Optimization of annual electricity consumption costs and the costs of insulation and phase change materials in the residential building using artificial neural network and genetic algorithm methods

被引:26
作者
Baghoolizadeh, Mohammadreza [1 ]
Dehkordi, Seyed Amir Hossein Hashemi [1 ]
Rostamzadeh-Renani, Mohammad [2 ]
Rostamzadeh-Renani, Reza [2 ]
Azarkhavarani, Narjes Khabazian [3 ]
Toghraie, Davood [4 ]
机构
[1] Shahrekord Univ, Dept Mech Engn, Shahrekord 8818634141, Iran
[2] Politecn Milan, Energy Dept, Via Lambruschini 4, I-20156 Milan, Italy
[3] Jami Inst Technol, Dept Mech Engn, Esfahan, Iran
[4] Islamic Azad Univ, Dept Mech Engn, Khomeinishahr Branch, Khomeinishahr, Iran
关键词
PCM (phase change materials); ANN (artificial neural network); GA (genetic algorithm); Annual cost electricity consumption building; Cost of insulation & PCMs; MULTIOBJECTIVE OPTIMIZATION; GMDH-TYPE; SENSITIVITY-ANALYSIS; THERMAL PERFORMANCE; PREDICTION; VALIDATION; SIMULATION; THICKNESS; STORAGE; DESIGN;
D O I
10.1016/j.est.2023.106916
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Overuse of energy resources (especially in residential building) has been one of the most important issues in recent decades. Researchers have often focused on the use of PCM (Phase Change Materials) and insulators to reduce energy consumption in a particular climatic condition. However, these materials themselves create a new cost. In this research, it is tried to use PCM and insulation in such a way that the costs are optimized. Hence, the effect of variation of several design parameters such as insulation thickness, PCM thickness, melting temperature, phase change temperature and insulation conductivity on the reduction of the objective functions such as annual electricity costs of building and the cost of building materials is investigated. Unlike most other studies that focused on the particular climate, this research aims to conduct the multi-objective optimization for various climatic conditions. Hence, building models in 8 cities with different climatic conditions is simulated using Energy Plus software. For multi-objective optimization, 36 Design of Experiment points based on the design variables are considered for each city. The annual cost of electricity consumption in the building and the cost of building materials are calculated by Energy Plus software. The relation between design variables and objective functions is then predicted by the GMDH (Group Method of Data Handling) neural network and the equations between input and output are obtained. Afterward, the Pareto optimal points of objective functions are acquired using the GA (Genetic Algorithm). Finally, the effect of the multi-objective optimization on occupant's thermal comfort is analyzed. The results indicated that using insulator and PCM with optimal properties can minimize the objective functions by a range of 12-18 % in cold, moderate and semi-arid cities, But PCM and insulator are not much recommended for hot and humid cities.
引用
收藏
页数:39
相关论文
共 79 条
[1]   Modeling and forecasting the mean hourly wind speed time series using GMDH-based abductive networks [J].
Abdel-Aal, R. E. ;
Elhadidy, M. A. ;
Shaahid, S. M. .
RENEWABLE ENERGY, 2009, 34 (07) :1686-1699
[2]   A case study for influence of building thermal insulation on cooling load and air-conditioning system in the hot and humid regions [J].
Aktacir, Mehmet Azmi ;
Buyukalaca, Orhan ;
Yilmaz, Tuncay .
APPLIED ENERGY, 2010, 87 (02) :599-607
[3]  
[Anonymous], 2013, ANSI/ASHRAE Standard 62.1-2013: Ventilation for Acceptable Indoor Air Quality
[4]  
[Anonymous], 2017, CO2 EM FUEL COMB
[5]  
[Anonymous], ENERGYPLUS HELP, pp67
[6]  
[Anonymous], 2011, COD 19 EN EFF BUR CO
[7]  
[Anonymous], 1402001 ANSIASHRAE
[8]  
[Anonymous], 2007, 10456 ISOFDIS
[9]   An overview of energy planning in Iran and transition pathways towards sustainable electricity supply sector [J].
Aryanpur, Vahid ;
Atabaki, Mohammad Saeid ;
Marzband, Mousa ;
Siano, Pierluigi ;
Ghayoumi, Kiarash .
RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2019, 112 :58-74
[10]  
Ataii F., 2015, SOLUTION ROUTING PRO, P36