CN110854908B - Overvoltage power control method, system and medium for photovoltaic access medium-low voltage distribution network - Google Patents
Overvoltage power control method, system and medium for photovoltaic access medium-low voltage distribution network Download PDFInfo
- Publication number
- CN110854908B CN110854908B CN201911089439.5A CN201911089439A CN110854908B CN 110854908 B CN110854908 B CN 110854908B CN 201911089439 A CN201911089439 A CN 201911089439A CN 110854908 B CN110854908 B CN 110854908B
- Authority
- CN
- China
- Prior art keywords
- output
- active power
- distribution network
- network
- power
- 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.)
- Active
Links
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
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
- H02J3/48—Controlling the sharing of the in-phase component
Abstract
The invention relates to an overvoltage power control method, system and medium for a photovoltaic access medium and low voltage distribution network, wherein in the method, when the output voltage of a grid connection point is lower than the rated voltage, the active power output by a photovoltaic system is completely output to the medium and low voltage distribution network; when the output voltage of the grid-connected point is higher than the rated voltage, the active power output by the photovoltaic system is limited due to the droop control coefficient in order to regulate the voltage to enable the system to stably operate. And establishing an execution neuron network to dynamically modify the droop control coefficient, and updating the execution neuron network by using the output of the evaluation neuron network. The invention can not only ensure that the voltage of the system operates in a rated range, but also reduce the active power loss of the system and improve the permeability of the whole distributed power supply in a power grid.
Description
Technical Field
The invention relates to the field of low-voltage power distribution networks, in particular to an overvoltage power control method, system and medium for a photovoltaic access medium-voltage and low-voltage power distribution network.
Background
With the development of socio-economic, energy and environmental issues are increasingly attracting social attention, and the development and utilization of renewable energy sources are more and more urgent. Solar photovoltaic power generation is rapidly developed in recent years as a sustainable energy alternative mode and is widely applied worldwide, and among them, distributed photovoltaic power generation is most widely applied. By the end of 2018, the installed power generation network of the photovoltaic system reaches 380PKW statistically, which is increased by about 30% compared with 2017 and accounts for about 1.8% of the world power supply, wherein the rooftop photovoltaic power generation accounts for more than 80%.
However, for voltage distribution, the conventional centralized power distribution network is generally radial, and in a steady-state operation state, the voltage gradually decreases along the power flow direction of the feeder line. After a large number of distributed photovoltaic power supplies are connected, the trend flow direction changes, the power direction on a feeder line has great uncertainty, if the access capacity is close to the maximum recommended access capacity allowed by the voltage class (generally, 400V is 200kW, and 10kV is 10MW), the local voltage rise is greatly influenced, and in order to ensure the normal operation of the grid voltage, the power factor of a photovoltaic power station needs to be strictly monitored. In addition, when the distributed photovoltaic power supply is connected to the power distribution network in a large number, due to randomness and intermittence of output power of the distributed photovoltaic power supply, the influence on the network loss of the power distribution network is inevitable, and researches show that the change of the network loss after the distributed photovoltaic power supply is connected to the power distribution network in a large number can not only influence the technical indexes of the power distribution network, but also can cause adverse influence on the economic indexes of the power distribution network.
In order to solve the above problems, an energy storage system such as a regulating device or an integrated battery may be installed to improve voltage loss, for example, a voltage regulating device such as an on-load tap changer and a voltage regulator is installed in a medium-low voltage distribution network, so that the voltage of a load node is controlled within a range conforming to regulations at a low cost. However, due to the limitations of the response speed and the mechanical wear of the equipment, the transformer and the parallel capacitor which comprise overload voltage dividing connectors are difficult to rapidly and frequently correspond to the change of the photovoltaic grid-connected power; and a large amount of energy storage equipment needs a large amount of capital investment, increases the maintenance difficulty and cannot be widely used in the existing medium and low voltage distribution network. In recent years, research has been focused at home and abroad on regulating the reactive power output of the inverter. The method is a common method at present, but the method needs to be provided with an additional reactive power compensation device, so that the maintenance frequency of the equipment is improved, and the reactive power compensation device can only be arranged aiming at one of the phenomena of voltage rise and voltage drop.
