Active Power Correction Strategies Based on Deep Reinforcement Learning Part II:A Distributed Solution for Adaptability

This article is the second part of Active Power Correction Strategies Based on Deep Reinforcement Learning.In Part II,we consider the renewable energy scenarios plugged into the large-scale power grid and provide an adaptive algorithmic implementation to maintain power grid stability.Based on the robustness method in Part I,a distributed deep reinforcement learning method is proposed to overcome the infuence of the increasing renewable energy penetration.A multi-agent system is implemented in multiple control areas of the power system,which conducts a fully cooperative stochastic game.Based on the Monte Carlo tree search mentioned in Part I,we select practical actions in each sub-control area to search the Nash equilibrium of the game.Based on the QMIX method,a structure of offine centralized training and online distributed execution is proposed to employ better practical actions in the active power correction control.Our proposed method is evaluated in the modified global competition scenario cases of“2020 Learning to Run a Power Network.Neurips Track 2”.

Active Power Correction Strategies Based on Deep Reinforcement Learning Part I:A Simulation-driven Solution for Robustness

Employing the novel Deep Reinforcement Learning approach,this paper addresses the active power corrective control in modern power systems.Seeking to minimize the joint effect engendered by operation cost and blackout penalty,this correction strategy focuses on evaluating the robustness and adaptability aspects of the control agent.In Part I of this paper,where robustness is the primary focus,the agent is developed to handle unexpected incidents and guide the stable operation of power grids A Simulation-driven Graph Attention Reinforcement Learning method is proposed to perform robust active power corrective control.The aim of the graph attention networks is to determine the representation of power system states considering the topological features.Monte Carlo tree search is adopted to select the best suitable action set out of the large action space,including generator redispatch and topology control actions.Finally,driven by simulation,a guided training mechanism along with a long-short-term action deployment strategy are designed to help the agent better evaluate the action set while training and to operate more stably when deployed.The efficacy of the proposed method has been demonstrated in the“2020 I earning to Run a Power Network.Neurips Track 1”global competition and the associated cases.Part II of this paper deals with the adaptability case,where the agent is equipped to better adapt to a grid that has an increasing share of renewable energies through the years.

A new high-performance AC/DC power factor correction switching converter based on one-cycle control technology and active floating-charge technology

A new family of converters,high-performance AC/DC power factor correction(PFC) switching converters with one-cycle control technology and active floating-charge technology,was derived and experimentally verified.The topology of a single-phase CCM and DCM Boost-PFC switching converter was also analyzed.Its operating prniciples and control methods were expounded.Based on these,a new type of AC/DC switching converter circuits for PFC combined with one-cycle control technology was presented herein.The proposed AC/DC switching converter significantly helps improve the converter efficiency and its power factor value.

Performance Evaluation of a Permanent Magnet Electric-Drive- Reconfigured Onboard Charger with Active Power Factor Correction

This paper presents a comprehensive charging operation for an electric-drive-reconfigured onboard charger(EDROC)with active power factor correction(APFC).The charging topology exclusively utilizes the three-phase permanent magnet synchronous motor(PMSM)propulsion system as a three-channel boost-type converter in which only a contactor and a small diode bridge are added.First,the operation scenario of the EDROC is introduced.Second,the relationship between electromagnetic torque and rotor position is investigated.Third,the current ripple cancellation of the EDROC is discussed in detail.Moreover,to implement the single-phase APFC along with charging voltage/current regulation of propulsion battery,control strategies including current balancing and synchronous/interleaving PWM strategies are incorporated.Finally,200W proof-of-concept prototype-based tests are conducted under different operation scenarios.

DC boost converter with buck buffer

For a conventional high-power active power factor correction(APFC)boost converter,its output capacitor needs to be precharged,which means that two power switches of the main circuit and the control circuit are needed to be respectively turned on and turned off in a fixed order.After the main circuit switch is turned on,it is necessary to wait for precharging before turning on the control circuit power switch.Once an inadvertent operation is performed,an overcurrent phenomenon from the output capacitor will occur.In this study,the buck circuit is used as the pre-stage snubber circuit,which can directly supply power to the circuit without precharging the output capacitor.As a result,potential safety hazard caused by the overcurrent due to the capacitor and the charging maloperation during the start-up stage can be avoided.Theoretical analysis and simulation experiment show that the DC boost converter with buck buffer can maintain the peak value of the main circuit within the safe range when the device boot does not precharge the output capacitor,and thus the safety and stable operation of the DC boost converter are ensured.

A double closed loop APFC control with feed-forward

In order to improve the steady state performance,dynamic response and power factor of traditional power factor correction(PFC)digital control method and reduce the harmonic distortion of input current,a double closed loop active power factorcorrection(APFC)control method with feed-forward is proposed.Firstly,the small signal model of Boost PFC control systemis built and the system transfer function is deduced,and then the parameters of the main device with Boost topology is estimated.By means of the feed-forward,the system can quickly respond to the change in input voltage.Furthermore,the use ofvoltage loop and current loop can achieve input current and output voltage regulation Simulink modeling shows that this methodcan effectively control the output voltage in case of input voltage largely fluctuating,improve the system dynamic response abilityand input power factor,and reduce the input current harmonic distortion