Data Mining and Machine Learning in Building Energy Analysis
Focusing on up-to-date artificial intelligence models to solve building energy problems, Artificial Intelligence for Building Energy Analysis reviews recently developed models for solving these issues, including detailed and simplified engineering methods, statistical methods, and artificial intelligence methods. The text also simulates energy consumption profiles for single and multiple buildings. Based on these datasets, Support Vector Machine (SVM) models are trained and tested to do the prediction. Suitable for novice, intermediate, and advanced readers, this is a vital resource for building designers, engineers, and students.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Other editions - View all
50 buildings algorithm applications approach artificial intelligence artificial neural networks audit building energy analysis building energy consumption building’s cache calculate calibration chiller classification problems constraints consumption data cooling load detection developed diagnosis district heating dual form efficient electricity consumption embedded methods energy performance EnergyPlus engineering equipment error evaluation faults feature selection Figure function gradient descent hidden layer hourly HVAC HVAC system input introduced iteration kernel matrix learning Libsvm linear machine learning MapReduce measured meter model performance model training MRPsvm multicore multiple buildings neural network neurons nonlinear optimal output parameters perceptron Pisvm predicting building energy prediction of building predictor programming proposed radial basis function RDP models recurrent neural network regression simulation solver solving speedup stochastic gradient descent support vector machines support vector regression target thermal training and testing training data training set values variables