Periodic Reporting for period 3 - Eco-Bot (Personalised ICT-tools for the Active Engagement of Consumers Towards Sustainable Energy)
Okres sprawozdawczy: 2020-04-01 do 2021-06-30
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.
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.
The main achievements of Eco-Bot so far include the following:
- Completion of WP2, which involved setting up of the use cases, state of the art review of taxonomies of energy efficiency models, definition of taxonomies and mapping to consumers’ needs.
- Completion of WP3, which involved online consumers surveys, the development of the behavioural model and the definition of metrics for system and user engagement validation.
- Two milestones achieved in WP4: a) the first integrated version of the Eco-Bot system ready for the small-scale demonstration, and b) the first Eco-Bot version ready for the WP5 large scale demonstration and validation activities.
- Preparatory work in WP5 for the launch of the large scale demonstration and validation activities has been completed.
- Under WP6, the dissemination and communication strategy has been defined, project dissemination material has been produced, and several dissemination and liaison activities have already taken place by the consortium.
- Under WP7, the exploitation plan has been elaborated, including Eco-Bot’s Key Exploitable Results (KER), the related risks, IP, and Business Models.
- Completion of WP2, which involved setting up of the use cases, state of the art review of taxonomies of energy efficiency models, definition of taxonomies and mapping to consumers’ needs.
- Completion of WP3, which involved online consumers surveys, the development of the behavioural model and the definition of metrics for system and user engagement validation.
- Two milestones achieved in WP4: a) the first integrated version of the Eco-Bot system ready for the small-scale demonstration, and b) the first Eco-Bot version ready for the WP5 large scale demonstration and validation activities.
- Preparatory work in WP5 for the launch of the large scale demonstration and validation activities has been completed.
- Under WP6, the dissemination and communication strategy has been defined, project dissemination material has been produced, and several dissemination and liaison activities have already taken place by the consortium.
- Under WP7, the exploitation plan has been elaborated, including Eco-Bot’s Key Exploitable Results (KER), the related risks, IP, and Business Models.
Eco-Bot goes beyond the state of the art in the baseline models of energy efficiency by defining a taxonomy of energy efficiency models spanned across various factors, covering multi-pillar sectors and consumers of different properties and characteristics. A proper market segmentation based on the consumers’ needs with regard to energy savings has also been performed, and the consumers’ segments have been mapped to the different classes of the taxonomy.
Building on existing socio-economic energy-related consumption models and behavioural models, Eco-Bot introduces a multi-factorial user behaviour modelling framework that takes into consideration several socio-cultural, economic, demographic settings that affect energy efficiency. This baseline information has been used to create the knowledge base of the Eco-Bot expert system, allowing the provision of personalized advice across energy consumers of different types.
Eco-Bot constitutes an innovative combination of a knowledge-based expert system with chatbot and energy disaggregation technologies towards personalised energy efficiency recommendations for consumers and facility managers. Chatbots have not yet been explored in the area of energy efficient behaviour change, thus Eco-Bot is expected to have a major impact in the field as an innovative tool that can appropriately target and actively engage consumers of different types and promote behaviour change towards energy efficiency. Moreover, providing the consumers with energy consumption information on an appliance level through the use of NILM, is expected not only to enhance personalization and user engagement, but also to further contribute to energy savings and towards more energy efficient behaviours.
Building on existing socio-economic energy-related consumption models and behavioural models, Eco-Bot introduces a multi-factorial user behaviour modelling framework that takes into consideration several socio-cultural, economic, demographic settings that affect energy efficiency. This baseline information has been used to create the knowledge base of the Eco-Bot expert system, allowing the provision of personalized advice across energy consumers of different types.
Eco-Bot constitutes an innovative combination of a knowledge-based expert system with chatbot and energy disaggregation technologies towards personalised energy efficiency recommendations for consumers and facility managers. Chatbots have not yet been explored in the area of energy efficient behaviour change, thus Eco-Bot is expected to have a major impact in the field as an innovative tool that can appropriately target and actively engage consumers of different types and promote behaviour change towards energy efficiency. Moreover, providing the consumers with energy consumption information on an appliance level through the use of NILM, is expected not only to enhance personalization and user engagement, but also to further contribute to energy savings and towards more energy efficient behaviours.