CN114362249B - Source load system countercurrent prevention control method and device and source load system - Google Patents
Source load system countercurrent prevention control method and device and source load system Download PDFInfo
- Publication number
- CN114362249B CN114362249B CN202210101374.7A CN202210101374A CN114362249B CN 114362249 B CN114362249 B CN 114362249B CN 202210101374 A CN202210101374 A CN 202210101374A CN 114362249 B CN114362249 B CN 114362249B
- Authority
- CN
- China
- Prior art keywords
- power
- current
- electric load
- power supply
- predicted value
- 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
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000002265 prevention Effects 0.000 title claims abstract description 32
- 238000004146 energy storage Methods 0.000 claims description 65
- 210000002569 neuron Anatomy 0.000 claims description 61
- 238000013528 artificial neural network Methods 0.000 claims description 59
- 230000000151 anti-reflux effect Effects 0.000 claims description 26
- 230000015654 memory Effects 0.000 claims description 19
- 230000002441 reversible effect Effects 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 14
- 230000003287 optical effect Effects 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 9
- 210000004027 cell Anatomy 0.000 claims description 7
- 238000007599 discharging Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 6
- 238000010992 reflux Methods 0.000 claims description 5
- 230000003111 delayed effect Effects 0.000 claims description 4
- 238000010248 power generation Methods 0.000 description 9
- 239000010410 layer Substances 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000004913 activation Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 229920002430 Fibre-reinforced plastic Polymers 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000011151 fibre-reinforced plastic Substances 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- 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
- H02J3/28—Arrangements for balancing of the load in a network by storage of energy
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a source load system backflow prevention control method, a device and a source load system, which are used for acquiring current power and current electric load power, determining a power predicted value of a preset future time period based on the current power and determining an electric load power predicted value of the preset future time period based on the current electric load power, obtaining grid-connected point power of the preset future time period according to the power predicted value, the electric load power predicted value and a backflow prevention threshold, and executing backflow prevention operation at a designated moment when backflow is determined to exist according to the grid-connected point power, wherein the designated moment is as follows: and a moment before the countercurrent moment corresponding to the grid-connected point power in a preset future time period. According to the invention, the countercurrent prediction is carried out on the preset future time period at the current moment, and the countercurrent prevention operation is carried out in advance at the moment before the countercurrent prevention operation is carried out, so that the situation that the grid connection point has countercurrent before the countercurrent prevention operation is carried out is effectively avoided, and the safety of the power grid is improved.
Description
Technical Field
The invention relates to the technical field of new energy, in particular to a method and a device for controlling countercurrent prevention of a source load system and the source load system.
Background
With the continuous development of energy storage technology, a source load system integrating a new energy power generation system, an energy storage system and an electric load system becomes a research hot spot. In the source load system, when the output power of the new energy source is larger than the sum of the stored energy charging power and the electric load power, or the sum of the output power of the new energy source and the stored energy discharging power is larger than the electric load power, the electric power which is not completely consumed by the source load system can be sent into the power grid, and the current direction which is transmitted to the power grid line by the source load system is opposite to the conventional current direction, so that the current which is opposite to the conventional current direction is called as 'countercurrent' for convenience of distinguishing. According to the requirements of the national grid company, the new energy power generation system needs to be designed into an irreversible grid connection mode, and when the reverse current power is detected to exceed 5% of the rated output power, the source load system needs to stop transmitting power to the grid line within 0.5s-2 s.
In the existing anti-backflow control technology, most of the anti-backflow control technology is to monitor grid-connected point power in real time, and when backflow occurs, new energy power is reduced or energy storage charging power is increased (or energy storage discharging power is reduced). However, due to the transmission delay and the control time length of the data line, before the anti-backflow operation is executed, the grid connection point can have backflow for a certain time, so that the safety of the power grid is affected.
Disclosure of Invention
In view of the above, the invention discloses a method and a device for controlling the countercurrent of a source load system and the source load system, so as to realize that when the countercurrent exists in a preset future time period, the countercurrent prevention operation is executed in advance at a time before the countercurrent time, thereby effectively avoiding the condition that the grid connection point has a certain time of countercurrent before the countercurrent prevention operation is executed, and further improving the safety of a power grid.
A method for controlling the anti-reflux of a source load system comprises the following steps:
acquiring current power supply power and current electric load power;
acquiring a power supply power predicted value of a preset future time period determined based on the current power supply power, and an electric load power predicted value of the preset future time period determined based on the current electric load power;
obtaining grid-connected point power of the preset future time period according to the power predicted value of the power supply, the power predicted value of the electric load and an anti-backflow threshold value;
judging whether countercurrent exists or not according to the grid-connected point power;
if the countercurrent exists, executing the countercurrent prevention operation at the appointed moment, wherein the appointed moment is as follows: and a moment before the countercurrent moment corresponding to the grid-connected point power in the preset future time period.
Optionally, the obtaining a power supply power predicted value of a preset future time period determined based on the current power supply and an electric load power predicted value of the preset future time period determined based on the current electric load power includes:
inputting the current power supply power to a pre-constructed power supply power prediction model to obtain the power supply power prediction value;
inputting the current electric load power into a pre-constructed electric load power prediction model to obtain the electric load power prediction value;
the power supply power prediction model is obtained after training an LSTM_BP deep neural network by adopting historical power supply power data, the electric load power prediction model is obtained after training the LSTM_BP deep neural network by adopting historical electric load power data, and the LSTM_BP deep neural network is determined based on LSTM neurons and BP neurons.
Optionally, the construction process of the lstm_bp deep neural network includes:
inserting one of said BP neurons between two or more of said LSTM neurons to form a sub-neuron;
and at least one sub-neuron is connected in series and parallel, and an output weight is set in the last layer, so that the LSTM_BP deep neural network is constructed.
