Artificial Neural Network based Three Phase Shunt Active Power Filter

Artificial Neural Network based Three Phase Shunt Active Power Filter


This work describes artificial neural network (ANN) based control algorithm for three phase three wire shunt active power filter (SAPF) to compensate harmonics and improve power quality. System consists of three phase insulated gate bipolar transistors IGBT based current controlled voltage source inverter (CC-VSI), series coupling inductor and self supported DC bus. Increasing application of non-linear loads causes power quality problem. SAPF is one of the possible configurations to improve power quality. Traditional SAPF have PLL based unit template generator for extraction of fundamental signal. Traditional PLL needs to be tuned to obtain optimal performance for frequency estimation. It requires initial assumptions for fundamental frequency and minimum frequency. With varying frequency, it can’t be dynamically tuned for optimal performance. A new ANN based fundamental extraction based on Lavenberg Marquardt back propagation algorithm is proposed. Proposed SAPF is modeled in Simulink environment. Simulated results show the capability of proposed system.



  1. Shunt Active Power Filter
  2. Artificial Neural Networks
  3. Indirect Current Control Technique
  4. Power Quality




configuration block with SAPF

Fig.1. Proposed system configuration block with SAPF



Fig.2. Source voltages


Fig.3. Unbalanced load voltages


Fig.4. Unbalanced load currents


Fig.5. Simulation result for proposed system under non linear with

unbalance load condition


Fig.6. DC link voltage

Fig.7. Active power

Fig.8. Reactive power

Fig.9. Power factor

Fig.10. Harmonic spectrum of load current before compensation for three phase SAPF with non linear load

Fig.11. Harmonic spectrum of source currents (phase a, phase b phase c respectively) after compensation for ANN based three phase APF with non linear load

Fig.12. Harmonic spectrum of source currents (phase a) after compensation for ANN based three phase APF with non linear load with unbalance



ANN based phase-locking scheme has been proposed in this paper to control three phase-three wire shunt APFs. Widrow-Hoff weights updating algorithm has been incorporated to reduce calculation time in estimation of harmonic components. To validate effectiveness of proposed approach for real-time applications, indirect current control theory based controller has been developed. Design parameters of power circuit and control circuit have been calculated and robustness of proposed system has been established with Matlab/Simulink. Simulation result and spectral response show that, obtained source current THDs is below 5% as prescribed by IEEE-519 standard. Dynamic performance of proposed approach has been found satisfactory under sudden change in load and frequency.



  • Kumar and D.K. Palwalia, “Decentralized autonomous hybrid renewable power generation”, Journal of Renew. Energy, pp. 1-18, 2015.
  • Dai, T. Huang, and N. Lin, “Design of single-phase shunt active power filter based on ANN”, IEEE Int. Symp. on Ind. Electron., pp. 770-774, 2007.
  • Akagi, Y. Kanazawa, and A. Nabae, “Instantaneous reactive power compensators comprising switching devices without energy storage components,” IEEE Trans. Ind. Applicat., vol. IA-20, pp. 625–630, 1984.
  • Akagi and A. Nabae, “The p-q theory in three-phase systems under nonsinusoidal conditions,” Eur. Trans. Elect. Power Eng., vol. 3, no. 1, pp. 27–31, 1993.
  • Akagi and H. Fujita, “A new power line conditioner for harmonic compensation in power systems,” IEEE Trans. Power Delivery, vol. 10, pp. 1570–1575, 1995.

Leave a Reply

Your email address will not be published. Required fields are marked *