Can ChatGPT help with energy efficiency?
Será que o ChatGPT pode ajudar na eficiência energética4

Artificial intelligence supporting many processes in the GTC is not something exactly new (nor is it in many other areas), but with all the hype around this topic mainly due to the new iteration of the language model chatGPTWe wanted to know whether this model can introduce new dynamics, point out directions or even give us the Holy Grail of energy efficiency.

Artificial intelligence models like chatGPT are not bias-free, as they learn to make decisions based on training data, which can include biased human decisions or reflect historical or social inequalities, even if sensitive variables like gender, race, or sexual orientation are removed. Amazon stopped using a hiring algorithm after it found it favoured candidates based on words like “executed” or “captured” that were more commonly found on men’s resumes, for example. Another source of bias is flawed data sampling, where groups are over- or under-represented in the training data. For example, Joy Buolamwini at MIT working with Timnit Gebru found that facial analysis technologies had higher error rates for minorities and particularly minority women, potentially due to unrepresentative training data.

Light-hearted questions

Well, to test the “animal” nothing better than asking it directly. We know that it is a generative machine learning model and not having access to information in real time, it will not be able to give answers based on information of what is happening, but on its collection. What we want to know is whether, through all the information you have available, you can give answers that go beyond what we know about energy efficiency and give specific instructions by compiling the answers. We started off lightly and asked if you could really help us with energy efficiency in buildings:

ChatGPT is a powerful tool that can help the energy efficiency of buildings and cities in many ways. Energy efficiency is an important concept that focuses on reducing the amount of energy required to perform a specific task. It is important to reduce greenhouse gas emissions, decrease dependence on fossil fuels and save money.

One of the ways ChatGPT can help with energy efficiency is by providing detailed information about the characteristics of a specific building or city. This can include information about the size and layout of the building, building materials, heating and cooling systems, lighting, appliances, office equipment and other systems. This information can be used to identify areas where energy efficiency can be improved and to develop plans to implement these improvements.

Can ChatGPT help with energy efficiency?
Can ChatGPT help with energy efficiency?
Can ChatGPT help with energy efficiency?
Can ChatGPT help with energy efficiency?
Now more specific

We replied that the information was very general. We asked you to be much more specific, for example, saying exactly how artificial intelligence can intervene in a building and propose concrete measures that no one might have thought to suggest:

Absolutely! Artificial intelligence (AI) can be used in a number of ways to help improve energy efficiency in buildings and cities. Some of the more specific ways include:

  1. Data analysis – AI can be used to collect, analyse and interpret energy data in real time, helping to identify areas where energy efficiency can be improved. For example, AI can analyse energy consumption data in different areas of a building and identify where waste or excesses are occurring. Based on this information, AI can suggest specific measures to reduce energy consumption, such as switching off unused equipment or adjusting the temperature of the air-conditioning.

  2. System control – AI can be used to control energy systems in real time, automatically adjusting energy consumption in response to changing building conditions. For example, AI can adjust the temperature of the air conditioner based on the outside temperature or the amount of people present in the building. In addition, AI can control lighting systems, turning off lights in unused areas or adjusting brightness based on available natural light.

  3. Predictive maintenance – AI can be used to predict failures in power systems, allowing preventative action to be taken before problems occur. For example, AI can analyse performance data from equipment such as motors and pumps and identify when a component is about to fail. Based on this information, the AI can suggest specific measures to repair or replace the component before failure occurs.

  4. Energy optimisation – AI can be used to optimise energy use in a building, helping to reduce energy costs. For example, AI can analyse energy consumption data and predict future energy demand. Based on this information, the AI can automatically adjust energy consumption to minimise costs and maximise energy efficiency.

Beyond these specific ways, AI can be used in a number of other ways to improve energy efficiency in buildings and cities. For example, AI can be used to model energy efficiency in different scenarios, allowing building owners to assess the costs and benefits of different energy efficiency measures. In addition, AI can be used to provide detailed analysis and reporting on energy consumption in a building or city, allowing users to monitor and manage energy consumption more efficiently.

Could it replace any profession?
We asked what professions it could replace related to technical building management and IoT implementation:

As an artificial intelligence language model, I am not programmed to replace or eliminate any profession. Instead, my aim is to assist and complement the work of professionals in various fields, including the technical management of buildings and the implementation of IoT solutions.

However, implementing IoT solutions can help automate routine tasks and collect important data, which can reduce the need for manpower in some areas. For example, temperature and humidity sensors can help monitor the building’s internal environment, reducing the need for manual monitoring. In addition, intelligent lighting systems can be programmed to switch on and off automatically, eliminating the need for a lighting operator.

However, the implementation of IoT solutions can also create new job opportunities in areas such as data analysis and maintenance of IoT systems. The data collected by IoT sensors needs to be analysed and interpreted to obtain useful information, which can be done by professionals in fields such as data analysis and computer science. In addition, maintaining IoT systems can also create new job opportunities for professionals in fields such as engineering and information technology.

In summary, the implementation of IoT solutions can have a significant impact on the technical management of buildings, but it is not something that can completely replace existing professions. Instead, it can create new opportunities and complement the work of professionals in various fields.

And can you invent or imagine a solution that has never been thought of by anyone else?
We also asked if there is any measure to improve energy efficiency that has never been applied but that you know could have good results:

As a model artificial intelligence language, I am not aware of all the energy efficiency solutions that have already been developed or implemented. However, I can mention some innovative solutions that have the potential to improve energy efficiency that may not have been widely adopted or known about.

One solution that could have great potential is the application of artificial intelligence (AI) and machine learning technologies in building energy management. These technologies can be used to predict and optimise energy consumption based on usage patterns, weather data and other information. In addition, AI can be used to identify problem areas in buildings, such as lighting or air conditioning systems that consume more energy than necessary.

Another solution that may be less well known is the use of building materials with advanced thermal insulation properties. This can include materials such as polyurethane foam insulation panels, which have excellent thermal insulation properties and can be used in walls, ceilings and floors of buildings. In addition, the use of intelligent glazing, which adjusts its transparency according to environmental conditions, can also be an effective measure to improve the energy efficiency of buildings.

Finally, a solution that has been widely discussed, but not always implemented, is the use of renewable energy sources to supply the energy needs of buildings. This could include installing solar panels on the roof of the building, wind turbines or geothermal systems. Using renewable energy sources can help to significantly reduce the carbon footprint of buildings and reduce energy costs in the long term.

In summary, there are many innovative solutions that can improve the energy efficiency of buildings and cities, including the application of AI technologies, the use of advanced building materials and the use of renewable energy sources.

Conclusion

The secret of getting the most out of these models is in the prompt, that is, the targeted way in which you question the model. We kept asking questions and the answers were always around the same.

While answers can be taken for granted and may help to better understand a topic, they are by no means a substitute for a qualified and experienced technician in any field, including those areas where language is the core business.

In conclusion, we consider that, although these models are good adjuvants for professionals in different areas, they are still in a very “green” phase and the predictions that certain professions are doomed are exaggerated. There will be, as there always has been, the need to adapt to evolution and what artificial intelligence can (and should) do is free us from routine, mechanical tasks so that we can put the focus of our effort on conceptual principles that enhance life.

As a note of trivia, all the images in this article were generated by ChatGPT’s OpenAI companion, Dall-E.

Será que o ChatGPT pode ajudar na eficiência energética3

WiseBuilding® is technically capable of supporting any technical building management project and has long been using artificial intelligence to improve processes. Contact us. You’ll always have a human on your side giving you the best of technology 😀.

WISEFRAMEWORK - The certified and customised solution.

WISEFRAMEWORK is a BACnet B-AWS certified software solution for state-of-the-art integration, control, management and visualisation in building automation systems. Designed to redefine the way buildings are operated through an open platform and seamless harmonisation between building-generated data by supporting multiple protocols including BACnet, Modbus, KNX, OPC-UA and MQTT. Through the use of Haystack technology, the software also empowers the building for the future at the forefront in the integration of the various technical systems.

Preferências de Privacidade
Quando visita o nosso site, podem ser armazenadas informações de serviços específicos através do seu navegador, geralmente em forma de cookies. Aqui pode alterar as suas preferências de privacidade. Observe que o bloqueio de alguns tipos de cookies pode afetar a sua experiência no site e nos serviços que oferecemos.