scholarly journals Particle Swarm Optimization- Artificial Neural Network For Power System Load Flow

2012 ◽  
pp. 180-189
Author(s):  
Avnish Singh ◽  
Shishir Dixit ◽  
L. Srivastava
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Power System ◽  
Power Flow ◽  
Flow Problem ◽  
Particle Swarm ◽  
Load Flow ◽  
Feed Forward Neural Network ◽  
Swarm Optimization ◽  
Bus Voltage

Load flow study is done to determine the power system static states (voltage magnitudes and voltage angles) at each bus to find the steady state working condition of a power system. It is important and most frequently carried out study performed by power utilities for power system planning, optimization, operation and control. In this paper a Particle Swarm Optimization Neural Network (PSO-ANN) is proposed to solve load flow problem under different loading/ contingency conditions for computing bus voltage magnitudes and angles of the power system. A multilayered feed-forward neural network is trained by using PSO technique. The results show the effectiveness of the proposed PSO-ANN based approach for solving power flow problem having different loading conditions and single-line outage contingencies in IEEE 14 bus system

Particle Swarm Optimization in Image Processing of Power Flow Learning Distribution

2020 ◽  
Author(s):  
Chuanchao Huang
Keyword(s):  
Particle Swarm Optimization ◽  
Power System ◽  
Power Flow ◽  
Integrated Control ◽  
Particle Swarm ◽  
Heating System ◽  
Swarm Optimization ◽  
Power Adjustment ◽  
The Mathematical Model ◽  
Tie Line

Abstract In order to realize the coordination and integration optimization of the power system itself, this paper constructed the mathematical model of the hybrid power system and solved the multi-objective optimization problem of the heating system through the optimized particle swarm optimization algorithm. Based on the back-to-back VSC-HVDC grid-connected composite system, this paper studied the integrated control strategy of the device to achieve the simultaneous parallel and tie line currents. At the same time, this paper simplified and improved the proposed disassembly criteria for grid-connected composite devices and integrated them into the grid-connected composite device. In addition, on this basis, the integrated control of the three functions of de-listing, juxtaposition and tie line power adjustment of the same device was further studied. Simulation studies show that the proposed algorithm has certain effects and can provide theoretical reference for subsequent related research.

Power Management System of a Particle Swarm Optimization Controlled Grid Integrated Hybrid PV/WIND/FC/Battery Distributed Generation System

2021 ◽  
Author(s):  
T. Praveen Kumar ◽  
N. Subrahmanyam ◽  
Maheswarapu Sydulu
Keyword(s):  
Particle Swarm Optimization ◽  
Power System ◽  
Power Management ◽  
Distributed Generation ◽  
Power Flow ◽  
Reactive Power ◽  
Particle Swarm ◽  
System Control ◽  
Swarm Optimization ◽  
Power System Control

In this manuscript, the Power management of grid integrated hybrid distributed generation (DG) system with Particle swarm optimization (PSO) algorithm is proposed. The hybrid DG system combines with photovoltaic, wind turbine, fuel cell, battery. Depending on the use of hybrid sources and the changes of power production the variation of power can occurs in the DG system. The major purpose of the proposed method restrains the power flow (PF) on active with reactive power between the source and grid side. In the power system control the proposed PSO method is utilized to maximize the active with reactive PF and the controllers. The proposed method interact the load requirement energy and maintain the load sensitivity due to charging and discharging battery control. In the DG system, the proposed PSO method allows maximum power flow. To assess the PF, the constraints of equality and inequality have been evaluated and they are utilized to determine the accessibility of renewable energy source (RES), electricity demand, and the storage elements of charge level. The protection of the power system is enhanced based on the proposed PSO method. Additionally, for retaining a stable output the renewable power system and battery is used. The proposed method is activated in MATLAB/Simulink working platform and the efficiency is likened with other existing methods.

Particle Swarm Optimization Neural Network for Flow Prediction in Vegetative Channel

2013 ◽  
Vol 22 (4) ◽  
pp. 487-501
Author(s):  
Anjaneya Jha ◽  
Bimlesh Kumar
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Hybrid Model ◽  
Particle Swarm ◽  
Model Performance ◽  
Analytical Form ◽  
Performance Criteria ◽  
Feed Forward Neural Network ◽  
Swarm Optimization ◽  
Flow Prediction

AbstractFlow prediction in a vegetated channel has been extensively studied in the past few decades. A number of equations that essentially differ from each other in derivation and form have been developed. Because the process is extremely complex, getting the deterministic or analytical form of the process phenomena is too difficult. Hybrid neural network model (combining particle swarm optimization with neural network) is particularly useful in modeling processes where an adequate knowledge of the physics is limited. This hybrid model is presented here as a complementary tool to model channel flow–vegetation interactions in submerged vegetation conditions. The hybrid model is used to overcome the local minima limitations of a feed-forward neural network. The prediction capability of model has been found to be better than past empirical predictors. The model developed herein showed significantly better results in several model performance criteria compared with empirical models.

Sign in / Sign up

Export Citation Format

Share Document