scholarly journals Deep-Reinforcement-Learning-Based Two-Timescale Voltage Control for Distribution Systems

Energies ◽  
2021 ◽  
Vol 14 (12) ◽  
pp. 3540
Author(s):  
Jing Zhang ◽  
Yiqi Li ◽  
Zhi Wu ◽  
Chunyan Rong ◽  
Tao Wang ◽  
...  

Because of the high penetration of renewable energies and the installation of new control devices, modern distribution networks are faced with voltage regulation challenges. Recently, the rapid development of artificial intelligence technology has introduced new solutions for optimal control problems with high dimensions and dynamics. In this paper, a deep reinforcement learning method is proposed to solve the two-timescale optimal voltage control problem. All control variables are assigned to different agents, and discrete variables are solved by a deep Q network (DQN) agent while the continuous variables are solved by a deep deterministic policy gradient (DDPG) agent. All agents are trained simultaneously with specially designed reward aiming at minimizing long-term average voltage deviation. Case study is executed on a modified IEEE-123 bus system, and the results demonstrate that the proposed algorithm has similar or even better performance than the model-based optimal control scheme and has high computational efficiency and competitive potential for online application.

Author(s):  
Muhamad Najib Kamarudin ◽  
Tengku Juhana Tengku Hashim

The operation and control of electricity in distribution networks has faced great challenges as a large number of distributed generations (DGs) are integrated. Connection of distributed generations (DGs) in the distribution system offers advantages in terms of reducing distribution and transmission costs as well as encouraging the use of renewable energy sources. The power flow in the distribution systems is no longer moving in a single direction and this resulted the system to become as active distribution networks (ADN). One of the main problems in ADN is the voltage regulation issue which is to maintain the voltage to be within its permissible limits. Several methods of voltage control methods are available and focus is given in finding the optimal voltage control using artificial intelligence techniques. This paper presents an optimal and coordinated voltage control method while minimizing losses and voltage deviation of the network. The optimal and coordinated voltage control scheme is implemented on an IEEE 13 bus distribution network for loss and voltage deviation minimization in the networks. Firefly Algorithm (FA) which is a known heuristic optimization technique for finding the optimal solution is used in this work. The results are compared with another optimization method known as Backtracking Search Algorithm (BSA) for identifying the best setting for solving the voltage regulation problem. In order to solve the multi-objective optimization issue, the MATPOWER load flow simulation is integrated in the MATLAB environment with the optimization algorithm.


Author(s):  
Sahar M. Sadek ◽  
Amal A. Hassan ◽  
Faten H. Fahmy ◽  
Amgad A. El-Deib ◽  
Hosam K.M. Yousef

The intermittent nature of photovoltaic (PV) generation causes the voltage to fluctuate and may lead to instability, especially, in case of high penetration. In this paper, a methodology is proposed to control the reactive power generation of PV-inverters. The objective is to mitigate the voltage fluctuations at the point of common coupling (PCC) resulted from increasing or decreasing the active power output of PV plants which is dependent on solar radiation level. The generic PV-inverter models developed and recommended by the Renewable Energy Modeling Task Force (REMTF) of the Western Electricity Coordinating Council (WECC) is used to analyze the effect of high PV penetration on the dynamic voltage stability of distribution networks. Then, the tested distribution network with the embedded PV plants is modeled and simulated using PSS/E software. Levels of control that are built-in PV-inverters are tested in the case of normal operation and during disturbances. Comparison results show that the most suitable control methodology in case of disturbances and after fault clearance is the local voltage control. While the plant voltage control with coordinated V/Q control is the most preferable control methodology during normal operation.


2018 ◽  
Vol 7 (2.28) ◽  
pp. 362
Author(s):  
Raed A. Shalwala

One of the most important operational requirements for any electrical power network for both distribution and transmission level is voltage control. Many studies have been carried out to improve or develop new voltage control techniques to facilitate safe connection of distributed generation. In Saudi Arabia, due to environmental, economic and development perspectives, a wide integration of photovoltaic (PV) genera-tion in distribution network is expected in the near future. This development in the network may cause voltage regulation problems due to the interaction with the existing conventional control system. In a previous paper, a control system has been described using a fuzzy logic control to set the on-line tap changer for the primary substation. In this paper a new control system is proposed for controlling the power factor of individual PV invertors based on observed correlation between net active and reactive power at each connection. A fuzzy logic control has been designed to alter the power factor for the remote invertors from the secondary substation to keep the feeder voltage within the permissible limits. In order to confirm the validity of the proposed method, simulations are carried out for a realistic distribution network with real data for load and solar radiation. Results showing the performance of the new control method are presented and discussed.  


