Two-Area Power System Load Frequency Regulation Using ANFIS and Genetic Algorithm

Kumari, Neha; Gill, Amandeep; Singh, Manjeet

doi:10.1109/incet57972.2023.10170037

Cited by 11 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This learning strategy has the advantage of low time complexity, but it cannot capture the internal correlation of various parameters and so it is difficult to find the optimal solution in the whole parameter space. To coordinate structure identification and parameter identification, meta-heuristic search methods such as particle swarm optimization algorithms and evolutionary algorithms are considered in some of the literature [32][33][34]. In these algorithms, all parameters to be learned, such as the number of rules and parameters of membership functions (MFs), are simultaneously encoded into a long and complex chromosome for joint optimization.…”

Section: Introductionmentioning

confidence: 99%

“…In these algorithms, all parameters to be learned, such as the number of rules and parameters of membership functions (MFs), are simultaneously encoded into a long and complex chromosome for joint optimization. For example, a self-organizing FNN based on the genetic algorithm is proposed in the literature [33], and a hybrid algorithm based on genetic algorithms, backpropagation, and recursive least square estimation is adopted to adjust all parameters, including the number of fuzzy rules. Moreover, the multi-objective evolutionary algorithm is regarded as a cooperative method for structure identification and parameter identification, and it has been used to construct FNNs with high prediction accuracy and a simple structure [35,36].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Symmetrical Fuzzy Neural Network Regression Method Coordinating Structure and Parameter Identifications for Regression

Zhang,

Hao,

et al. 2023

Symmetry

View full text Add to dashboard Cite

Fuzzy neural networks have both the interpretability of fuzzy systems and the self-learning ability of neural networks, but they will face the challenge of “rule explosion” when dealing with high-dimensional data. Moreover, the structure and parameter identifications of models are generally performed in two stages, and this always attends to one thing and loses another in terms of interpretability and predictive performance. In this paper, a fuzzy neural network regression method (FNNR) that coordinates structure identification and parameter identification is proposed. To alleviate the problem of rule explosion, the structure identification and parameter identification are coordinated in the training process, and the numbers of fuzzy rules and fuzzy partitions are effectively limited, while the parameters of fuzzy rules are optimized. The symmetrical architecture of the FNNR is designed for automatic structure identification. An alternate training strategy is adopted by treating discrete and continuous parameters differently, and thus the convergence efficiency of the algorithm is improved. To enhance interpretability, regularized terms are designed from fuzzy rule level and fuzzy partition level to guide the model to learn fuzzy rules with simple structures and clear semantics. The experimental results show that the proposed method has both a compact structure and high precision.

show abstract

Section: Introductionmentioning

confidence: 99%