CN109217702A - A MMC Parameter Optimization Method Based on Adaptive Firefly Algorithm - Google Patents

A MMC Parameter Optimization Method Based on Adaptive Firefly Algorithm Download PDF

Info

Publication number
CN109217702A
CN109217702A CN201710544780.XA CN201710544780A CN109217702A CN 109217702 A CN109217702 A CN 109217702A CN 201710544780 A CN201710544780 A CN 201710544780A CN 109217702 A CN109217702 A CN 109217702A
Authority
CN
China
Prior art keywords
firefly
adaptive
mmc
algorithm
parameter
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201710544780.XA
Other languages
Chinese (zh)
Inventor
刘青
焦晓鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
North China Electric Power University
Original Assignee
North China Electric Power University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by North China Electric Power University filed Critical North China Electric Power University
Priority to CN201710544780.XA priority Critical patent/CN109217702A/en
Publication of CN109217702A publication Critical patent/CN109217702A/en
Pending legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02M—APPARATUS FOR CONVERSION BETWEEN AC AND AC, BETWEEN AC AND DC, OR BETWEEN DC AND DC, AND FOR USE WITH MAINS OR SIMILAR POWER SUPPLY SYSTEMS; CONVERSION OF DC OR AC INPUT POWER INTO SURGE OUTPUT POWER; CONTROL OR REGULATION THEREOF
    • H02M7/00—Conversion of AC power input into DC power output; Conversion of DC power input into AC power output
    • H02M7/42—Conversion of DC power input into AC power output without possibility of reversal
    • H02M7/44—Conversion of DC power input into AC power output without possibility of reversal by static converters
    • H02M7/48—Conversion of DC power input into AC power output without possibility of reversal by static converters using discharge tubes with control electrode or semiconductor devices with control electrode
    • H02M7/483—Converters with outputs that each can have more than two voltages levels
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02M—APPARATUS FOR CONVERSION BETWEEN AC AND AC, BETWEEN AC AND DC, OR BETWEEN DC AND DC, AND FOR USE WITH MAINS OR SIMILAR POWER SUPPLY SYSTEMS; CONVERSION OF DC OR AC INPUT POWER INTO SURGE OUTPUT POWER; CONTROL OR REGULATION THEREOF
    • H02M7/00—Conversion of AC power input into DC power output; Conversion of DC power input into AC power output
    • H02M7/42—Conversion of DC power input into AC power output without possibility of reversal
    • H02M7/44—Conversion of DC power input into AC power output without possibility of reversal by static converters
    • H02M7/48—Conversion of DC power input into AC power output without possibility of reversal by static converters using discharge tubes with control electrode or semiconductor devices with control electrode
    • H02M7/483—Converters with outputs that each can have more than two voltages levels
    • H02M7/4835—Converters with outputs that each can have more than two voltages levels comprising two or more cells, each including a switchable capacitor, the capacitors having a nominal charge voltage which corresponds to a given fraction of the input voltage, and the capacitors being selectively connected in series to determine the instantaneous output voltage

Landscapes

  • Engineering & Computer Science (AREA)
  • Power Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Feedback Control In General (AREA)

Abstract

本发明专利公开了一种基于自适应萤火虫算法的MMC参数优化方法，可以对采用载波移相调制的模块化多电平换流器(MMC)进行控制参数的优化计算。本技术方案主要步骤包括：初始化自适应萤火虫算法参数，将控制器参数表示为萤火虫位置，表示出萤火虫种群的矩阵；初始化萤火虫的位置分布；运行仿真模型，计算每个萤火虫的目标函数值、吸引度；萤火虫依据吸引度大小对其他萤火虫进行搜寻，根据位置公式对位置进行更新；判断是否满足迭代结束条件，如果满足将结果输出即为优化后的控制器参数。如果不满足，则再次更新亮度和吸引度，进行搜寻，直到满足条件。实施例的仿真结果说明经过该方法优化后可以显著提高控制器精度，优化MMC的电流输出波形。

