CN114039346A - Voltage regulation and current sharing method based on neural network - Google Patents
Voltage regulation and current sharing method based on neural network Download PDFInfo
- Publication number
- CN114039346A CN114039346A CN202111398185.2A CN202111398185A CN114039346A CN 114039346 A CN114039346 A CN 114039346A CN 202111398185 A CN202111398185 A CN 202111398185A CN 114039346 A CN114039346 A CN 114039346A
- Authority
- CN
- China
- Prior art keywords
- voltage
- current
- network
- neural network
- controller
- 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
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 41
- 230000033228 biological regulation Effects 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000004364 calculation method Methods 0.000 claims abstract description 7
- 230000005540 biological transmission Effects 0.000 claims abstract description 6
- 238000011156 evaluation Methods 0.000 claims description 26
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 230000001105 regulatory effect Effects 0.000 claims description 6
- 238000013461 design Methods 0.000 claims description 5
- 238000012886 linear function Methods 0.000 claims description 3
- 230000000087 stabilizing effect Effects 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 4
- 230000008447 perception Effects 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000032683 aging Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 238000004146 energy storage Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 241000287196 Asthenes Species 0.000 description 1
- 208000003098 Ganglion Cysts Diseases 0.000 description 1
- 208000005400 Synovial Cyst Diseases 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000009123 feedback regulation Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J1/00—Circuit arrangements for dc mains or dc distribution networks
- H02J1/10—Parallel operation of dc sources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
Landscapes
- Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a voltage regulation and current sharing method based on a neural network, which is characterized in that a new controller is constructed by adopting a precompensation technology on the basis of a model with unknown voltage drop, so that the dynamic calculation of a system is avoided, wherein secondary auxiliary control of a control unit and a computer network carry out information transmission to regulate voltage and current, information perception with the outside is realized, the voltage regulation and current sharing can be effectively realized, and the stability of the system is improved.
Description
Technical Field
The invention relates to the technical field of power electronic engineering, in particular to a voltage regulation and current sharing method based on a neural network.
Background
The power grid is a power generation and distribution network system consisting of a distributed power supply, an energy conversion device, an energy storage device and a load. The micro-grid is one of important components of the smart grid, and has important significance in promoting energy conservation and emission reduction and realizing sustainable development of energy. At present, there are two types of microgrid: a direct current microgrid and an alternating current microgrid. Compared with an alternating-current micro-grid, direct-current power loads such as wind, light and other distributed renewable energy power generation systems, household appliances and energy storage equipment can be efficiently and reliably connected to the direct-current micro-grid. Therefore, direct current micro-grids have received much attention from researchers. In the research of the dc microgrid, voltage regulation and current sharing are two basic problems. The voltage regulation means that the voltage of a regulation node reaches a specified value, and the current sharing means that the ratio of the current of each node in the direct current microgrid to the regulation rate is equal. At present, the voltage and current regulation of a direct current micro-grid is realized by adopting the control of a circuit, in the circuit transmission process, a plurality of unknown factors such as environmental influence, circuit aging and the like can cause voltage loss, and meanwhile, the external world lacks regulation perception in practical application, so that the existing method can not regulate or regulate to lose efficacy under the condition of unknown voltage drop, and has certain limitation in practical application.
Disclosure of Invention
The invention aims to provide a voltage regulation and current sharing method based on a neural network in order to solve the problem that voltage loss may be caused by factors such as environmental influence and circuit aging in an actual direct-current micro-grid, so that a voltage and current regulation method may fail along with the problem of voltage drop. The invention provides a voltage regulation and current sharing method based on a three-layer forward neural network, a new controller is constructed by adopting a precompensation technology on the basis of the current sharing controller, and the problem that voltage and current cannot be regulated or regulated to be invalid due to voltage drop caused by unknown factors such as environmental influence, circuit aging and the like is solved by constructing a system error related to the voltage and the current through the controller.
