Automatic generation control of multi source interconnected power system using adaptive neuro-fuzzy inference system

Sharma, Deepesh

doi:10.4314/ijest.v12i3.7

Cited by 7 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For a 2% change in load, these values are -0.2289 Hz (min) and 15.8983 sec (min), respectively, and at a 1% change in load, these values are further reduced to -0.0647 Hz (min) and 12.2472 sec (min), respectively. Thus, the obtained time response characteristics are smaller compared to the values given in the literature by Deepesh Sharma (2020) andFeng Liu (2017). Hence, the proposed ANFIS controller is more effectively tuned with GRCs than PID and FL controllers.…”

Section: Resultscontrasting

confidence: 64%

Neuro-Fuzzy Intelligent Controller for LFC of a Four-Area Power System

Basavarajappa¹,

Nagaraj²

2022

Int. J. Eng. Tech. Mgmt. Res.

View full text Add to dashboard Cite

In modern complex power systems, the problem of automatic generation control arises due to a sudden increase or decrease in load. This problem leads to instability in the system if the frequency control is not automatic, which may finally lead to system collapse. Hence, automatic control of frequency and tie-line power is significant. This research paper develops and compares the performance of an adaptive neuro-fuzzy inference system (ANFIS) controller with the conventional PID controller and the Takagi-Sugeno-Kang fuzzy logic controller for load frequency control (LFC) of a four-area power system with generation rate constraint (GRC) on turbines. The performance is compared in terms of errors, settling time and maximum undershoot of the frequency deviation for different step load changes using Matlab. The proposed ANFIS controller performs with less peak undershoot of - 0.7374 Hz and a settling time of 27.9823 sec at a 4% change in load. It reduces the steady-state error to zero. Thus, the proposed controller is the most suitable LFC in energy centers. The system parameters are taken from the IEEE press, and EPRI published books.

show abstract

Section: Resultscontrasting

confidence: 64%

Neuro-Fuzzy Intelligent Controller for LFC of a Four-Area Power System

Basavarajappa¹,

Nagaraj²

2022

Int. J. Eng. Tech. Mgmt. Res.

View full text Add to dashboard Cite

show abstract

“…ANFIS (Adaptive Neuro Fuzzy Inference System) merupakan metode penggabungan dari metode Fuzzy Inference System (FIS) dan jaringan saraf Tiruan (JST) yang dapat memetakan nilai masukan menuju nilai keluaran berdasarkan logika Fuzzy sesuai dengan bentuk aturan Fuzzy untuk mendapatkan efektivitas yang tinggi karena prediksi tingkat kesalahannya kecil dengan tahapan pengambilan data,pengolahan data, perancangan sistem ANFIS, pelatihan ANFIS, uji validasi, dan analis hasil [10] [11].…”

Section: Adaptive Neuro-fuzzy Inference System (Anfis)unclassified

Penerapan Kontroler ANFIS untuk Load Frequency Control

Dewanto,

Bachtiar,

Setiawan

et al. 2023

bees

View full text Add to dashboard Cite

Load Frequency Control (LFC) is a system that works as a unit with the boiler-turbine-generator system which functions to maintain a frequency of 50 HZ by giving control to the governor system at the power plant when the peak load position results in a decrease in frequency, later LFC instructs the turbine governor to open a valve to drain the steam generated from the boiler system. In this study, we compared the performance of two controllers on LFC, namely PID and ANFIS through Matlab simulations. The simulation results show that the Setlling Time of the ANFIS Mamounia control is 76% faster than the PID control. ANFIS control can respond to changes in load to steady state frequency conditions with an error of 0.6% which is more effective than the PID control.

show abstract

“…This FIS can be signified in a parametric form, which allows its constituents to be tuned by neural networks. When this is done, the fuzzy system develops a neuro-fuzzy system (3) . To design the AGC controller, the inputs are the Area Control Error (ACE) and its derivative (d(ACE)/dt).…”

Section: Adaptive Neuro-fuzzy Controllermentioning

confidence: 99%

“…A detailed literature review on LFC is described. Adaptive neural network (ANN) controller for hydro thermal power plant is suggested and its implementation for improving ACE is given in (3) , Fuzzy logic controller (FLC) effectiveness for Interconnected Power system (IPS) having multi-source such has hydro, gas and thermal are illustrated in (4) . Hybrid GSA-PSO Technique is proposed for tuning the gain of PID controller applied for AGC in Interconnected Power Systems having Constant Generation Rate constraints (GRC) is demonstrated in (5) .…”

Section: Introductionmentioning

confidence: 99%

Application of Intelligent controller For Load Frequency Control for Multi-Area Multi-Source Power System

Nath,

Sambariya

2023

IJST

View full text Add to dashboard Cite

Objectives: This paper demonstrates the application of an artificial intelligence (AI) based controller for load frequency control for a two-area multi-source interconnected power system. Fuzzy PID controller parameters area Tuned using Artificial BEE colony (ABC) algorithm. The FLC-PID performance is simulated and verified using MATLAB. Method: For evaluating LFC Problem two different systems are considered. The first system consists of four units of the non-reheat thermal power system. The analysis is further extended by adding a hydropower plant unit with a non-reheat thermal unit. A perturbation of 0.01 P.U in step load form is considered for each area for the automatic generation control (AGC) study. Finding: The suggested controller Fuzzy-PID robustness is observed by varying operating loading conditions and plant parameters for a wide range. The variation in time constant (seconds) of system parameters is carried out in a range of +75% to -75%. The objective is to improve the steady-state error of the tie-line power deviation and frequency variation of an interlinked power plant. By the suggested approach, the variation in frequency and tie-line power is minimized to a great extent. Novelty: Artificial BEE colony (ABC) algorithm is effective. The performance of the adapted controller is compared with the previously published tuned PID controller based on Settling Time (ST) and ITAE Error. The proposed controller shows superiority. It is observed that the proposed technique can handle abrupt amplification of load (PU) and variation in system parameters like the governor, and turbine time constant. Eigenvalue analysis is also carried out. The result of the Fuzzy-PID controller is also compared with the proposed-FOPID and Proposed-ANFIS controller. The parameter of fractional order is also optimized by the ABC algorithm. For simulation, MATLAB 2016 @ Version is taken.

show abstract

Automatic generation control of multi source interconnected power system using adaptive neuro-fuzzy inference system

Cited by 7 publications

References 15 publications

Neuro-Fuzzy Intelligent Controller for LFC of a Four-Area Power System

Neuro-Fuzzy Intelligent Controller for LFC of a Four-Area Power System

Penerapan Kontroler ANFIS untuk Load Frequency Control

Application of Intelligent controller For Load Frequency Control for Multi-Area Multi-Source Power System

Contact Info

Product

Resources

About