Since electricity plays a crucial role in countries' industrial infrastructures, power companies are trying to monitor and control infrastructures to improve energy management and scheduling. Accurate forecasting is a critical task for a stable and efficient energy supply, where load and supply are matched. This paper discusses various algorithms and a new hybrid deep learning model which combines long short-term memory networks (LSTM) and convolutional neural network (CNN) model to analyze their performance for short-term load forecasting. The proposed model is called parallel LSTM-CNN Network or PLCNet. Two real-world data sets, namely "hourly load consumption of Malaysia" as well as "daily power electric consumption of Germany", are used to test and compare the presented models. To evaluate the tested models' performance, root mean squared error (RMSE), mean absolute percentage error (MAPE), and R-squared were used. In total, this paper is divided into two parts. In the first part, different machine learning models, including the PLCNet, predict the next time step load. In the second part, the model's performance, which has shown the most accurate results in the first part, is discussed in different time horizons. The results show that deep neural networks models, especially PLCNet, are good candidates for being used as short-term prediction tools. PLCNet improved the accuracy from 83.17% to 91.18% for the German data and achieved 98.23% accuracy in Malaysian data, which is an excellent result in load forecasting.

A general approach is proposed to determine the common sensors that shall be used to estimate and classify the approximate number of people (within a range) in a room. The range is dynamic and depends on the maximum occupancy met in a training data set for instance. Means to estimate occupancy include motion detection, power consumption, CO 2 concentration sensors, microphone or door/window positions. The proposed approach is inspired by machine learning. It starts by determining the most useful measurements in calculating information gains. Then, estimation algorithms are proposed: they rely on decision tree learning algorithms because these yield decision rules readable by humans, which correspond to nested if-then-else rules, where thresholds can be adjusted depending on the living areas considered. In addition, the decision tree depth is limited in order to simplify the analysis of the tree rules. Finally, an economic analysis is carried out to evaluate the cost and the most relevant sensor sets, with cost and accuracy comparison for the estimation of occupancy. C45 and random forest algorithms have been applied to an office setting, with average estimation error of 0.19-0.18. Over-fitting issues and best sensor sets are discussed.

A general approach is proposed to determine occupant behavior (occupancy and activity) in offices and residential buildings in order to use these estimates for improved energy management. Occupant behavior is modelled with a Bayesian network in an unsupervised manner. This algorithm makes use of domain knowledge gathered via questionnaires and recorded sensor data for motion detection, power, and hot water consumption as well as indoor CO2 concentration. Different case studies have been investigated with diversity according to their context (available sensors, occupancy or activity feedback, complexity of the environment, etc.). Furthermore, experiments integrating occupancy estimation and hot water production control show that energy efficiency can be increased by roughly 5% over known optimal control techniques and more than 25% over rule-based control while maintaining the same occupant comfort.