The invention realizes the purpose through the following technical scheme:
a voltage regulation and current sharing method based on a neural network is used for a direct current micro-grid system consisting of M power supplies and N loads, wherein each power supply is communicated with a neighbor of the power supply through a wide area network; the control system comprises a main control unit, a secondary auxiliary control unit and an external neural network control unit, wherein the secondary auxiliary control unit is a constructed compensation controller, the main control unit mainly performs droop control, the secondary auxiliary control unit performs information transmission with the outside, and the source of the direct current micro-grid is represented as PSThe load of the dc microgrid is denoted as P ═ 1,2L1,2, N }; each power supply is connected to the bus via a step-up DC/DC converter, and a load is connected in parallel toA bus; the model utilizes an unknown non-linear function f (V)i(k) To describe the voltage loss of the power line, thereby designing the current-sharing controller, adopting a pre-compensation technology according to the current-sharing controller, proposing a new controller, simultaneously avoiding the requirement of system dynamics, and constructing the system error about the voltage and the current on the basis of the new controllerProviding a strategy iterative algorithm related to the system error, finishing stable control on the system error according to the strategy iterative algorithm, and finally realizing a control scheme based on a three-layer forward neural network, wherein the control scheme consists of a compensator network, a controller and an evaluation network; the compensator network generates a compensator control parameter by using the voltage and current system error, the network is evaluated to generate iterative performance and the compensator control parameter is adjusted, and the controller constructs a control voltage by using the compensator control parameter; the system main control unit and the secondary control unit realize voltage regulation and current equalization according to control voltage feedback regulation; the invention can realize effective control of voltage regulation and current sharing under the condition of unknown voltage drop and improve the stability of the direct current micro-grid system.
Definition VcomIs a dc bus voltage; i isiAnd ViExpressed as the output current and output voltage of the ith power supply; the target expression of current regulation in a certain proportion in the direct-current microgrid is as follows:
wherein d isiThe adjustment rate is represented and is a proportional parameter of the adjustment current;
the target for voltage regulation is expressed as:
Vcom=Vrated, (2)
wherein VratedRepresenting the rated voltage of the direct current bus, and aiming at regulating the voltage to be stabilized to the rated voltage;
to make it practicalNow voltage regulation and current sharing, a control framework based on a layered structure is proposed, as shown in fig. 1; as seen in fig. 1, for each source, its control framework comprises a main control unit and a secondary control unit; the main control unit consists of a droop controller, a voltage controller and a current controller; the main function of the voltage and current controller in the master control unit is to regulate the output voltage of the converter and drive it to a reference voltage Vi Ref(ii) a The droop controller is used for stabilizing the voltage and frequency in the micro-grid by adding a virtual resistorTo realize the operation; voltage u for secondary controlleriCompensating the voltage deviation; using an unknown non-linear function f (V)i(k) To describe voltage loss on the power line; therefore, the current sharing controller can be designed as follows:
assuming that the microgrid is dc and does not produce reactive power, the virtual resistance is set in question asThen, the current share controller rewrites to:
Vi(k+1)=Vrated-f(Vi(k))+ui(k) (4)
due to f (V)i(k) Unknown), in order to avoid calculations, by using pre-compensation techniques, the compensation controller is designed to:
ui(k+1)=gi(ui(k))+hi(ui(k))υi(k), (5)
wherein upsilon isi(k) Is an input to a compensation controller, which is at ui(k) 0 and upsiloni(k) Singularity at 0; and g isiAnd hiIs a controllable nonlinear function;
suppose thatIs the constant resistance of the ith load, GiIs the conductance in the transmission line from the ith converter to the dc bus, the description of the dc microgrid evolves to:
Ii=Gi(Vi+f(Vi)-Vcom). (7)
according to (1) and (2), the voltage error and the current error are defined as:
eV(k)=Vcom-Vrated. (8)
by (6) to (9), there are obtained:
combining the compensation controller (5) and the dynamics (10) - (11) to obtain an auxiliary error system:
Hi=[0 0 hi(ui(k))]T
Obviously, the error system (12) isHas a singularity; if it is notObtaining eI,i(k)=0,i∈PSAnd eV(k) 0, this means thatAnd Vcom=VratedThe implementation is carried out; therefore, the problems of voltage constant voltage and current uniform flow are converted into the stability problem of the error system (12);
since all sources want to minimize their own cost, the cost of source i, also called the performance index, is defined as follows:
