# An Integrated Seamless Control Strategy for Distributed Generators Based on a Deep Learning Artificial Neural Network

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

- No transition between different control schemes is required.
- The strategy enables the DG to be a local load-follower.
- It eliminates harmonics from the utility current in the case of a non-linear local load.
- Moreover, using the DL-ANN controller allows the DG system to overcome sudden changes without the need to change the controller’s parameters.

## 2. System Model

#### 2.1. Power Stage

#### 2.2. Control Stage

_{Gq}. The direct and quadrature projections of the VSI reference currents, i

_{VSId}* and i

_{VSIq}*, are the controlled variables that are transformed to the three-phase reference frame afterward. Eventually, the VSI gate signals are generated using the hysteresis current control (HCC) switching scheme, due to its fast dynamics and simplicity [32].

_{cd}* is set to the highest permitted load voltage, Vmax, which is much higher than the real voltage, v

_{cd}. Consequently, the proposed controller, based on the DL-ANN, will force the limiter to generate i

_{Gd}*, the upper setting of the limiter. Hence, the deactivation of the outer voltage loop occurs. In addition, by setting the reference quadrature-axis voltage v

_{cq}* to zero, where v

_{cq}is made zero by the PLL, it causes a zero output from the P compensator. Figure 2 illustrates that only the inner current loop will be responsible for generating the reference currents of the VSI, i

_{VSId}* and i

_{VSIq}*, to demonstrate grid-following during the grid-connection mode. The local load is fed from the DG, which is represented as a current source, while the grid receives the rest of the generated power. The injected powers to the grid, P

_{g}and Q

_{g}, are given by:

_{g}= 3/2 × (v

_{cd}× i

_{Gd}+ v

_{cq}× i

_{Gq}) = 3/2 v

_{cd}× i

_{Gd}

_{g}= 3/2 × (v

_{cq}× i

_{Gd}− v

_{cd}× i

_{Gq}) = −3/2 v

_{cd}× i

_{Gq}

_{Gd}and i

_{Gq}are the grid current projections in the d-q axes. i

_{Gd}should be positive and i

_{Gq}should be negative, according to (1) and (2), to supply power to the grid.

_{Gd}and i

_{Gq}to zero will occur. Moreover, v

_{cd}rises due to an increase in i

_{Ld}and a reduction in i

_{Lq}, according to the load voltage equations, as follows:

_{cd}= Rs × i

_{Ld}− Xs × i

_{Lq}

_{cq}= Rs × i

_{Lq}+ Xs × i

_{Ld}

_{cd}* is set to the maximum rated phase voltage, that is, roughly 0.3 KV. During islanding, the outer voltage loop is activated to regulate the load voltage at v

_{cd}*, while i

_{Gq}* is set to zero, as illustrated in Figure 3. The frequency is fixed at its value when islanding is initiated and the PLL is not working in this mode. Thus, the local load is supplied from the DG, which can be represented as a voltage source that is grid-forming in this mode. It is clear that this approach guarantees a smooth and seamless transfer between the different modes of operation, without the need for a control strategy switching between two different control schemes.

_{Ld}, and i

_{Lq}, and feeding these measurements through a forward loop to form the VSI reference current, allowing the DG to become a local load follower. Thus, the harmonics from the utility current are mitigated and the reference tracking is much more accurate.

## 3. The Proposed DL-ANN-Based PID Controller

_{cd}* and v

_{cd}., the error accumulation ΔT$\sum _{i=0}^{k}e\left(i\right)$, and the error rate of change [$\frac{e\left(k\right)-e\left(k-1\right)}{\Delta T}]$. The training data is sampled from a system model from the PSCAD/EMTDC software [33], where an adaptive PI controller, based on (SMAPA) [34], is used in place of the proposed DL-ANN. The training process flowchart is presented in Figure 4.

^{−10}; the coefficient of correlation ($R$) is near unity, verifying that the DL-ANN is well-trained.

## 4. Simulation Results

#### 4.1. Mode of Grid Connection

_{Gq}* is set to zero, a unity power factor is achieved.

#### 4.2. Islanding Transition

_{cd}will also follow its reference voltage, v

_{cd}*, within the permitted tolerances, as in Figure 8c. The voltage regulation error, which is the input to the DL-ANN controller, is displayed in Figure 8d.