Disclosure of Invention
The invention aims to provide an overvoltage power control method and system for a photovoltaic access medium and low voltage distribution network, so as to ensure that the voltage of the system operates within a rated range, reduce the active power loss of the system and improve the permeability of the whole distributed power supply in a power grid.
In a first aspect, an embodiment of the present invention provides an overvoltage power control method for a medium and low voltage distribution network in photovoltaic access, including the following steps:
step S101, setting initial control parameters: rated voltage V of medium-low voltage distribution networkcriMaximum output power P of photovoltaic power supply under certain solar radiation illuminationMPPTDroop control coefficient mT；
Step S102, according to the rated voltage V of the medium and low voltage distribution networkcriMaximum output power P of photovoltaic power supplyMPPTDroop control coefficientmTAnd the following formula (1) controls the active power output by the photovoltaic system in situ to obtain the active power P of the grid-connected pointinv；
Pinv＝PMPPT-mT(V(t)-Vcri) (1)
Wherein m isTV (t) is the voltage of a connection point of a medium-voltage distribution network and a low-voltage distribution network in photovoltaic access at the moment t;
step S103, inputting a pre-trained multilayer execution neuron network to process and output m by taking voltage drop delta V and active power attenuation as input quantitiesADP(ii) a Wherein Δ V is V (t) and the rated voltage VcriActive power attenuation of PMPPTAnd grid-connected active power PinvA difference of (d);
step S104, output quantity m of the multi-layer execution neuron networkADPAnd formula (2) update mTAnd returning to step S102;
mT＝mT+mADP (2)。
wherein the step S102 includes:
when V (t) is lower than VcriIn the process, all active power output by the photovoltaic system is output to the medium and low voltage distribution network;
when V (t) exceeds VcriTime, the active power of the output of the photovoltaic system is controlled by the droop control coefficient mTAnd is limited.
Wherein the multi-layer execution neuron network comprises an input layer, an intermediate layer and an output layer, wherein the input layer comprises 6 input nodes X1…X6Said intermediate layers comprising n layers, each layer having n intermediate nodes, said output layer comprising an output node U;
wherein, X1Is the per unit value, X, of the voltage sag Δ V2、X3The voltage drop DeltaV is the per unit value X of one-time stepping delay and two-time stepping delay4To limit the power PcurtPer unit value of (X)5、X6Respectively, limit power PcurtOutputting the per unit value of one-step delay and two-step delayNode U outputs mADP；
Wherein the output m of the multi-layer execution neuron networkADPThis can be derived from the following formula:
in the above formula, wkPerforming the kth hidden layer H in a neural network for multiple layerskThe weight to the output layer is determined,
wijfor the ith input node XiTo jth hidden layer HjI e (1,2,3,4,5,6), j e (1,2,3,4,5, 6).
Preferably, the method further comprises:
step S105, executing output quantity m of the neural network by the plurality of layersADPInputting the voltage drop delta V and the active power attenuation as input quantities into a pre-trained multilayer evaluation neuron network for processing and outputting J (t);
and S106, optimizing the weight of the multilayer execution neuron network according to the output J (t) of the multilayer evaluation neuron network, and returning to the step S103.
Wherein the multi-layer evaluation neuron network comprises an input layer, an intermediate layer and an output layer, wherein the input layer comprises 7 input nodes X1…X6U; the intermediate layers comprise n layers, each layer having n intermediate nodes; the output layer comprises an output node J;
where U is the output m of the executive neuron networkADPThe output J (t) of J is shown in equation (3) below:
w in formula (3)j1Evaluating the jth hidden layer H in a neuron network for multiple layersjThe weight to the output layer is determined,
wijevaluating the ith input node X in a neural network for multiple layersiTo jth hidden layer HjThe weight of (c).
Wherein, the weight optimization process in step S106 is shown in the following formula (4):
where eta is the learning rate, ekPerforming output m of neural network for multiple layersADPDifference from the desired output j (t).
