Microgrid countercurrent electric quantity prediction method, storage medium and electronic equipment

Abstract

The invention discloses a microgrid countercurrent electric quantity prediction method, a storage medium and electronic equipment, and relates to the technical field of new energy, and the method comprises the steps: obtaining the output prediction information of photovoltaic equipment supplying power to a microgrid, and the load information, weather information and time information of the microgrid in an electricity price peak period before the electricity price peak period; constructing input features based on the output prediction information, the load information, the weather information and the time information; and inputting the input features into a pre-trained countercurrent electric quantity prediction model to obtain predicted countercurrent electric quantity output by the countercurrent electric quantity prediction model. By applying the scheme provided by the embodiment of the invention, the accuracy of obtaining the counter-current electric quantity in the electricity price peak period can be improved.

Description

Technical Field

[0001] The present invention relates to the field of new energy technology, and in particular to a microgrid reverse current power prediction method, a storage medium and an electronic device. Background Art

[0002] With the rapid development of distributed energy and renewable energy, as well as the rise of microgrids, power reverse flow has become an important topic. Power reverse flow occurs when the power generated within a microgrid exceeds the local load demand. Power reverse flow may cause overload of transmission lines, transformers and other equipment, increase the operating load of the system, and even cause equipment damage or failure.

[0003] Moreover, in the integrated microgrid system of load, photovoltaic and storage, energy storage is often used for peak-valley arbitrage, that is, charging during the peak and valley electricity price period of the State Grid time-of-use electricity price, and discharging during the peak electricity price period, so as to maximize the energy storage arbitrage profit. However, due to the existence of the energy storage anti-reverse flow mechanism, if the reverse flow amount during the peak electricity price period is too large, the discharge plan will be suppressed and unable to discharge, which will reduce the peak-valley arbitrage income. Therefore, a technical solution is needed to accurately obtain the reverse flow amount during the peak electricity price period in advance to adjust the discharge plan, thereby ensuring the safety of the equipment. Summary of the invention

[0004] The present invention aims to solve one of the technical problems in the related art to at least some extent. To this end, one object of the present invention is to propose a microgrid reverse flow power prediction method, storage medium and electronic device to improve the accuracy of obtaining reverse flow power during peak electricity price periods.

[0005] According to a first aspect of an embodiment of the present invention, a method for predicting reverse flow power in a microgrid is provided, the method comprising:

[0006] During a peak electricity price period before a peak electricity price period, obtaining output forecast information of a photovoltaic device supplying power to a microgrid, load information of the microgrid, weather information, and time information;

[0007] constructing input features based on the output forecast information, load information, weather information, and time information;

[0008] Inputting the input features into a pre-trained reverse flow power prediction model to obtain a predicted reverse flow power output by the reverse flow power prediction model;

[0009] Among them, the reverse flow electricity prediction model is: a model obtained by training a preset neural network model using sample input features. The reverse flow electricity prediction model is used to predict the reverse flow electricity during peak periods. The sample input features are: features constructed from sample output prediction information, sample load information, sample weather information and sample time information.

[0010] According to a second aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned microgrid reverse flow power prediction method is implemented.

[0011] According to a third aspect of an embodiment of the present invention, an electronic device is provided, comprising: a memory and a processor; a computer program is stored in the memory, and when the computer program is executed by the processor, the above-mentioned microgrid reverse current power prediction method is implemented.

[0012] In the solution provided by the embodiment of the present invention, sample output prediction information, sample load information, sample weather information and sample time information are obtained to construct input sample input features, so that the information contained in the input features is richer and more comprehensive, and the neural network model can be trained to learn the law of electricity changes on different dates and time periods, so that the reverse flow electricity can be predicted based on the input characteristics of the same type of output prediction information, load information, weather information and time information of the microgrid. In this way, the use of a trained model and a variety of information obtained in real time for prediction can improve the accuracy of predicting the reverse flow electricity.

[0013] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a flow chart of a first microgrid reverse current power prediction method provided by an embodiment of the present invention;

[0015] Figure 2 It is a flow chart of a second microgrid reverse current power prediction method provided by an embodiment of the present invention;

[0016] Figure 3 It is a flow chart of a third microgrid reverse current power prediction method provided by an embodiment of the present invention;

[0017] Figure 4 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0019] The following describes a microgrid reverse flow power prediction method, storage medium, and electronic device according to an embodiment of the present invention with reference to the accompanying drawings.

[0020] In one embodiment of the present invention, see Figure 1 , provides a microgrid reverse flow power prediction method, the method comprising the following steps S101-S103.

