Abstract
After reading this chapter you should be able to:
-
Understand the different ML techniques applied to energy demand management
-
Understand the main tools available for demand aggregation and forecasting
-
Apply different behavioral analyses to energy pattern classification
-
Understand demand forecasting at the individual and aggregated demand levels.
Encouraging consumers in responsible consumption is essential to sustainable energy use. Effective demand-side planning is based on categorizing consumers and their demand behaviors and in-depth analysis of reallocation responses. Consequently, major streams in residential energy consumption research are ecological trends and consumer behaviors. This chapter analyzes consumption linkages, estimates energy footprints according to consumer preferences, describes the analysis and definition of the behavioral patterns of consumers participating in aggregated DR services, and demonstrates how consumer profiles can influence validation of these services. Categorizing consumers according to their demand preferences and understanding consumption in different scenarios improves planning and decision-making by both the consumer and the energy manager. Also described is optimal demand forecasting based on clustering models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
New flexibility scenarios are set for the NREL data as described in Sect. 5.3.2.
- 2.
The perceptron model is a simple model that can only be applied in linearly separable problems. It is understood as a hyperplane that separates a space and whose position depends on the weights (W). The value of the function is obtained with the scalar product of the point vector and the vector representing the hyperplane. The weights are updated using the Cartesian product of the unclassified points and the current value of the weights. \(W_{k+1}\) = \(W_k\) + \(y_nx_n\).
References
C. Cruz, E. Palomar, I. Bravo, M. Aleixandre, Behavioural patterns in aggregated demand response developments for communities targeting renewables. Sustain. Cities Soc. 72, 103001 (2021)
M. Muratori, M. Roberts, R. Sioshansi, V. Marano, G. Rizzoni, A highly resolved modeling technique to simulate residential power demand. Appl. Energy 107, 465–473 (2013). https://doi.org/10.1016/j.apenergy.2013.02.057
NREL (2020) [Residential Profiles Dataset], https://data.nrel.gov/system/files/69/Residential-Profiles.xlsx. Accessed 01 May 2021
L.A. Zadeh, G.J. Klir, B. Yuan, Fuzzy Sets, Fuzzy Logic, and Fuzzy Systems: Selected Papers, vol. 6 (World Scientific, 1996)
M.S. Piscitelli, S. Brandi, A. Capozzoli, Recognition and classification of typical load profiles in buildings with non-intrusive learning approach. Appl. Energy 255, 113727 (2019)
L. Breiman, Random forests. Mach. Learn. 45(1), 5–32 (2001)
M. Claesen, B. De Moor, Hyperparameter search in machine learning (2015), ar**v:abs/1502.02127
J. Bergstra, B. Komer, C. Eliasmith, D. Yamins, D.D. Cox, Hyperopt: a python library for model selection and hyperparameter optimization. Comput. Sci. & Discov. 8(1), 014008 (2015)
C.C. de la Torre, Sistema cooperativo de planificacion de demanda de electricidad agregada: comunidades sostenibles que optimizan el consumo de renovables. Ph.D. thesis, Universidad de Alcala (2022)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Cruz, C. (2024). Behavioral Analysis and Pattern Validation. In: Sustainable Energy Efficient Communities. The Springer Series in Sustainable Energy Policy. Springer, Cham. https://doi.org/10.1007/978-3-031-49992-0_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-49992-0_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-49991-3
Online ISBN: 978-3-031-49992-0
eBook Packages: EnergyEnergy (R0)