Wherein the output of the multi-layer neuronal network J (t) satisfies the Bellman optimality principle, as shown in equation (5) below:
wherein r (t) is the direct power cost generated at time t u (t), which is shown in the following formula (6):
wherein, c, a1，a2，a3，a4，a5、a6And UcGiven a constant.
In a second aspect, an embodiment of the present invention provides an overvoltage power control system for a medium and low voltage distribution network in photovoltaic access, which is used to implement the overvoltage power control method for the medium and low voltage distribution network in photovoltaic access, and includes:
an initialization unit for setting initial control parameters: rated voltage V of medium-low voltage distribution networkcriMaximum output power P of photovoltaic power supply under certain solar radiation illuminationMPPTDroop control coefficient mT；
Active power control unitFor regulating the rated voltage V of the medium-low voltage distribution networkcriMaximum output power P of photovoltaic power supplyMPPTDroop control coefficient mTAnd the following formula (1) controls the active power output by the photovoltaic system in situ to obtain the active power P of the grid-connected pointinv；
Pinv＝PMPPT-mT(V(t)-Vcri) (1)
Wherein m isTV (t) is the voltage of a connection point of a medium-voltage distribution network and a low-voltage distribution network in photovoltaic access at the moment t;
a first neural network unit for inputting a pre-trained multilayer execution neuron network with voltage drop Δ V and active power attenuation as input quantities to process and output mADP(ii) a Wherein Δ V is V (t) and the rated voltage VcriActive power attenuation of PMPPTAnd grid-connected active power PinvA difference of (d);
a first update unit for executing an output quantity m of the neural network according to the plurality of layersADPAnd formula (2) update mTAnd sending the active power to the active power control unit;
mT＝mT+mADP (2)。
preferably, the system further comprises:
a second neural network unit for performing an output quantity m of the neural network in the plurality of layersADPInputting the voltage drop delta V and the active power attenuation as input quantities into a pre-trained multilayer evaluation neuron network for processing and outputting J (t);
and the second updating unit is used for optimizing the weight of the multilayer execution neuron network according to the output J (t) of the multilayer evaluation neuron network and sending the optimized weight to the first neural network unit.
In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the overvoltage power control method for a low-voltage distribution network in photovoltaic access according to the embodiment.
The embodiment of the invention provides an overvoltage power control method and system for a photovoltaic access medium and low voltage distribution network and a computer readable storage medium, wherein when the output voltage of a grid-connected point is lower than the rated voltage, all the active power output by a photovoltaic system is output to the medium and low voltage distribution network; when the output voltage of the grid-connected point is higher than the rated voltage, in order to regulate the voltage to enable the system to stably operate, the active power output by the photovoltaic system is limited due to the droop control coefficient, an execution neuron network is established to dynamically correct the droop control coefficient, and the execution neuron network is updated by the output of the evaluation neuron network. The embodiment of the invention not only can ensure that the voltage of the system operates in a rated range, but also can reduce the active power loss of the system and improve the permeability of the whole distributed power supply in a power grid.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings. Of course, not all of the advantages described above need to be achieved at the same time in the practice of any one product or method of the invention.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, 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 can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of an overvoltage power control method for a medium-low voltage distribution network in photovoltaic access according to a first embodiment of the present invention.
Fig. 2 is a schematic diagram of an overvoltage power control method for a medium-low voltage distribution network in photovoltaic access according to a first embodiment of the present invention.
Fig. 3 is a schematic flow chart of an overvoltage power control method for a medium-low voltage distribution network in photovoltaic access according to a second embodiment of the present invention.
Fig. 4 is a schematic diagram of an overvoltage power control method for a medium-low voltage distribution network in photovoltaic access according to a second embodiment of the present invention.
Fig. 5 is a system framework diagram of a photovoltaic access medium and low voltage distribution network overvoltage power control method according to a third embodiment of the present invention.
Fig. 6 is a system framework diagram of a photovoltaic access medium and low voltage distribution network overvoltage power control method according to the fourth embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that, in order to avoid obscuring the present invention with unnecessary details, only the structures closely related to the solution according to the present invention are shown in the drawings, and other details not closely related to the present invention are omitted.