[0021] S101: obtaining output forecast information of photovoltaic equipment supplying power to a microgrid, load information of the microgrid, weather information, and time information during a peak electricity price period before a peak electricity price period;

[0022] S102: constructing input features based on output forecast information, load information, weather information, and time information;

[0023] S103: inputting the input features into a pre-trained reverse flow power prediction model to obtain a predicted reverse flow power output by the reverse flow power prediction model;

[0024] Among them, the reverse flow electricity prediction model is: a model obtained by training the preset neural network model with sample input features. The reverse flow electricity prediction model is used to predict the reverse flow electricity during peak periods. The sample input features are: features constructed by sample output prediction information, sample load information, sample weather information and sample time information.

[0025] According to the electricity price from high to low, different electricity price periods are respectively positioned as peak electricity price period, peak electricity price period, normal electricity price period and valley electricity price period. The specific electricity prices of different electricity price periods can be specified manually.

[0026] During the peak electricity price period, sampling can be performed at fixed time intervals to obtain output forecast information, load information, weather information, and time information.

[0027] For example, in Figure 2 In the illustrated embodiment, sampling may be performed at intervals of 15 minutes.

[0028] Specifically, for the current time ts, it can be determined whether there is a peak electricity price period.

[0029] For example, for microgrid A on a certain day, the normal electricity price period is [13,14,23], the peak electricity price period is [8,17,18,19,20,21,22], the peak electricity price period is [9,10,15,16], and the valley electricity price period is [0,1,2,3,4,5,6,7,11,12]. Each data represents an entire hour, and the hour after each entire hour is in the same electricity price period. For example, the peak electricity price period includes 8, which means that the period from 8 to 9 is the peak electricity price period, and the peak electricity price period includes 9 and 10, that is, 9 to 10, and 10 to 11 constitute the peak electricity price period. In other words, the peak electricity price period represented by the number 8 is before the peak electricity price period from 9 to 10.

[0030] If yes, it is determined whether ts is in the peak electricity price period. Using the above embodiment, assuming that ts is 8:15, it is in the peak electricity price period;

[0031] If yes, then determine whether the minute corresponding to ts is divisible by 15. Continuing with the above embodiment, assuming that ts is 8:15 and the minute corresponding to ts is 15, then ts is divisible by 15.

[0032] If the above judgments are all yes, then the output forecast information, load information, weather information, and time information are obtained, and feature construction is performed to obtain input features.

[0033] Model reasoning is to use the reverse flow power prediction model output in the above steps to predict the reverse flow power.

[0034] The output of a photovoltaic device refers to the power generation capacity of a photovoltaic device within a specific period of time. A photovoltaic device may include a photovoltaic panel array formed by a photovoltaic panel. Photovoltaic output is affected by many factors, including solar radiation intensity, ambient temperature, weather humidity, rainfall, and wind speed.

[0035] The prediction method based on photovoltaic output can predict the output of photovoltaic equipment and generate output prediction information, which mainly includes statistical methods, physical methods and artificial intelligence methods. The statistical method analyzes the historical data of photovoltaic equipment output and establishes a mapping relationship between the input and output of photovoltaic equipment for prediction; the physical method uses NWP (Numerical Weather Prediction) data and the characteristics of photovoltaic equipment for prediction; the artificial intelligence method predicts photovoltaic output through machine learning algorithms. The embodiments of the present invention are not limited to this.

[0036] The output prediction information may include the average value of the predicted photovoltaic output at multiple times. For example, when the current time is ts and the peak electricity price period is [E, F], the average value of the photovoltaic output is predicted between ts and F as the photovoltaic output feature pv;

[0037] In the preset energy storage plan, the time interval [start, end] for charging and discharging of the microgrid can be set, that is, the start time of this round of charging and discharging is start, and the end time is end. Neither charging nor discharging is performed outside the time interval. Taking the embodiment of microgrid A as an example, the peak electricity price period is [9, 10, 15, 16], which means that there are peak electricity price periods from 9:00 to 10:00 and 10:00 to 11:00 in the morning, and from 15:00 to 16:00 and 16:00 to 17:00 in the afternoon. Then, a time interval can be set in the morning and afternoon. For example, the time interval set in the morning is [6, 12], and the time interval set in the afternoon is [12, 18].

[0038] In this case, the load information may include the average net load of the microgrid from the start time to the ts time.

[0039] In addition to using the average net load, the median of the net load in the time interval of the peak electricity price period or the net load at any time may be used as the load information, which is not limited in the embodiment of the present invention.