2021 ◽  
Vol 19 ◽  
pp. 85-90
Author(s):  
Priscila Costa Nascimento ◽  
◽  
Michel Girotto de Oliveira ◽  
José Carlos M. Vieira

The growth of micro and mini distributed generation and, more recently, the use of electric energy storage systems and the incentives for electric mobility are important examples of the transformations that distribution networks have been going through. In this context, this paper firstly presents the impacts of uncoordinated plug-in electric vehicles (PEVs) charging in a real Brazilian distribution system. Four scenarios were elaborated with different PEVs penetration levels and the results show increased voltage unbalance, system losses, and violations of the steady-state voltage limits, even in the presence of an automatic voltage regulator installed in the medium voltage network. Then, as the main contribution, the potential usage of automatic voltage regulation at the low voltage network was investigated to minimize the negative impacts of uncontrolled PEV charging on distribution system steady-state operation. It is important to highlight that this is not a common practice of utilities in Brazil. The obtained results showed that regulating the voltage at the low voltage side could be an effective solution to keep the voltages within statutory limits.


2021 ◽  
Vol 72 (6) ◽  
pp. 356-365
Author(s):  
Jordan Radosavljević

Abstract High penetration of photovoltaic (PV) generation in low voltage (LV) distribution networks can leads some power quality problems. One of the most important issues in this regard is the impermissible voltage deviation in periods with a large imbalance between PV generation and local load consumption. Accordingly, many authors deal with this issue. This work investigates voltage regulation for LV distribution networks equipped with the hybrid distribution transformer (HDT), and with high penetration of PV units. A two-stage algorithm for voltage regulation is proposed. In the first stage, a local (distributed) voltage control is performed by minimizing the injection power of the PV-battery storage system (BS)-local load entity at the common bus. In the second stage, optimal coordination is performed between the HDT and the local voltage control. In fact, the second stage is an optimal voltage regulation problem. The aim is to minimize the voltage deviations at load buses by optimal settings the voltage support of the HDT. A PSO algorithm is used to solve this optimization problem. the proposed approach is implemented in MATLAB software and evaluated on the IEEE european LV test feeder.


Author(s):  
Minh Y Nguyen

AbstractRecently, the voltage stability and control of distribution networks become challenges due to the large line impedance, load variations and particularly the presence of distributed generation. This paper presents a coordinated voltage control scheme of distribution systems with distributed generation based on on-load tap changer and shunt capacitors. The problem is to determine the optimal operation of voltage regulation devices to minimize a multi-objective function including power losses, voltage deviations and operation stresses while subject to the allowable voltage ranges, line capacity and switching stresses, etc. The problem is formulated and solved by a modified particle swarm optimization algorithm to treat the large-scale and high nonlinearity property. The proposed scheme is applied to a typical 48-bus distribution network in Vietnam. The result of simulation shows that the voltage profile can be improved while the power loss of distribution systems can be reduced significantly.


Vestnik MEI ◽  
2021 ◽  
pp. 27-36
Author(s):  
Mikhail G. Astashev ◽  
◽  
Artem S. Vanin ◽  
Vladimir M. Korolev ◽  
Dmitriy I. Panfilov ◽  
...  

The article addresses the problem of ensuring permissible voltage levels in distribution electrical networks of various types: distribution networks of large cities, regional distribution electrical networks, and distribution electrical networks containing renewable energy sources. The most typical factors causing the voltage to go beyond the permissible limits specified by the relevant regulatory documents are pointed out. The negative factors conducive to the voltage at the consumer end deviating from the permissible limits, including a long length of network lines, high network load, low controllability of the network, load schedule nonuniformity, and poor observability of the network, are analyzed. The existing principles of voltage control in electrical distribution networks, namely, automatic and seasonal regulation, are studied. A distribution electrical network test model representing a real network fragment is developed. The model operation modes have been verified based on the data of measurements carried out in the original distribution electrical network. The voltage distributions in a medium voltage network during its operation under the conditions of the highest and lowest loads are demonstrated. It is shown, on the test model example, how the network voltage can be controlled by automatically regulating the voltage at the power supply center and selecting a fixed position of the NLTC at 10/0.4 kV transformer substations. It is shown that the use of power transformer OLTCs does not ensure sufficient means for adequately controlling the voltage in networks containing long power lines and featuring highly nonuniform seasonal and daily load schedules. The technical efficiency and economic feasibility of using automatic voltage regulation devices on 10/0.4 kV transformers for local voltage control are analyzed. The economic efficiency of applying automatic voltage regulation devices at 6--10/0.4 kV substations was evaluated in comparison with other means for improving the power distribution network voltage quality by upgrading the 10 kV feeder lines or installing a voltage booster at the inlet to the problematic 10 kV network section. The application field of automatic voltage regulators in the form of semiconductor devices for regulating the transformer output voltage at distribution transformer substations is shown.


Sign in / Sign up

Export Citation Format

Share Document