wherein gamma ∈ (0, 1)]Is a discount factor, RiiIs a positive weight; obviously, the performance index is control dependent;
the objective problem to be solved herein translates into designing a compensation control to stabilize (12) and minimize the local performance indicators for each source, i.e. the control of each genset not only minimizes its own cost, but also stabilizes the error system (12);
According to the bellman optimality principle, the following equation is obtained:
whereinIs an optimal strategy, Vi *Is the optimal performance index; based on the bellman optimality principle, (15) is written as:
according to (16), upsiloniIs expressed as
In (16), by pairing ViSolving for vi(k) And then an expression for optimal control is obtained:
to solve the optimal control problem, only the optimal solution of equation (15) needs to be obtained; however, this is often difficult to solve; therefore, a strategy iterative algorithm is designed to obtain the optimal control and optimal value function of the system; the algorithm is as follows:
initialization:
Let d equal 1
Iteration:
finishing;
stability analysis was performed after convergence was guaranteed: suppose Vi *Satisfies the condition of upsilon in (18) when (15) is satisfiedi(k) Ensure (12) is asymptotically stable and JiIs optimal, which means that the objective problems of voltage regulation and current sharing are solved;
realizing an algorithm based on a neural network so as to complete the implementation of the control scheme; the control scheme of the generator set node i is shown in fig. 2 and comprises an evaluation network, a compensator network and a controller; estimating V using an evaluation networki (d)The compensator is also implemented using a neural network, which is used to constructThe controller is used for acquiring ui(k) (ii) a The evaluation network and the compensator network are both realized by adopting a three-layer feedforward neural network;
evaluating network design by evaluating network implemented using three-layer neural networkIn the following formulaWherein N isc,iRepresenting the number of hidden nodes of the ith control unit; performance index ViIs the output of the evaluation network of the ith control unit, expressed in the form:
wherein Vi d(k) Representing the output of the evaluation network at d iterations,an input representing an evaluation network is presented and,andweights between the first layer and the second layer, respectively;
defining the prediction error of the evaluation network as
ξc(k)=Vi d+1(k)-[ψi(k)+γVi d(k+1)] (24)
To calculate the weight update rule for the evaluation network, a new error is defined:
the weights of the evaluation network have an iteration index t, denoted asThe update rule is designed as
And the number of the first and second electrodes,
wherein β represents a step size; the requirements are satisfiedAndotherwise it will receive the next error state, then the update will end;
the design of the compensator network is such that,the method comprises the steps of generating by a compensator, wherein the compensator is realized by using a three-layer neural network; in the following formulaAndwherein N isa,iRepresenting the number of hidden nodes of the ith control unit in the neural network; the compensator is then designed to:
whereinRepresenting the output, U, of the neural network at the d-th iterationmaxWhich is indicative of the maximum value of the control signal,representing an input of a neural network;andweights for a first layer and a second layer in the neural network, respectively;
the prediction error of the neural network is defined as:
to calculate the weight update rule of the compensator, a new error is defined:
And the number of the first and second electrodes,
wherein β represents a step size; the requirements are satisfiedAndotherwise it will receive the next error state and the update will stop.
The invention has the beneficial effects that:
according to the voltage regulation and current sharing method based on the neural network, a new controller is constructed by adopting a precompensation technology on the basis of a model with unknown voltage drop, and the dynamic calculation of a system is avoided, wherein the secondary auxiliary control of a control unit and a computer network carry out information transmission to regulate voltage and current, so that the voltage regulation and current sharing can be effectively realized, and the stability of the system is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the embodiments or drawings needed to be practical in the prior art description, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings are obtained according to these drawings without creative efforts.
Fig. 1 is a hierarchical control model of a dc microgrid.
Fig. 2 is a voltage regulation and current sharing control scheme based on a neural network.
Fig. 3 is a simulated microgrid model containing 3 power sources and 4 loads.
Fig. 4 is a current sharing effect diagram of simulation.
Fig. 5 is a graph of the voltage regulation effect of the simulation.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without any inventive step, are within the scope of the present invention.