Example one
The first embodiment of the present invention provides an overvoltage power control method for a photovoltaic access medium and low voltage distribution network, a flow chart of which is shown in fig. 1, and fig. 2 is a schematic diagram of the method, and referring to fig. 1-2, the first embodiment of the method includes the following steps S101-S104:
step S101, setting initial control parameters: rated voltage V of medium-low voltage distribution networkcriMaximum output power P of photovoltaic power supply under certain solar radiation illumination (unit kW)MPPTDroop control coefficient mT；
Step S102, according to the rated voltage V of the medium and low voltage distribution networkcriMaximum output power P of photovoltaic power supplyMPPTDroop control coefficient mTAnd the following formula (1) is carried out on the active power output by the photovoltaic systemGround control to obtain the active power P of the grid-connected pointinv；
Pinv＝PMPPT-mT(V(t)-Vcri) (1)
Wherein m isTThe droop coefficient is kW/V, and V (t) is the voltage of a connecting point of a medium-low voltage distribution network in photovoltaic access at the moment t;
step S103, inputting a pre-trained multilayer execution neuron network to process and output m by taking voltage drop delta V and active power attenuation as input quantitiesADP(ii) a Wherein Δ V is V (t) and the rated voltage VcriActive power attenuation of PMPPTAnd grid-connected active power PinvA difference of (d);
step S104, output quantity m of the multi-layer execution neuron networkADPAnd formula (2) update mTAnd returning to step S102;
mT＝mT+mADP (2)。
wherein the step S102 includes:
in the step, the output active power of the photovoltaic system is controlled on site based on a medium and low voltage distribution network voltage-active power droop control method; specifically, the method comprises the following steps:
when V (t) is lower than VcriIn the process, all active power output by the photovoltaic system is output to the medium and low voltage distribution network;
when V (t) exceeds VcriTime, the active power of the output of the photovoltaic system is controlled by the droop control coefficient mTAre limited;
wherein the power P is limitedcurtCan be represented by the following formula:
Pcurt＝PMPPT-Pinv。
wherein the multi-layer execution neuron network comprises an input layer, an intermediate layer and an output layer, wherein the input layer comprises 6 input nodes X1…X6Said intermediate layers comprising n layers, each layer having n intermediate nodes, said output layer comprising an output node U;
wherein, X1Is the per unit value, X, of the voltage sag Δ V2、X3The voltage drop DeltaV is the per unit value X of one-time stepping delay and two-time stepping delay4To limit the power PcurtPer unit value of (X)5、X6Respectively, limit power PcurtThe output node U outputs m according to the per unit value of one-time stepping delay and two-time stepping delayADP；
Wherein the output m of the multi-layer execution neuron networkADPThis can be derived from the following formula:
in the above formula, wkPerforming the kth hidden layer H in a neural network for multiple layerskThe weight to the output layer is determined,
wijfor the ith input node XiTo jth hidden layer HjI e (1,2,3,4,5,6), j e (1,2,3,4,5, 6).
Example two
Based on the first embodiment of the present invention, the second embodiment of the present invention provides another overvoltage power control method for a medium and low voltage distribution network in a photovoltaic access, the flowchart of which is shown in fig. 3, fig. 4 is a schematic diagram thereof, referring to fig. 3-4, except for steps S101-S104 of the method of the first embodiment, the method of the second embodiment includes the following steps S105-S106:
step S105, executing output quantity m of the neural network by the plurality of layersADPInputting the voltage drop delta V and the active power attenuation as input quantities into a pre-trained multilayer evaluation neuron network for processing and outputting J (t);
and S106, optimizing the weight of the multilayer execution neuron network according to the output J (t) of the multilayer evaluation neuron network, and returning to the step S103.
Wherein the multi-layer evaluation neuron network comprises an input layer, an intermediate layer and an output layer, wherein the input layer comprises 7 input nodes X1…X6、U(ii) a The intermediate layers comprise n layers, each layer having n intermediate nodes; the output layer comprises an output node J;
where U is the output m of the executive neuron networkADPThe output J (t) of J is shown in equation (3) below:
w in formula (3)j1Evaluating the jth hidden layer H in a neuron network for multiple layersjThe weight to the output layer is determined,
wijevaluating the ith input node X in a neural network for multiple layersiTo jth hidden layer HjThe weight of (c).