Optionally, the method further comprises:
acquiring latest power supply power data and latest electric load power data;
updating the predicted neural network weight of the LSTM_BP deep neural network according to the latest power supply power data and the latest electric load power data;
wherein the predicted neural network weights include: forgetting gate weight W in the LSTM neuron F (k) Input gate selection state weight W I (k) Input the intrinsic state weight W of the door x (k) Outputting the gate weight W o (k) The method comprises the steps of carrying out a first treatment on the surface of the BP network weight W in the BP neuron b (k)。
Optionally, the LSTM neuron comprises: forget gate, input gate and output gate;
the forgetting gate is used for determining the forgetted information of the data stored in the memory unit in the LSTM neural network through the sigmoid neuron, wherein the last moment output item in the memory unit in the forgetting gate is delayed by the current moment output item to change z -1 The obtained product;
the input gate is used for determining data which are reserved in the memory unit in the current data through the sigmoid neuron and the tanh neuron;
the output gate is used for determining output data in the memory unit through the sigmoid neuron and the tanh neuron, and the current state of the memory unit in the output gate is delayed to change z through the current state of the memory unit at the last moment -1 The obtained product.
Optionally, if the source load system includes energy storage, the obtaining the current power supply and the current electric load power further includes: and acquiring the current energy storage power.
Optionally, the anti-backflow threshold is determined based on an absolute value of a maximum prediction error of the power supply and an absolute value of a maximum prediction error of the electrical load.
Optionally, the method further comprises:
re-determining the maximum prediction error absolute value of the power supply every preset time period to obtain the maximum prediction error absolute value of the latest power supply, and re-determining the maximum prediction error absolute value of the electric load to obtain the maximum prediction error absolute value of the latest electric load;
and determining the latest anti-backflow threshold according to the absolute value of the maximum prediction error of the latest power supply and the absolute value of the maximum prediction error of the latest electric load.
Optionally, the obtaining the grid-connected point power of the preset future time period according to the power predicted value of the power supply, the power predicted value of the electric load and the anti-backflow threshold value includes:
if the source load system comprises energy storage, acquiring current energy storage power, and acquiring the grid-connected point power of the preset future time period according to the power supply power predicted value, the electric load power predicted value, the current energy storage power and an anti-reflux threshold value;
And if the energy storage is not included in the source load system, obtaining grid-connected point power of the preset future time period according to the power predicted value of the power supply, the power predicted value of the electric load and the anti-reflux threshold value.
Optionally, if the countercurrent exists, performing the anti-countercurrent operation at the designated moment, including:
determining the specified time and a maximum value of the reflux for the preset future time period when the existence of the reflux is determined;
judging whether the current time reaches the appointed time or not;
if yes, judging whether the energy storage exists in the control allowance or not if the source load system comprises the energy storage;
if so, increasing the energy storage charging power or reducing the energy storage discharging power according to the countercurrent maximum value.
Optionally, the method further comprises:
and when the source load system does not comprise the energy storage or the energy storage does not have the control allowance, reducing power supply or disconnecting part of power supply components according to the reverse current maximum value.
Optionally, when the source load system is an optical storage load system, the current source power includes: current photovoltaic power;
the obtaining a power supply predicted value of a preset future time period determined based on the current power supply and an electric load power predicted value of the preset future time period determined based on the current electric load power includes:
Determining a photovoltaic power forecast for a preset future time period based on the current photovoltaic power, and determining an electrical load power forecast for the preset future time period based on the current electrical load power;
and obtaining the photovoltaic power predicted value and the electric load power predicted value.
A source load system anti-reflux control device, comprising:
a power acquisition unit for acquiring current power supply power and current electric load power;
a predicted value acquisition unit configured to acquire a power supply power predicted value for a preset future period of time determined based on the current power supply power, and an electric load power predicted value for the preset future period of time determined based on the current electric load power;
the grid-connected point power determining unit is used for obtaining grid-connected point power of the preset future time period according to the power predicted value of the power supply, the power predicted value of the electric load and the backflow prevention threshold value;
the judging unit is used for judging whether countercurrent exists according to the grid-connected point power;
the anti-backflow executing unit is used for executing anti-backflow operation at a designated time when the judging unit judges that the backflow exists, wherein the designated time is: and a moment before the countercurrent moment corresponding to the grid-connected point power in the preset future time period.
A source load system, comprising: the energy management server comprises the source load system anti-reflux control device;
the power supply module is connected with the electric load module through a bus;
the energy management server is in communication with the power module.
Optionally, the method further comprises: the power supply module, the energy storage module and the electric load module are connected through a bus; the energy management server is respectively in communication connection with the power module and the energy storage module.
As can be seen from the above technical solution, the present invention discloses a method and an apparatus for controlling anti-backflow of a source load system, and a source load system, which acquire current power and current power of an electric load, determine a predicted value of power of a power source in a preset future time period based on the current power of the power source, and determine a predicted value of power of the electric load in the preset future time period based on the current power of the electric load, obtain grid-connected point power in the preset future time period according to the predicted value of power source, the predicted value of power of the electric load, and an anti-backflow threshold, and execute anti-backflow operation at a designated time when it is determined that there is backflow according to the grid-connected point power, where the designated time is: and a moment before the countercurrent moment corresponding to the grid-connected point power in a preset future time period. According to the invention, the countercurrent prediction is carried out on the preset future time period at the current moment, and when the countercurrent exists in the preset future time period, the countercurrent prevention operation is carried out in advance at the moment before the countercurrent moment, so that the condition that the grid-connected point has countercurrent for a certain time before the countercurrent prevention operation is carried out is effectively avoided, and the safety of the power grid is further improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the disclosed drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for controlling the anti-reflux of a source-load system according to an embodiment of the invention;
FIG. 2 is a flowchart of a method for determining a predicted value of power supply power and a predicted value of power of electric load according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of LSTM neurons in an LSTM neural network according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an lstm_bp deep neural network according to an embodiment of the present invention;
FIG. 5 is a flowchart of a method for determining that there is a reverse flow according to grid-tie point power and performing an anti-reverse flow operation at a specified time according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a source load system anti-backflow control device according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a source load system according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment of the invention discloses a source load system backflow prevention control method, a device and a source load system, which are used for acquiring current power and current electric load power, determining a power predicted value of a preset future time period based on the current power and determining an electric load power predicted value of the preset future time period based on the current electric load power, acquiring grid-connected point power of the preset future time period according to the power predicted value, the electric load power predicted value and a backflow prevention threshold, and executing backflow prevention operation at a designated moment when backflow is determined to exist according to the grid-connected point power, wherein the designated moment is as follows: and a moment before the countercurrent moment corresponding to the grid-connected point power in a preset future time period. According to the invention, the countercurrent prediction is carried out on the preset future time period at the current moment, and when the countercurrent exists in the preset future time period, the countercurrent prevention operation is carried out in advance at the moment before the countercurrent moment, so that the condition that the grid-connected point has countercurrent for a certain time before the countercurrent prevention operation is carried out is effectively avoided, and the safety of the power grid is further improved.
