Hermano Bernardo

Abstract
As the access to consumption data available in household smart meters is now very common in several developed countries, this kind of information is assuming a providential role for different players in the energy sector. The proposed study was applied to data available from the Smart Meter Energy Consumption Data in the London Households dataset, provided by UK Power Networks, containing half-hourly readings from an original sample of 5567 households (71 households were hereby carefully selected after a justified filtering process). The main aim is to forecast the day-ahead load profile, based only on previous load values and some auxiliary variables. During this research different forecasting models are applied, tested and compared to allow comprehensive analyses integrating forecasting accuracy, processing times and the interpretation of the most influential features in each case. The selected models are based on Multivariate Adaptive Regression Splines, Random Forests and Artificial Neural Networks, and the accuracies resulted from each model are compared and confronted with a baseline (Naive model). The different forecasting approaches being evaluated have been revealed to be effective, ensuring a mean reduction of 15% in Mean Absolute Error when compared to the baseline. Artificial Neural Networks proved to be the most accurate model for a major part of the residential consumers.

Abstract
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.

Abstract
Forecasting heating and cooling energy demand in buildings plays a critical role in supporting building management and operation. Thus, analysing the energy consumption pattern of a building could help in the design of potential energy savings and also in operation fault detection, while contributing to provide proper indoor environmental conditions to the building's occupants.This paper aims at presenting the main results of a study consisting in forecasting the hourly heating and cooling demand of an office building located in Lisbon, Portugal, using machine learning models and analysing the influence of exogenous variables on those predictions. In order to forecast the heating and cooling demand of the considered building, some traditional models, such as linear and polynomial regression, were considered, as well as artificial neural networks and support vector regression, oriented to machine learning. The input parameters considered in the development of those models were the hourly heating and cooling energy historical records, the occupancy, solar gains through glazing and the outside dry-bulb temperature.The models developed were validated using the mean absolute error (MAE) and the root mean squared error (RMSE), used to compare the values obtained from machine learning models with data obtained through a building energy simulation performed on an adequately calibrated model.The proposed exploratory analysis is integrated in a research project focused on applying machine learning methodologies to support energy forecasting in buildings. Hence, the research line proposed in this article corresponds to a preliminary project task associated with feature selection/extraction and evaluation of potential use of machine learning methods. © 2020 IEEE.

Abstract
There is a large consensus on the importance of human behaviour on the energy performance of buildings. Energy policy orientations consistently take into account the importance of the building stock in the overall energy use by societies. Existing buildings are specially challenging, as reliable diagnoses are required to take appropriate action towards comfort and energy efficiency. Managers also play a determinant role in building performance, either on investment decisions in technology or on the building operation. Middle-out agents may determine effective energy use options and positively influence behaviours at both levels, top management and occupants. Interdisciplinary cooperation amongst members of research teams is required for energy-efficient building design, coping simultaneously with technological and behavioural issues and their interrelations, privileging occupant-centred approaches.

Abstract