The patent of the present invention discloses an MMC parameter optimization method based on an adaptive firefly algorithm, which can optimize the control parameters of a modular multilevel converter (MMC) using carrier phase-shift modulation. The main steps of the technical solution include: initializing the parameters of the adaptive firefly algorithm, expressing the controller parameters as the firefly position, and representing the matrix of the firefly population; initializing the firefly position distribution; running the simulation model, calculating the objective function value of each firefly, attracting degree; fireflies search for other fireflies according to the size of the attraction, and update the position according to the position formula; judge whether the iteration end condition is satisfied, and output the result if it is satisfied is the optimized controller parameter. If not, update the brightness and attractiveness again, and search until the conditions are met. The simulation results of the embodiment show that after the optimization of the method, the accuracy of the controller can be significantly improved, and the current output waveform of the MMC can be optimized.

Description

A kind of MMC parameter optimization method based on adaptive glowworm swarm algorithm
Technical field
The invention patent relates to the power electronics fields in HVDC transmission system, are mainly used in flexible direct current The modularization multi-level converter part for link of transmitting electricity, specifically designs a kind of controller of modularization multi-level converter (MMC) Parameter optimization method.
Background technique
Voltage-source type HVDC transmission system (VSC-HVDC) is widely used in electric system transmission of electricity link, and voltage source Inverter is its core component.German scholar Lesnicar and Marquardt propose modularization multi-level converter (MMC) with Its unique high modularization structure becomes one kind superior in VSC-HVDC with advantages such as good fault ride-through capacities Topological structure.MMC has modular topological structure, opens the variation of submodule number purpose using upper and lower bridge arm and realizes voltage and function The change of rate grade, output voltage waveforms can save the friendship of large capacity smoothly close to ideal sinusoidal waveform in this way on hardware Filter is flowed, cost is saved.But power dissipation is stored in the capacitor of each submodule by MMC, therefore submodule at runtime The equalization problem of capacitance voltage is particularly critical.
For the equalization problem of submodule capacitor voltage, there is scholar to propose to answer phase-shifting carrier wave modulation strategy (CPS-SPWM) For in MMC, according to two kinds of principles of the submodule equipartition of energy and electric voltage equalization, design to be suitable for the voltage balancing control plan of MMC Slightly.But the big multi-parameter of the strategy relies primarily on artificial experience setting, related commissioning heavy workload.In order to solve this problem, The present invention proposes the MMC Optimization about control parameter based on adaptive glowworm swarm algorithm in phase-shifting carrier wave modulation strategy theoretical basis Method.
Summary of the invention
Present invention aims at carry out parameter optimization for using the MMC controller of phase-shifting carrier wave modulator approach, propose one Parameter optimization method of the kind based on adaptive glowworm swarm algorithm, makes the parameter of controller reach best configuration, mentions high control precision And control effect, inverter output current wave are improved.
To achieve the above object, the technical solution adopted is that:
(1) parameters such as population number, the number of iterations, the initial step length of adaptive glowworm swarm algorithm are initialized, are arranged in population Firefly number is N, is W by the controller parameter of required optimization, then the position vector of each firefly has W control parameter Composition, i.e., the array of one two dimension D=W, the firefly population can be expressed as the matrix of N* (D+2).Initial parameter choose according to It is chosen according to requirement of engineering in the range that each parameter generally allows for.