Referring to fig. 1, a flow chart of a method for controlling anti-backflow of a source load system is disclosed in an embodiment of the present invention, and the method is applied to an energy management server in the source load system, and includes:
step S101, acquiring current power supply power and current electric load power;
in practical application, when the anti-reflux control of the source load system is performed, the power supply and the electric load power are obtained in real time, so that the anti-reflux control of the source load system is performed in real time. The source in the source load system refers to a power supply, and the power supply can be at least one of new energy power supplies such as photovoltaic power, wind power and the like. The present embodiment refers to the power supply power at the present time as "present power supply power", and the electric load power at the present time as "present electric load power".
Step S102, obtaining a power supply power predicted value of a preset future time period determined based on the current power supply power and an electric load power predicted value of the preset future time period determined based on the current electric load power;
the value of the preset future time period is determined according to actual needs, and the invention is not limited herein.
Step S103, grid-connected point power of the preset future time period is obtained according to the power predicted value of the power supply, the power predicted value of the electric load and the backflow prevention threshold value;
Specifically, the grid-connected point power can be obtained by calculation according to the following formula:
P g '(t)＝P source '(t)+P load '(t)-E,t∈[t 1 ,t 1 +Δt]；
wherein P is g ' t is the grid-connected point power, P source ' t is the predicted value of the power supply power, P load 't' is the predicted value of the electric load power, E is the threshold value for preventing reverse flow, t is the moment of time, t 1 And as the current moment, deltat is the preset future time period.
The anti-backflow threshold E is determined based on the absolute value of the maximum prediction error of the power supply and the absolute value of the maximum prediction error of the electric load.
Step S104, judging whether countercurrent exists according to the grid-connected point power, and if so, executing step S105;
step S105, executing the anti-reflux operation at the appointed time.
Wherein, the appointed time is: and a moment before the countercurrent moment corresponding to the grid-connected point power in the preset future time period. The time difference between the designated time and the reverse flow time can be determined according to the transmission delay and the control time length of the data line, and the invention is not limited by specific numerical values.
When the power is supplied to the bus through the grid-connected point, the current direction is positive, that is, when the power is supplied to the bus through the grid-connected point, then, when the power is supplied to the bus through the grid-connected point, the current direction is negative, that is, when the power is negative, it is indicated that the current direction supplied to the grid by the source load system is opposite to the normal current direction, that is, the reverse current occurs,
In addition, when the grid-connected point power reaches a preset countercurrent threshold (for example, -100W), determining that countercurrent exists, and the invention does not limit the judging condition for judging whether countercurrent exists according to the grid-connected point power.
For convenience of discussion, the moment corresponding to the negative value of the grid-connected point power is recorded as the countercurrent moment, and in order to avoid countercurrent existing in the grid-connected point before the countercurrent operation is executed, the countercurrent operation is executed in advance at the moment before the countercurrent moment.
In summary, the invention discloses a source load system anti-reflux control method, which is characterized in that current power and current electric load power are obtained, a power predicted value of a preset future time period is determined based on the current power, and an electric load power predicted value of the preset future time period is determined based on the current electric load power, grid-connected point power of the preset future time period is obtained according to the power predicted value, the electric load power predicted value and an anti-reflux threshold, when the existence of reflux is determined according to the grid-connected point power, anti-reflux operation is executed at a designated time, and the designated time is as follows: and a moment before the countercurrent moment corresponding to the grid-connected point power in a preset future time period. According to the invention, the countercurrent prediction is carried out on the preset future time period at the current moment, and when the countercurrent exists in the preset future time period, the countercurrent prevention operation is carried out in advance at the moment before the countercurrent moment, so that the condition that the grid-connected point has countercurrent for a certain time before the countercurrent prevention operation is carried out is effectively avoided, and the safety of the power grid is further improved.
In order to further optimize the foregoing embodiments, referring to fig. 2, a flowchart of a method for determining a power predicted value and an electrical load power predicted value according to an embodiment of the present invention, that is, step S102 may specifically include:
step S201, inputting the current power supply power into a pre-constructed power supply power prediction model to obtain a power supply power prediction value;
step S202, inputting the current electric load power into a pre-constructed electric load power prediction model to obtain an electric load power prediction value;
the power supply power prediction model is obtained by training an LSTM_BP deep neural network by adopting historical power supply power data, the electric load power prediction model is obtained by training an LSTM_BP deep neural network by adopting historical electric load power data, the LSTM_BP deep neural network is determined based on LSTM neurons and BP neurons, the LSTM neurons are single neurons of the LSTM neural network, and the BP neurons are single-layer BP neural networks.
Specifically, (1) obtaining historical power data of a power source and historical power data of an electric load in a preset historical time period.
(2) Dividing the historical power data into a power training set and a power testing set according to a first preset proportion, and dividing the historical power data into an electric load power training set and an electric load power testing set according to a second preset proportion, wherein the first preset proportion and the second preset proportion can be the same or different.
(3) And training the LSTM_BP deep neural network by using a power training set to obtain a power prediction model, and training the LSTM_BP deep neural network by using an electric load power training set to obtain an electric load power prediction model.
In the invention, the LSTM_BP deep neural network is a combined model of the LSTM neural network and the BP neural network, and the LSTM_BP deep neural network is determined based on LSTM neurons and BP neurons.
The construction process of the LSTM_BP deep neural network comprises the following steps:
inserting a BP neuron between two or more LSTM neurons to form a sub-neuron;
and at least one sub-neuron is connected in series and parallel, and an output weight is set in the last layer, so that the LSTM_BP deep neural network is constructed.
