A Platform for the Promotion of Energy Efficiency and Monitoring in Hotel Units

A Platform for the Promotion of Energy Efficiency and Monitoring in Hotel Units

Sergey Nogin (University of Algarve, Portugal), Jânio Monteiro (University of Algarve, Portugal & INESC-ID, Portugal), Sergio Gómez Melgar (University of Huelva, Spain & LAR Arquitectura, Spain), José Peyroteo (University of Algarve, Portugal), António Mortal (University of Algarve, Portugal), Carlos Miguel A. Santos (University of Algarve, Portugal), José Livramento (University of Algarve, Portugal), Pedro J. S. Cardoso (University of Algarve, Portugal) and Jorge Semião (University of Algarve, Portugal)
DOI: 10.4018/978-1-5225-2927-9.ch020


Tourists today are more likely to be concerned with the environment and greener lifestyle choices. In this context, a green flagship of some hotels can be an important selection criteria at the time of selecting one. In the near future, buildings should become nearly zero energy, consuming as low as possible and producing almost all the energy they need, using renewable energy sources. To achieve this goal, hotel buildings need to pass through a transformation process that will make them more efficient. In this process, a decision support platform would be important to help hoteliers monitor their energy consumption, identify which points are consuming more than expected, decide which investments are more cost effective and manage their equipment in an optimum way. This chapter describes the challenges involved in developing such a platform, covering several research and development fields, including Internet of Things networks, ICT, Smart Grids, Renewable Energy, Energy efficiency, as well as algorithms for machine learning and optimization.
Chapter Preview


There has been a gradual shift in the expectations and demands of tourists, regarding hotels. Today’s typical hotel guests are more likely to be concerned about environmental issues comprising greener lifestyle choices, such as recycling, fuel-efficient vehicles or organic food. While the location of hotels is still one of the most important features to select them, it is also common to find many hotels in the same region or area. In these cases, the green flagship of some of these hotels can be an important differentiating factor that make them more attractive to some tourists.

To achieve that green flagship, a better energy efficiency of hotels is required. In this field, the Directive 2010/31 of the European Union (European Parliament, council on the energy performance of buildings, 2010) makes mandatory for all new public buildings after January 2020 and all other new buildings from January 2021 onward to become nearly zero energy. This means that, they will have to consume as low as possible and at the same time will have to produce almost all the energy they need, in their own building or in their vicinity.

As tourism is one of the priorities for the economic activities of several European regions, the implications of the European Directive 2010/31 are of high importance for touristic companies and in particular for hotel units, affecting their competitiveness and image. Monitoring energy consumption to achieve the zero energy goal also helps to accomplish the sustainability of the region where the hotel is. By conveying the achievements obtained with these measures in future eTourism Applications, the image of the region as a whole can be improved.

In order for them to achieve the goals of zero energy building, a complete set of decision support tools is required that, besides monitoring consumption, could support the development of innovative methods to improve energy efficiency. Their aim is to give hoteliers and technicians a set of tools that include recommendations on building insulation, amount of renewable energy needed, automated detection and identification of excessive consumption levels, and management of consuming devices.

In some cases, as for instance in the detection and automatic identification of abnormal consumption levels, machine learning algorithms are required to compare the current level of consumption with the expected one, obtained from the consumption history of the building and weighted by several factors such as occupancy levels and environmental variables. Machine learning algorithms are thus used to perform a real time and continuous analysis, selecting the relevant information between huge amounts of data generated, e.g., by a network of IoT (Internet of Things) sensors and SCADA (Supervisory Control and Data Acquisition) devices.

Regarding the energy generation from renewable sources, the understanding of which set of solutions allows the building to reach the goal of nearly zero consumption is of crucial importance. As nearly zero means that the amount of energy generated locally should equal what is consumed in a certain time period (usually one year) the understanding of the consumption profile of the building is of crucial importance to define what should be the most appropriate installation levels.

This should also be combined with an effective reduction in energy costs, taking into consideration the tariff rates of energy suppliers. In order to accomplish it, hotel managers need to know which of the tariff rates, of the energy retailers, is the best solution for them, and also, need to adjust consumption levels accordingly. Thus not only the selection of the tariff rates should depend on the consumption profile, but also the consumption profile should change according with the contracted tariff rates. When these decisions are also based on generation from renewable energy sources, the complexity of the whole system increases significantly, as it requires maximizing the use of the locally generated energy, avoiding selling it at a lower price. Thus a set of actions should be defined that could increase the correlation between production and consumption through rescheduling of loads and the commensurate design of generation systems.

Key Terms in this Chapter

Machine Learning (ML): Automated learning concept that uses different methods and models to learn from past experience through the analysis of historical data.

Internet of Things (IoT): A networks of hardware devices capable of sensing environmental and consumption data and communicate it to Internet Protocol based servers.

Decision Support Platform (DSP): A software capable of helping people to make decisions in complex environments with several sources of uncertainty, by making use of Computational Intelligence methods.

Nearly Zero Energy Building (nZEB): A building having a very high energy performance that results from reduced consumption and a significant production of energy, using renewable energy sources, either produced in the building, or in its vicinity.

Complete Chapter List

Search this Book: