Table 1 Relationship between... | Emerald Publishing

Table 1

Relationship between theoretical-construct labels and their optimisation characteristics

Theoretical construct label (n)	Most frequent objective function(s)	Predominant optimisation algorithms	Surrogate models (yes/total)
Method (7)	Cost, LCCE, LCC, LCCF, GHG, CED, Water usage, Solid waste	FCM-ELM, PSO, NSGA-II, LP	1/7
Model (5)	TEC, LCC, LCA, MSE, LCCE, LCC	GPR, ANN and linear regression, ANN (MLP), NSGA-II and ANN, GA (NSGA-II)	4/5
Framework (4)	TEDSC, EEDL, DH, LCCE, LCC, TEC, Cooling and heating energy load	MOGA, Epsilon constraint methiod, MOGA (PSO), NSGA-II	1/4
Conceptual framework (1)	single-objective scalar function of LCA and LCC	MOLP	0/1
Decision-support tool (1)	LCCF, LCC	NSGA-II	0/1

Theoretical construct label (n)	Most frequent objective function(s)	Predominant optimisation algorithms	Surrogate models (yes/total)
Method (7)	Cost, LCCE, LCC, LCCF, GHG, CED, Water usage, Solid waste	FCM-ELM, PSO, NSGA-II, LP	1/7
Model (5)	TEC, LCC, LCA, MSE, LCCE, LCC	GPR, ANN and linear regression, ANN (MLP), NSGA-II and ANN, GA (NSGA-II)	4/5
Framework (4)	TEDSC, EEDL, DH, LCCE, LCC, TEC, Cooling and heating energy load	MOGA, Epsilon constraint methiod, MOGA (PSO), NSGA-II	1/4
Conceptual framework (1)	single-objective scalar function of LCA and LCC	MOLP	0/1
Decision-support tool (1)	LCCF, LCC	NSGA-II	0/1

Note(s): Nomenclature: LCC = Life cycle cost, LCCE = Life cycle carbon emissions, LCCF = Life cycle carbon footprint, MOGA = multi-objective genetic algorithms, TEC = Total energy consumption, ANN = Artificial neural networks, DH = Discomfort hours, NSGA-II = Non-dominated Sorting Genetic Algorithm II, MOLP = Multi-objective linear programming, GPR = Gaussian process regression, FCM = Fuzzy C-Means, ELM = Extreme learning machine, PSO = Particle swarm optimisation, TEDSC = thermal energy demand for space conditioning, EEDL = Electrical energy demand for lighting, CED = Cumulative Energy Demand

Source(s): The authors

[ViewLarge]

Sharing Unavailable