The NATCONSUMERS project aims to address the EU need in the Europe 2020 strategy for reduction of the primary energy use by 20% by 2020, as well as the 20% of greenhouse emission, by proposing integral measures and activities that promote energy saving in domestic area.

The main problem that NATCONSUMERS solves and this makes it be better than other projects in the energy efficiency area, is the obstacle for the uptake of energy efficiency products and measures by consumers. Until now, several actions have been implemented toward the reduction of energy consumption but these tend to ignore the different factors affecting user behavior and demographic characteristic of the target group and do not consider any inbuilt bias in the selection. Thus, many of them fail due to low user engagement and participation.

Finally, the new knowledge (results) that the NATCONSUMERS generates focuses on the complete characterization of household consumers’ profiles, including people behavior, attitudes, and energy consumption habits. NATCONSUMERS develops user’s feedback methodologies that lead to the engagement of people in more efficient energy use practices as a basis for a large-scale EU demonstration of feedback methodologies for sustainability residential use of electricity.


The NATCONSUMERS offers to Stakeholder Group (market players, technological partners, consumer organisations, energy consultancies, policy makers, and research community) a methodological framework which they may adopt to their consumers, and help the consumers with tailored advices in Natural Language to reduce energy usage.
In this respect, NATCONSUMERS provides to the project Stakeholder Group both the Handbook for the implementation of the proposed methodology, and the corresponding web tool to validate it.


NATCONSUMERS offers a Handbook which obtains provides to project Stakeholder Group a methodological Framework to address their residential consumers and offers them tailored advice how reduce the energy consumption, through the use of Natural Language.

The Handbook describes:

  • What information to collect
  • How to collect it
  • Other relevant factors to be aware of that affect a home’s energy use at a wider level.

In order to build this Handbook, the NATCONSUMERS consortium undertook a review of evidence of the latest research into what factors shape a consumers’ relationship with energy use at home. The review looked factors at three levels:

  1. Wider context factors – such as how the energy system is organised within a particular state or region
  2. Individual context factors – such as the type of building a consumer lives in and how they are influenced by peers they live among
  3. Psychological and knowledge factors – including consumer attitudes and values.

How it works?

The essential of the Handbook is to provide project Stakeholder Group a methodological Framework to give tailored advice to their consumers about their energy usage. In order to send tailored messages, multiple segmentations based on load profiles (from smart meters) and attitudinal surveys are made. Based on user load profiles we search for typical load curves, which could distinguish different types of user profiles. In order to compare the household’s energy consumption to benchmarks we segment the volume of consumption by demographics with various statistical models. The result of load profile and demographic segmentation defines the content of the message. We are convinced that communication efficiency depends not only on the content of the message (“What”), but is also very much influenced by the messaging style and argumentation (“How”). Therefore, different segmentations are needed, including load profile classification and segmentation based on demographics, as well as segmentation based on social values and attitudes.

Example: If a household is over consuming energy during weekday evenings, we want to send a message to encourage them to decrease the consumption. If we know that household members are interested in energy savings, and are rather characterized by individual / materialistic values, the message should focus on the potential savings by shifting the consumption to off‐peak period. However, if we know that the household members are not interested in energy savings, and are characterized by collective / ecological values, the message should focus on collective benefits of energy saving.


NATCONSUMERS Web Tool main purpose is to validate the methodology of the Natural Language messages generation. It will also be used to present it to the Project Stakeholders; this will allow receiving specific feedback of the future potential of the project results.

The Web Tool is used to validate the NATCONSUMERS service developed during the project, from the collection of the information, until the generation of the Natural Language message. By performing step by step the same tasks that are defined in the Handbook it will help to understand the logic of NATCONSUMERS process.

The next graph shows the workflow of the Tool, with the steps that are performed in it:


The operation of the Tool is designed to simulate how a user operation to obtain natural language messages by uploading his smart meter data. The first step of the user is to Sing up in the tool, accept the privacy terms and fill up a questionnaire. This questionnaire will include:

  • Attitudinal questions, to obtain the altitudinal profile of the user
  • Demographic questions, to obtain the classification of the user

The questionnaire is intended to be fulfilled only once, or when some of the parameters change.

After it is completed the user may upload the smart meter data. The tool is going to accept by default a specific format for the smart data, but there will be available converters, as the data format is not a standard.

After the uploading of the smart meter data the processes described in the Handbook starts, the first step is to determine the load profile or cluster of the user. During the project, we have identified different load profiles from five countries (UK, IR, IT, HU, DK), if the user is not from any of these countries the tool will automatically select the more similar one and is going to identify the user with one of load profiles.

The tool is going to calculate the indicators in the next step. Indicators are parameters that are going to be used in a later stage to generate the Natural Language message. At this moment, the indicators are not defined completely but can be for example, the daily consumption, the monthly consumption or the consumption in the peak hours.

At this stage, we have some information about the user that is going to be used to generate the message.

  • Attitudinal classification from the questionnaire
  • Load profile from the smart meter data
  • Indicators from the smart meter data

The information above is used to generate the message using Natural Language generation technics. Then the message will be reported to user in the same Web Tool.


The above picture shows an example of a possible message generated by the Tool.

Other options of generation will be also possible like for example generating multiple messages from one unique smart meter data upload.


Download the exploitation plan to read about the usage of project results by the project consortium members 


About Post Author