[0040] Weather information may include different weather types, such as "sunny", "cloudy", and different weather types may be represented by different numbers. For example, "sunny" is represented by 1, "cloudy" is represented by 2, and so on.

[0041] The time information may include at least one of the following:

[0042] The number of the week when the electricity price peaks, the time characteristics of the target time for obtaining time information, the time interval between the target time and the start time of the discharge plan for the microgrid, the time interval between the target time and the end time of the discharge plan, and the time interval between the target time and noon.

[0043] The target time is the time at which sampling is performed at time intervals in the above embodiment. For example, starting from 8 o'clock, sampling is performed every 15 minutes to obtain the above information. 8:00, 8:15, 8:30, and 8:45 are the target times.

[0044] Specifically, the target time may be converted into a decimal number in hours as the time feature, for example, 8:00, 8:15, 8:30, 8:45 may be converted into 8.0, 8.25, 8.50, 8.75.

[0045] The start time of the above-mentioned discharge plan is determined based on the rated capacity of the microgrid, the rated power of the energy storage of the microgrid and the peak period of electricity price.

[0046] The rated capacity refers to the maximum current load of the microgrid; the energy storage rated power refers to the preset rate at which the microgrid provides or absorbs electrical energy.

[0047] For example, the energy storage rated power rated_power of microgrid A is 1500, the rated capacity rated_capacity is 3186, and the equivalent charging and discharging time is rated_timecost=rated_capacity / rated_power=2.124. In the above embodiment, 9:00 to 10:00 and 10:00 to 11:00 constitute the peak electricity price period. The peak electricity price period before the peak electricity price period is 8:00-9:00. The end time of the discharge plan is 11:00, and the start time is start_ts=end_ts-rated_timecost, that is, 11-2.124=8.876 hours.

[0048] When the target time is 8:00, the time interval between the target time and the end time of the discharge plan at 11:00 is 3, and the time nf from the target time to noon at 12:00 is 4. Generally, noon is the peak of photovoltaic output. The closer to noon, the greater the photovoltaic output, and the farther away from noon, the smaller the photovoltaic output. Therefore, the characteristics represented by the time interval from the target time to noon can be used to associate the trend of photovoltaic output in the next period of time, and thus serve as reference information for predicting electricity.

[0049] The constructed input features can be represented by feature vectors generated by prediction information, load information, weather information, and time information. Among them, the output prediction information is represented by pv, the load information is represented by the average net load load, the weather information is represented by weather, the time information includes the weekday during which the peak electricity price period is located, the time feature of the target time is represented by a decimal number ts, the time interval between the target time and the start time of the discharge plan for the microgrid is represented by ets, the time interval between the target time and the end time of the discharge plan is represented by fts, and the time interval with noon is represented by nf. In the above embodiment, the generated feature vector is [pv, load, weather, workday, ts, ets, fts, nf].

[0050] The sample input features are obtained in the same way as the input features, the difference is the time of acquisition. For example, the sample input features can be obtained in the peak electricity price period before the historical electricity price peak period that has occurred. The acquisition method is the same as the above embodiment. The only difference is the difference in the names and concepts such as load information and sample load information, output prediction information and sample output prediction information, which will not be described in detail here.

[0051] In the solution provided by the embodiment of the present invention, sample output prediction information, sample load information, sample weather information and sample time information are obtained to construct input sample input features, so that the information contained in the input features is richer and more comprehensive, and the neural network model can be trained to learn the law of electricity changes on different dates and time periods, so that the reverse flow electricity can be predicted based on the input characteristics of the same type of output prediction information, load information, weather information and time information of the microgrid. In this way, the use of a trained model and a variety of information obtained in real time for prediction can improve the accuracy of predicting the reverse flow electricity.

[0052] Furthermore, after obtaining the predicted reverse flow power output by the reverse flow power prediction model, the start time of the discharge plan for the microgrid can be adjusted according to the relationship between the predicted reverse flow power and the preset power threshold. In this way, if the reverse flow power is predicted to be too large during the peak electricity price period, the discharge can be completed in advance, effectively reducing the peak-valley arbitrage caused by the microgrid's anti-reverse flow mechanism.

[0053] Specifically, when the predicted reverse flow power is greater than the preset power threshold, it is considered that the predicted reverse flow power is too large, and the start time of the discharge plan corresponding to the peak power price period is set earlier. Otherwise, the start time of the discharge plan is calculated in the manner of the above embodiment.