Wherein, the weight optimization process in step S106 is shown in the following formula (4):
where η is the learning rate and is initialized to 0.1, ekPerforming output m of neural network for multiple layersADPDifference from desired output J (t), i.e. ek＝mADP-J(t)。
Wherein the output of the multi-layer neuronal network J (t) satisfies the Bellman optimality principle, as shown in equation (5) below:
wherein r (t) is the direct power cost generated at time t u (t), which is shown in the following formula (6):
wherein, c, a1，a2，a3，a4，a5、a6And UcGiven a constant, c is 0 or 1, a1…a6Between 0 and 1, and the sum is 1. U shapecTo balance the power cost, set to 0.
EXAMPLE III
The third embodiment of the present invention provides an overvoltage power control system for a medium and low voltage distribution network in photovoltaic access, which is used to implement the overvoltage power control method for the medium and low voltage distribution network in photovoltaic access described in the first embodiment, fig. 5 is a schematic diagram of a framework of the system described in the third embodiment, and referring to fig. 5, the system includes:
an initialization unit 1, configured to set initial control parameters: rated voltage V of medium-low voltage distribution networkcriMaximum output power P of photovoltaic power supply under certain solar radiation illuminationMPPTDroop control coefficient mT；
An active power control unit 2 for controlling the active power according to the rated voltage V of the medium and low voltage distribution networkcriMaximum output power P of photovoltaic power supplyMPPTDroop control coefficient mTAnd the following formula (1) controls the active power output by the photovoltaic system in situ to obtain the active power P of the grid-connected pointinv；
Pinv＝PMPPT-mT(V(t)-Vcri) (1)
Wherein m isTV (t) is the voltage of a connection point of a medium-voltage distribution network and a low-voltage distribution network in photovoltaic access at the moment t;
a first neural network unit 3 for inputting a pre-trained multi-layer execution neuron network with the voltage drop Δ V and the active power attenuation as input quantities to process and output mADP(ii) a Wherein Δ V is V (t) and the rated voltage VcriActive power attenuation of PMPPTAnd grid-connected active power PinvA difference of (d);
a first updating unit 4 for executing an output quantity m of the neural network according to the plurality of layersADPAnd formula (2) update mTAnd sending the active power to the active power control unit;
mT＝mT+mADP (2)。
it should be noted that the system described in the third embodiment corresponds to the method described in the first embodiment, and therefore, a part of the system described in the third embodiment that is not described in detail in the third embodiment can be obtained by referring to the content of the method described in the first embodiment, and is not described again here.
Example four
Based on the third embodiment of the present invention, the fourth embodiment of the present invention provides another overvoltage power control method for a medium and low voltage distribution network in photovoltaic access, a frame diagram of which is shown in fig. 6, and referring to fig. 6, in addition to the content described in the third embodiment, the system described in the fourth embodiment further includes:
a second neural network unit 5 for executing an output quantity m of the neural network in the plurality of layersADPInputting the voltage drop delta V and the active power attenuation as input quantities into a pre-trained multilayer evaluation neuron network for processing and outputting J (t);
and the second updating unit 6 is configured to optimize the weights of the multilayer execution neuron network according to the output j (t) of the multilayer evaluation neuron network, and send the optimized weights to the first neural network unit.
It should be noted that the system according to the fourth embodiment corresponds to the method according to the second embodiment, and therefore, a part of the system according to the fourth embodiment that is not described in detail can be obtained by referring to the content of the method according to the second embodiment, and is not described again here.
EXAMPLE five
The fifth embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the overvoltage power control method for the low-voltage distribution network in the photovoltaic access according to the first or second embodiment.
It is to be noted that, based on the content, those skilled in the art can clearly understand that the embodiments of the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) to implement the methods/systems described in the foregoing embodiments.
