Case-based reasoning using expert systems to determine electricity reduction in residential buildings

Case-based reasoning enables solving new problems using past experience, by reusing solutions for past problems. The simplicity of this technique has made it very popular in several domains. However, the use of this type of approach to support decisions in the power and energy domain is still rather unexplored, especially regarding the flexibility of consumption in buildings in response to recent environmental concerns and consequent governmental policies that envisage the increase of energy efficiency. In order to determine the amount of consumption reduction that should be applied in a building, this article proposes a methodology that adapts the past results of similar cases in order to achieve a decision for the new case. A clustering methodology is used to identify the most similar previous cases, and an expert system is developed to refine the final solution after the combination of the similar cases results. The proposed CBR methodology is evaluated using a set of real data from a residential building. Results prove the advantages of the proposed methodology, demonstrating its applicability to enhance house energy management systems by determining the amount of reduction that should be applied in each moment, thus allowing such systems to carry out the reduction through the different loads of the building

[1]  Shihong Yue,et al.  The Energy-Saving Strategy of Electromagnetic Flowmeters Based on Various Predicting Methods , 2016, IEEE Transactions on Applied Superconductivity.

[2]  Kyoung-jae Kim,et al.  Bankruptcy prediction modeling with hybrid case-based reasoning and genetic algorithms approach , 2009, Appl. Soft Comput..

[3]  Ricardo Faia,et al.  Dynamic Fuzzy Estimation of Contracts Historic Information Using an Automatic Clustering Methodology , 2015, PAAMS.

[4]  Jean-Marc Desharnais,et al.  Estimating Software Development Effort with Case-Based Reasoning , 1997, ICCBR.

[5]  Avi Arampatzis,et al.  Phase-Based Information Retrieval , 1998, Inf. Process. Manag..

[6]  Isabel Praça,et al.  Data mining approach to support the generation of Realistic Scenarios for multi-agent simulation of electricity markets , 2014, 2014 IEEE Symposium on Intelligent Agents (IA).

[7]  Kristian J. Hammond,et al.  Case-Based Planning: Viewing Planning as a Memory Task , 1989 .

[8]  Jiawei Han,et al.  Data Mining: Concepts and Techniques , 2000 .

[9]  Negny Stéphane,et al.  Case Based Reasoning for Chemical Engineering Design , 2008 .

[10]  C. R. Mount,et al.  A case-based reasoning system for identifying failure mechanisms , 2000 .

[11]  Zita Vale,et al.  Dynamic load management in a smart home to participate in demand response events , 2014 .

[12]  A. Pohl.  Cross-border portability of online content services in the internal market , 2017 .

[13]  Gang Chen,et al.  An online case-based reasoning system for coal blends combustion optimization of thermal power plant , 2014 .

[14]  Kyung In Kang,et al.  A case-based reasoning cost estimating model using experience by analytic hierarchy process , 2007 .

[15]  Gwang-Hee Kim,et al.  Comparing Cost Prediction Methods for Apartment Housing Projects: CBR versus ANN , 2005 .

[16]  Danielle Monfet,et al.  Development of an energy prediction tool for commercial buildings using case-based reasoning , 2014 .

[17]  R. A. M. O N L O P E Z D E M A N T A R A S,et al.  Retrieval, reuse, revision and retention in case-based reasoning , 2006 .

[18]  V. R. Dehkordi,et al.  Hourly prediction of a building's electricity consumption using case-based reasoning, artificial neural networks and principal component analysis , 2015 .

[19]  Taehoon Hong,et al.  An estimation methodology for the dynamic operational rating of a new residential building using the advanced case-based reasoning and stochastic approaches , 2015 .