2022
DOI: 10.1016/j.jestch.2022.101278
|View full text |Cite
|
Sign up to set email alerts
|

A data-driven multi-objective optimization framework for optimal integration planning of solid-state transformer fed energy hub in a distribution network

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
5
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
2
2
1

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(5 citation statements)
references
References 31 publications
0
5
0
Order By: Relevance
“…Here's how the convolution operation is calculated: We begin with the initial input data, which is often shown as a 2D matrix with dimensions of 4 by 4. Given that the convolution kernel has dimensions of 2 by 2, the convolution window's size is also equal to the convolution kernel's size 21 . The convolution window's original location is in the 2D matrix's top left corner.…”
Section: Modelling and Solvingmentioning
confidence: 99%
“…Here's how the convolution operation is calculated: We begin with the initial input data, which is often shown as a 2D matrix with dimensions of 4 by 4. Given that the convolution kernel has dimensions of 2 by 2, the convolution window's size is also equal to the convolution kernel's size 21 . The convolution window's original location is in the 2D matrix's top left corner.…”
Section: Modelling and Solvingmentioning
confidence: 99%
“…[140], [141], [142], [143]. Among them, the evolutionary and meta-heuristic algorithms applied to EH energy management and planning problems include: genetic algorithms [144], [145], [146], shuffled frog leaping algorithm [147], grey wolf optimization [148], improved water wave optimization algorithm [149], ϵ-domination based multi-objective evolutionary algorithm [150], differential evolution quantum particle swarm optimization algorithm [151], group search optimizer [152], [153], nondominated sorting genetic algorithm [154], [155], [156], time varying acceleration coefficient gravitational search algorithm [157], [158], time varying acceleration coefficients particle swarm optimization algorithm [159], flower pollination algorithm [160], particle swarm optimization [161], [162], [163], [164], modified teaching-learning based optimization [165], [166], [167], [168], and quantum artificial bee colony algorithm [169]; and, their hybrid versions, such as combination of the multiple-mutations adaptive genetic algorithm with an interior point optimization solver [170], hybrid genetic particle swarm optimization [171], combination of adaptive neuro-fuzzy inference system and genetic algorithms [172], hybrid algorithm of ant-lion optimizer and krill herd optimization [81], hybrid teaching-learning-based optimization and crow search algorithm [173], and hybrid particle swarm -neurodynamic algorithm…”
Section: Appendix a Application Of Evolutionary Algorithms To Operati...mentioning
confidence: 99%
“…In [33] mobile energy hubs are considered for enhancing the resiliency of the electricity distribution grids by the shortest path algorithm and minimizing the restoration time of the system by transporting the mobile energy hubs. A datadriven multi-objective modeling is used in [34] for energy loss reduction and voltage profile improvement in energy hub by non-dominated sorted genetic algorithm (NSGA-II). In [35] configuration planning of the energy hub considering load characteristics and spatio-temporal synergistic effects of resources is implemented by Genetic algorithm (GA).…”
Section: Related Studiesmentioning
confidence: 99%
“…The energy balance constraint for electrical energy, natural gas and heat energy are modeled by ( 32)- (34), respectively.…”
Section: P T D P T P T Ed T P T P T Tmentioning
confidence: 99%