Identification of the Heat Equation Parameters for Estimation of a Bare Overhead Conductor’s Temperature by the Differential Evolution Algorithm

This paper deals with the Differential Evolution (DE) based method for identification of the heat equation parameters applied for the estimation of a bare overhead conductor`s temperature. The parameters are determined in the optimization process using a dynamic model of the conductor; the measured environmental temperature, solar radiation and wind velocity; the current and temperature measured on the tested overhead conductor; and the DE, which is applied as the optimization tool. The main task of the DE is to minimise the difference between the measured and model-calculated conductor temperatures. The conductor model is relevant and suitable for the prediction of the conductor temperature, as the agreement between measured and model-calculated conductor temperatures is exceptional, where the deviation between mean and maximum measured and model-calculated conductor temperatures is less than 0.03 °C.

Download Full-text

Modified Differential Evolution Algorithm Based Neural Network for Nonlinear Discrete Time System

Handbook of Research on Recent Developments in Intelligent Communication Application - Advances in Wireless Technologies and Telecommunication ◽

10.4018/978-1-5225-1785-6.ch016 ◽

2017 ◽

pp. 397-420 ◽

Cited By ~ 1

Author(s):

Uday Pratap Singh ◽

Sanjeev Jain ◽

Rajeev Kumar Singh ◽

Mahesh Parmar

Keyword(s):

Neural Network ◽

Nonlinear Systems ◽

Differential Evolution ◽

Differential Evolution Algorithm ◽

Uncertain Nonlinear Systems ◽

Discrete Time System ◽

Brushless Dc ◽

Unknown Disturbances ◽

Evolution Algorithm ◽

The Difference

Two main important features of neural networks are weights and bias connection, which is still a challenging problem for researchers. In this paper we select weights and bias connection of neural network (KN) using modified differential evolution algorithm (MDEA) i.e. MDEA-NN for uncertain nonlinear systems with unknown disturbances and compare it with KN using differential evolution algorithm (DEA) i.e. DEA-KN. In this work, MDEA is based on exploitation and exploration of capability, we have implemented differential evolution algorithm and modified differential evolution algorithm, which are based on the consideration of the three main operator's mutation, crossover and selection. MDEA-KN is applied on two different uncertain nonlinear systems, and one benchmark problem known as brushless dc (BDC) motor. Proposed method is validated through statistical testing's methods which demonstrate that the difference between target and output of proposed method are acceptable.

Download Full-text

Bare Conductor Temperature Coefficient Identification by Means of Differential Evolution Algorithm

Advanced Technologies, Systems, and Applications III - Lecture Notes in Networks and Systems ◽

10.1007/978-3-030-02574-8_25 ◽

2018 ◽

pp. 316-325

Author(s):

Mirza Sarajlić ◽

Marko Pocajt ◽

Peter Kitak ◽

Nermin Sarajlić ◽

Jože Pihler

Keyword(s):

Differential Evolution ◽

Temperature Coefficient ◽

Differential Evolution Algorithm ◽

Coefficient Identification ◽

Evolution Algorithm ◽

Conductor Temperature

Download Full-text

Multi-Population Coevolutionary Differential Evolution Algorithm

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.40-41.235 ◽

2010 ◽

Vol 40-41 ◽

pp. 235-241

Author(s):

Yi Zhang ◽

Xiu Xia Yang

Keyword(s):

Differential Evolution ◽

Differential Evolution Algorithm ◽

Population Evolution ◽

Estimation Of Distribution ◽

Evolution Algorithm ◽

Simulation Results ◽

The Difference ◽

The Individual ◽

Global Population ◽

Chaotic Initialization

The multi-population coevolutionary differential evolution (DE) based on estimation of distribution algorithm (EDA) is proposed. DE completes optimum search using the difference information between the individuals in the population, but the global population evolution information can not be used sufficiently. In this paper, the multi-population co-evolutionary is introduced, which incorporate the merits of the DE and EDA. The elite mutation is proposed in DE. To overcome the greed characteristic, the chaotic initialization and replacement are introduced in DE and the individual diversity in EDA is adjusted based on the individual density. Simulation results show the good global search ability of the proposed algorithm.

Download Full-text

Modified Differential Evolution Algorithm Based Neural Network for Nonlinear Discrete Time System

Deep Learning and Neural Networks ◽

10.4018/978-1-7998-0414-7.ch089 ◽

2020 ◽

pp. 1598-1621

Author(s):

Uday Pratap Singh ◽

Sanjeev Jain ◽

Rajeev Kumar Singh ◽

Mahesh Parmar

Keyword(s):

Neural Network ◽

Nonlinear Systems ◽

Differential Evolution ◽

Differential Evolution Algorithm ◽

Uncertain Nonlinear Systems ◽

Discrete Time System ◽

Brushless Dc ◽

Unknown Disturbances ◽

Evolution Algorithm ◽

The Difference

Download Full-text

Subspace Clustering Mutation Operator for Developing Convergent Differential Evolution Algorithm

Mathematical Problems in Engineering ◽

10.1155/2014/154626 ◽

2014 ◽

Vol 2014 ◽

pp. 1-18 ◽

Cited By ~ 2

Author(s):

Zhongbo Hu ◽

Shengwu Xiong ◽

Xiuhua Wang ◽

Qinghua Su ◽

Mianfang Liu ◽

...

Keyword(s):

Differential Evolution ◽

Optimization Problems ◽

Differential Evolution Algorithm ◽

Subspace Clustering ◽

Convergence In Probability ◽

Mutation Operator ◽

Mutation Operators ◽

Evolution Algorithm ◽

The Difference ◽

Theoretical Analyses

Many researches have identified that differential evolution algorithm (DE) is one of the most powerful stochastic real-parameter algorithms for global optimization problems. However, a stagnation problem still exists in DE variants. In order to overcome the disadvantage, two improvement ideas have gradually appeared recently. One is to combine multiple mutation operators for balancing the exploration and exploitation ability. The other is to develop convergent DE variants in theory for decreasing the occurrence probability of the stagnation. Given that, this paper proposes a subspace clustering mutation operator, called SC_qrtop. Five DE variants, which hold global convergence in probability, are then developed by combining the proposed operator and five mutation operators of DE, respectively. The SC_qrtop randomly selects an elite individual as a perturbation’s center and employs the difference between two randomly generated boundary individuals as a perturbation’s step. Theoretical analyses and numerical simulations demonstrate that SC_qrtop prefers to search in the orthogonal subspace centering on the elite individual. Experimental results on CEC2005 benchmark functions indicate that all five convergent DE variants with SC_qrtop mutation outperform the corresponding DE algorithms.

Download Full-text