[0054] In one embodiment of the present invention, the reverse flow power prediction model is trained in the following manner:

[0055] Input the sample input features into a preset neural network model to obtain the target reverse flow amount output by the neural network model; obtain the actual reverse flow amount corresponding to the sample input features; and adjust the model parameters of the neural network model based on the difference between the actual reverse flow amount and the target reverse flow amount.

[0056] The model parameters are adjusted to make the neural network model converge, or this process is executed for a preset number of times, that is, the training process is completed to obtain the reverse current power prediction model.

[0057] The specific neural network model may be a gradient boosting regression model (GBR), an Xgboost model, a logistic regression model, etc., which is not limited in the embodiment of the present invention.

[0058] The following describes a calculation method for obtaining the actual reverse flow amount. In addition to the following calculation method, if the sample input feature is obtained during the peak electricity price period before the historical electricity price peak period that has occurred, the actual reverse flow amount can also be obtained by measuring the reverse flow amount of the microgrid in the field when the historical electricity price peak period arrives.

[0059] As follows, the calculation method includes:

[0060] Calculate the net load value of the microgrid during the target electricity price peak period after the target period corresponding to the sample input characteristics; determine the reverse flow power based on the net load value and the energy storage rated power of the microgrid; and calculate the actual reverse flow power based on the determined reverse flow power.

[0061] Reverse power refers to the power of reverse flow of electricity. The reverse power is the net load value minus the rated energy storage power. The reverse power at each moment is [r_1, r_2, r_3, ...., r_i], and the net load value at the corresponding moment is [n_1, n_2, n_3, ..., n_i], then r_i = n_i-rated_power, where rated_power is the rated energy storage power.

[0062] Specifically, for any time during the target electricity price peak period, the net load value is calculated according to the following formula:

[0063] n_i=t_i+s_i+p_i-o_i

[0064] Among them, n_i represents the net load value at the i-th moment, t_i represents the total forward active power of the meter at the i-th moment, s_i represents the real-time charging and discharging power of the energy storage of the microgrid at the i-th moment, p_i represents the total photovoltaic output power at the i-th moment, and o_i represents the total photovoltaic grid-connected power at the i-th moment.

[0065] In one embodiment, the sampling frequency can be preset, for example, to 15 minutes, that is, the net load value is calculated in the above manner every fifteen minutes during the peak period of the target electricity price. The total meter forward active power is the power recorded by the total electric energy meter of the microgrid.

[0066] The total photovoltaic output power is the sum of the output power of the photovoltaic devices supplying power to the microgrid before the i-th moment.

[0067] The total photovoltaic grid-connected power is the sum of the power generated by the photovoltaic equipment and integrated into the public grid before the i-th moment.

[0068] In one embodiment of the present invention, the actual reverse current amount can be calculated according to the following formula:

[0069] reverse_capacity=sum(r_E,...,r_F)*(T / 60)

[0070] Among them, reverse_capacity represents the actual reverse flow power, r_E represents the reverse flow power at the beginning of the target electricity price peak period, r_F represents the reverse flow power at the end of the target electricity price peak period, and T represents the time interval between the times corresponding to each reverse flow power.

[0071] r_E, ..., r_F represent the reverse flow power at multiple moments during the peak period of the target electricity price. Specifically, the reverse flow power can be measured every 15 minutes between the moments corresponding to r_E, ..., r_F to obtain the respective reverse flow powers. T is the sampling frequency, that is, T = 15min.

[0072] In one embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, any of the above-mentioned microgrid reverse current power prediction methods is implemented.

[0073] In one embodiment of the present invention, an electronic device is provided, comprising: a memory and a processor; a computer program is stored in the memory, and when the computer program is executed by the processor, the microgrid reverse current power prediction method described in any one of the above items is implemented.

[0074] Figure 3 The flowchart shown illustrates that the solution provided by the embodiment of the present invention generally includes three stages, namely, sample design, model training, and model reasoning.

[0075] In the sample design stage, during the historical electricity price peak period before the historical electricity price peak period, sample output forecast information of photovoltaic equipment supplying power to the microgrid, sample load information of the microgrid, sample weather information and sample time information are obtained to construct sample input features; in the model training stage, the sample input features are used to train the reverse flow power prediction model; in the model inference stage, the input features are constructed to obtain the predicted reverse flow power output by the model.

[0076] Figure 4 It is a structural block diagram of an electronic device according to an embodiment of the present invention.

[0077] like Figure 4 As shown, the electronic device 400 includes: a processor 401 and a memory 403. The processor 401 and the memory 403 are connected, such as through a bus 402. Optionally, the electronic device 400 may further include a transceiver 404. It should be noted that in actual applications, the transceiver 404 is not limited to one, and the structure of the electronic device 400 does not constitute a limitation on the embodiments of the present invention.