It should be noted that, the invention can reduce the steps of input and output normalization of the traditional LSTM neural network by designing the output weight at the last layer, and the designed neural network updates the weight through error back propagation. The number of hidden layer neurons and the number of layers in the LSTM_BP deep neural network can be selected according to simulation analysis results, and the invention is not limited herein.
It should be noted that, LSTM neural networks, i.e. long and short term memory neural networks, have certain advantages for dealing with problems highly related to time series, but the random volatility of new energy power and load data is large, and the effect is not ideal when the LSTM neural networks are independently used for prediction. Meanwhile, the BP neural network is a multi-layer feedforward network trained according to an error back propagation algorithm, has the problems of being trapped in local optimum, slow in convergence speed and the like, and is not suitable for independent prediction. Whereas the lstm_bp neural network formed herein has improved advantages in that: compared with the traditional LSTM neural network, the LSTM neuron provided by the invention mainly carries out z on the internal state and the output state -1 The internal state of the LSTM neuron can be reserved and is not transmitted to the next neuron, meanwhile, the output state of the neuron at the last moment can influence the calculation of the output state at the current moment, and the data obtained by the LSTM neuron prediction are ensured to have time sequence and relevance. BP neurons are inserted between LSTM neurons, which can reduce the complexity of the neural network and speed up the neural network operation. And then, setting an output weight value in the last layer, unifying a plurality of groups of neurons, and ensuring that the output duty ratio of the neuron group with high prediction accuracy is larger.
For ease of understanding, the present invention is described in detail for LSTM neurons and BP neurons as follows:
referring to fig. 3, in an LSTM neuron structure of an LSTM neural network disclosed in the embodiment of the present invention, LSTM neurons are provided with three gates, which are respectively: forgetting gate, input gate and output gate, forgetting gate, input gate and output gate are contained in a memory unit that attempts to store information for a longer period of time. The forgetting gate, the input gate and the output gate are all essentially a logic unit structure, and the logic unit structure is mainly used for setting weights at the connection positions of specific network structures so as to enhance the memory of neurons.
And the forgetting gate is used for selectively forgetting the state of the last neuron to correct the parameter.
And the input gate is used for receiving the parameters and correcting the parameters.
And an output gate for outputting the parameter and correcting the parameter.
Wherein, the expression of the forgetting gate is as follows:
F(k)＝σ(W F (k)[y(k-1),u(k)])；
where F (k) is a forgetting gate, σ is a sigmoid activation function, σ=1 means to hold this state, σ=0 means to get rid of this state, W F (k) For forgetting the gate weight, y (k-1) is the output term of the memory unit at the last time, and the delay change z is realized by the output term y (k) at the current time -1 The obtained u (k) is an input item, and k is the current sampling time;
the expression of the input gate is as follows:
I(k)＝σ(W I (k)[y(k-1),u(k)])；
wherein I (k) is the input gate selection state quantity, W I (k) A state weight is selected for the input gate,is in an intrinsic state, W x (k) For inputting the intrinsic state weight of the door, tanh is a tanh activation function;
the expression of the output gate is as follows:
O(k)＝σ(W o (k)[y(k-1),u(k)])；
y(k)＝O(k)tanh(x(k))；
wherein x (k) is the current state of the memory cell, x (k-1) is the last time state of the memory cell, and the change z is delayed by the current state x (k) of the memory cell -1 The obtained O (k) determines the output data of the memory cell, W o (k) To output the gate weight.
In the present invention, the expression of BP neurons is as follows:
y'(k)＝σ(W b (k)x'(k))；
where y '(k) is the output term, σ is the sigmoid activation function, x' (k) is the input term, W b (k) Is BP network weight.
Since the LSTM_BP deep neural network is constructed by cross-connecting LSTM neurons and BP neurons as a unit and adding an output weight in the last layer, the invention discloses an LSTM_BP deep neural network for facilitating understanding of the structure of the LSTM_BP deep neural network, and the LSTM_BP deep neural network is shown in FIG. 4 in detail. It should be noted that the cross-connection between LSTM neurons and BP neurons in the LSTM_BP deep neural network is not limited to that shown in FIG. 4, W in FIG. 4 NN Representing the output weights, those skilled in the art can adjust or alter the cross-connection relationship between LSTM neurons and BP neurons as desired.
It should be noted that, the anti-reverse flow threshold in the embodiment shown in fig. 1 is determined based on the power supply power prediction model and the electric load power prediction model.
Wherein, the expression of the anti-reflux threshold value is as follows:
E＝e source +e load ；
wherein E is an anti-reflux threshold value, E source E is the absolute value of the maximum prediction error of the power supply load For electric loadsMaximum prediction error absolute value.
Absolute value e of maximum predictive error of power supply source The method comprises the following steps: and testing the power supply power prediction model by adopting a power supply power test set to obtain the absolute value of the maximum prediction error.
Absolute value e of maximum predictive error of electrical load load The method comprises the following steps: and testing the electric load power prediction model by adopting an electric load power test set to obtain the absolute value of the maximum prediction error.
In practical application, in order to improve the accuracy of the anti-reflux threshold, the invention reckons the absolute value of the maximum prediction error every preset time period and adjusts the anti-reflux threshold.
Therefore, the method for controlling the source load system to prevent the countercurrent can further comprise the following steps:
re-determining the maximum prediction error absolute value of the power supply every preset time period to obtain the maximum prediction error absolute value of the latest power supply, and re-determining the maximum prediction error absolute value of the electric load to obtain the maximum prediction error absolute value of the latest electric load;
and determining the latest anti-backflow threshold according to the absolute value of the maximum prediction error of the latest power supply and the absolute value of the maximum prediction error of the latest electric load.
The value of the preset time period is determined according to actual needs, for example, three months, and the invention is not limited herein.
In order to improve the prediction precision of the power supply power prediction model and the electric load power prediction model, the invention can also continuously update the prediction neural network weight of the LSTM_BP deep neural network.
