Voltage/VAR Control and Optimization: AI approach

Tomin, Nikita; Kurbatsky, Victor; Panasetsky, Daniil; Sidorov, Denis; Жуков, А. В.

doi:10.1016/j.ifacol.2018.11.685

Cited by 5 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Genetic algorithms are used in [15] to equalize APC among nd-DERs optimally. Nevertheless, it is worth reinforcing that, besides the lack of model-free features, most optimization methods present significant computational complexity [16], making them difficult to be embedded in DERs' digital processors. Moreover, many strategies do not guarantee optimal global solutions, and formulating objective functions is not trivial.…”

Section: Automatic Overvoltage Control Of Distributed Energy Resource...mentioning

confidence: 99%

Integrated Local and Coordinated Overvoltage Control to Increase Energy Feed-In and Expand DER Participation in Low-Voltage Networks

Alonso

Arenas

Brandão

et al. 2022

IEEE Trans. Sustain. Energy

View full text Add to dashboard Cite

Large amounts of active power injection by inverter-interfaced distributed energy resources (DER) is a common cause of overvoltage in low-voltage networks. Hence, local active and reactive power control (i.e., Volt/Watt and Volt/VAR, respectively) are adopted to limit voltage rise, leading to active power curtailment. This paper proposes an automatic control strategy to steer non-dispatchable (nd-DER) and dispatchable (d-DER) inverters in low-voltage networks, mitigating overvoltage through local and coordinated Volt/Watt and Volt/VAR functionalities. Active power curtailment is avoided whenever possible. The method does not require i) the implementation of optimization algorithms or ii) knowledge about line impedance parameters or the location of DERs. The control approach exploits the power flow dispatchability of lowvoltage networks comprising one point-of-common coupling with the distribution grid, allowing DERs close to the distribution transformer to also contribute to voltage regulation by only using a low-bandwidth communication link. Simulation results show the flexibilities of the proposed approach and demonstrate that energy exploitation can be increased by up to 25% for the considered scenario in comparison to conventional local Volt/Watt or Volt/VAR schemes. Experimental results based on a laboratory prototype with three inverter-interfaced DERs certify the applicability of the approach to real-life implementations.

show abstract

Section: Automatic Overvoltage Control Of Distributed Energy Resource...mentioning

confidence: 99%

Integrated Local and Coordinated Overvoltage Control to Increase Energy Feed-In and Expand DER Participation in Low-Voltage Networks

Alonso

Arenas

Brandão

et al. 2022

IEEE Trans. Sustain. Energy

View full text Add to dashboard Cite

show abstract

“…In relation to applied computational intelligence in energy distribution systems, reference [13] shows the design of an automatic voltage regulator using machine learning; this system is tested in distribution systems with 6 and 118 nodes. A related work can be seen in [14], where is proposed the use of reinforcement learning technique to implement a decentralized voltage control of the distribution network.…”

Section: Complexitymentioning

confidence: 99%

Proposal of an Adaptive Neurofuzzy System to Control Flow Power in Distributed Generation Systems

et al. 2019

View full text Add to dashboard Cite

Systems of distributed generation have shown to be a remarkable alternative to a rational use of energy. Nevertheless, the proper functioning of them still manifests a range of challenges, including both the adequate energy dispatch depending on the variability of consumption and the interaction between generators. This paper describes the implementation of an adaptive neurofuzzy system for voltage control, regarding the changes observed in the consumption within the distribution system. The proposed design employs two neurofuzzy systems, one for the plant dynamics identification and the other for control purposes. This focus optimizes the controller using the model achieved through the identification of the plant, whose changes are produced by charge variation; consequently, this process is adaptively performed. The results show the performance of the adaptive neurofuzzy system via statistical analysis.

show abstract

“…If MACS rapidly identifies the absence of possibility to support voltage by RPSs coordination (all the requested GA stop increasing Q g but the overload is not eliminated), the overloaded GA triggers the load-shedding procedure. It is important to note, that any overloaded GA included in the proposed MACS can determine the time when it is necessary to start load-shedding procedure [34].…”

Section: Emergency Vvc Using Macsmentioning

confidence: 99%