Central HVAC units have dominated home and work spaces for decades. And while they prove to be very effective at maintaining temperature, the subjective nature of comfort tends to be an issue in large workspaces with multiple people. For this, you can opt for a Personal Comfort System or PCS, such as heated seats and fans that can help meet each individual's needs.
However, the effectiveness of PCS is limited due to a communication gap between the central HVAC and individual PCS units. The constant temperature that these systems provide also does not take into account changes in the external environment and requires manual adjustment. This lack of integration can be overcome with AI and the Internet of Things. In this article, we will discuss proposed models for integrating PCSs with a central HVAC.
1. Search algorithms
A search algorithm finds the shortest path to a problem by looking for possible solutions. For HVAC, you would find the best operating time for maximum comfort by intuitively cooling or heating the space before work hours begin. This takes into account people's preferences, determining a set of parameters that provide the greatest comfort for everyone; for example, learning how the HVAC is manually adjusted throughout the day and incorporating those changes into an automated system.
2. Logical Inferences
While the search algorithm could find multiple ways to automatically adjust central HVAC, only a few of these answers would make intuitive sense for human comfort. Computers operate based on TRUE and FALSE binary logic, but human reasoning is much more advanced.
AI has to make decisions based on more complex logical inferences. For example, if the outside temperature drops overnight, what new temperature should the HVAC target and under what circumstances should this response be different? This will result in automation that eliminates the need for human intervention.
3. Machine Learning
Machine learning is a sub-branch of Artificial Intelligence that interprets data and creates models that better simulate the human brain.
Accurate interpretation of data is essential to ensure that the AI controlling HVAC heating or cooling does not overestimate or underestimate the desired temperature of a workspace. An HVAC system must be able to make informed decisions based on the logical inferences mentioned above. Using machine learning, it is possible to train a model that would change HVAC parameters as if it were a real human being.
4. Connected Systems
Due to variation in human preference, PCS are used to create a local environment made specifically for an individual. For example, if you find that the air conditioning in your space is too cold, you can use a smart foot or seat heater to achieve a more desirable temperature. When you add AI to the mix, manual settings contribute to training the AI and automatically turn on and off as it learns your preferences over time.
These PCSs need to be connected to the central HVAC system to account for the dynamic external environment. For an algorithmic approach to be fully successful, all of these devices must be interconnected and controlled by a single AI for more precise control. Having PCSs connected to an HVAC via the Internet or local LAN can be one way to achieve this.
Challenges and disadvantages
There are several difficulties to be observed in implementing such a system. Such an advanced system requires significant time and memory. Second, PCSs alone are intended to be inexpensive devices that use a fraction of the energy of an HVAC and provide individual comfort. Adding AI functionality would defeat this purpose due to increased manufacturing and operating costs.
Second, algorithms require more accurate sensor data to function as intended due to the precise control we desire. These sensors increase the cost of a PCS or HVAC system. Buying cheap replacement parts for pumps and sensors for a traditional HVAC system is much more cost-effective. An AI-powered solution, on the other hand, would require more money for repairs.
Final grade
Although current research on automatic control is promising, it is not yet known whether it can be implemented on a large scale. Still, decreasing computer parts costs and more economical manufacturing techniques could make such systems a norm in the near future.