Therefore, the method for controlling the source load system to prevent the countercurrent can further comprise the following steps:
acquiring latest power supply power data and latest electric load power data;
updating the predicted neural network weight of the LSTM_BP deep neural network according to the latest power supply power data and the latest electric load power data;
wherein the predicted neural network weights include: forgetting gate weight W in LSTM neurons F (k) Input doorSelecting a state weight W I (k) Input the intrinsic state weight W of the door x (k) Outputting the gate weight W o (k) The method comprises the steps of carrying out a first treatment on the surface of the BP network weight W in BP neuron b (k) A. The invention relates to a method for producing a fibre-reinforced plastic composite For example, the collected power data of the power source and the power data of the electric load of one day are stored, and the predicted neural network weight is updated under the condition of no vehicle at night, wherein the condition of no vehicle at night refers to the condition of less load operation.
When the source load system includes energy storage, step S101 may specifically include:
the method comprises the steps of obtaining current power supply power, current electric load power and current energy storage power.
To further optimize the above embodiment, step S103 may specifically include:
(1) If the source load system comprises energy storage, acquiring current energy storage power, and acquiring the grid-connected point power of the preset future time period according to the power supply power predicted value, the electric load power predicted value, the current energy storage power and an anti-reflux threshold value;
Specifically, the grid-connected point power can be obtained by calculation according to the following formula:
P g '(t)＝P source '(t)+P load '(t)+P B -E,t∈[t 1 ,t 1 +Δt]；
wherein P is g ' t is the grid-connected point power, P source ' t is the predicted value of the power supply power, P load ' t is the predicted value of the electric load power, P B For the current energy storage power, E is the anti-reflux threshold value, t is the moment, t 1 And as the current moment, deltat is the preset future time period.
(2) And if the energy storage is not included in the source load system, obtaining grid-connected point power of the preset future time period according to the power predicted value of the power supply, the power predicted value of the electric load and the anti-reflux threshold value.
Specifically, the grid-connected point power can be obtained by calculation according to the following formula:
P g '(t)＝P source '(t)+P load '(t)-E,t∈[t 1 ,t 1 +Δt]；
wherein P is g ' t is the grid-connected point power, P source ' t is the predicted value of the power supply power, P load 't' is the predicted value of the electric load power, E is the threshold value for preventing reverse flow, t is the moment of time, t 1 And as the current moment, deltat is the preset future time period.
The anti-backflow threshold E is determined based on the absolute value of the maximum prediction error of the power supply and the absolute value of the maximum prediction error of the electric load.
In order to further explain the anti-countercurrent control process of the source load system, the invention also provides a specific anti-countercurrent operation process.
Referring to fig. 5, a flowchart of a method for determining that there is a reverse flow according to grid-connected point power and performing an anti-reverse flow operation at a designated time is disclosed in an embodiment of the present invention, where the method includes:
step S301, when determining that the countercurrent exists, determining a designated moment and a maximum value of the countercurrent in a preset future time period;
the designated time is: and a moment before the countercurrent moment corresponding to the grid-connected point power in a preset future time period.
Step S302, judging whether the current time reaches the designated time, if so, executing step S303, and if not, continuing to wait until the current time reaches the designated time;
if the current time does not reach the appointed time, waiting is continued until the appointed time is reached.
When the grid-connected point power is positive, that is, no reverse flow exists, the step S303 is continuously executed when the current time reaches the designated time.
Step S303, when the source load system comprises energy storage, judging whether the energy storage has control allowance, if so, executing step S304, and if not, executing step S305;
when determining whether the energy storage has a control margin, whether the energy storage can be charged or discharged or not can be judged according to the State Of Charge (SOC), and whether the required control amount exceeds the maximum Charge/discharge power or not can be judged. And when the charge and discharge can be carried out according to the determination of the energy storage electric quantity SOC and the required control quantity does not exceed the maximum charge and discharge power, determining that the energy storage has control allowance.
Step S304, the energy storage charging power is increased or the energy storage discharging power is reduced according to the countercurrent maximum value.
Step S305, reducing the power of the power supply or turning off part of the power supply components according to the maximum value of the reverse current.
It should be noted that, when it is determined that charging and discharging are possible according to the stored electric power SOC and the required control amount exceeds the maximum charging and discharging power, step S304 and step S305 are performed simultaneously.
It should also be noted that when the source load system does not include energy storage, the power supply is reduced or a portion of the power supply components is disconnected based solely on the reverse current maximum.
The number of the power-off components is determined according to actual needs, and the invention is not limited herein.
To further optimize the above embodiment, when the source load system is an optical storage system, the current source power includes: current photovoltaic power.
At this time, step S102 may specifically include:
determining a photovoltaic power forecast for a preset future time period based on the current photovoltaic power, and determining an electrical load power forecast for the preset future time period based on the current electrical load power;
and obtaining the photovoltaic power predicted value and the electric load power predicted value.
Corresponding to the embodiment of the method, the invention also discloses a countercurrent prevention control device of the source-load system.
Referring to fig. 6, a schematic structural diagram of an anti-backflow control device of a source load system is disclosed in an embodiment of the present invention, where the device is applied to an energy management server in the source load system, and the device includes:
a power acquisition unit 401 for acquiring a current power supply power and a current electric load power;
a predicted value acquisition unit 402 configured to acquire a power supply predicted value of a preset future period of time determined based on the current power supply and an electric load power predicted value of the preset future period of time determined based on the current electric load power;
the value of the preset future time period is determined according to actual needs, and the invention is not limited herein.
A grid-connected point power determining unit 403, configured to obtain grid-connected point power of the preset future time period according to the power predicted value of the power source, the power predicted value of the electrical load, and an anti-backflow threshold;
a judging unit 404, configured to judge whether there is a reverse flow according to the grid-connected point power;
an anti-backflow executing unit 405, configured to determine that there is a backflow and execute an anti-backflow operation at a specified time, where the specified time is: and a moment before the countercurrent moment corresponding to the grid-connected point power in the preset future time period.