In any embodiment, the hierarchical control model of the dc micro-grid shown in fig. 1 is a dc micro-grid composed of M power sources and N loads, each power source node communicates with its neighbors through the wide area network, that is, the output voltage, current and power of each node are related to the impedance of the unit circuit, and are determined by the outputs of its neighboring parallel units. Each power supply is connected to the bus through a boost DC/DC converter and the load is connected in parallel to the bus. First, initial approximate power distribution is achieved by droop control of the main control unit in fig. 1, then bus voltage is collected from the voltage sensor on the bus side, the converter of each unit collects local voltage and current data, and then voltage error and current error in the collected current configuration (8) - (9) are calculated by collected bus voltage, expected rated voltage, expected current ratio of each unit:
eV(k)=Vcom-Vrated. (8)
and then unifying an auxiliary error system as an input parameter of the neural network model according to the voltage error and the current error in (8) - (9), wherein the neural network control scheme comprises an evaluation network, a compensator network and a compensation controller as shown in fig. 2. The network adopts three layers of neural networks including an input layer, a hidden layer and an output layer, and V is estimated by evaluating the networki (d)(k) Designed in the following form:
evaluating the prediction error of the network as
ξc(k)=Vi d+1(k)-[ψi(k)+γVi d(k+1)] (24)
To calculate the weight update rule of the evaluation network, a new error is designed:
the updating rule of the evaluation network is designed as
And the number of the first and second electrodes,
the design of the compensator network is such that,generated by a compensator implemented using a three-layer neural network. The compensator is then designed to:
the prediction error of the neural network is:
to calculate the weight update rule for the compensator network, a new error is defined:
the update rule calculation for the compensator network is expressed as:
and the number of the first and second electrodes,
the control design of the compensator network and the evaluation network is completed, and finally a new compensation controller is constructed according to the output of the compensator network, wherein the compensation controller is designed as follows:
ui(k+1)=gi(ui(k))+hi(ui(k))υi(k), (5)
the compensation controller constitutes a secondary auxiliary control unit. So far, the whole control scheme is designed.
In order to verify the effectiveness of the model, a simulation model is constructed according to fig. 3, and the required parameters are as follows: rated voltage of the direct current micro-grid is set to be 48V, and resistance of the lead is set to be R1=0.2,R2=0.3,R3=0.25,R40.35. The load resistance is RL1=20, RL2=40,RL340. Inductance of DC/DC converter is L1=L2=L3=L4200 muH, capacitance is set to C1=C2=C3=C41000 μ F. DC supply voltage is set to Vs12V. Further, the discount coefficient γ is set to 095. A compensator and an evaluation network are designed by adopting a three-layer neural network structure, and the number of the ganglion points of the hidden layer is set to be 6. Structure of activation functionIs selected asThe initial weight of these networks is in the interval [ -1,1]To select. The upper weight limit is set to 1. The average flow rates of the four power sources are respectively set to 35%, 30%, 25% and 10%, i.e. d is respectively set1=3.5,d2=3,d3=2.5,d4=1。
The effect graph of current sharing in proportion is shown in fig. 4, and the effect graph of voltage regulation is shown in fig. 5.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims. It should be noted that, in the above embodiments, the various features described in the above embodiments may be combined in any suitable manner, and in order to avoid unnecessary repetition, various combinations that are possible in the present invention are not described again. In addition, any combination of the various embodiments of the present invention can be made, and the same should be considered as the disclosure of the present invention, as long as the combination does not depart from the idea of the present invention.
