ISOA‐DBN: A New Data‐Driven Method for Studying the Operating Characteristics of Air Conditioners DOI Creative Commons
Mengran Zhou, Qiqi Zhang, Feng Hu

et al.

Energy Science & Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 28, 2024

ABSTRACT Air conditioning load is a crucial demand response resource for optimizing energy consumption control, and its accurate analysis provides an essential basis achieving efficient management. We aim at solving the problems of scarcity, single type, low accuracy difficult construction high‐quality data sets available air operation characteristic models present. This paper proposes method model based on improved seagull optimization algorithm to optimize deep belief network (ISOA‐DBN). Firstly, set study characteristics obtained through experiments. Secondly, Restricted Boltzmann Machine (RBM) Deep Belief Network (DBN) are used operating conditioning. The results show that effect better when DBN conditioning, coefficient determination reaches 0.9439. Then, SOA improved, performance tested. ISOA performs than in test 14 standard functions. Finally, adjust parameters finely. compared with SOA‐DBN, ISOA‐DBN has conditioners, 0.9534. can provide strong support studying under different working conditions broad application prospects control.

Language: Английский

Inner-Outer Array Based on Genetic Algorithm With Constraint Relaxation for Constrained Integer Optimization Engineering Problems DOI
Omnia Osman Fadel Abouhabaga, Mohamed H. Gadallah

Practice, progress, and proficiency in sustainability, Journal Year: 2025, Volume and Issue: unknown, P. 183 - 218

Published: Jan. 3, 2025

The Inner-Outer Array (IOA) and Constraint Relaxation method (CR) are introduced into Genetic Algorithm (GA) to propose hybrid based on with (IOA-GA-CR) for solving hard-to-solve problems. This hybridized approach's search uses IOA roughly scan the entire domain before concentrating search, using GA, promising regions. Combining GA algorithms balances powers of exploration exploitation, increasing efficiency finding global or nearly optima. adaptive control parameters neglected, in this proposed technique, which is reflecting robustness algorithm. Moreover, CR utilized block ineffective constraints, turning difficult problems handled ones. efficacy suggested IOA-GA-CR algorithm verified through two complicated integer engineering design challenges, then compared well-known optimization algorithms. experimental results show that has a good computational effort convergence.

Language: Английский

Citations

0
A Comprehensive Survey on Seagull Optimization Algorithm and Its Variants DOI
Vimal Kumar Pathak, Swati Gangwar, Mithilesh K. Dikshit

et al.

Archives of Computational Methods in Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: March 1, 2025

Language: Английский

Citations

0
A Multi-strategy Improved Grasshopper Optimization Algorithm for Solving Global Optimization and Engineering Problems DOI Creative Commons

Wei Liu,

Wenlv Yan,

Tong Li

et al.

International Journal of Computational Intelligence Systems, Journal Year: 2024, Volume and Issue: 17(1)

Published: July 11, 2024

Abstract This paper presents a multi-strategy improved grasshopper optimization algorithm (MSIGOA), which aims to address the shortcomings of (GOA), including its slow convergence, vulnerability trapping into local optima, and low accuracy. Firstly, improve uniformity population distribution in search space, MSIGOA uses circle mapping for initialization. A nonlinear decreasing coefficient is utilized instead an original linear exploitation global exploration capabilities. Then, modified golden sine mechanism added during position update stage change single mode GOA enhance capability. The greedy strategy greedily select new old positions individual retain better increase speed convergence. Finally, quasi-reflection-based learning construct populations multiplicity capability escape from optima. verifies efficacy by comparing it with other advanced algorithms on six engineering design problems, CEC2017 test functions, 12 classical benchmark functions. experimental results show that performs than compared has stronger comprehensive

Language: Английский

Citations

2
ISOA‐DBN: A New Data‐Driven Method for Studying the Operating Characteristics of Air Conditioners DOI Creative Commons
Mengran Zhou, Qiqi Zhang, Feng Hu

et al.

Energy Science & Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 28, 2024

ABSTRACT Air conditioning load is a crucial demand response resource for optimizing energy consumption control, and its accurate analysis provides an essential basis achieving efficient management. We aim at solving the problems of scarcity, single type, low accuracy difficult construction high‐quality data sets available air operation characteristic models present. This paper proposes method model based on improved seagull optimization algorithm to optimize deep belief network (ISOA‐DBN). Firstly, set study characteristics obtained through experiments. Secondly, Restricted Boltzmann Machine (RBM) Deep Belief Network (DBN) are used operating conditioning. The results show that effect better when DBN conditioning, coefficient determination reaches 0.9439. Then, SOA improved, performance tested. ISOA performs than in test 14 standard functions. Finally, adjust parameters finely. compared with SOA‐DBN, ISOA‐DBN has conditioners, 0.9534. can provide strong support studying under different working conditions broad application prospects control.

Language: Английский

Citations

0