(2) position distribution of each firefly is initialized according to location formula, and initializes controller ginseng to be optimized Number.
(3) operation simulation model calculates the target function value of each firefly according to objective function Equation.
(4) each firefly searches other fireflies according to Attraction Degree size in algorithm, is greater than itself to brightness Individual, moved to it, and position is updated according to location formula.
(5) judge whether to meet iteration termination condition, if meeting result output is optimal solution, after being optimized Controller parameter.If conditions are not met, then updating brightness and Attraction Degree by third step again, it is iterated search again, until meeting Condition.
The invention patent has following gain effect:
The MMC parameter optimization method based on adaptive glowworm swarm algorithm that the invention patent is proposed, Algorithm Convergence is strong, It is possible to prevente effectively from Premature Convergence and the case where falling into local optimum, for the controller of modularization multi-level converter (MMC) After carrying out parameter optimization, output current wave is improved, loop current suppression effect enhancing, for the equalization stable of submodule voltage Play positive effect.
Detailed description of the invention
Fig. 1 MMC topology diagram
The flow chart of parameter optimization in Fig. 2 present invention
MMC control block diagram in Fig. 3 embodiment of the present invention
Optimization Simulation result figure in Fig. 4 embodiment of the present invention
Specific embodiment
The MMC parameter optimization method based on adaptive glowworm swarm algorithm is carried out specifically with example with reference to the accompanying drawing It is bright.
As shown in Figure 1 in MMC topological diagram, modular multilevel (MMC) has 6 bridge arms, and each bridge arm is by many submodules It cascades.This example uses 11 level MMC HVDC transmission systems, so each bridge arm has 10 submodules, upper and lower bridge Each 5, arm.11 level MMC control systems are built in Matlab/simulink.AC system voltage is 220V, bridge arm inductance 3mH is taken, nominal DC side voltage is 250V, transformer capacity 1200MVA.Submodule capacitor is 1.3mF.
From the figure 3, it may be seen that the control of MMC capacitance voltage is divided into two parts, capacitor voltage balance and bridge arm loop current suppression.Capacitor Be balance of voltage mesh guarantee submodule on bridge arm voltage-tracing its with reference to threshold voltage, pass through each submodule electricity of real-time monitoring Pressure value ucWith nominal reference threshold voltage ucref, and determine according to the direction of bridge arm current the working condition of the submodule.When bridge arm electricity Stream is timing, if ucLess than nominal reference voltage ucref, circulator should from DC side obtain energy to capacitor charging, adjust at this time Voltage u processedcIt * is positive value, module capacitance will constantly charge and voltage increases；Work as uc> ucrefWhen, modulation voltage ucIt * is negative value, this When the submodule charging time reduce, capacitance voltage amplitude incrementss reduce.
The purpose of bridge arm loop current suppression is to limit the circulation between bridge arm in a certain range, reduces it to bridge arm current Influence.By the double-closed-loop control of external voltage outer ring and current inner loop, make the variation of circulation tracking circulation reference value, by ring Flow control is within tolerance interval.Outer voltage uses pi regulator, and control phase element average voltage level tracks nominal reference Voltage signal, and the PI controller of current inner loop is used to control the variation of circulation tracking circulation reference value, output is used as capacitor The regulated quantity u of voltage balance controlzj*。
It is as follows that outer voltage controls formula
Current inner loop control formula is as follows
In above-mentioned formulaucjiFor the capacitance voltage of i-th of submodule of jth phase.
Finally, the amplitude of phase-shifting carrier wave modulating wave is
Upper bridge arm modulating wave
Lower bridge arm modulating wave