As can be seen from the above, the present invention discloses a source load system anti-backflow control device, which obtains current power and current electric load power, and determines a predicted value of the power in a preset future time period based on the current power, and determines a predicted value of the electric load power in the preset future time period based on the current electric load power, and obtains grid-connected point power in the preset future time period according to the predicted value of the power, the predicted value of the electric load power and an anti-backflow threshold, and when it is determined that backflow exists according to the grid-connected point power, performs anti-backflow operation at a designated time, where the designated time is: and a moment before the countercurrent moment corresponding to the grid-connected point power in a preset future time period. According to the invention, the countercurrent prediction is carried out on the preset future time period at the current moment, and when the countercurrent exists in the preset future time period, the countercurrent prevention operation is carried out in advance at the moment before the countercurrent moment, so that the condition that the grid-connected point has countercurrent for a certain time before the countercurrent prevention operation is carried out is effectively avoided, and the safety of the power grid is further improved.
To further optimize the above embodiment, the predicted value acquisition unit 402 may specifically be configured to:
Inputting the current power supply power to a pre-constructed power supply power prediction model to obtain the power supply power prediction value;
inputting the current electric load power into a pre-constructed electric load power prediction model to obtain the electric load power prediction value;
the power supply power prediction model is obtained after training an LSTM_BP deep neural network by adopting historical power supply power data, the electric load power prediction model is obtained after training the LSTM_BP deep neural network by adopting historical electric load power data, and the LSTM_BP deep neural network is determined based on LSTM neurons and BP neurons.
The specific working principle of each component in the anti-backflow control device of the source load system is described specifically, please refer to the corresponding part of the method embodiment, and the description is omitted here.
Corresponding to the above embodiment, the present invention also discloses a source load system, including: the energy management server comprises the source load system anti-reflux control device;
the power supply module is connected with the electric load module through a bus;
the energy management server is in communication with the power module.
To further optimize the above embodiments, the source load system may further include: the power supply module, the energy storage module and the electric load module are connected through a bus; the energy management server is respectively in communication connection with the power module and the energy storage module.
In practical application, the source load system may be an optical load system, a wind-light load system, an optical load system, etc., and the optical load system is described below as an example:
referring to fig. 7, a schematic structural diagram of an optical storage system according to the present disclosure includes: a photovoltaic power generation module 10, an energy storage module 20, an electrical load module 30, and an energy management server 40.
The energy management server 40 includes an optical storage system anti-backflow control device in the embodiment shown in fig. 6.
The photovoltaic power generation module 10, the energy storage module 20, and the electrical load module 30 are connected by a bus 60, an ac bus being shown as an example.
Specifically, the photovoltaic power generation module 10 includes: photovoltaic module 11 and photovoltaic inverter 12, photovoltaic module 11 is connected to bus bar 60 through photovoltaic inverter 12.
The energy storage module 20 includes: an energy storage converter 21 and an energy storage device 22, the energy storage device 22 being connected to the bus bar 60 by the energy storage converter 21.
The energy management server 40 is communicatively connected to the photovoltaic power generation module 10 and the energy storage module 20, respectively.
Specifically, the energy management server 40 is connected to the photovoltaic inverter 12 in the photovoltaic power generation module 10 and the energy storage converter 21 in the energy storage module 20, respectively.
It should be noted that, the grid-connected point of the optical storage system is designed at the low-voltage side of the transformer 50, and the photovoltaic power generation module 10, the energy storage module 20, the electrical load module 30 and the grid-connected point all have devices for monitoring the power data in real time. In this embodiment, the electrical load module 30 is not controllable, so the energy management server 40 of the present invention only controls the photovoltaic inverter 12 and the energy storage converter 21.
It is specifically noted that, the energy management server 40 performs the anti-backflow control process of the optical storage system according to the above embodiment, and the description thereof will be omitted herein.
As can be seen from the above, the present invention discloses an optical storage system, which includes: the photovoltaic power generation module 10, the energy storage module 20, the electrical load module 30 and the energy management server 40, the energy management server 40 obtains the current photovoltaic power, the current electrical load power and the current energy storage power, determines a photovoltaic power predicted value of a preset future time period based on the current photovoltaic power, determines an electrical load power predicted value of the preset future time period based on the current electrical load power, obtains grid-connected point power of the preset future time period according to the photovoltaic power predicted value, the electrical load power predicted value, the current energy storage power and the anti-backflow threshold, and executes anti-backflow operation at a time before a backflow time corresponding to the grid-connected point power in the preset future time period when it is determined that backflow exists according to the grid-connected point power. According to the invention, the countercurrent prediction is carried out on the preset future time period at the current moment, and when the countercurrent exists in the preset future time period, the countercurrent prevention operation is carried out in advance at the moment before the countercurrent moment, so that the condition that the grid-connected point has countercurrent for a certain time before the countercurrent prevention operation is carried out is effectively avoided, and the safety of the power grid is further improved.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (14)
1. The method for controlling the source load system to prevent the countercurrent is characterized by comprising the following steps of:
acquiring current power supply power and current electric load power;
acquiring a power supply power predicted value of a preset future time period determined based on the current power supply power, and an electric load power predicted value of the preset future time period determined based on the current electric load power;
obtaining grid-connected point power of the preset future time period according to the power predicted value of the power supply, the power predicted value of the electric load and an anti-backflow threshold value; the anti-backflow threshold value is the sum of the absolute value of the maximum prediction error of the power supply and the absolute value of the maximum prediction error of the electric load;
judging whether countercurrent exists or not according to the grid-connected point power;
if the countercurrent exists, executing the countercurrent prevention operation at the appointed moment, wherein the appointed moment is as follows: and a moment before the countercurrent moment corresponding to the grid-connected point power in the preset future time period.
2. The method according to claim 1, wherein the obtaining a predicted value of the power supply power for a preset future period of time determined based on the current power supply power, and a predicted value of the electric load power for the preset future period of time determined based on the current electric load power, comprises:
Inputting the current power supply power to a pre-constructed power supply power prediction model to obtain the power supply power prediction value;
inputting the current electric load power into a pre-constructed electric load power prediction model to obtain the electric load power prediction value;
the power supply power prediction model is obtained after training an LSTM_BP deep neural network by adopting historical power supply power data, the electric load power prediction model is obtained after training the LSTM_BP deep neural network by adopting historical electric load power data, and the LSTM_BP deep neural network is determined based on LSTM neurons and BP neurons.