Claims (5)
1. A voltage regulation and current sharing method based on a neural network is characterized in that the method is used for a direct current micro-grid system consisting of M power supplies and N loads, and each power supply is communicated with the neighbor through a wide area network;
definition VcomIs a DC bus voltage, IiAnd ViExpressed as the output current and output voltage of the ith power supply; the target for proportionally regulating current in a direct current microgrid is expressed as follows:
wherein d isiThe adjustment rate is represented and is a proportional parameter of the adjustment current;
the target for voltage regulation is expressed as:
Vcom=Vrated (2)
wherein VratedRepresenting the rated voltage of the direct current bus, and aiming at regulating the voltage to be stabilized to the rated voltage;
in order to realize voltage regulation and current sharing, a control framework based on a layered structure is provided, and for each source, the control framework comprises a main control unit and an auxiliary control unit; the main control unit comprises a droop controller, a voltage controller and a current controller, and the voltage controller and the current controller in the main control unit are used for regulating the output voltage of the converter and driving the output voltage to a reference voltageThe droop controller is used for stabilizing the voltage and frequency in the microgrid by adding a virtual resistor Ri DTo realize the operation; voltage u for secondary controlleriCompensating the voltage deviation; using an unknown non-linear function f (V)i(k) To describe the voltage loss on the power line, the current share controller is:
assuming that the microgrid is dc and does not produce reactive power, the virtual resistance is set in question asThe current share controller is rewritten as:
Vi(k+1)=Vrated-f(Vi(k))+ui(k) (4)
due to f (V)i(k) Unknown, to avoid calculations, by using precompensation techniques, compensatingThe compensation controller is as follows:
ui(k+1)=gi(ui(k))+hi(ui(k))υi(k), (5)
wherein upsilon isi(k) Is an input to a compensation controller, which is at ui(k) 0 and upsiloni(k) Singularity at 0; and g isiAnd hiIs a controllable nonlinear function;
suppose thatIs the constant resistance of the ith load, GiIs the conductance in the transmission line from the ith converter to the dc bus, the description of the dc microgrid evolves to:
Ii=Gi(Vi+f(Vi)-Vcom). (7)
since all sources want to minimize their own cost, the cost of source i, also called the performance index, is defined as follows:
wherein gamma ∈ (0, 1)]Is a discount factor, RiiIs a positive weight, the performance index depends on the control;
it is therefore necessary to design compensation controls to stabilize (12) and minimize the local performance index of each source, i.e. the control of each genset not only minimizes its own cost, but also stabilizes the error system (12);
According to the bellman optimality principle, the following equation is obtained:
whereinIs the optimal strategy and is the result of the optimization,is the optimal performance index; based on the bellman optimality principle, (15) is written as:
according to (16), upsiloniIs expressed as
In (16), by pairing ViSolving for vi(k) And then an expression for optimal control is obtained:
to solve the optimal control problem, only the optimal solution of equation (15) needs to be obtained; designing a strategy iterative algorithm to obtain the optimal control and optimal value function of the system;
realizing an algorithm based on a neural network so as to complete the implementation of the control scheme; obtaining a control scheme of a generator set node i, wherein the control scheme comprises an evaluation network, a compensator network and a controller; estimating with an evaluation networkThe compensator is implemented by a neural network, which is used for constructingThe controller is used for acquiring ui(k) (ii) a The evaluation network and the compensator network are both realized by adopting a three-layer feedforward neural network;
defining the prediction error of the evaluation network as
To calculate the weight update rule for the evaluation network, a new error is defined:
the weights of the evaluation network have an iteration index τ, denoted asThe update rule is designed as
And the number of the first and second electrodes,
wherein β represents a step size; the requirements are satisfiedAndotherwise it will receive the next error state, then the update will end;
the prediction error of the neural network is defined as:
to calculate the weight update rule of the compensator, a new error is defined:
And the number of the first and second electrodes,
2. The neural network-based voltage regulation and current sharing method of claim 1, wherein the system error includes a current error, a voltage error and a control voltage constructed by a pre-compensation technique, and the voltage error and the current error are respectively defined as:
eV(k)=Vcom-Vrated. (8)
by (6) to (9), there are obtained:
combining the compensation controller (5) and the dynamics (10) - (11) to obtain an auxiliary error system:
Hi=[0 0 hi(ui(k))]T。
3. The neural network-based voltage regulation and current sharing method of claim 1, wherein the strategy iterative algorithm is as follows:
initialization:
Let d equal 1
Iteration:
and (6) ending.
