Nonlinear dynamic measurement method of software reliability based on data mining

Fu, Yinsheng; Kumar, Jitendra; Ganthia, Bibhu Prasad; Neware, Rahul

doi:10.1007/s13198-021-01389-0

Cited by 6 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A specific activation function is used after each neuron to limit its output in a specific required range. With different activation functions and different synaptic weight adjustments, it is possible to solve numerous amounts of problems in artificial neural networks [35]. The network usually gets information from the input & output data using training techniques and transfer functions.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Artificial Neural Network Optimized Load Forecasting of Smartgrid using MATLAB

Ganthia,

Mohanty,

Mohapatra

et al. 2023

Control Syst. Optim. Lett.

View full text Add to dashboard Cite

The motivation behind the research is the requirement of error-free load prediction for the power industries in India to assist the planners in making important decisions on unit commitments, energy trading, system security reliability, and optimal reserve capacity. The objective is to produce a desktop version of a personal computer-based complete expert system that can be used to forecast the future load of a smart grid. Using MATLAB, we can provide adequate user interfaces in graphical user interfaces. This paper devotes a study of load forecasting in smart grids, a detailed study of the architecture and configuration of Artificial Neural Network (ANN), Mathematical modeling and implementation of ANN using MATLAB, and a detailed study of load forecasting using the backpropagation algorithm.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

Artificial Neural Network Optimized Load Forecasting of Smartgrid using MATLAB

Ganthia,

Mohanty,

Mohapatra

et al. 2023

Control Syst. Optim. Lett.

View full text Add to dashboard Cite

show abstract

“…In further section the use of various modes of techniques for the adaptive controller described and discussed. [14][20-21][27] [22][23][24][25][26][27][28][29]…”

Section: Wind Energy Conversion Systemsmentioning

confidence: 99%

Radial Basis Function Artificial Neural Network Optimized Stability Analysis in Modified Mathematical Modeled Type-III Wind Turbine System Using Bode Plot and Nyquist Plot

Ganthia¹,

Barik²,

Nayak³

2022

ECS Trans.

View full text Add to dashboard Cite

Stability is the major factor that should be maintained in every power system. To predict and to optimize the nonlinear parameters this research provides a control system transient analysis using Bode plot and Nyquist plot to regulate the stability in wind power generation. The rotor speed should be balanced with respect to the generation of generator power for viable wind power generation. This study introduces a sliding mode controller for controlling wind speed and preserving system stability, and it may be improved using an Artificial Neural Network based Radial Basis Function Neural Network to eliminate nonlinearities induced by changing wind speed. The tip speed ratio approach is utilized in this study to harvest the most power from wind energy. To optimize this TSR method, a PI-RBFN tuned sliding mode controller was utilized to get maximum power while minimizing active power losses. This proposed approach may be used to address nonlinearities in the pitch angle caused by changing wind speed. As a result, the resilience of the redesigned Type-III wind turbine system is investigated using MATLAB simulink in this study. The simulation results are compared to the current DFIG-based modified Type-III wind turbine method.

show abstract