Initialisation of the augmented Hopfield network for improved generator scheduling

被引：11

作者：

Dillon, JD

Walsh, MP

O'Malley, MJ

机构：

[1] ESB Natl Grid, Dublin 2, Ireland

[2] Univ Coll Dublin, Dept Elect & Elect Engn, Dublin 4, Ireland

来源：

IEE PROCEEDINGS-GENERATION TRANSMISSION AND DISTRIBUTION | 2002年 / 149卷 / 05期

关键词：

D O I：

10.1049/ip-gtd:20020460

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

An artificial neural network algorithm for generator scheduling is proposed. The algorithm employs an unfeasible Lagrangian dual maximum solution to initialise the neurons of an augmented Hopfield network. The proposed algorithm produces cheaper solutions when compared with Lagrangian relaxation or a randomly initialised augmented Hopfield network. The algorithm also has shorter convergence times than the augmented Hopfield network, but is not as fast to converge as Lagrangian relaxation.

引用

收藏

页码：593 / 599

页数：7

相关论文

共 21 条

[1] UNIT COMMITMENT IN A LARGE-SCALE POWER-SYSTEM INCLUDING FUEL CONSTRAINED THERMAL AND PUMPED-STORAGE HYDRO [J].

AOKI, K ;

SATOH, T ;

ITOH, M ;

ICHIMORI, T ;

MASEGI, K .

IEEE TRANSACTIONS ON POWER SYSTEMS, 1987, 2 (04) :1077-1084

[2] THE GENERALIZED UNIT COMMITMENT PROBLEM [J].

BALDICK, R .

IEEE TRANSACTIONS ON POWER SYSTEMS, 1995, 10 (01) :465-475

[3] DAILY GENERATION SCHEDULING OPTIMIZATION WITH TRANSMISSION CONSTRAINTS - A NEW CLASS OF ALGORITHMS [J].

BATUT, J ;

RENAUD, A .

IEEE TRANSACTIONS ON POWER SYSTEMS, 1992, 7 (03) :982-989

[4]

ELSHARKAWI M, 1996, 1120 TP IEEE POW ENG

[5] AN OPTIMIZATION-BASED METHOD FOR UNIT COMMITMENT [J].

GUAN, X ;

LUH, PB ;

YAN, H ;

AMALFI, JA .

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS, 1992, 14 (01) :9-17

[6] Efficient determination of optimal radial power system structure using hopfield neural network with constrained noise [J].

Hayashi, Y ;

Iwamoto, S ;

Furuya, S ;

Liu, CC .

IEEE TRANSACTIONS ON POWER DELIVERY, 1996, 11 (03) :1529-1535

[7] NEURAL NETWORKS AND PHYSICAL SYSTEMS WITH EMERGENT COLLECTIVE COMPUTATIONAL ABILITIES [J].

HOPFIELD, JJ .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA-BIOLOGICAL SCIENCES, 1982, 79 (08) :2554-2558

[8] UNIFYING THE TANK AND HOPFIELD LINEAR-PROGRAMMING CIRCUIT AND THE CANONICAL NONLINEAR-PROGRAMMING CIRCUIT OF CHUA AND LIN [J].

KENNEDY, MP ;

CHUA, LO .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1987, 34 (02) :210-214

[9] ANNSTLF - Artificial neural network short-term load forecaster - Generation three [J].

Khotanzad, A ;

Afkhami-Rohani, R ;

Maratukulam, D .

IEEE TRANSACTIONS ON POWER SYSTEMS, 1998, 13 (04) :1413-1422

[10] Improving convergence and solution quality of Hopfield-type neural networks with augmented Lagrange multipliers [J].

Li, SZ .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1996, 7 (06) :1507-1516