Driving Net-Zero Energy Targets Using Smart Sensors
05 October 2023

The MRS Census and GeoDems group champions new thinking and new talent; one area they have been particularly impressed with is the CDRC Masters Dissertation Scheme (MDS)

This programme offers an exciting opportunity to link students on Masters courses with leading retail companies on projects which are important to the retail industry. The scheme provides the opportunity to work directly with an industrial partner and to link students’ research to important retail and ‘open data’ sources. The project titles are devised by retailers and are open to students from a wide range of disciplines.

MRS CGG are proud to have been granted permission to publish abstracts from the dissertations and we are sure the students have a great future ahead of them.

This abstract is by Subbhashinee Subbiah

Title: Driving Net-Zero Energy Targets Using Smart Sensors

Academic Institution: University of Liverpool

Industry Sponsor: Movement Strategies, a GHD company

Introduction
Achieving net zero energy targets is the need of the hour.
(i) Soaring energy prices in the UK and Europe. With the current factors affecting the world, it is expected that the household energy price cap in the UK will rise to 80% in the coming October.
(ii) Climate action goals of COP21 aimed to keep global warming to a 1.5-degree Celsius to a 2-degree Celsius increase. The need to reduce carbon outputs and control emissions was the primary goal of COP21.
(iii) Buildings alone contribute to around 30% of the total greenhouse gas emissions.
Hence, energy savings is advisable to minimise cost and meet the climate action goals.

Data

These Datasets are provided for two individual buildings of
(i) GHD London Office (ii) GHD London Retail

Methods

Time Series Anomaly Detection

This technique identifies instances or dates where there is the extensive usage of cooling or heating required. 16-04-2022 was identified as an anomaly. The reason is, it is the first hot weekend of 2022. GHD office does not air condition during the weekends.
Thus, identifying occurrences of extreme events from the data, helps in better preparation and handling of the extensive heating/cooling needed. Thereby, conserving energy.

Time Series Forecasting and Prediction

This technique helps in predicting and forecasting temperature values. The environmental sensor readings and the local temperature correspond to the indoor and outdoor temperatures of the building. A new feature is created by calculating the difference in the indoor and outdoor temperature predicted values called the 'Temperature_Difference'. These temperature difference values are then related to other variables such as occupancy and energy usage using the OLS Regression technique to find the energy consumption of the building due to heating and cooling.

The amount of energy that can be saved by employing few energy saving techniques is identified and the amount of money that can be saved is calculated by 1 KWH = £ 0.1436