Self-Adaptive Genetic Algorithm for Modeling Energy Consumption in a Passive House

This paper explores the possibility to optimize a mathematical model developed for energy prediction, by transitioning from performing a simple one-time Genetic Algorithm for parameter estimation to performing parameter estimation in a self-adaptive manner. This novel chained-GA method is used to recompute the parameters in the base equation in order to preserve accuracy as external conditions change over time.

[1]  Justin Bere An Introduction to Passive House , 2014 .

[2]  Francesco Palmieri,et al.  Energy-oriented denial of service attacks: an emerging menace for large cloud infrastructures , 2014, The Journal of Supercomputing.

[3]  M. Brambley,et al.  Energy Savings for Occupancy-Based Control (OBC) of Variable-Air-Volume (VAV) Systems , 2013 .

[4]  Dorothea Heiss-Czedik,et al.  An Introduction to Genetic Algorithms. , 1997, Artificial Life.

[5]  Tariq Samad,et al.  Parameter estimation for process control with neural networks , 1991, Defense + Commercial Sensing.

[6]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[7]  A.H.M. van Roermund,et al.  Mixed-Signal Layout Generation Concepts , 2003 .

[8]  Fatos Xhafa,et al.  L-EncDB: A lightweight framework for privacy-preserving data queries in cloud computing , 2015, Knowl. Based Syst..

[9]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[10]  P. Holtberg,et al.  International Energy Outlook 2016 With Projections to 2040 , 2016 .

[11]  O. Nelles Nonlinear System Identification: From Classical Approaches to Neural Networks and Fuzzy Models , 2000 .

[12]  Narri Yadaiah,et al.  Neural network algorithm for parameter identification of dynamical systems involving time delays , 2007, Appl. Soft Comput..

[13]  Christoph S. Herrmann,et al.  Multi-objective parameter estimation of biologically plausible neural networks in different behavior stages , 2009, 2009 IEEE Congress on Evolutionary Computation.