Eco-Bot aims to utilize recent advances in chatbot tools and advanced signal processing (i.e. energy disaggregation) using low-resolution smart meter-type data with the goal of changing their behaviour towards energy efficiency. Eco-Bot targets to a personalized virtual energy assistant to deliver information on itemized (appliance-level) energy usage through a chat-bot tool.
The "chat-bot" functionality will use an attractive frontend interface, permitting seamless communication in a more natural and interactive way than a traditional mobile application. This way, Eco-Bot aims to achieve a higher level of engagement with consumers than previous efforts (i.e. serious games, gamification, competitions or other interactive ICT), by adding a more engaging form of interaction with existing platforms that has been proven in different market settings.
The proposed system considers knowledge of the delivered multi-factorial models, including rebound-effects, as a result of the baseline research on both European and International activities. Then, based on advanced ICT, such as knowledge engineering, machine learning, expert systems, the project transforms the multi-factorial models for energy reduction to interactive, personalized and targeted recommendations to consumers on how to save energy.
Eco-Bot uses also existing NILM, e.g. energy disaggregation methods, and data analytics to break down consumption to the appliance level, where this is possible (smart meters at reasonable granularity, adequate number of information collected) so as to make consumers aware of their most energy-consuming devices.
The project will demonstrate the system in three different use cases, each one representing a different business model (B2B / B2B2C /B2C). We aim to validate our system across real and diverse conditions such as socio-cultural, environmental, demographic, climate and consumption, so as to draw concrete conclusions regarding performance, effectiveness, affordability, etc.
The main objectives of the project are as follows:
a) Collect and analyse energy efficiency models and classify them with respect to core factors (including social, demographic, gender, cultural, occupation, etc.), thus creating a taxonomy of the energy efficiency models.
b) Design optimal personalized engagement strategies based on market segmentation along consumer needs and “classes” (so called taxonomies in the proposal) of the energy efficiency models, focusing, for example, on target groups such as early adopters of technology, use of mobile, and high potential for making impactful behavioral changes and investments.
c) Deploy, configure and promote an appropriate low-cost ICT platform including (i) integration with existing platforms, such as the interactive Energy Savings Account and Energy Check App (SEC), Energy Management Systems (EMS), Forecast, energy disaggregation and personalised recommendations , (ii) the chat-bot tool (BOT) and (iii) interfaces with social media that will further support and widen the user engagement.
d) Adopt energy disaggregation algorithms for itemized billing.
e) Demonstrate and validate the Eco-Bot concept by monitoring the increase in energy efficiency for targeted advices, on the basis of user feedback and providing of itemized billing.
f) Identify and improve awareness of the potential impacts of energy efficiency and develop understanding of the economic and social benefits and ways in which these can be realistically achieved, including the ways different stakeholders influence sustainability and take up.
g) Articulate communication and consultation with EU and international organisations in order to gain common understanding and establish mutual support. Create a channel of communication with the EU Member States Expert Groups in order to foster consultations on future policy dialogues and mutual learning exercises and studies, including design studies for new policies for improved energy efficiency.
