Sample-Based Neural Approximation Approach for Probabilistic Constrained Programs

被引：35

作者：

Shen, Xun ^{[1
]}

Ouyang, Tinghui ^{[2
]}

Yang, Nan ^{[3
]}

Zhuang, Jiancang ^{[4
]}

机构：

[1] Grad Univ Adv Studies, Dept Stat Sci, SOKENDAI, Tokyo 1068569, Japan

[2] Natl Inst Adv Ind Sci & Technol, Tokyo 1350064, Japan

[3] China Three Gorges Univ, Dept Hubei Prov Collaborat Innovat Ctr New Energy, Yichang 443002, Peoples R China

[4] Inst Stat Math, Tokyo 1908562, Japan

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS | 2023年 / 34卷 / 02期

关键词：

Probabilistic logic; Random variables; Convergence; Approximation algorithms; Wind power generation; Optimization; Neural networks; Neural network model; nonlinear optimization; probabilistic constraints; quantile function; sample average approximation; OPTIMIZATION;

D O I：

10.1109/TNNLS.2021.3102323

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This article introduces a neural approximation-based method for solving continuous optimization problems with probabilistic constraints. After reformulating the probabilistic constraints as the quantile function, a sample-based neural network model is used to approximate the quantile function. The statistical guarantees of the neural approximation are discussed by showing the convergence and feasibility analysis. Then, by introducing the neural approximation, a simulated annealing-based algorithm is revised to solve the probabilistic constrained programs. An interval predictor model (IPM) of wind power is investigated to validate the proposed method.

引用

页码：1058 / 1065

页数：8

共 50 条

[41] Tight and Compact Sample Average Approximation for Joint Chance-Constrained Problems with Applications to Optimal Power Flow
Porras, Alvaro
Dominguez, Concepcion
Morales, Juan Miguel
Pineda, Salvador
INFORMS JOURNAL ON COMPUTING, 2023, 35 (06) : 1454 - 1469
[42] Motion primitives and sample-based trajectory planning for fixed-wing unmanned aircraft
Fu, Qianyi
Li, Jun
Zhao, Wenjie
TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL, 2024,
[43] Neural network based constrained predictive control using stochastic approximation algorithm
Rusnák, A
Najim, K
Mészáros, K
Fikar, M
NEW TRENDS IN DESIGN OF CONTROL SYSTEMS 1997, 1998, : 345 - 350
[44] Stability and Sample-Based Approximations of Composite Stochastic Optimization Problems
Dentcheva, Darinka
Lin, Yang
Penev, Spiridon
OPERATIONS RESEARCH, 2023, 71 (05) : 1871 - 1888
[45] Regularized Sample Average Approximation Approach for Two-Stage Stochastic Variational Inequalities
Jiang, Jie
Li, Shengjie
JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS, 2021, 190 (02) : 650 - 671
[46] Convergence and bound computation for chance constrained distributionally robust models using sample approximation
Lei, Jiaqi
Mehrotra, Sanjay
OPERATIONS RESEARCH LETTERS, 2025, 60
[47] Interpretable logical-probabilistic approximation of neural networks
Vityaev, Evgenii
Korolev, Alexey
COGNITIVE SYSTEMS RESEARCH, 2024, 88
[48] Probabilistic Approximation of Stochastic Time Series Using Bayesian Recurrent Neural Network
Wang, Yuhang
Cai, Kaiquan
Meng, Deyuan
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2025,
[49] A New Projection-Based Neural Network for Constrained Variational Inequalities
Gao, Xing-Bao
Liao, Li-Zhi
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2009, 20 (03): : 373 - 388
[50] An Improved Constrained LMS Algorithm for Fast Adaptive Beamforming Based on a Low Rank Approximation
Vadhvana, Sanket
Yadav, Shekhar Kumar
Bhattacharjee, Sankha Subhra
George, Nithin V.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2022, 69 (08) : 3605 - 3609

← 1 2 3 4 5 →