IRJET- Power Quality Improvement by DSTATCOM Control by Artificial Neural Network Technique
0 likes25 views
This document presents a method for using an artificial neural network to control a DSTATCOM (Distribution Static Compensator) to improve power quality in a distribution system. A DSTATCOM is connected to the distribution system and used to compensate for power quality issues like voltage variations caused by nonlinear loads. An instantaneous symmetrical component theory is used to generate reference supply currents. Terminal voltages are compared to a reference to produce an error signal that is fed into an artificial neural network. The neural network output controls the DSTATCOM to inject compensating currents and regulate the voltage at the point of common coupling, improving power quality. Simulation results demonstrate the DSTATCOM is able to maintain sinusoidal voltages during load changes that previously caused undervoltage issues
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 05 Issue: 12 | Dec 2018 www.irjet.net p-ISSN: 2395-0072
© 2018, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 1397
Power Quality Improvement by DSTATCOM Control by Artificial Neural
Network Technique
Anand Chauhan1, Amit Goswami2
1P.G. Student, Dept. Of Electrical & Electronics Engineering, DIMAT Raipur, Chhattisgarh, India
2Professor, Dept. Of Electrical & Electronics Engineering, DIMAT Raipur, Chhattisgarh, India
---------------------------------------------------------------------***----------------------------------------------------------------------
Abstract – Distribution system faces various types of
power quality problem such as voltage, Current unbalance,
voltage variations also harmonics generated by the non
linear loads. Therefore it’s necessary to design a system that
compensates power quality problems. In this paper shunt
compensating device DSTATCOM (Distribution Static
Converter) control by artificial neural network is used to
eliminate power quality problem.
Key Words: Power Quality, DSTATCOM, Linear and Non
Linear Loads, PWM, Artificial Neural Network (ANN), ISCT,
VSC.
1. INTRODUCTION
In present era, many types of load are working in
domestic, commercial as well as in industrial system with
power quality problems. Non linear loads are working on
precise control on system’s waveform for their operation.
When non linear loads are switching on causes harmonics
generated and enter into the system. Harmonics are the
integral multiple of fundamental frequency. Its need to
design a compensating system that eliminate above power
quality [1] problem. When any load phases off and heavy
loads are connected causes source voltage are disturbed
DSTATCOM (Distribution Static compensator) is used to
compensate harmonics by extracting it from the loads by
proposed control technique.
2. SYSTEM DESIGN
In distribution system [2] where three phase linear and
non linear loads are connected with three phase AC 415 V
50 Hz power supply through source impedance.
DSTATCOM is connected at PCC (Point of Common
Coupling) through coupling inductor [2], [5], [9]. Shown in
fig. 1.
3. PROPOSED CONTROL DESIGN
In control design shown in fig. 2 instantaneous
symmetrical component theory (ISCT) [2] is used for
generating the reference supply current. In this technique,
PCC phase voltage, average load power and average power
factor angle is used. Here average load are estimated by
instantaneous load current and PCC phase voltage.
Instantaneous load current with PCC (Point of Common
Coupling) phase voltage generate instantaneous load
power. This instantaneous load power is passes to LPF
(Low Pass Filter). Instantaneous load power has both ac
and DC power component. After LPF, average load powers
(PLdc) are extracted [2].
Fig -1: Distribution System with DSTATCOM
(1)
(2)
Instantaneous active power of load which have PLac is
the pulsating ripple component. PLdc is the average
power consume by loads.
Reference supply current are generated [2] by using eq.
(3), (4) & (5),](https://image.slidesharecdn.com/irjet-v5i12261-190107054454/85/IRJET-Power-Quality-Improvement-by-DSTATCOM-Control-by-Artificial-Neural-Network-Technique-1-320.jpg)
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 05 Issue: 12 | Dec 2018 www.irjet.net p-ISSN: 2395-0072
© 2018, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 1398
⌈ ⌉
(3)
⌈ ⌉
(4)
⌈ ⌉
(5)
Vsa, Vsb & Vsc is PCC phase voltage.
⌊ ⌋ is defined as,
⌊ ⌋ ∑ (6)
Now, calculate terminal voltage of PCC phase voltage [2],
[3] by eq. (7),
⁄ (7)
Fig-2: Proposed Control Design
After that this terminal voltage is apply to LPF (Low Pass
Filter) to eliminate ripples present on it during non linear
load switching. Then compared with reference PCC
terminal voltage. After the comparison error is generated
and this is goes to artificial neural network (ANN) [7]
where it is regulated to get desired output. Artificial neural
network have input layer, three hidden layer and output
layer shown in fig. 3. Hidden layer is activated by logistic
sigmoid transfer function [7] and output is activated by
linear transfer function [7]. Output of ANN is the value of
β. Compute reference current and compared with sensed
supply current to generate gate pulse for switching of VSC
(Voltage Source Converter) of DSTATCOM.