#### 4.3. Grid-Connected Transition

#### 4.4. Comparison

## 5. Conclusions

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Conflicts of Interest

## References

- Jayaram, J.; Srinivasan, M.; Prabaharan, N.; Senjyu, T. Design of Decentralized Hybrid Microgrid Integrating Multiple Renewable Energy Sources with Power Quality Improvement. Sustainability
**2022**, 14, 7777. [Google Scholar] [CrossRef] - Wang, J.; Li, D.; Lv, X.; Meng, X.; Zhang, J.; Ma, T.; Pei, W.; Xiao, H. Two-Stage Energy Management Strategies of Sustainable Wind-PV-Hydrogen-Storage Microgrid Based on Receding Horizon Optimization. Energies
**2022**, 15, 2861. [Google Scholar] [CrossRef] - Pattabiraman, D.; Lasseter, R.H.; Jahns, T.M. Comparison of grid following and grid forming control for a high inverter penetration power system. In Proceedings of the IEEE Power & Energy Society General Meeting in 2018 (PESGM), Portland, OR, USA, 5–10 August 2018; pp. 1–5. [Google Scholar]
- Omar, O.A.; Badra, N.M.; Attia, M.A. Enhancement of on-grid pv system under irradiance and temperature variations using new optimized adaptive controller. Int. J. Electr. Comput. Eng.
**2018**, 8, 2650. [Google Scholar] [CrossRef] - González, I.; Calderón, A.J.; Portalo, J.M. Innovative multi-layered architecture for heterogeneous automation and monitoring systems: Application case of a photovoltaic smart microgrid. Sustainability
**2021**, 13, 2234. [Google Scholar] [CrossRef] - Zeng, Q.; Chang, L. Study of advanced current control strategies for three-phase grid-connected pwm inverters for distributed generation. In Proceedings of the 2005 IEEE Conference on Control Applications, Toronto, ON, Canada, 28–31 August 2005; pp. 1311–1316. [Google Scholar]
- Kim, H.; Yu, T.; Choi, S. Indirect current control algorithm for utility interactive inverters in distributed generation systems. IEEE Trans. Power Electron.
**2008**, 23, 1342–1347. [Google Scholar] - Li, X.; Zhang, H.; Shadmand, M.B.; Balog, R.S. Model predictive control of a voltage-source inverter with seamless transition between islanded and grid-connected operations. IEEE Trans. Ind. Electron.
**2017**, 64, 7906–7918. [Google Scholar] [CrossRef] - Liu, Z.; Liu, J.; Zhao, Y. A unified control strategy for three-phase inverter in distributed generation. IEEE Trans. Power Electron.
**2013**, 29, 1176–1191. [Google Scholar] - Singh, M.; Khadkikar, V.; Chandra, A.; Varma, R.K. Grid interconnection of renewable energy sources at the distribution level with power-quality improvement features. IEEE Trans. Power Deliv.
**2010**, 26, 307–315. [Google Scholar] [CrossRef] - Rodriguez, P.; Luna, A.; Munoz-Aguilar, R.S.; Etxeberria-Otadui, I.; Teodorescu, R.; Blaabjerg, F. A stationary reference frame grid synchronization system for three-phase grid-connected power converters under adverse grid conditions. IEEE Trans. Power Electron.
**2011**, 27, 99–112. [Google Scholar] [CrossRef] - Marei, M.I. A unified control strategy based on phase angle estimation for matrix converter interface system. IEEE Syst. J.
**2012**, 6, 278–286. [Google Scholar] [CrossRef] - Gao, F.; Iravani, M.R. A control strategy for a distributed generation unit in grid-connected and autonomous modes of operation. IEEE Trans. Power Deliv.
**2008**, 23, 850–859. [Google Scholar] - Yu, T.; Choi, S.; Kim, H. Indirect current control algorithm for utility interactive inverters for seamless transfer. In Proceedings of the 2006 37th IEEE Power Electronics Specialists Conference, Jeju, Korea, 18–22 June 2006; pp. 1–6. [Google Scholar]
- Kwon, J.; Yoon, S.; Choi, S. Indirect current control for seamless transfer of three-phase utility interactive inverters. IEEE Trans. Power Electron.
**2012**, 27, 773–781. [Google Scholar] [CrossRef] - Lim, K.; Choi, J. PR based indirect current control for seamless transfer of grid-connected inverter. In Proceedings of the 2016 IEEE 8th International Power Electronics and Motion Control Conference (IPEMC-ECCE Asia), Hefei, China, 22–26 May 2016; pp. 3749–3755. [Google Scholar]
- Kim, K.; Kim, H.J.; Shin, D.; Lee, J.P.; Kim, T.J.; Yoo, D.W. A novel seamless transfer control strategy for wide range load. In Proceedings of the 2016 IEEE Energy Conversion Congress and Exposition (ECCE), Milwaukee, WI, USA, 18–22 September 2016; pp. 1–5. [Google Scholar]
- Mohamed, Y.A.R.I.; Radwan, A.A. Hierarchical control system for robust microgrid operation and seamless mode transfer in active distribution systems. IEEE Trans. Smart Grid