The foregoing is directed to embodiments of the present invention, and it is understood that various modifications and improvements can be made by those skilled in the art without departing from the spirit of the invention.
Claims (9)
1. An overvoltage power control method for a photovoltaic access medium and low voltage distribution network is characterized by comprising the following steps:
step S101, setting initial control parameters: rated voltage V of medium-low voltage distribution networkcriMaximum output power P of photovoltaic power supply under certain solar radiation illuminationMPPTDroop control coefficient mT；
Step S102, according to the rated voltage V of the medium and low voltage distribution networkcriMaximum output power P of photovoltaic power supplyMPPTDroop control coefficient mTAnd the following formula (1) controls the active power output by the photovoltaic system in situ to obtain the active power P of the grid-connected pointinv；
Pinv＝PMPPT-mT(V(t)-Vcri) (1)
Wherein m isTV (t) is the voltage of a connection point of a medium-voltage distribution network and a low-voltage distribution network in photovoltaic access at the moment t;
step S103, attenuating P with voltage drop delta V and active powercurtInputting a pre-trained multi-layer execution neuron network as input quantity to process and output mADP(ii) a Wherein Δ V is V (t) and the rated voltage VcriActive power attenuation of PMPPTAnd are combinedNet active power PinvA difference of (d);
step S104, output quantity m of the multi-layer execution neuron networkADPAnd formula (2) update mTAnd returning to step S102;
mT＝mT+mADP (2)
the multi-layer execution neuron network comprises an input layer, a middle layer and an output layer, wherein the input layer comprises 6 input nodes X1…X6Said intermediate layers comprising n layers, each layer having n intermediate nodes, said output layer comprising an output node U;
wherein, X1Is the per unit value, X, of the voltage sag Δ V2、X3The voltage drop DeltaV is the per unit value X of one-time stepping delay and two-time stepping delay4To limit the power PcurtPer unit value of (X)5、X6Are respectively PcurtThe output node U outputs m according to the per unit value of one-time stepping delay and two-time stepping delayADP；
Wherein the output m of the multi-layer execution neuron networkADPThis can be derived from the following formula:
in the above formula, wjPerforming the jth hidden layer H in a neural network for multiple layersjThe weight to the output layer is determined,
wijfor the ith input node XiTo jth hidden layer HjI e (1,2,3,4,5,6), j e (1,2,3,4,5, 6).
2. The overvoltage power control method for the low-voltage distribution network in the photovoltaic access according to claim 1, wherein the step S102 comprises:
when V (t) is lower than VcriTime, output of photovoltaic systemThe active power of the power grid is completely output to a medium-low voltage distribution network;
when V (t) exceeds VcriTime, the active power of the output of the photovoltaic system is controlled by the droop control coefficient mTAnd is limited.
3. The method for overvoltage power control of a low voltage distribution network in photovoltaic access according to any one of claims 1-2, characterized in that the method further comprises:
step S105, executing output quantity m of the neural network by the plurality of layersADPVoltage drop Δ V, active power attenuation PcurtInputting a pre-trained multilayer evaluation neuron network as an input quantity to process and output J (t);
and S106, optimizing the weight of the multilayer execution neuron network according to the output J (t) of the multilayer evaluation neuron network, and returning to the step S103.
4. The overvoltage power control method for the low-voltage distribution network in the photovoltaic access according to claim 3, wherein the multilayer evaluation neuron network comprises an input layer, an intermediate layer and an output layer, wherein the input layer comprises 7 input nodes X1…X6U; the intermediate layers comprise n layers, each layer having n intermediate nodes; the output layer comprises an output node J;
where U is the output m of the executive neuron networkADPThe output J (t) of J is shown in equation (3) below:
w in formula (3)j1Evaluating the jth hidden layer H in a neuron network for multiple layersjThe weight to the output layer is determined,
wijevaluating the ith input node X in a neural network for multiple layersiImplicit to jthLayer HjThe weight of (c).
5. The method for controlling the overvoltage power of the low-voltage distribution network in the photovoltaic access according to claim 4, wherein the weight optimization process in the step S106 is shown in the following formula (4):
where eta is the learning rate, ekPerforming output m of neural network for multiple layersADPDifference from the desired output j (t).