4. The neural network-based voltage regulation and current sharing method of claim 1, wherein the evaluation network is estimated by using an evaluation network implemented by a three-layer neural networkIn the following formula Wherein N isc,iRepresenting the number of hidden nodes of the ith control unit; performance index ViIs the output of the evaluation network of the ith control unit, expressed in the form:
5. The neural network-based voltage regulation and current sharing method of claim 1, wherein the compensator networkThe method comprises the steps of generating by a compensator, wherein the compensator is realized by using a three-layer neural network; in the following formulaAndwherein N isa,iRepresenting the number of hidden nodes of the ith control unit in the neural network; the compensator is then designed to:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111398185.2A CN114039346A (en) | 2021-11-19 | 2021-11-19 | Voltage regulation and current sharing method based on neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111398185.2A CN114039346A (en) | 2021-11-19 | 2021-11-19 | Voltage regulation and current sharing method based on neural network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114039346A true CN114039346A (en) | 2022-02-11 |
Family
ID=80138552
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111398185.2A Pending CN114039346A (en) | 2021-11-19 | 2021-11-19 | Voltage regulation and current sharing method based on neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114039346A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116581770A (en) * | 2022-11-24 | 2023-08-11 | 长春工程学院 | Micro-grid system VSG double-droop control method based on self-adaptive neural network |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011075838A1 (en) * | 2009-12-21 | 2011-06-30 | Audigen Inc. | Method of treating or preventing hearing loss |
CN113189513A (en) * | 2021-04-29 | 2021-07-30 | 电子科技大学 | Ripple-based redundant power supply current sharing state identification method |
-
2021
- 2021-11-19 CN CN202111398185.2A patent/CN114039346A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011075838A1 (en) * | 2009-12-21 | 2011-06-30 | Audigen Inc. | Method of treating or preventing hearing loss |
CN113189513A (en) * | 2021-04-29 | 2021-07-30 | 电子科技大学 | Ripple-based redundant power supply current sharing state identification method |
Non-Patent Citations (1)
Title |
---|
RUI SHI等: "Data-driven current sharing and voltage regulation for DC microgrid with unknown voltage loss", 《2021 INTERNATIOAL CONFERENCE ON SECURITY,PATTERN ANALYSIS, AND CYBERNETICS (SPAC) 》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116581770A (en) * | 2022-11-24 | 2023-08-11 | 长春工程学院 | Micro-grid system VSG double-droop control method based on self-adaptive neural network |
CN116581770B (en) * | 2022-11-24 | 2024-02-20 | 长春工程学院 | Micro-grid system VSG double-droop control method based on self-adaptive neural network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109687526B (en) | Island micro-grid layered distributed control strategy based on consistency theory | |
Wang et al. | Accurate current sharing and voltage regulation in hybrid wind/solar systems: an adaptive dynamic programming approach | |
Alavi et al. | Forecast-based consensus control for DC microgrids using distributed long short-term memory deep learning models | |
Xu et al. | A robust droop-based autonomous controller for decentralized power sharing in DC microgrid considering large-signal stability | |
Nawaz et al. | Mitigation of circulating currents for proportional current sharing and voltage stability of isolated DC microgrid | |
CN104779607B (en) | One of direct-current micro-grid distributed and coordinated control method and system | |
CN108320080B (en) | Energy internet real-time dynamic power distribution method based on two-layer consistency algorithm | |
Chopra et al. | Power-flow-based energy management of hierarchically controlled islanded AC microgrids | |
CN113078645B (en) | Micro-grid parameter self-adaptive control method considering time delay and topology switching | |
Iovine et al. | Nonlinear control of an AC-connected DC MicroGrid | |
Engels et al. | A distributed gossip-based voltage control algorithm for peer-to-peer microgrids | |
CN111725798A (en) | Distributed economic dispatching prediction control method for direct-current micro-grid cluster | |
CN111258211A (en) | Micro-grid frequency control system and method based on fuzzy neuron PID | |
CN106786550B (en) | Distributed control method and device for cost optimization of micro-grid | |
CN114039346A (en) | Voltage regulation and current sharing method based on neural network | |
Yin et al. | Expandable deep width learning for voltage control of three-state energy model based smart grids containing flexible energy sources | |
de Dieu Nguimfack-Ndongmo et al. | Adaptive terminal synergetic-backstepping technique based machine learning regression algorithm for MPPT control of PV systems under real climatic conditions | |
CN110601246A (en) | Direct-current micro-grid current sharing method based on radial basis function neural network prediction | |
Macana et al. | A distributed real-time energy management system for inverter-based microgrids | |
CN112531715A (en) | Droop control multi-terminal direct-current micro-grid load flow calculation method based on virtual resistor | |
Macana et al. | Online energy management strategy for islanded microgrids with feedback linearizing inner controllers | |
CN115987086A (en) | Single-switch DC-DC converter on-line control method based on neural network | |
Liu et al. | Composite passivity-based control of DC/DC boost converters with constant power loads in DC Microgrids | |
Chaturvedi et al. | Reinforcement Learning Based Integrated Control to Improve the Efficiency of DC Microgrids | |
Liu et al. | Optimal power sharing control for dc microgrids via adaptive dynamic programming |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220211 |