Data Mining and Machine Learning in Building Energy Analysis

Introduction

The building energy conservation is a crucial topic in the energy field since buildings account for a considerable rate in the total energy consumption. The building’s energy system is very complex, since it is influenced by many factors, such as ambient weather conditions, building structure and characteristics, occupants and their behaviors, the operation of sublevel components like heating, ventilating and air-conditioning (HVAC) systems. These complex properties make the prediction, or fault detection/diagnosis of building energy consumption very difficult to perform quickly and accurately.

Artificial intelligence models attract a lot of attention in solving complex problems. In this book, recently developed models for solving these problems, including detailed and simplified engineering methods, statistical methods and efficient artificial intelligence methods are reviewed. Then, energy consumption profiles are determined from measurements or are simulated for single and multiple buildings. Based on these datasets, support vector machine models are trained and tested to do the prediction. The results obtained on extensive experiments demonstrate high prediction accuracy and robustness of these models. Then, recursive deterministic perceptron (RDP) neural network model is used to detect and diagnose faulty building energy consumption. A new approach is proposed to diagnose faults. It is based on the evaluation of RDP models, each of which is able to detect an ...