Analysis of Heating and Cooling Energy Demand of School Buildings

Abstract Climate change affects the energy demand in different sectors of the society. To investigate this possible impact, in this research, temporal trends and change points in heating degree-days (HDD), cooling degree-days (CDD), and their simultaneous combination (HDD+CDD) were analysed for a 60-year period (1960-2019) in Iran. The results show that less than 20% of the study stations had significant trends (either upward or downward) in HDD time series, while more than 80% of the stations had significant increasing trends in CDD and HDD+CDD time series. Abrupt changes in HDD time series mostly occurred in the early 1980s, but those in CDD time series were mostly observed in the 1990s. The cooling energy demand in Iran has dramatically increased as CDD values have raised up from 690 ºC-days to 1010 ºC-days in the last 60 years. HDD, however, almost remained constant in the same period. The results suggest that if global warming continues with the current pace, cooling energy demand in the residential sector will considerably increase in the future, calling for a change in residential energy consumption policies.

Download Full-text

The Right Amount of Technology in School Buildings

Sustainability ◽

10.3390/su12031134 ◽

2020 ◽

Vol 12 (3) ◽

pp. 1134 ◽

Cited By ~ 1

Author(s):

Thomas Auer ◽

Philipp Vohlidka ◽

Christine Zettelmeier

Keyword(s):

Energy Demand ◽

Age Groups ◽

Heat Losses ◽

School Buildings ◽

School Construction ◽

Passive House ◽

Technical Aspects ◽

Heating And Cooling ◽

The Right ◽

Indoor Comfort

What is an adequate school building nowadays and which amount of technology does it need? How high is the indoor comfort in terms of thermal, visual, hygienic, and acoustical comfort? Are there technical aspects that stand out to other solutions? How do users feel and act in the buildings? For this purpose, the Chair compared, in total, twelve selected modern, older, and renovated school buildings from different building age groups. For the comparison, it was essential to intensively analyze each of the twelve schools. This included visiting the schools, talking with the participating architects, specialist planners, builders, and school managers, procuring and analyzing planning documents and, where available, publications and reports, performing simulations and measurements in the classrooms, and surveying the buildings’ users. The predominant energy demand in schools is the energy expenditure for heating and cooling the air, especially for heating the air in the winter. Nevertheless, it turns out that from a purely energy-focused perspective, mechanical ventilation cannot be justified. It is also evident that transmission heat losses play a negligible role in school construction, which is why the “passive house” as a goal for renovations must be called into question.

Download Full-text

Forecasting Heating and Cooling Energy Demand in an Office Building using Machine Learning Methods

2020 International Young Engineers Forum (YEF-ECE) ◽

10.1109/yef-ece49388.2020.9171807 ◽

2020 ◽

Author(s):

Xavier Godinho ◽

Hermano Bernardo ◽

Filipe Tadeu Oliveira ◽

Joao C. Sousa

Keyword(s):

Machine Learning ◽

Energy Demand ◽

Office Building ◽

Learning Methods ◽

Machine Learning Methods ◽

Heating And Cooling ◽

Cooling Energy Demand

Download Full-text

A Data-Driven Approach to Forecasting Heating and Cooling Energy Demand in an Office Building as an Alternative to Multi-Zone Dynamic Simulation

Applied Sciences ◽

10.3390/app11041356 ◽

2021 ◽

Vol 11 (4) ◽

pp. 1356

Author(s):

Xavier Godinho ◽

Hermano Bernardo ◽

João C. de Sousa ◽

Filipe T. Oliveira

Keyword(s):

Neural Networks ◽

Dynamic Simulation ◽

Energy Demand ◽

Office Building ◽

Data Driven ◽

Support Vector ◽

Simulation Tools ◽

Heating And Cooling ◽

Vector Machines ◽

Cooling Energy Demand

Nowadays, as more data is now available from an increasing number of installed sensors, load forecasting applied to buildings is being increasingly explored. The amount and quality of resulting information can provide inputs for smarter decisions when managing and operating office buildings. In this article, the authors use two data-driven methods (artificial neural networks and support vector machines) to predict the heating and cooling energy demand in an office building located in Lisbon, Portugal. In the present case-study, these methods prove to be an accurate and appealing alternative to the use of accurate but time-consuming multi-zone dynamic simulation tools, which strongly depend on several parameters to be inserted and user expertise to calibrate the model. Artificial neural networks and support vector machines were developed and parametrized using historical data and different sets of exogenous variables to encounter the best performance combinations for both the heating and cooling periods of a year. In the case of support vector regression, a variation introduced simulated annealing to guide the search for different combinations of hyperparameters. After a feature selection stage for each individual method, the results for the different methods were compared, based on error metrics and distributions. The outputs of the study include the most suitable methodology for each season, and also the features (historical load records, but also exogenous features such as outdoor temperature, relative humidity or occupancy profile) that led to the most accurate models. Results clearly show there is a potential for faster, yet accurate machine-learning based forecasting methods to replace well-established, very accurate but time-consuming multi-zone dynamic simulation tools to forecast building energy consumption.

Download Full-text