Produced in Association with
SERIES 22 / Module 01 AI and Energy Management
AI and the Fourth Industrial Revolution AI is part of a wider digital revolution encompassing a range of digital technologies, concepts and trends. For example, alongside AI sits the Internet of Things (IoT). Some have named this the ‘Fourth Industrial Revolution’. According to the World Economic Forum: “We stand on the brink of a technological revolution that will fundamentally alter the way we live, work, and relate to one another. In its scale, scope, and complexity, the transformation will be unlike anything humankind has experienced before.”7 2019 research by PwC UK,
commissioned by Microsoft8, estimated that using AI for environmental applications could contribute up to $5.2 trillion USD to the global economy in 2030 and reduce GHG emissions by 4%. This is/was an amount equivalent to 2.4 GT CO2e – equivalent to the 2030 annual emissions of Australia, Canada and Japan combined. The International Energy Agency
(IEA) recognises the significant role of AI in improving energy efficiency and reducing greenhouse gas emissions. In its 2017 report 'Digitalisation and Energy'9, the IEA estimated digital technologies such as AI could cut total energy use in residential and commercial buildings by around 10% by 2040. It stated: “These efficiency gains are largest in heating and cooling, particularly through the use of smart
thermostats and sensors. Smart lighting allows for potentially substantial cuts in lighting electricity demand." Similarly, the Energy Institute reports
that if scaled across industry, digital technologies could deliver up to 20% of the 2050 reduction needed to hit the IEA’s net zero trajectories in the energy, materials and mobility industries10. These kinds of figures have led the
UK government to predict the UK AI market will grow to over $1 trillion (USD) by 2035 11.
AI in energy management AI can be used in energy management in several ways. Firstly, it can be used to optimise energy consumption. AI algorithms can analyse data from various sources such as weather forecasts, historical energy usage patterns, and real-time data from sensors. This analysis can assist in forecasting future energy requirements and modifying control strategies in building services, industrial processes, transportation and energy infrastructure systems alike. Secondly, AI can be used to manage
renewable energy sources more effectively. For instance, AI can predict the output of solar panels or wind turbines based on weather forecasts and adjust the operation of these systems to maximise their efficiency. This helps to reduce reliance on fossil fuels and lowers greenhouse gas emissions.
Thirdly, AI can be used to detect
faults and anomalies in energy systems. By continuously monitoring the performance of these systems, AI can identify any deviations from normal operation(s) and alert maintenance staff before a major breakdown occurs. This not only prevents costly repairs and potential downtime to critical infrastructure but also ensures that energy systems are always operating at their peak efficiency.
AI in buildings In the UK 80% of the buildings that will be standing in 2050 have already been built12. At the same time, it is widely understood that there is a significant performance gap between ‘as designed’ new buildings and the reality of their operations. If we are to deliver a zero- carbon estate, we must get better at predicting energy consumption and managing that consumption throughout the lifecycle of a building, and AI has a significant role to play in this. AI algorithms can analyse historical
data on energy usage and environmental conditions to predict future energy needs. This allows building managers to adjust heating, ventilation, and air conditioning (HVAC) systems in advance to meet anticipated demand, reducing energy waste and saving money. Smart thermostats can learn
from occupant behaviour and adjust temperature settings accordingly to
Figure 1: How AI and machine learning can bring life to physics-based simulations to create Generative AI digital twinning.
optimise comfort and energy efficiency. Similarly, AI-powered lighting systems can automatically control and adjust brightness levels based on natural light availability and occupancy patterns. These systems, which are already available, can also be operated through wireless controls systems using open protocols such as DALI. With the removal of additional cabling requirements, networks can be expanded with minimal disruption - extra spaces or even separate buildings can be integrated into the same system. Forming part of an IoT, these lighting
systems can ‘track occupants’ as they move around the building, while also allowing connection to the BMS for HVAC controls and optimisation strategies. They could potentially be used to identify if and where occupants are in a building in the event of an emergency such as a fire. By continuously monitoring system
performance and analysing data from sensors installed throughout the building, AI can detect anomalies that may indicate a malfunctioning piece of equipment or an area of the building that is not being heated, cooled or ventilated efficiently. This allows for proactive maintenance and repairs, preventing energy waste and reducing operational costs. This approach to maintenance is often referred to as predictive maintenance. AI can also play a crucial role in
predicting peak demand periods and adjusting building systems accordingly. An example might be using AI to ensure buildings reduce their energy consumption during the times when electricity prices are highest. This not only saves money but also helps stabilise the grid. Advanced analytics also enable the
creation of digital replicas of physical assets (“digital twins”) that can be used to simulate and optimise design and operation. Rather like BIM, which allows for integrated coordinated space planning in a virtual environment before, during and after construction, an AI enabled digital twin allows organisations to stress test multiple design and/ or operational scenarios in a virtual environment using self-learned and predictive generative algorithms. IES has prepared a 3.5 minute video13
on how it uses AI in its digital twinning solutions. Readers should watch the video as part of this CPD.
AI in industrial processes AI can learn from past performance data
SUBMIT YOUR ENTRY NOW! 06 DECEMBER 2024
DE VERE GRAND CONNAUGHT ROOMS, LONDON 22 EIBI | JUNE 2024
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36