This example optimal target is exactly that two controller parameters in the control of bridge arm circulation are optimized.It is arranged first Firefly population number is 50, and firefly population number is 50, and the number of iterations is 20 times, and dimension 4, step-length initial value takes 0.02, is attracted Degree initial value takes 0.5.There are four Optimal Parameters needed for controller, respectively Proportional coefficient K p1, Kp2 and integral parameter Ki1, Ki2. For set firefly, specific algorithm Optimization Steps are as follows
(1) each firefly i is by a vector xiIt indicates, wherein m is the number for needing optimal control parameter
The value of step factor α influences the distance that firefly is moved in search space, and bigger step factor value has Conducive to remote search.And the value of optical absorption intensity γ influences Attraction Degree with the change degree of distance, under normal circumstances Value range is between 0 to 10.The selection of the two coefficients influences convergence and final result.Firefly in the present invention Fireworm algorithm adaptivity just embodies herein, and α and γ participate in whole search process, and the addition of auto-adaptive parameter will make algorithm Convergence greatly increase
(2) initial position of firefly is obtained by formula
Wherein, rand is to obey equally distributed random number on 0 to 1.
(3) brightness of each firefly is obtained by formula,
Ii=f (xm)
F (x) is generally corresponding target function value.Objective function is chosen for energy reaction system regulation quality in the present invention Time multiplies objective function of the integral of absolute value of error ITAE as optimizing.Its expression formula is
E (t) is to miss absolute value of the difference；T is time definite value, and general value is larger to allow system to enter stabilization.Due to control The purpose of the parameter optimization of device processed is that input value is allowed to track given reference value, i.e., PI controller error input e (t) is minimum, and firefly What fireworm algorithm optimizing was asked is maximum value.So objective function should be rewritten as
(4) the Attraction Degree formula between firefly i and j is as follows
βij=(βMax, i, j-βMin, i, j)exp(-γmrM, n 2)+βMin, i, j
Wherein, rI, jFor the distance between i and j
γ is light intensity absorption coefficient, depends on the dynamic range of search space.
(5) when firefly i is mobile to the firefly j stronger than oneself brightness, its position will be updated by location formula.
xi=xi+βij×(xj-xi)+α×(rand-1/2)
Wherein α is step factor, and value is 0 to 1.Rand is to obey equally distributed random number on [0,1].Pass through addition α × (rand-1/2) disturbance term, increases search range, avoids falling into local optimum.
The core of glowworm swarm algorithm is exactly to constantly update brightness and Attraction Degree, allows firefly in iteration moving process, most After concentrate on the maximum position of brightness, as optimal solution.
Optimization method process of the invention is as shown in Fig. 2, the firefly population in the present embodiment is expressed in matrix as
N is population number, i.e. it is 6 in this example that 50, D, which is dimension,.After initializing each firefly position, each firefly Position is the parameter setting of controller, by the way that simulation model is run multiple times, makes the brightness (i.e. target function value) of firefly no It is disconnected to update, location updating iteration is carried out by algorithm firefly, it is finally most of to gather near a certain position, represented by the position Parameter be optimal solution, can realize the optimization of MMC parameter.Since adaptive glowworm swarm algorithm can be optimized with adjust automatically In parameter, the case where local optimum can occur to avoid algorithm Premature Convergence, optimizing effect is better than general optimization algorithm. Optimization method of the invention can be generalized to the parameter optimization of other controllers, have certain extensibility.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, although referring to aforementioned reality Applying example, invention is explained in detail, for those skilled in the art, still can be to aforementioned each implementation Technical solution documented by example is modified or equivalent replacement of some of the technical features.It is all in essence of the invention Within mind and principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.

Claims (4)

1.一种基于自适应萤火虫算法的MMC参数优化方法，包含以下步骤：1. An MMC parameter optimization method based on an adaptive firefly algorithm, comprising the following steps: 1)初始化自适应萤火虫算法的种群数、迭代次数、初始步长等参数，设置种群中萤火虫个数为N，由所需要优化的控制器参数为W，则每个萤火虫的位置矢量有W个控制参数组成，即一个二维D＝W的数组，该萤火虫种群可以表示为N*(D+2)的矩阵。初始参数选取依据工程需要在每个参数大致允许的范围选取。1) Initialize the parameters such as the number of populations, the number of iterations, and the initial step size of the adaptive firefly algorithm, set the number of fireflies in the population to N, and the controller parameter to be optimized is W, then the position vector of each firefly has W The control parameter is composed of a two-dimensional array of D=W, and the firefly population can be represented as a matrix of N*(D+2). The initial parameter selection is based on the project needs and is selected within the approximate allowable range of each parameter. 2)根据位置公式初始化每一个萤火虫的位置分布。每一个萤火虫的位置信息即为待优化的控制器各参数取值。2) Initialize the location distribution of each firefly according to the location formula. The position information of each firefly is the value of each parameter of the controller to be optimized. 3)运行仿真模型，根据目标函数公式，计算每个萤火虫对应的目标函数值，即为自适应算法中的萤火虫亮度。3) Run the simulation model, and calculate the objective function value corresponding to each firefly according to the objective function formula, which is the firefly brightness in the adaptive algorithm. 4)算法中每个萤火虫依据吸引度大小对其他萤火虫进行搜寻，对亮度大于自身的个体，向其进行移动，并根据位置公式对位置进行更新。4) In the algorithm, each firefly searches for other fireflies according to the size of the attraction, moves to the individual whose brightness is greater than itself, and updates the position according to the position formula. 5)判断是否满足迭代结束条件，如果满足将结果输出即为最优解，得到优化后的控制器参数。如果不满足，则再由第三步更新亮度和吸引度，再次进行迭代搜寻，直到满足条件。5) Judging whether the iteration end condition is satisfied, if satisfied, the result is output as the optimal solution, and the optimized controller parameters are obtained. If it is not satisfied, the brightness and attractiveness are updated in the third step, and the iterative search is performed again until the conditions are satisfied. 2.根据权利要求1所述的基于自适应萤火虫算法的MMC参数优化方法，其特征在于，步骤1)中对于自适应萤火虫种群矩阵的建立，每个萤火虫i都由一个矢量xi表示，其中m为需要优化控制参数的个数2. the MMC parameter optimization method based on self-adaptive firefly algorithm according to claim 1, is characterized in that, in step 1), for the establishment of self-adaptive firefly population matrix, each firefly i is all represented by a vector x i , wherein m is the number of control parameters to be optimized 步长因子α的取值影响搜索空间中萤火虫所移动的距离，而光吸收强度γ的取值影响到吸引度随距离的改变程度，一般情况下取值范围在0到10之间。将α和γ也作为优化参数参与全程的搜索过程，自适应参数的加入将使算法的收敛性大大增加。The value of the step factor α affects the distance that the fireflies move in the search space, and the value of the light absorption intensity γ affects the degree of change of the attraction degree with the distance. Generally, the value ranges from 0 to 10. α and γ are also used as optimization parameters to participate in the whole search process, and the addition of adaptive parameters will greatly increase the convergence of the algorithm. 3.根据权利要求1所述的基于自适应萤火虫算法的MMC参数优化方法，其特征在于，步骤3)中，通过运行仿真模型得出目标函数值。目标函数选取为能反应系统调节品质的时间乘绝对误差积分ITAE作为寻优的目标函数。其表达式为3. the MMC parameter optimization method based on adaptive firefly algorithm according to claim 1, is characterized in that, in step 3), obtain objective function value by running simulation model. The objective function is selected as the time multiplied by the absolute error integral ITAE which can reflect the adjustment quality of the system as the objective function of optimization. Its expression is 控制器的参数优化的目的是让输入值跟踪给定参考值，即PI控制器误差输入e(t)最小，而萤火虫算法寻优求的是最大值。所以，目标函数应当改写为The purpose of parameter optimization of the controller is to make the input value track the given reference value, that is, the error input e(t) of the PI controller is the smallest, while the firefly algorithm seeks the maximum value. Therefore, the objective function should be rewritten as 设置优化目标函数为Set the optimization objective function as Q(t)＝c1f1(t)+c2f2(t)Q(t)=c 1 f 1 (t)+c 2 f 2 (t) 4.根据权利要求1所述的基于自适应萤火虫算法的MMC参数优化方法，其特征在于，步骤5)中，通过不断的迭代运行仿真控制器，计算目标函数，将其作为萤火虫的亮度并更新每一个萤火虫的亮度，通过算法萤火虫移动，当达到迭代次数，满足结束条件时，最终大多数聚在某一位置附近，该位置所表示的参数即为最优解，便可以实现MMC参数的优化。4. the MMC parameter optimization method based on self-adaptive firefly algorithm according to claim 1, is characterized in that, in step 5), by continuous iterative operation simulation controller, calculate objective function, it is used as the brightness of firefly and update The brightness of each firefly is moved through the algorithm. When the number of iterations is reached and the end condition is met, most of them will eventually gather near a certain position. The parameters represented by this position are the optimal solution, and the optimization of MMC parameters can be realized. .
CN201710544780.XA 2017-07-06 2017-07-06 A MMC Parameter Optimization Method Based on Adaptive Firefly Algorithm Pending CN109217702A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710544780.XA CN109217702A (en) 2017-07-06 2017-07-06 A MMC Parameter Optimization Method Based on Adaptive Firefly Algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710544780.XA CN109217702A (en) 2017-07-06 2017-07-06 A MMC Parameter Optimization Method Based on Adaptive Firefly Algorithm

Publications (1)

Publication Number Publication Date
CN109217702A true CN109217702A (en) 2019-01-15

Family

ID=64992795

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710544780.XA Pending CN109217702A (en) 2017-07-06 2017-07-06 A MMC Parameter Optimization Method Based on Adaptive Firefly Algorithm

Country Status (1)

Country Link
CN (1) CN109217702A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112764785A (en) * 2020-12-24 2021-05-07 江苏云涌电子科技股份有限公司 Method for automatically upgrading multi-stage controller
CN113541170A (en) * 2021-06-16 2021-10-22 武汉理工大学 Fuel cell emergency power supply grid-connected inversion control method and system
CN114614690A (en) * 2022-03-07 2022-06-10 中国矿业大学 Model Predictive Control Algorithm of MMC Optimal Switching Sequence Based on 2D Control Region

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112764785A (en) * 2020-12-24 2021-05-07 江苏云涌电子科技股份有限公司 Method for automatically upgrading multi-stage controller
CN113541170A (en) * 2021-06-16 2021-10-22 武汉理工大学 Fuel cell emergency power supply grid-connected inversion control method and system
CN113541170B (en) * 2021-06-16 2023-11-24 武汉理工大学 Grid-connected inversion control method and system for emergency power supply of fuel cell
CN114614690A (en) * 2022-03-07 2022-06-10 中国矿业大学 Model Predictive Control Algorithm of MMC Optimal Switching Sequence Based on 2D Control Region

Similar Documents

Publication Publication Date Title
Meng et al. Dynamic consensus algorithm based distributed global efficiency optimization of a droop controlled DC microgrid
Wang et al. Adaptive type-2 FNN-based dynamic sliding mode control of DC–DC boost converters
CN110048606B (en) DC-DC boost converter dynamic sliding mode voltage control method based on interval two-type self-adaptive fuzzy neural network
CN109217702A (en) A MMC Parameter Optimization Method Based on Adaptive Firefly Algorithm
CN107508275B (en) A kind of DC micro-electric network control method based on adaptive Dynamic Programming
Khorashadizadeh et al. Voltage tracking control of DC-DC boost converter using brain emotional learning
Tehrani et al. Design of fractional order PID controller for boost converter based on multi-objective optimization
CN109980666A (en) A kind of adaptive disturbance compensation passive control method of microgrid mixed energy storage system
Yu et al. Multi-step predictive current control for NPC grid-connected inverter
Darvill et al. An ANFIS-PI based boost converter control scheme
Oshnoei et al. Data-driven coordinated control of AVR and PSS in power systems: A deep reinforcement learning method
Mohammadzadeh et al. Application of mixture of experts in machine learning-based controlling of DC-DC power electronics converter
Dhivya et al. Neural network controller for boost converter
Ye et al. Deep deterministic policy gradient algorithm based reinforcement learning controller for single-inductor multiple-output DC–DC converter
Huh et al. An adaptive fuzzy controller for power converters
CN112072893B (en) Power electronic converter control method with synthesized variable feedback
Vittal et al. Comparative study of PI, PID controller for buck-boost converter tuned by bio-inspired optimization techniques
CN114637204B (en) Virtual synchronous machine control parameter setting method based on mixed H2/H infinity performance index
CN113839578B (en) Multi-level converter neutral point voltage balance system and method based on reinforcement learning
Aribowo et al. Optimal tuning fractional order PID based on marine predator algorithm for DC motor
Hussain et al. Designing an optimal PID controller for a PV-connected Zeta converter using genetic algorithm
Pandey et al. PSS tuning with firefly driven knowledge domain-a smart control concept
Al-Mosawi et al. An Adaptive Parallel Fuzzy And Proportional Integral Controller (APFPIC) For The Contractor Pneumatic Muscle Actuator Position Control
Chang et al. A non-singular terminal sliding mode control of the DC microgrid with constant power loads
Venkatesh et al. Real time analysis of positive output super lift converter using ANN controller

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
DD01 Delivery of document by public notice

Addressee: Jiao Xiaopeng

Document name: Notification of before Expiration of Request of Examination as to Substance

DD01 Delivery of document by public notice
DD01 Delivery of document by public notice

Addressee: Jiao Xiaopeng

Document name: Deemed as a notice of withdrawal

DD01 Delivery of document by public notice
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20190115

WD01 Invention patent application deemed withdrawn after publication