Multi-objective optimization for building retrofit: A model using genetic algorithm and artificial neural network and an application

Abstract

Page 2 of 46 A c c e p t e d M a n u s c r i p t 2 Retrofitting of existing buildings offers significant opportunities for improving occupants' comfort and well-being, reducing global energy consumption and greenhouse gas emissions. This is being considered as one of the main approaches to achieve sustainability in the built environment at relatively low cost and high uptake rates. Although a wide range of retrofit technologies is readily available, methods to identify the most suitable set of retrofit actions for particular projects are still a major technical and methodological challenge. This paper presents a multi-objective optimization model using genetic algorithm (GA) and artificial neural network (ANN) to quantitatively assess technology choices in a building retrofit project. This model combines the rapidity of evaluation of ANNs with the optimization power of GAs. A school building is used as a case study to demonstrate the practicability of the proposed approach and highlight potential problems that may arise. The study starts with the individual optimization of objective functions focusing on building's characteristics and performance: energy consumption, retrofit cost, and thermal discomfort hours. Then a multi-objective optimization model is developed to study the interaction between these conflicting objectives and assess their trade-offs.

A comparison between cost optimality and return on investment for energy retrofit in buildings-A real options perspective

“…These problems may be tackled using multi-objective optimization models, in which the set of potential alternatives is implicitly defined by constraints defining a feasible region and multiple objective functions are optimized, or multi-criteria decision analysis, in which the alternatives are explicitly known apriori to be appraised by (qualitative and/or quantitative) multiple criteria. Simulation techniques are also used to deal with this problem, in general focusing on particular aspects rather than following a global approach (Asadi, Silva, Antunes, Dias, & Glicksman, 2014;Caccavelli & Gugerli, 2002;Chidiac, Catania, & Morofsky, 2011a;Chidiac, Catania, Morofsky, & Foo, 2011b;Diakaki, Grigoroudis, & Kolokotsa, 2008;Doukas, Nychtis, & Psarras, 2009;Soares et al, in press;Verbruggen, Al Marchohi, & Janssens, 2011).…”

“…The algorithm proposed was called Genetic Algorithm for Energy Efficiency in Buildings (GAEEB) and its pseudo-code is presented in Algorithm 1. The GAEEB is based on NSGA-II (Deb, Pratap, Agarwal, & Meyarivan, 2002), which has been used to solve combinatorial problems in several areas as building retrofit (Asadi et al, 2014), optimal placement and sizing of distributed generation (Wanxing, Ke-yan, Yuan, Xiaoli, & Yunhua, 2015) and generation expansion planning (Kannan, Baskar, McCalley, & Murugan, 2009), among many others.…”

Energy in buildings—Policy, materials and solutions

“…The authors also state that volatile energy prices make postponing the retrofit measure the more profitable option. Taking into account three target parameters, namely energy consumption, retrofit cost, and thermal discomfort hours, Asadi et al 201 showed that genetic algorithms combined with artificial neural networks solve the optimization problem much faster than conventional approaches. The optimization results can be used to evaluate the impact of individual retrofit measures and to facilitate decision making in a retrofit project.…”

Two-Stage Integer Programing Model for Building Retrofit Planning for Energy Saving in South Korea

“…Equation (25) reflects the construction delay. Equation (26) denotes the idle penalty due to construction which reflects the value of the building. Equation (27) presents a single construction constraint for each floor and construction material.…”

“…Malatji et al [10] suggested a multi-objective optimization model for maximizing energy savings in buildings, and minimizing the return period of the initial budget with the genetic algorithm. Asadi et al [26] proposed an energy consumption prediction model through an artificial neural network and genetic algorithm to solve the multi-objective optimization problem.…”