IoT-enabled Real-time Energy Analytics Platform (i-REAP) for commercial buildings
Summary and project details on I-REAP.
i-REAP will develop a one-step solution to measure, predict and optimize energy consumption in commercial buildings utilising the latest in Artificial Intelligence (AI) and Internet-of-Things (IoT) based hardware, to develop a complete “whole building approach” to driving down costs of improving thermal efficiency in existing buildings.
It will develop an affordable solution that will provide a personalised and optimal energy consumption regime. It will contribute to fast-forwarding the adoption of AI and IoT for energy savings and help the Building Sector to move from ‘reactive’ approaches to ‘predictive’ ones developing guidelines for ideal retrofitting actions and low carbon heating.
Department for Business, Energy and Industrial Strategy (DBEIS)
- Teropta Ltd
- Costain Ltd
The adoption of thermal efficiency measures has been slow, and the use of low carbon measures for existing buildings accounts for only 1.6% of all the heat used in buildings (UK’s Committee on Climate Change 2016). Main barriers are the lack of awareness of the benefits and financial constraints. This project will develop a whole building approach to drive down costs of improving thermal efficiency in existing buildings. It will produce an affordable solution to provide a personalised and optimal energy consumption regime. It will contribute to fast-forward the adoption of Artificial Intelligence (AI) and Internet-of-Things (IoT) solutions for energy savings and help the sector to move from ‘reactive’ approaches to ‘predictive’ ones.
An IoT-enabled Real-time Energy Analytics Platform (i-REAP) for commercial buildings will be developed as a one-stop solution to measure, predict and optimise energy consumption. i-REAP will leverage the characteristics of each building to optimise heating/cooling operations and develop guidelines for ideal retrofitting actions and low carbon heating technologies. The following are the attributes of i-REAP:
- Measure: i-REAP will use off-the-shelf IoT-sensors to capture real-time changes in temperature, energy consumption, and user occupancy. Then, it will integrate the data acquired with historic and current weather data, heating/cooling equipment specifications, architectural designs, and building fabric characteristics.
- Predict: Using the compiled data, i-REAP will leverage Machine Learning techniques (e.g. deep neural networks, long short-term memory neural networks) to predict future energy consumption patterns 24 hours a day and 365 days a year.
- Optimise: Novel evolutionary and deterministic optimisation models will use the predicted energy consumption patterns to optimise and control the operation of the heating and cooling equipment. For example, the energy demand for heating units could be dynamically adjusted based on weather changes and the number of users at any given time in the building.
Ideal retrofitting and low carbon heating technologies: Once i-REAP system has been running for a time, it will have the necessary data to identify which elements of the building fabric are responsible for the greatest thermal losses. This data will be used to develop a guideline for optimal retrofitting of the specific building. i-REAP will also identify the most beneficial low carbon heating technologies given the specific context of the building.
The combination of IoT and AI will facilitate the development of truly predictive energy consumption models, prescriptive operation plans, and personalised retrofitting and low carbon technologies guidelines, which are not currently available in the market. The main outputs include:
- i-REAP application is the interface in which the user can check the status of the IoT-devices (sensors, processors, controls, etc.), view the predicted energy demands, monitor, and adjust the heating/cooling operations, and track the achieved energy savings.
- i-REAP personalised simulation audit platform, which will run what-if scenarios to determine which parts of the building fabric will improve thermal efficiency the most if retrofitted. It will also identify which low carbon heating technologies are the most effective.