3. The method for controlling the anti-reflux of the source load system according to claim 2, wherein the constructing process of the lstm_bp deep neural network comprises the following steps:
inserting one of said BP neurons between two or more of said LSTM neurons to form a sub-neuron;
and at least one sub-neuron is connected in series and parallel, and an output weight is set in the last layer, so that the LSTM_BP deep neural network is constructed.
4. The method of claim 2, further comprising:
Acquiring latest power supply power data and latest electric load power data;
updating the predicted neural network weight of the LSTM_BP deep neural network according to the latest power supply power data and the latest electric load power data;
wherein the predicted neural network weights include: forgetting gate weight W in the LSTM neuron F (k) Input gate selection state weight W I (k) Input the intrinsic state weight W of the door x (k) Outputting the gate weight W o (k) The method comprises the steps of carrying out a first treatment on the surface of the BP network weight W in the BP neuron b (k)。
5. The method of claim 2, wherein the LSTM neurons comprise: forget gate, input gate and output gate;
the forgetting gate is used for determining the forgetted information of the data stored in the memory unit in the LSTM neural network through the sigmoid neuron, wherein the last moment output item in the memory unit in the forgetting gate is delayed by the current moment output item to change z -1 The obtained product;
the input gate is used for determining data which are reserved in the memory unit in the current data through the sigmoid neuron and the tanh neuron;
the saidAn output gate for determining output data in the memory cell through the sigmoid neuron and the tanh neuron, the current state of the memory cell in the output gate passing through the current state delay change z of the memory cell at the last moment -1 The obtained product.
6. The method for controlling reverse flow prevention of a source load system according to claim 1, wherein if the source load system includes energy storage, the obtaining the current source power and the current electrical load power further includes: and acquiring the current energy storage power.
7. The method of claim 1, further comprising:
re-determining the maximum prediction error absolute value of the power supply every preset time period to obtain the maximum prediction error absolute value of the latest power supply, and re-determining the maximum prediction error absolute value of the electric load to obtain the maximum prediction error absolute value of the latest electric load;
and determining the latest anti-backflow threshold according to the absolute value of the maximum prediction error of the latest power supply and the absolute value of the maximum prediction error of the latest electric load.
8. The method for controlling the source load system to prevent reverse flow according to claim 1, wherein the obtaining the grid-connected point power of the preset future time period according to the power predicted value of the power source, the power predicted value of the electric load and the reverse flow prevention threshold value comprises:
if the source load system comprises energy storage, acquiring current energy storage power, and acquiring the grid-connected point power of the preset future time period according to the power supply power predicted value, the electric load power predicted value, the current energy storage power and an anti-reflux threshold value;
And if the energy storage is not included in the source load system, obtaining grid-connected point power of the preset future time period according to the power predicted value of the power supply, the power predicted value of the electric load and the anti-reflux threshold value.
9. The method according to claim 1, wherein the step of performing the anti-reflux operation at a predetermined timing if the counter current exists, comprises:
determining the specified time and a maximum value of the reflux for the preset future time period when the existence of the reflux is determined;
judging whether the current time reaches the appointed time or not;
if yes, judging whether the energy storage exists in the control allowance or not if the source load system comprises the energy storage;
if so, increasing the energy storage charging power or reducing the energy storage discharging power according to the countercurrent maximum value.
10. The method of claim 9, further comprising:
and when the source load system does not comprise the energy storage or the energy storage does not have the control allowance, reducing power supply or disconnecting part of power supply components according to the reverse current maximum value.
11. The method of claim 1, wherein when the source load system is an optical storage system, the current source power comprises: current photovoltaic power;
The obtaining a power supply predicted value of a preset future time period determined based on the current power supply and an electric load power predicted value of the preset future time period determined based on the current electric load power includes:
determining a photovoltaic power forecast for a preset future time period based on the current photovoltaic power, and determining an electrical load power forecast for the preset future time period based on the current electrical load power;
and obtaining the photovoltaic power predicted value and the electric load power predicted value.
12. A source load system anti-reflux control device, comprising:
a power acquisition unit for acquiring current power supply power and current electric load power;
a predicted value acquisition unit configured to acquire a power supply power predicted value for a preset future period of time determined based on the current power supply power, and an electric load power predicted value for the preset future period of time determined based on the current electric load power;
the grid-connected point power determining unit is used for obtaining grid-connected point power of the preset future time period according to the power predicted value of the power supply, the power predicted value of the electric load and the backflow prevention threshold value; the anti-backflow threshold value is the sum of the absolute value of the maximum prediction error of the power supply and the absolute value of the maximum prediction error of the electric load;
The judging unit is used for judging whether countercurrent exists according to the grid-connected point power;
the anti-backflow executing unit is used for executing anti-backflow operation at a designated time when the judging unit judges that the backflow exists, wherein the designated time is: and a moment before the countercurrent moment corresponding to the grid-connected point power in the preset future time period.
13. A source load system, comprising: a power module, an electrical load module, and an energy management server comprising the source load system anti-reflux control device of claim 12;
the power supply module is connected with the electric load module through a bus;
the energy management server is in communication with the power module.
14. The source loading system of claim 13, further comprising: the power supply module, the energy storage module and the electric load module are connected through a bus; the energy management server is respectively in communication connection with the power module and the energy storage module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210101374.7A CN114362249B (en) | 2022-01-27 | 2022-01-27 | Source load system countercurrent prevention control method and device and source load system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210101374.7A CN114362249B (en) | 2022-01-27 | 2022-01-27 | Source load system countercurrent prevention control method and device and source load system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114362249A CN114362249A (en) | 2022-04-15 |
| CN114362249B true CN114362249B (en) | 2024-03-26 |
Family
ID=81093915
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210101374.7A Active CN114362249B (en) | 2022-01-27 | 2022-01-27 | Source load system countercurrent prevention control method and device and source load system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114362249B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117543708B (en) * | 2024-01-10 | 2024-04-30 | 上海聚信海聚新能源科技有限公司 | Control method of energy storage system, processor, energy storage system and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012175792A (en) * | 2011-02-21 | 2012-09-10 | Denso Corp | Electric power supply system |
| WO2015003443A1 (en) * | 2013-07-09 | 2015-01-15 | 京东方科技集团股份有限公司 | Anti-countercurrent grid-connected photovoltaic power generation system |
| WO2018161722A1 (en) * | 2017-03-08 | 2018-09-13 | 深圳市景程信息科技有限公司 | Power load forecasting method based on long short-term memory neural network |
| CN110298501A (en) * | 2019-06-21 | 2019-10-01 | 河海大学常州校区 | Electric load prediction technique based on long Memory Neural Networks in short-term |
| CN111008909A (en) * | 2019-11-19 | 2020-04-14 | 远景智能国际私人投资有限公司 | Anti-reflux protection method, device, equipment and storage medium of energy storage system |
| CN112329990A (en) * | 2020-10-20 | 2021-02-05 | 昆明理工大学 | User power load prediction method based on LSTM-BP neural network |
| CN112346338A (en) * | 2020-10-10 | 2021-02-09 | 北京工业大学 | Sewage treatment process layered model prediction control method based on fuzzy neural network |
| CN113708411A (en) * | 2021-09-26 | 2021-11-26 | 阳光电源股份有限公司 | Comprehensive energy system and countercurrent control method thereof |
-
2022
- 2022-01-27 CN CN202210101374.7A patent/CN114362249B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012175792A (en) * | 2011-02-21 | 2012-09-10 | Denso Corp | Electric power supply system |
| WO2015003443A1 (en) * | 2013-07-09 | 2015-01-15 | 京东方科技集团股份有限公司 | Anti-countercurrent grid-connected photovoltaic power generation system |
| WO2018161722A1 (en) * | 2017-03-08 | 2018-09-13 | 深圳市景程信息科技有限公司 | Power load forecasting method based on long short-term memory neural network |
| CN110298501A (en) * | 2019-06-21 | 2019-10-01 | 河海大学常州校区 | Electric load prediction technique based on long Memory Neural Networks in short-term |
| CN111008909A (en) * | 2019-11-19 | 2020-04-14 | 远景智能国际私人投资有限公司 | Anti-reflux protection method, device, equipment and storage medium of energy storage system |
| CN112346338A (en) * | 2020-10-10 | 2021-02-09 | 北京工业大学 | Sewage treatment process layered model prediction control method based on fuzzy neural network |
| CN112329990A (en) * | 2020-10-20 | 2021-02-05 | 昆明理工大学 | User power load prediction method based on LSTM-BP neural network |
| CN113708411A (en) * | 2021-09-26 | 2021-11-26 | 阳光电源股份有限公司 | Comprehensive energy system and countercurrent control method thereof |
Non-Patent Citations (2)
| Title |
|---|
| Study of Energy Management for Decreasing Reverse Power Flow from Photovoltaic Power Systems;2009 IEEE PES/IAS conference on sustainable alternative energy(ASE);2009 IEEE PES/IAS conference on sustainable alternative energy(ASE);1-5页 * |
| Study of Energy Management for Decreasing Reverse Power Flow from Photovoltaic Power Systems;Hiroyuki Hatta et al;Study of Energy Management for Decreasing Reverse Power Flow from Photovoltaic Power Systems;第1-5页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114362249A (en) | 2022-04-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lujano-Rojas et al. | Optimum load management strategy for wind/diesel/battery hybrid power systems | |
| US20200191117A1 (en) | Adaptive dynamic planning control method and system for energy storage station, and storage medium | |
| Brka et al. | Predictive power management strategies for stand-alone hydrogen systems: Lab-scale validation | |
| Faisal et al. | Particle swarm optimised fuzzy controller for charging–discharging and scheduling of battery energy storage system in MG applications | |
| CN107546781B (en) | Micro-capacitance sensor multiple target running optimizatin method based on PSO innovatory algorithm | |
| Mohammedi et al. | Fuzzy logic and passivity-based controller applied to electric vehicle using fuel cell and supercapacitors hybrid source | |
| CN108964103B (en) | Microgrid energy storage configuration method considering schedulability of microgrid system | |
| CN105896575B (en) | Hundred megawatt energy storage power control method and system based on self-adaptive dynamic programming | |
| Zou | Design of reactive power optimization control for electromechanical system based on fuzzy particle swarm optimization algorithm | |
| WO2019006995A1 (en) | Intelligent prediction system for power battery soc of electric vehicle | |
| CN114362249B (en) | Source load system countercurrent prevention control method and device and source load system | |
| CN112418496B (en) | Power distribution station energy storage configuration method based on deep learning | |
| Ameur et al. | Intelligent optimization and management system for renewable energy systems using multi-agent | |
| Rajasekaran et al. | Combined HCS–RBFNN for energy management of multiple interconnected microgrids via bidirectional DC–DC converters | |
| Behera et al. | Modelling and simulations of modified slime mould algorithm based on fuzzy PID to design an optimal battery management system in microgrid | |
| CN113872213B (en) | Autonomous optimization control method and device for power distribution network voltage | |
| CN112600244B (en) | Photovoltaic power station voltage control method based on neural network | |
| Shaker et al. | Adaptive nonlinear controllers based approach to improve the frequency control of multi islanded interconnected microgrids | |
| CN117691707A (en) | Multi-state fusion energy storage battery compartment power distribution method and system | |
| CN115000994B (en) | Grouping consistency power distribution method for multiple energy storage units | |
| CN115411776B (en) | Thermoelectric collaborative scheduling method and device for residence comprehensive energy system | |
| Yu et al. | A fuzzy Q-learning algorithm for storage optimization in islanding microgrid | |
| CN112613229A (en) | Energy management method and model training method and device for hybrid power equipment | |
| Zhu et al. | Research on volt/var control of distribution networks based on PPO algorithm | |
| CN110729759A (en) | Method and device for determining distributed power supply configuration scheme in micro-grid |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221221 Address after: Room 423, Sunshine Power R&D Center Building, No. 1699, Xiyou Road, High-tech Zone, Hefei City, Anhui Province, 230088 Applicant after: Sunshine Hui Carbon Technology Co.,Ltd. Address before: 230088 No. 1699 Xiyou Road, Hefei High-tech Zone, Anhui Province Applicant before: SUNGROW POWER SUPPLY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |