Optimal design of building environment with hybrid genetic algorithm, artificial neural network, multivariate regression analysis and fuzzy logic controller

Zhang, Tianhu; Liu, Yuanjun; Rao, Yandi; Li, Xiaopeng; Zhao, Qingxin

doi:10.1016/j.buildenv.2020.106810

Cited by 62 publications

(19 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The GA is one of the optimization algorithms that is widely used for optimizing different problems such as training machine learning algorithms (Park et al, 2020), optimal design of the building environment (Zhang T. et al, 2020), optimization of the culture condition , optimizing bank lending decisions (Metawa et al, 2017), and face recognition (Zhi and Liu, 2019). The GA has consisted of the population of chromosomes that gradually mature during the optimization process to converge to an optimal solution.…”

Section: Genetic Algorithmmentioning

confidence: 99%

Inclusive Multiple Model Using Hybrid Artificial Neural Networks for Predicting Evaporation

Ehteram

Panahi

Ahmed

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

Predicting evaporation is essential for managing water resources in basins. Improvement of the prediction accuracy is essential to identify adequate inputs on evaporation. In this study, artificial neural network (ANN) is coupled with several evolutionary algorithms, i.e., capuchin search algorithm (CSA), firefly algorithm (FFA), sine cosine algorithm (SCA), and genetic algorithm (GA) for robust training to predict daily evaporation of seven synoptic stations with different climates. The inclusive multiple model (IMM) is then used to predict evaporation based on established hybrid ANN models. The adjusting model parameters of the current study is a major challenge. Also, another challenge is the selection of the best inputs to the models. The IMM model had significantly improved the root mean square error (RMSE) and Nash Sutcliffe efficiency (NSE) values of all the proposed models. The results for all stations indicated that the IMM model and ANN-CSA could outperform other models. The RMSE of the IMM was 18, 21, 22, 30, and 43% lower than those of the ANN-CSA, ANN-SCA, ANN-FFA, ANN-GA, and ANN models in the Sharekord station. The MAE of the IMM was 0.112 mm/day, while it was 0.189 mm/day, 0.267 mm/day, 0.267 mm/day, 0.389 mm/day, 0.456 mm/day, and 0.512 mm/day for the ANN-CSA, ANN-SCA, and ANN-FFA, ANN-GA, and ANN models, respectively, in the Tehran station. The current study proved that the inclusive multiple models based on improved ANN models considering the fuzzy reasoning had the high ability to predict evaporation.

show abstract

Section: Genetic Algorithmmentioning

confidence: 99%

Inclusive Multiple Model Using Hybrid Artificial Neural Networks for Predicting Evaporation

Ehteram

Panahi

Ahmed

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…Most researchers (Zhang et al 2020; Khan and Mathew 2019) agreed that fuzzy logic approaches are suited to manage the integrated power system. Fuzzy control methods offer a systemic way to control the randomly varying loads and energy sources to increase the reliability of the integrated power system.…”

Section: Literature Reviewmentioning

confidence: 99%

Design of optimal hybrid power system to provide reliable supply to rural areas of Ethiopia using MATLAB and Homer

Nebey

2021

Renewables

View full text Add to dashboard Cite

Integrating different energy resources, like solar PV, wind, and hydro is used to ensure reliable power to the rural community loads. Hybrid power system offers sufficient power supply for the rural villages by providing alternative supply for intermittent nature of renewable energy resource. Hence, intermittency of renewable energy resources is a challenge to electrify the rural community in a sustainable manner with the above sources. Thus, efficient resources management is a reasonable choice for intermittent renewable energy resources. The majority of rural villages in Ethiopia are suffering from lack of electricity. This causes deforestation, travel for long distance to fetch water, and no good social services, like clinic and schools, sufficiently. Therefore, the objective of this study was to maximize reliability of power supply by renewable energy sources. Data on wind speed and solar radiation are obtained from the NASA surface meteorological agency. While hydro data are obtained from physical measurements. Different configuration options are considered by Homer software to find the optimal configuration of hybrid system. The optimal configuration system is selected and hybrid components are sized. The optimal hybrid system consists of solar PV, wind, and hydro to supply a community load with a share of 13%, 52%, and 35% respectively. The fuzzy logic controller is designed to manage the intermittent nature of energies. Hence, the demand and energy sources are unpredictable; intelligent control system is important to manage the system accordingly. The control system is designed in MATALAB software. The result obtained from resource combination shows demand and supply are balanced. From the Twelve probabilistic combinations of demand and energy sources, one of the combinations shows that when 7.5 kW is demanded, the power generated/output from hybrid system is 10 kW which is greater than demand. To satisfy 7.5 kW demand control system takes 4.25 kW, 2.75 kW, and 1.08 kW share from wind, hydro, and solar sources respectively. The fuzzy logic control system is designed, to monitor the resource availability and load demand. This controller was managing the demand and the available resources according to the rule.

show abstract

“…Several typologies of Artificial Neural Networks were analyzed, and the best results were selected by a deep statistical analysis and results comparison. In [45], a new method integrating a genetic algorithm (GA), an artificial neural network (ANN), a multivariate regression analysis (MRA) and a fuzzy logic controller (FLC) was proposed in order to optimize the indoor environment and energy consumption, based on simulation results. In particular, the GA process was used to search for the optimal solution, whereas the ANN and CFD tools were used to obtain the values of the objectives for each individual.…”

Section: State Of the Art In Artificial Neural Network And Fuzzy Logic Toolsmentioning

confidence: 99%

Development of a Decisional Procedure Based on Fuzzy Logic for the Energy Retrofitting of Buildings

et al. 2021

View full text Add to dashboard Cite

This paper concerns the development of an automatic tool, based on Fuzzy Logic, which is able to identify the proper solutions for the energy retrofitting of existing buildings. Regarding winter heating, opaque and glazing surfaces are considered in order to reduce building heat dispersions. Starting from energy diagnosis, it is possible to formulate retrofitting proposals and to evaluate the effectiveness of the intervention considering several aspects (energy savings, costs, intervention typology). The innovation of this work is represented by the application of a fuzzy logic expert system to obtain an indication about the proper interventions for building energy retrofitting, providing as inputs only few parameters, with a strong reduction in time and effort with respect to the software tools and methodologies currently applied by experts. The novelty of the paper is the easy handling properties of the developed tool, which requires only a few data about the buildings: not many such methods were developed in the last years. The energy requirements for winter heating before and after particular interventions were evaluated for a consistent set of buildings in order to produce the required knowledge base for the tool’s development. The identified appropriate inputs and outputs, their domains of discretization, the membership functions associated to each fuzzy set, and the linguistic rules were deduced on the basis of the knowledge determined in this was. Therefore, the system was successfully validated with reference to further buildings characterized by different design and architecture features, showing a good agreement with the intervention opportunities evaluated.

show abstract

Optimal design of building environment with hybrid genetic algorithm, artificial neural network, multivariate regression analysis and fuzzy logic controller

Cited by 62 publications

References 44 publications

Inclusive Multiple Model Using Hybrid Artificial Neural Networks for Predicting Evaporation

Inclusive Multiple Model Using Hybrid Artificial Neural Networks for Predicting Evaporation

Design of optimal hybrid power system to provide reliable supply to rural areas of Ethiopia using MATLAB and Homer

Development of a Decisional Procedure Based on Fuzzy Logic for the Energy Retrofitting of Buildings

Contact Info

Product

Resources

About