This paper presents results of work developed in the field of building energy benchmarking applied to the building stock of the Polytechnic Institute of Leiria, Portugal, based on a thorough energy performance characterisation of each of its buildings. To address the benchmarking of the case study buildings, an energy efficiency ranking system was applied. Following an energy audit of each building, they were grouped in different typologies according to the main end-use activities developed: Pedagogic buildings, canteens, residential buildings and office buildings. Then, an energy usage indicator was used to establish a metric to rank the buildings of each typology according to their energy efficiency. The energy savings potential was also estimated, based on the reference building energy usage indicator for each typology, and considering two different scenarios, yielding potential savings between 10% and 34% in final energy consumption.

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.

An AC arc furnace is an unbalanced, nonlinear and time varying load, which can cause many problems to power system quality. Different studies on arc furnaces harmonics analysis can be found in the bibliography on the topic; however, it is very difficult obtain an exact model that takes into account all the parameters that have influence on the process, therefore it is necessary to take measurements under different conditions. In this paper we'll present the harmonic distortion, flicker and unbalance results and conclusions on three different measurement campaigns in an iron and steel industry (SNL) with an AC arc furnace of 83 MW (170 TM) with a transformer of 120 MVA connected with a dedicated power line of 220 kV (55 km) to the Carregado Substation, where there are another other branches that connect industrial and domestic consumers.

In order to support the intensive development of agricultural crops and, in particular the floricultural inside a greenhouse, with the perspective of a quick distribution in the market, increasing the economic benefits and supported on efficient and intelligent management systems energy, it is mandatory to conceive a model based on Cyber-Physical Systems (CPS) This implies, accordingly, increases in renewable primary energy sources utilization coupled with sensing technologies, include developments on Internet of Things (IoT) and Cloud Computing (CC), supported with Information and Communication Technologies (ICT) that will lead to new architectural approach applied to a proposed energy system, based on a sustainable and more engineering autonomous process. This work comes up with a new energy model that retrofits the system of a greenhouse supported with multiple sensors in one grid, to expand into CPS concept to manage sensors and controllers that will improve a profitable energy system.

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.