**2011**, 2, 352–362. [Google Scholar] [CrossRef] - Jin, C.; Gao, M.; Lv, X.; Chen, M. A seamless transfer strategy of islanded and grid-connected mode switching for microgrid based on droop control. In Proceedings of the 2012 IEEE Energy Conversion Congress and Exposition (ECCE), Raleigh, NC, USA, 15–20 September 2012; pp. 969–973. [Google Scholar]
- Mansour, A.M.; Arafa, O.M.; Marei, M.I.; Abdelsalam, I.; Aziz, G.A.A.; Sattar, A.A. Hardware-in-the-loop testing of seamless interactions of multi-purpose grid-tied PV inverter based on SFT-PLL control strategy. IEEE Access
**2021**, 9, 123465–123483. [Google Scholar] [CrossRef] - Meng, X.; Liu, Z.; Liu, J.; Wu, T.; Wang, S.; Liu, B. A seamless transfer strategy based on special master and slave DGs. In Proceedings of the 2017 IEEE 3rd International Future Energy Electronics Conference and ECCE Asia (IFEEC 2017-ECCE Asia), Kaohsiung, Taiwan, 3–7 June 2017; pp. 1553–1558. [Google Scholar]
- Zhang, W.; Liu, H.; Wang, W.; Loh, P.C. Seamless transfer scheme for parallel PV inverter system. IET Power Electron.
**2020**, 13, 1051–1058. [Google Scholar] [CrossRef] - Amin, M.; Zhong, Q.C. Resynchronization of distributed generation based on the universal droop controller for seamless transfer between operation modes. IEEE Trans. Ind. Electron.
**2019**, 67, 7574–7582. [Google Scholar] [CrossRef] [Green Version] - Patino, H.D.; Liu, D. Neural network-based model reference adaptive control system. IEEE Trans. Syst. Man Cybern. Part B (Cybern.)
**2000**, 30, 198–204. [Google Scholar] [CrossRef] - Mokhtar, M.; Marei, M.I.; El-Sattar, A.A. A control scheme for islanded and grid-connected DC microgrids. In Proceedings of the 2017 Nineteenth International Middle East Power Systems Conference (MEPCON), Cairo, Egypt, 19–21 December 2017; pp. 176–180. [Google Scholar]
- Sameh, M.A.; Badr, M.A.; Mare, M.I.; Attia, M.A. Enhancing the performance of photovoltaic systems under partial shading conditions using cuttlefish algorithm. In Proceedings of the 2019 8th International Conference on Renewable Energy Research and Applications (ICRERA), Brasov, Romania, 3–6 November 2019; pp. 874–885. [Google Scholar]
- Mokhtar, M.; Marei, M.I.; El-Sattar, A.A. Improved current sharing techniques for DC microgrids. Electr. Power Compon. Syst.
**2018**, 46, 757–767. [Google Scholar] [CrossRef] - Sefa, I.; Altin, N.E.C.M.İ.; Ozdemir, S.; Kaplan, O.R.H.A.N. Fuzzy PI controlled inverter for grid interactive renewable energy systems. IET Renew. Power Gener.
**2015**, 9, 729–738. [Google Scholar] [CrossRef] [Green Version] - Yu, L.; Zhang, J.; Jiang, C. D-STATCOM control based on self-tuning PI with neural networks. In Proceedings of the China International Conference on Electricity Distribution 2012, Shanghai, China, 10–14 September 2012; pp. 1–4. [Google Scholar]
- Zare, A.; Moattari, M.; Melicio, R. Distributed Generation Control Using Modified PLL Based on Proportional-Resonant Controller. Appl. Sci.
**2020**, 10, 8891. [Google Scholar] [CrossRef] - Bianchini, M.; Scarselli, F. On the complexity of neural network classifiers: A comparison between shallow and deep architectures. IEEE Trans. Neural Netw. Learn. Syst.
**2014**, 25, 1553–1565. [Google Scholar] [CrossRef] [PubMed] - Marei, M.I.; El-Saadany, E.F.; Salama, M.M. A novel control scheme for STATCOM using space vector modulation-based hysteresis current controller. In Proceedings of the 2004 11th International Conference on Harmonics and Quality of Power (IEEE Cat. No. 04EX951), Lake Placid, NY, USA, 12–15 September 2004; pp. 58–65. [Google Scholar]
- Power Systems Computer Aided Design Software PSCAD/EMTDC Manual; Manitoba HVDC Research Center: Winnipeg, MB, Canada, 1994.
- El-Ebiary, A.H.; Attia, M.A.; Marei, M.I. An Adaptive Unified Seamless Control Strategy for Distributed Generator Inverter. In Proceedings of the 2019 IEEE Conference on Power Electronics and Renewable Energy (CPERE), Aswan, Egypt, 23–25 October 2019; pp. 264–269. [Google Scholar]
- Kotsiantis, S.B.; Zaharakis, I.; Pintelas, P. Supervised machine learning: A review of classification techniques. Emerg. Artif. Intell. Appl. Comput. Eng.
**2007**, 160, 3–24. [Google Scholar] - Yang, Q.; Jagannathan, S. Reinforcement learning controller design for affine nonlinear discrete-time systems using online approximators. IEEE Trans. Syst. Man Cybern. Part B (Cybern.)
**2012**, 42, 377–390. [Google Scholar] [CrossRef] [PubMed] - Kumar, R.; Srivastava, S.; Gupta, J.R.P. Artificial neural network based PID controller for online control of dynamical systems. In Proceedings of the 2016 IEEE 1st International Conference on Power Electronics, Intelligent Control and Energy Systems (ICPEICES), Delhi, India, 4–6 July 2016; pp. 1–6. [Google Scholar] [CrossRef]