6. The overvoltage power control method for the medium and low voltage distribution network in the photovoltaic access according to claim 5, wherein the output J (t) of the multi-layer evaluation neuron network satisfies Bellman optimality principle, as shown in the following formula (5):
wherein r (t) is the direct power cost generated at time t u (t), which is shown in the following formula (6):
wherein, c, a1，a2，a3，a4，a5、a6And UcGiven a constant.
7. An overvoltage power control system of a low-voltage distribution network in photovoltaic access, which is used for realizing the control method of any one of claims 1-2, and is characterized by comprising the following steps:
an initialization unit for setting initial control parameters: rated voltage V of medium-low voltage distribution networkcriUnder a certain solar radiation illuminationMaximum output power P of photovoltaic power supplyMPPTDroop control coefficient mT；
An active power control unit for controlling the active power according to the rated voltage V of the medium-low voltage distribution networkcriMaximum output power P of photovoltaic power supplyMPPTDroop control coefficient mTAnd the following formula (1) controls the active power output by the photovoltaic system in situ to obtain the active power P of the grid-connected pointinv；
Pinv＝PMPPT-mT(V(t)-Vcri) (1)
Wherein m isTV (t) is the voltage of a connection point of a medium-voltage distribution network and a low-voltage distribution network in photovoltaic access at the moment t;
a first neural network unit for attenuating P active power with a voltage drop of Δ VcurtInputting a pre-trained multi-layer execution neuron network as input quantity to process and output mADP(ii) a Wherein Δ V is V (t) and the rated voltage VcriDifference of (A), PcurtIs PMPPTAnd grid-connected active power PinvA difference of (d);
a first update unit for executing an output quantity m of the neural network according to the plurality of layersADPAnd formula (2) update mTAnd sending the active power to the active power control unit;
mT＝mT+mADP (2)。
8. an overvoltage power control system of a low-voltage distribution network in photovoltaic access, which is used for realizing the control method of any one of claims 3-6, and is characterized by comprising the following steps:
an initialization unit for setting initial control parameters: rated voltage V of medium-low voltage distribution networkcriMaximum output power P of photovoltaic power supply under certain solar radiation illuminationMPPTDroop control coefficient mT；
An active power control unit for controlling the active power according to the rated voltage V of the medium-low voltage distribution networkcriMaximum output power P of photovoltaic power supplyMPPTDroop control coefficient mTAnd the following formula (1) controls the active power output by the photovoltaic system in situ to obtain the active power P of the grid-connected pointinv；
Pinv＝PMPPT-mT(V(t)-Vcri) (1)
Wherein m isTV (t) is the voltage of a connection point of a medium-voltage distribution network and a low-voltage distribution network in photovoltaic access at the moment t;
a first neural network unit for inputting a pre-trained multilayer execution neuron network with voltage drop Δ V and active power attenuation as input quantities to process and output mADP(ii) a Wherein Δ V is V (t) and the rated voltage VcriActive power attenuation of PMPPTAnd grid-connected active power PinvA difference of (d);
a first update unit for executing an output quantity m of the neural network according to the plurality of layersADPAnd formula (2) update mTAnd sending the active power to the active power control unit;
mT＝mT+mADP (2)
a second neural network unit for performing an output quantity m of the neural network in the plurality of layersADPVoltage drop Δ V, active power attenuation PcurtInputting a pre-trained multilayer evaluation neuron network as an input quantity to process and output J (t);
and the second updating unit is used for optimizing the weight of the multilayer execution neuron network according to the output J (t) of the multilayer evaluation neuron network and sending the optimized weight to the first neural network unit.
9. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program realizing the steps of the method for overvoltage power control of a low voltage distribution network in a photovoltaic access according to any one of claims 1 to 6 when being executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911089439.5A CN110854908B (en) | 2019-11-08 | 2019-11-08 | Overvoltage power control method, system and medium for photovoltaic access medium-low voltage distribution network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911089439.5A CN110854908B (en) | 2019-11-08 | 2019-11-08 | Overvoltage power control method, system and medium for photovoltaic access medium-low voltage distribution network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110854908A CN110854908A (en) | 2020-02-28 |
| CN110854908B true CN110854908B (en) | 2021-12-07 |
Family
ID=69600074
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911089439.5A Active CN110854908B (en) | 2019-11-08 | 2019-11-08 | Overvoltage power control method, system and medium for photovoltaic access medium-low voltage distribution network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110854908B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112904930B (en) * | 2021-01-21 | 2022-03-25 | 山东大学 | Maximum power point tracking control method of medium-voltage photovoltaic power generation system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108258719A (en) * | 2016-12-28 | 2018-07-06 | 北京金风科创风电设备有限公司 | Method for controlling converter to absorb active power, converter controller and converter |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140139260A1 (en) * | 2012-11-21 | 2014-05-22 | Sunedison Llc | Anti-islanding for grid tied inverters |
-
2019
- 2019-11-08 CN CN201911089439.5A patent/CN110854908B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108258719A (en) * | 2016-12-28 | 2018-07-06 | 北京金风科创风电设备有限公司 | Method for controlling converter to absorb active power, converter controller and converter |
Non-Patent Citations (1)
| Title |
|---|
| 组合式电压互感器二次回路过电压抑制技术;王廷凰等;《现代建筑电气》;20140513;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110854908A (en) | 2020-02-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hosseinipour et al. | Virtual inertia control of PV systems for dynamic performance and damping enhancement of DC microgrids with constant power loads | |
| US11387651B2 (en) | Coordinated voltage control and reactive power regulation between transmission and distribution systems | |
| Jahangiri et al. | Distributed Volt/VAr control by PV inverters | |
| Bhatti | AGC of two area power system interconnected by AC/DC links with diverse sources in each area | |
| Shen et al. | Adaptive wide‐area power oscillation damper design for photovoltaic plant considering delay compensation | |
| Arya et al. | AGC of a two‐area multi‐source power system interconnected via AC/DC parallel links under restructured power environment | |
| Farooq et al. | Power generation control of restructured hybrid power system with FACTS and energy storage devices using optimal cascaded fractional‐order controller | |
| Sadiq et al. | A review of STATCOM control for stability enhancement of power systems with wind/PV penetration: Existing research and future scope | |
| Sayadi et al. | Two‐layer volt/var/total harmonic distortion control in distribution network based on PVs output and load forecast errors | |
| CN113224769A (en) | Multi-time scale power distribution network voltage optimization method considering photovoltaic multi-state adjustment | |
| CN112467748A (en) | Double-time-scale distributed voltage control method and system for three-phase unbalanced active power distribution network | |
| Khorram-Nia et al. | A novel stochastic framework for the optimal placement and sizing of distribution static compensator | |
| CN110854908B (en) | Overvoltage power control method, system and medium for photovoltaic access medium-low voltage distribution network | |
| Kumar et al. | Reactive power control in renewable rich power grids: A literature review | |
| Verma et al. | An extensive study on optimization and control techniques for power quality improvement | |
| Sahu et al. | Operational hosting capacity‐based sustainable energy management and enhancement | |
| CN116388262A (en) | Reactive power optimization method and system for distributed photovoltaic distribution network based on multi-objective optimization | |
| Maharjan | Voltage regulation of low voltage distribution networks | |
| CN113013884B (en) | Three-section type reactive voltage control method for photovoltaic power distribution system with high permeability | |
| CN111769570B (en) | Day-ahead two-stage dynamic reactive power reserve optimization method and system considering transient voltage constraint and storage medium | |
| EP3226374B1 (en) | Method and control device for controlling a power grid | |
| Maharjan et al. | Adaptive droop-based active power curtailment method for overvoltage prevention in low voltage distribution network | |
| Kim et al. | Economic analysis on multi-terminal VSC HVDC systems with wind farms based on hierarchical optimal power flow with stability constraint | |
| CN108985579B (en) | Power supply configuration planning method and system | |
| Elsaied et al. | Optimal sliding mode control for frequency stabilization of hybrid renewable energy systems |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |