A summary of our interviews
Most respondents indicated that the energy efficiency of pumping and pressurization systems in tall buildings tends to be moderate to low, regardless of the size or sector of the companies or organizations where they work. In terms of the most valuable component, more than half of the respondents stated that the proposed monitoring system is the most valuable part of the presented solution. The majority of respondents said that the decisive factor for adopting the solution in their company or organization is a competitive ROI, followed by the scalability of the solution. They also identified the main competitive advantage as potentially stemming from AI and IoT-related features, leading to improved energy and water efficiency in the facilities. Enhanced control capabilities over the systems were also mentioned as a key advantage. Suggested improvements by respondents ranged from technical aspects, such as pumps with soft starters and integration with monitoring and maintenance systems, to legal aspects, highlighting the need to adapt to municipal regulations and national legal frameworks as they evolve. It is noteworthy that a large proportion of respondents reported being employed by ANA, and they were generally the most negative in terms of the current energy efficiency of buildings. They also expressed particular concern about challenges related to water storage and the efficiency and cleanliness of pumping systems. This suggests there is potential to apply our solution in airports.
Progress regarding our solar panel integration
We've finished the calculations regarding the useful energy generation of our solar panel system.
Our interviews are a success!
We had almost 30 answers to our survey about what, not only companies, but individuals as well, think that would be the best solution suited for them. This was a major step in the project becaause it showed us what the consumer finds more valuable.
LSTM for our AI model
We've been searching for the best option to train our AI model, in terms of it being aple to make predictions of water consumptions by the time of the day, month of the year or even just the season we're in. So we chose a LSTM (Long short-term memory), which is a type of RNN(Recurrent neural network) predominantly used to learn, process, and classify sequential data.
The materials list is finished
Due to some constraints, we only finished our materials list today. Hope we get them soon so we can start our model.
The materials finally arrived!
The materials we ordered are finally here.We're going to start working on our physical model as soon as we can.
Our model's structure is done
We begun building our model a few weeks ago and it's finally finished.There's still some work to be done related to programming our microcontroller and finishing some electrical connections.