**Figure 1.**(

**a**) DG system (

**b**) Unified control scheme block diagram for the DG system. * Refers to reference value of the variable.

**Figure 2.**Unified control scheme during the grid-connected mode. * Refers to reference value of the variable.

**Figure 3.**Unified control scheme during islanding conditions. * Refers to reference value of the variable.

**Figure 5.**(

**a**) The best validation performance for the DL-ANN controller. (

**b**) Regression plots for the DL-ANN.

**Figure 7.**Sudden grid loading: (

**a**) grid voltage and current when the load is switched on at t = 0.5 s. (

**b**) Grid voltage and current when the load is switched on at t = 0.505 s, and (

**c**) inverter current.

**Figure 8.**Islanding and re-synchronization: (

**a**) load voltage, (

**b**) load current, (

**c**) the reference and actual d-axis PCC voltage, vcd, and (

**d**) the error signal of the DL-ANN controller.

**Figure 9.**Non-linear loading case: (

**a**) Non-Linear load current, (

**b**) Inverter current, and (

**c**) grid current.

V_{dc} | 600 V |

L_{filter} | 8 mH |

C_{filter} | 15 μF |

R_{load} | 60 Ω |

L_{load} | 1 mH |

Frequency | 50 Hz |

Non-linear Local Load | Three-phase rectifier |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

EL-Ebiary, A.H.; Attia, M.A.; Marei, M.I.; Sameh, M.A.
An Integrated Seamless Control Strategy for Distributed Generators Based on a Deep Learning Artificial Neural Network. *Sustainability* **2022**, *14*, 13506.
https://doi.org/10.3390/su142013506

**AMA Style**

EL-Ebiary AH, Attia MA, Marei MI, Sameh MA.
An Integrated Seamless Control Strategy for Distributed Generators Based on a Deep Learning Artificial Neural Network. *Sustainability*. 2022; 14(20):13506.
https://doi.org/10.3390/su142013506

**Chicago/Turabian Style**

EL-Ebiary, Ahmed H., Mahmoud A. Attia, Mostafa I. Marei, and Mariam A. Sameh.
2022. "An Integrated Seamless Control Strategy for Distributed Generators Based on a Deep Learning Artificial Neural Network" *Sustainability* 14, no. 20: 13506.
https://doi.org/10.3390/su142013506