[0078] Processor 401 may be a CPU (Central Processing Unit), a general purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. Processor 401 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0079] The bus 402 may include a path to transmit information between the above components. The bus 402 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 402 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0080] The memory 403 is used to store a computer program corresponding to the microgrid reverse current power prediction method of the above embodiment of the present invention, and the computer program is controlled and executed by the processor 401. The processor 401 is used to execute the computer program stored in the memory 403 to implement the content shown in the above method embodiment.

[0081] Among them, the electronic device 400 includes but is not limited to: mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The electronic device 400 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0082] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0083] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0084] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0085] In the description of the present invention, it is to be understood that the terms “center”, “longitudinal”, “lateral”, “length”, “width”, “thickness”, “up”, “down”, “front”, “back”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inside”, “outside”, “clockwise”, “counterclockwise”, “axial”, “radial”, “circumferential”, etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0086] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0087] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0088] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0089] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for predicting reverse current in a microgrid, characterized in that: The method comprises: During a peak electricity price period before a peak electricity price period, obtaining output forecast information of a photovoltaic device supplying power to a microgrid, load information of the microgrid, weather information, and time information; constructing input features based on the output forecast information, load information, weather information, and time information; Inputting the input features into a pre-trained reverse flow power prediction model to obtain a predicted reverse flow power output by the reverse flow power prediction model; Among them, the reverse flow electricity prediction model is: a model obtained by training a preset neural network model using sample input features. The reverse flow electricity prediction model is used to predict the reverse flow electricity during peak periods. The sample input features are: features constructed from sample output prediction information, sample load information, sample weather information and sample time information.

2. The method according to claim 1, characterized in that: After obtaining the predicted reverse flow power output by the reverse flow power prediction model, the method further includes: According to the relationship between the predicted reverse flow power and the preset power threshold, the start time of the discharge plan for the microgrid is adjusted.

3. The method according to claim 1, characterized in that The time information includes at least one of the following: The number of the week in which the peak electricity price period occurs, the time characteristics of the target time for obtaining the time information, the time interval between the target time and the start time of the discharge plan for the microgrid, the time interval between the target time and the end time of the discharge plan, and the time interval between the target time and noon.

4. The method according to claim 1, characterized in that: The reverse flow power prediction model is trained in the following manner: Inputting the sample input feature into a preset neural network model to obtain a target reverse current quantity output by the neural network model; Obtain the actual reverse flow amount corresponding to the sample input characteristics; Based on the difference between the actual reverse flow amount and the target reverse flow amount, the model parameters of the neural network model are adjusted.

5. The method according to claim 4, characterized in that The obtaining of the actual reverse flow amount corresponding to the sample input feature includes: Calculating the net load value of the microgrid in the target electricity price peak period after the target period corresponding to the sample input feature; Determining reverse flow power based on the net load value and the energy storage rated power of the microgrid; The actual reverse flow amount is calculated based on the determined reverse flow power.

6. The method according to claim 5, characterized in that The calculating the net load value of the microgrid in the target electricity price peak period after the target period corresponding to the sample input feature includes: For any moment during the target electricity price peak period, the net load value is calculated according to the following formula: n_i=t_i+s_i+p_i-o_i Among them, n_i represents the net load value at the i-th moment, t_i represents the total forward active power of the meter at the i-th moment, s_i represents the real-time charging and discharging power of the energy storage of the microgrid at the i-th moment, p_i represents the total photovoltaic output power at the i-th moment, and o_i represents the total photovoltaic grid-connected power at the i-th moment.

7. The method according to claim 6, characterized in that The actual reverse current amount is calculated according to the following formula: reverse_capacity=sum(r_E,...,r_F)*(T / 60) Among them, reverse_capacity represents the actual reverse flow power, r_E represents the reverse flow power at the beginning of the target electricity price peak period, r_F represents the reverse flow power at the end of the target electricity price peak period, and T represents the time interval between the times corresponding to each reverse flow power.

8. The method according to claim 2, characterized in that: The start time of the discharge plan is determined based on the rated capacity of the microgrid, the energy storage rated power of the microgrid and the peak electricity price period.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the microgrid reverse flow power prediction method according to any one of claims 1 to 8 is implemented.

10. An electronic device, characterized in that: include: Memory, processor; The memory stores a computer program, and when the computer program is executed by the processor, the microgrid reverse flow power prediction method according to any one of claims 1 to 8 is implemented.

Images