Decentralized voltage control in distribution system using neural network

Toma, Shohei; Senjyu, Tomonobo; Miyazato, Y.; Yona, Atsushi; Tanaka, Kenichi; Kim, Chul‐Hwan

doi:10.1109/pecon.2008.4762729

Cited by 24 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even though controlling the output of distributed generation could improve the voltage profile, voltage regulators and shunt capacitors are the fundamental devices for a utility to realize voltage regulation. In [22], the distributed control is achieved by using a neural network, but the performance of voltage control is dependent on the training data, which will not work when there is sudden change in the system. In [12], a multiagent system (MAS) is implemented for all the voltage control devices and VVC is realized through two-way communication between all intelligent agents.…”

Section: Introductionmentioning

confidence: 99%

Agent-Based Distributed Volt/Var Control With Distributed Power Flow Solver in Smart Grid

Zhang

Flueck

Nguyen³

2016

IEEE Trans. Smart Grid

View full text Add to dashboard Cite

In this paper, a new and completely distributed algorithm for integrated volt/var control is presented. The algorithm is based on a multiagent system, which provides distributed intelligence to smart grid. The voltage regulator and shunt capacitor controlled by intelligent agents collaborate to determine the optimal setting for the entire system. The optimization objectives include maintaining the system voltage profile within a specified range, minimizing system loss, and reducing the switching of shunt capacitors. To achieve these objectives, an updated agentbased distributed power flow solver is used. The proposed algorithm is validated through the modified IEEE 34 node test feeder.Index Terms-Distribution automation (DA), multiagent system (MAS), shunt capacitor, smart grid, volt/var control (VVC), voltage regulator.

show abstract

Section: Introductionmentioning

confidence: 99%

Agent-Based Distributed Volt/Var Control With Distributed Power Flow Solver in Smart Grid

Zhang

Flueck

Nguyen³

2016

IEEE Trans. Smart Grid

View full text Add to dashboard Cite

show abstract

“…By an intelligent management of the active and reactive power of BESS for a stand-alone microgrid, this technique can prevent the stand-alone microgrid from instability and collapse in the presence of violent changes of loads or outage of distributed generations. In a number of studies, the aspect of a managing reference power of distributed generations in the distribution system has been presented [7][8][9]. In [10], the management of BESS power for the typical 4Q-load has been proposed and analyzed.…”

Section: Introductionmentioning

confidence: 99%

RBF neural network-based online intelligent management of a battery energy storage system for stand-alone microgrids

et al. 2016

View full text Add to dashboard Cite

Background: An offline optimization approach based on energy storage management response in a microgrid was not fast and not reliable enough to control and adjust the system efficiently after the loss of the utility grid. Thus, it causes system inefficiency and collapse in the presence of violent changes of loads or outage of distributed generations. To solve such a problem, more real-time management is needed. Any changes in loads/generations should be compensated successfully by a battery energy storage system (BESS) in a short period of time.Methods: This paper presents a new method for the intelligent online management of both active and reactive power of a BESS based on a radial basis function neural network (RBFNN) incorporating particle swarm optimization (PSO) to prevent the stand-alone microgrid from instability and system collapse. BESS is centrally controlled by a controller developed by the proposed RBFNN. PSO is used to determine the optimized active and reactive power at every load/generation changing situation to monitor the effect of system frequency, voltage, and reference power regulation. These optimized power data are then employed as target data for the RBFNN generalization and training process. To enable the online updating of the operating parameters, the proposed RBFNN is implemented in the management process. With an appropriate RBFNN training, the optimum active and reactive power can directly be obtained without the necessity of performing the PSO optimization process at any change of load/generation. Results: The results show that the predictive results of the proposed RBFNN model only slightly differed from the target results based on PSO and have a minimum statistical error compared to the predictive results based on the multilayer perceptron neural network (MLPNN) model. Conclusions: The proposed RBFNN is suitable for the online estimation of the active and reactive power of BESS and can be used for real-time energy storage management as an online controller.

show abstract

“…A decentralized control of distribution voltage with distributed installations, such as step voltage regulator (SVR), load ratio control transformer (LRT), shunt reactor (SHR), static var compensator (SVC), and shunt capacitor (SC) is achieved using neural network [3]. The optimal data for training is created by Genetic Algorithm.…”

Section: Introductionmentioning

confidence: 99%

Coordinated voltage and reactive power control scheme for smart grids with distributed generation

P¹,

Sreejaya²

2015

2015 International Conference on Control Communication &Amp; Computing India (ICCC)

View full text Add to dashboard Cite

The presence of distributed generation (DG) in electrical grids increases the complexity of the regulation process because the injection of power from these sources, which is intrinsically random for generators based on renewable sources, can alter the voltage profiles on the network buses. This requires the design of a suitable methodology aimed at assuring effective grid operation by the optimal coordination of DGs operations with traditional voltage regulating devices. In this paper, a coordinated voltage-control (CVC) scheme for smart grids with distributed generation depending on system conditions is introduced. Based on voltage and reactive power constraints three states are defined in which roles (Master/Slave)of the devices (DGs, OLTCs) are interchanged to allow maximum reactive power reserve for DGs. A mathematical formulation of optimal VAR control problem is performed for all the states in order to minimize the system real power loss. The 12-Bus test system is modified with DGs connected. Application of algorithm to the test system results in reduced system losses and improved voltage profile.

show abstract

Decentralized voltage control in distribution system using neural network

Cited by 24 publications

References 10 publications

Agent-Based Distributed Volt/Var Control With Distributed Power Flow Solver in Smart Grid

Agent-Based Distributed Volt/Var Control With Distributed Power Flow Solver in Smart Grid

RBF neural network-based online intelligent management of a battery energy storage system for stand-alone microgrids

Coordinated voltage and reactive power control scheme for smart grids with distributed generation

Contact Info

Product

Resources

About