargers. Socioeconomic and demographic variables will be collected through public census data and a survey will estimate the existence of specific behavioral biases regarding energy consumption. The goal is to estimate consumer propensities, by using a logistic regression model over the set of socioeconomic, demographic, and behavioral variables. Statistical results will show whether housing type, number of inhabitants, age, and end use behavior are strong predictors for choosing energy efficient appliances and building energy retrofit investments. Based on project s results policy measures will be suggested for increasing energy efficiency designing improved information campaigns by targeting key demographics.
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No