Fig -3: Artificial Neural Network Architecture
4. RESULT & DISCUSSIONS
Distribution system with DSTATCOM is simulated firstly
without compensation when load phase “c” is off during
0.5 second to 0.8 second where source voltage having
short duration RMS variations [1] and second one heavy
load is connected to the system at the duration of 1.4
second to 1.8 second. Due to which source voltage have
undervoltage power quality issues [1]. Source Voltage and
source current without compensation shown in fig. 4 & fig.
5,
Fig -4: Source Voltage without Compensation](https://image.slidesharecdn.com/irjet-v5i12261-190107054454/85/IRJET-Power-Quality-Improvement-by-DSTATCOM-Control-by-Artificial-Neural-Network-Technique-2-320.jpg)
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 05 Issue: 12 | Dec 2018 www.irjet.net p-ISSN: 2395-0072
© 2018, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 1399
Fig -5: Source Current without Compensation
Fig -6: Compensating Current
Fig -7: Source Voltage with compensation
Then applying DSTATCOM, power quality issues during
0.5 second to 0.8 second and 1.4 second to 1.8 second are
compensate by compensating current shown in fig. 6
provided by DSTATCOM where source voltage are become
sinusoidal with balanced waveform shown in fig. 7.
5. CONCLUSION
Distribution system with DSTATCOM controlled by
proposed control technique having satisfactory
performance. Proposed control technique work
satisfactory with fast response on power quality issues.
REFERENCES
[1] IEEE Recommended Practice for Monitoring Electric
Power Quality, IEEE Std. 1159, 2009.
[2] B. Singh, A. Chandra, and K. Al-Haddad, “Power
quality: problems and mitigation techniques,” John
Wiley & Sons Ltd., U.K, 2015.
[3] B. Singh and S. Kumar, “Modified power balance
theory for control of DSTATCOM,” in Proc. Joint Int.
Conf. Power Electronics., Drives Energy System Power
India, pp. 1–8, 2010
[4] A. Ghosh and G. Ledwich, “Load compensating
DSTATCOM in weak AC systems.” IEEE Trans. on Pow.
Deliv., vol. 18, no. 4, october 2003
[5] C. Kumar and M. K. Mishra, “Operation and control of
an improved performance interactive DSTATCOM,”
IEEE Trans. Ind. Electron., vol. 62, no. 10, pp. 6024-
6034, Oct. 2015
[6] IEEE Recommended Practices and Requirement for
Harmonic Control on Electric Power System, IEEE Std.
519, 1992
[7] S. N. Sivanandam and S.N.Deepa, Principles of soft
computing, John Wiley & Sons, 2007
[8] M. Badoni, A. Singh and B. Singh, “Adaptive neuro
fuzzy inference system least-mean-square-based
control algorithm for DSTATCOM,” IEEE Trans. Ind.
Inform. pp. 483–492, 2016
[9] B. Singh, P. Jayaprakash, D.P. Kothari, A. Chandra, and
K. Al Haddad, “Comprehensive study of DSTATCOM
configurations,” IEEE Trans. Ind. Inform., vol. 10, no. 2,
pp. 854-870 , May 2014
[10] A. Ghosh and G. Ledwich, “Power quality enhancement
using custom power devices,” Springer International
Edition, Delhi, 2009](https://image.slidesharecdn.com/irjet-v5i12261-190107054454/85/IRJET-Power-Quality-Improvement-by-DSTATCOM-Control-by-Artificial-Neural-Network-Technique-3-320.jpg)
IRJET- Power Quality Improvement by DSTATCOM Control by Artificial Neural Network Technique
- 1. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 05 Issue: 12 | Dec 2018 www.irjet.net p-ISSN: 2395-0072 © 2018, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 1397 Power Quality Improvement by DSTATCOM Control by Artificial Neural Network Technique Anand Chauhan1, Amit Goswami2 1P.G. Student, Dept. Of Electrical & Electronics Engineering, DIMAT Raipur, Chhattisgarh, India 2Professor, Dept. Of Electrical & Electronics Engineering, DIMAT Raipur, Chhattisgarh, India ---------------------------------------------------------------------***---------------------------------------------------------------------- Abstract – Distribution system faces various types of power quality problem such as voltage, Current unbalance, voltage variations also harmonics generated by the non linear loads. Therefore it’s necessary to design a system that compensates power quality problems. In this paper shunt compensating device DSTATCOM (Distribution Static Converter) control by artificial neural network is used to eliminate power quality problem. Key Words: Power Quality, DSTATCOM, Linear and Non Linear Loads, PWM, Artificial Neural Network (ANN), ISCT, VSC. 1. INTRODUCTION In present era, many types of load are working in domestic, commercial as well as in industrial system with power quality problems. Non linear loads are working on precise control on system’s waveform for their operation. When non linear loads are switching on causes harmonics generated and enter into the system. Harmonics are the integral multiple of fundamental frequency. Its need to design a compensating system that eliminate above power quality [1] problem. When any load phases off and heavy loads are connected causes source voltage are disturbed DSTATCOM (Distribution Static compensator) is used to compensate harmonics by extracting it from the loads by proposed control technique. 