Abstract
The proper functioning of higher education institutions depends on multiple factors. The teaching-learning process is essential, which turns professors and students into leading actors. However, there are many other factors that must be considered. A key element is the quality and comfort of the air (including temperature, degree of humidity, and purity). This aspect is related to two issues of great importance that are energy efficiency and indoor pollution. In this chapter, the authors want to make visible the importance of maintaining adequate air quality and comfort in the buildings of higher education institutions, not only to achieve energy efficiency and consequent cost reduction, but also to improve the well-being and health of the entire university community by reducing, as much as possible, air pollutants in university campus buildings. In addition, the main emerging technologies available to achieve this objective, such as artificial intelligence, big data, internet of things, or edge computing, will be presented together with practical use cases.
TopIntroduction
The proper functioning of higher education institutions depends on multiple factors. The teaching-learning process is essential, which turns professors and students into leading actors. However, there are many other factors that must be considered, since they can also contribute, in one way or another, to improving the functioning of higher education institutions by increasing the well-being of the entire university community, including professors, researchers, students and all support staff.
One of the aspects that is beginning to pay more attention in recent times is the quality and comfort of the air (including temperature, degree of humidity and purity). This aspect is related to two issues of great importance that are 1) energy efficiency and 2) indoor pollution.
At the moment, many higher education institutions are promoting recovery, transformation and resilience plans, that include energy efficiency optimization and air quality improvement, relying on emerging technologies, such as Artificial Intelligence, Big Data, Internet of Thing (IoT) or Edge Computing, which allow addressing the problem from a perspective and with expectations of results that are unthinkable without the use of these technologies.
The objective is to develop systems that are able to improve energy efficiency, as well as the health conditions of university infrastructures, with little or no human intervention. These systems collect data through an Internet of Things wireless sensor network and transmit it to processing servers, where said data will be stored and analysed in real time using Big Data and Artificial Intelligence techniques. With small, inexpensive and low-consumption sensors distributed throughout the different buildings of a university campus, operators responsible for maintenance can know the situation in real time, at any time. By collecting the appropriate data and using data-driven techniques, it would be possible to act when and where it was necessary to maintain, at all times, levels of temperature, humidity and air purity that would preserve the health of all members of the university community, and promote a comfortable environment for the development of university activity.
Moreover, if Edge Computing is integrated into the Internet of Things wireless sensor network, computing services can be brought closer to the data source, with the help of IoT devices. This enables data to be collected and processed at the edge of the network, rather than sending it to the data centre or the cloud, helping to faster identify patterns for immediate action. The ability of IoT devices to use computing power for rapid and immediate data analysis is becoming increasingly valuable. Using Edge Computing, an organization can distribute a common set of resources across a large number of locations to fine-tune the centralized infrastructure to meet the needs of an increasing number of devices and data.
Today a lot of energy resources are wasted in maintaining buildings, with conditions of temperature, lighting, etc., that are considered adequate during the opening hours of the facilities. This causes a part of the energy to be wasted in classrooms, laboratories and spaces where, for a good part of the day, there is no type of activity. While it is true that the economic improvement would be evident, the objective should also be to develop ecological and sustainable systems that use energy efficiently, and do not waste resources unnecessarily, connecting universities with current technological advances and ecology. In addition, it is important to guarantee the well-being of the entire university community by mitigating, or limiting as much as possible, the potential effects that indoor pollution can cause on their health, both, in the short term, and in the medium and long term.
In this chapter, the authors want to make visible the need and importance of maintaining adequate indoor air quality and comfort (temperature, degree of humidity and air purity) in the buildings of higher education institutions, not only to achieve energy efficiency and consequent cost reduction, but also to improve the well-being and health of the entire university community by reducing, as much as possible, the indoor pollution of university campus buildings. In addition, the main emerging technologies available to achieve these objectives, such as Artificial Intelligence, Big Data, Internet of Things or Edge Computing, will be presented, together with practical use cases. This chapter provides valuable information for higher education institutions’ leaders, in a moment where many of these institutions are promoting a transformation that must include energy efficiency optimization and air quality improvement, and face the challenge of integrating the use of emerging technologies to implement the best solutions.
Key Terms in this Chapter
Supervised Learning: It is a subcategory of Machine Learning (and Artificial Intelligence). It is characterized by the use of labelled datasets to train algorithms that classify data or predict results accurately.
Artificial Intelligence: A branch of computer science focused on building smart machines capable of performing tasks that typically require human intelligence.
Edge Computing: A distributed computing paradigm that brings computation capabilities closer to the data source to improve response times and save bandwidth. It is used to process time-sensitive data and it is preferred over Cloud Computing in remote locations, where there is limited or no connectivity to a centralized location.
Unsupervised Learning: It is a subcategory of Machine Learning (and Artificial Intelligence). It uses learning algorithms to analyse and cluster unlabelled datasets. These algorithms focus on discovering hidden patterns or data groupings without the need for human intervention.
Reinforcement Learning: It is a subcategory of Machine Learning (and Artificial Intelligence). The algorithm discovers through its own experiences which actions produce the greatest rewards.
Cloud Computing: It refers to on-demand availability of computer system resources, especially data storage and computing power, without direct active management by the user. It is commonly used to process data that is not time-driven.
Internet of Things: It refers to the interconnection of computing devices embedded in everyday objects, through the Internet, enabling them to send and receive data.
Machine Learning: It is a learning technique that gives machines the ability to learn without being explicitly programmed. It is seen as a subset of Artificial Intelligence.
Deep Learning: It refers to Artificial Neural Networks and related Machine Learning algorithms that uses using multiple layers of neurons. It is seen as a subset of Machine Learning in Artificial Intelligence.
LEED: The acronym means Leadership in Energy and Environmental Design, and refers to a widely used green building rating system.
Big Data: The possibility of analysing and systematically extracting information from data sets that are too large or complex to be managed with by traditional data-processing techniques.
Artificial Neural Network: A computing system inspired by the biological neural networks that constitute a human brain.