2. SYSTEM DESIGN In distribution system [2] where three phase linear and non linear loads are connected with three phase AC 415 V 50 Hz power supply through source impedance. DSTATCOM is connected at PCC (Point of Common Coupling) through coupling inductor [2], [5], [9]. Shown in fig. 1. 3. PROPOSED CONTROL DESIGN In control design shown in fig. 2 instantaneous symmetrical component theory (ISCT) [2] is used for generating the reference supply current. In this technique, PCC phase voltage, average load power and average power factor angle is used. Here average load are estimated by instantaneous load current and PCC phase voltage. Instantaneous load current with PCC (Point of Common Coupling) phase voltage generate instantaneous load power. This instantaneous load power is passes to LPF (Low Pass Filter). Instantaneous load power has both ac and DC power component. After LPF, average load powers (PLdc) are extracted [2]. Fig -1: Distribution System with DSTATCOM (1) (2) Instantaneous active power of load which have PLac is the pulsating ripple component. PLdc is the average power consume by loads. Reference supply current are generated [2] by using eq. (3), (4) & (5),
- 2. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 05 Issue: 12 | Dec 2018 www.irjet.net p-ISSN: 2395-0072 © 2018, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 1398 ⌈ ⌉ (3) ⌈ ⌉ (4) ⌈ ⌉ (5) Vsa, Vsb & Vsc is PCC phase voltage. ⌊ ⌋ is defined as, ⌊ ⌋ ∑ (6) Now, calculate terminal voltage of PCC phase voltage [2], [3] by eq. (7), ⁄ (7) Fig-2: Proposed Control Design After that this terminal voltage is apply to LPF (Low Pass Filter) to eliminate ripples present on it during non linear load switching. Then compared with reference PCC terminal voltage. After the comparison error is generated and this is goes to artificial neural network (ANN) [7] where it is regulated to get desired output. Artificial neural network have input layer, three hidden layer and output layer shown in fig. 3. Hidden layer is activated by logistic sigmoid transfer function [7] and output is activated by linear transfer function [7]. Output of ANN is the value of β. Compute reference current and compared with sensed supply current to generate gate pulse for switching of VSC (Voltage Source Converter) of DSTATCOM. Fig -3: Artificial Neural Network Architecture 4. RESULT & DISCUSSIONS Distribution system with DSTATCOM is simulated firstly without compensation when load phase “c” is off during 0.5 second to 0.8 second where source voltage having short duration RMS variations [1] and second one heavy load is connected to the system at the duration of 1.4 second to 1.8 second. Due to which source voltage have undervoltage power quality issues [1]. Source Voltage and source current without compensation shown in fig. 4 & fig. 5, Fig -4: Source Voltage without Compensation
- 3. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 05 Issue: 12 | Dec 2018 www.irjet.net p-ISSN: 2395-0072 © 2018, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 1399 Fig -5: Source Current without Compensation Fig -6: Compensating Current Fig -7: Source Voltage with compensation Then applying DSTATCOM, power quality issues during 0.5 second to 0.8 second and 1.4 second to 1.8 second are compensate by compensating current shown in fig. 6 provided by DSTATCOM where source voltage are become sinusoidal with balanced waveform shown in fig. 7. 5. CONCLUSION Distribution system with DSTATCOM controlled by proposed control technique having satisfactory performance. Proposed control technique work satisfactory with fast response on power quality issues. REFERENCES [1] IEEE Recommended Practice for Monitoring Electric Power Quality, IEEE Std. 1159, 2009. [2] B. Singh, A. Chandra, and K. Al-Haddad, “Power quality: problems and mitigation techniques,” John Wiley & Sons Ltd., U.K, 2015. [3] B. Singh and S. Kumar, “Modified power balance theory for control of DSTATCOM,” in Proc. Joint Int. Conf. Power Electronics., Drives Energy System Power India, pp. 1–8, 2010 [4] A. Ghosh and G. Ledwich, “Load compensating DSTATCOM in weak AC systems.” IEEE Trans. on Pow. Deliv., vol. 18, no. 4, october 2003 [5] C. Kumar and M. K. Mishra, “Operation and control of an improved performance interactive DSTATCOM,” IEEE Trans. Ind. Electron., vol. 62, no. 10, pp. 6024- 6034, Oct. 2015 [6] IEEE Recommended Practices and Requirement for Harmonic Control on Electric Power System, IEEE Std. 519, 1992 [7] S. N. Sivanandam and S.N.Deepa, Principles of soft computing, John Wiley & Sons, 2007 [8] M. Badoni, A. Singh and B. Singh, “Adaptive neuro fuzzy inference system least-mean-square-based control algorithm for DSTATCOM,” IEEE Trans. Ind. Inform. pp. 483–492, 2016 [9] B. Singh, P. Jayaprakash, D.P. Kothari, A. Chandra, and K. Al Haddad, “Comprehensive study of DSTATCOM configurations,” IEEE Trans. Ind. Inform., vol. 10, no. 2, pp. 854-870 , May 2014 [10] A. Ghosh and G. Ledwich, “Power quality enhancement using custom power devices,” Springer International Edition, Delhi, 2009