Power dispatching method, device, electronic device and computer readable medium

Abstract

The embodiments of the present disclosure disclose a power dispatching method, device, electronic device and computer-readable medium. A specific implementation of the method includes: obtaining a power supply node identification set; for each power supply node identification in the power supply node identification set, performing the following power dispatching processing: obtaining the current day power flow condition information and current day environmental information of the corresponding power supply node identification; obtaining the historical power flow condition information set and the historical environmental information set; determining similar day dates; obtaining similar day data; generating the current day predicted electricity value sequence, the current day predicted new energy power generation sequence and the current day predicted load sequence; inputting the controllable load information, the current day predicted electricity value sequence, the current day predicted new energy power generation sequence and the current day predicted load sequence into a preset power dispatching information generation model to obtain power dispatching information; and dispatching the electric energy storage device. This implementation reduces the waste of storage resources of the electric storage device.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a power dispatching method, device, electronic device, and computer-readable medium. Background Art

[0002] As the proportion of renewable energy (such as solar and wind energy) in the power system continues to increase, its intermittent and unpredictable nature poses challenges to the stable operation of the power system. In order to improve the stability of the power system, power dispatch is particularly important. In the process of power dispatch, it is necessary to consider a variety of factors that affect power dispatch (for example, electricity demand, electricity value, and renewable energy generation). Power dispatch is a technology for dispatching power resources. At present, when dispatching power resources, the usual method is to dispatch power resources according to the preset power demand or to dispatch power according to the preset power demand, renewable energy generation, and historical power value.

[0003] However, when the above method is used for power dispatching, the following technical problems often occur:

[0004] First, power resources are dispatched according to preset power demand, and the potential supply of renewable energy (for example, solar energy and wind energy) is not taken into account during the power dispatch process. When renewable energy is abundant, scheduling power resources according to preset power demand may lead to a waste of storage resources of power storage devices.

[0005] Second, power dispatch is carried out according to preset power demand, renewable energy power generation and historical power value. The use of historical power value for power dispatch lacks real-time performance. The historical power value cannot accurately reflect the current supply and demand situation of the power circulation market. If there is a large difference between power supply and actual demand, the generated power dispatch quantity sequence will have low accuracy. Power dispatch based on the low-accuracy power dispatch quantity sequence may cause waste or shortage of power resources.

[0006] Furthermore, after power dispatching, the power value range often changes with the dispatching of power resources. When storing the generated power value range information, the following technical problems further exist:

[0007] Third, the generated information representing the value range of electricity is directly stored in a storage device (e.g., a hard disk), and the stored information is not encrypted during the storage process, resulting in the risk of unencrypted information representing the value range of electricity being vulnerable to hacker attacks or internal personnel leakage, causing sensitive information to be stolen or tampered with, which in turn leads to low storage security of the information representing the value range of electricity.

[0008] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention

[0009] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0010] Some embodiments of the present disclosure propose a power dispatching method, an apparatus, an electronic device, and a computer-readable medium to solve one or more of the technical problems mentioned in the above background technology section.

[0011] In a first aspect, some embodiments of the present disclosure provide a method for power dispatching, the method comprising: obtaining a power supply node identification set; for each power supply node identification in the above power supply node identification set, performing the following power dispatching processing: obtaining the current day power flow condition information corresponding to the above power supply node identification and the current day environment information corresponding to the above power supply node identification; obtaining a historical power flow condition information set corresponding to the above power supply node identification and a historical environment information set corresponding to the above power supply node identification, wherein one historical power flow condition information in the above historical power flow condition information set corresponds to a historical date, and one historical environment information in the above historical environment information set corresponds to a historical date; determining a similar day date based on the above current day power flow condition information, the above current day environment information, the above historical power flow condition information set and the above historical environment information set; obtaining Get similar day data corresponding to the above similar day date, wherein the above similar day data includes at least one of the following: electricity value sequence, new energy power generation sequence, load sequence; generate the daily predicted electricity value sequence, daily predicted new energy power generation sequence and daily predicted load sequence corresponding to the above power supply node identifier according to the above similar day data, the above daily power flow condition information and the daily environmental information; obtain the controllable load information corresponding to the above power supply node identifier; input the above controllable load information, the above daily predicted electricity value sequence, the above daily predicted new energy power generation sequence and the above daily predicted load sequence into a preset power dispatching information generation model to obtain power dispatching information, wherein the above power dispatching information includes a power dispatching quantity sequence; according to the above power dispatching quantity sequence, perform power dispatching on the electric energy storage device corresponding to the above power supply node identifier.

[0012] In a second aspect, some embodiments of the present disclosure provide a power dispatching device, the device comprising: an acquisition unit, configured to acquire a power supply node identification set; a power dispatching processing unit, configured to perform the following power dispatching processing for each power supply node identification in the above power supply node identification set: acquiring the current day power flow condition information corresponding to the above power supply node identification and the current day environmental information corresponding to the above power supply node identification; acquiring a historical power flow condition information set corresponding to the above power supply node identification and a historical environmental information set corresponding to the above power supply node identification, wherein a historical power flow condition information in the above historical power flow condition information set corresponds to a historical date, and a historical environmental information in the above historical environmental information set corresponds to a historical date; based on the above current day power flow condition information, the above current day environmental information, the above historical power flow condition information set and the above historical environmental information set , determine the similar day date; obtain similar day data corresponding to the above similar day date, wherein the above similar day data includes at least one of the following: electricity value sequence, new energy power generation sequence, load sequence; generate the daily predicted electricity value sequence, daily predicted new energy power generation sequence and daily predicted load sequence corresponding to the above power supply node identifier according to the above similar day data, the above daily power flow condition information and the daily environmental information; obtain the controllable load information corresponding to the above power supply node identifier; input the above controllable load information, the above daily predicted electricity value sequence, the above daily predicted new energy power generation sequence and the above daily predicted load sequence into the preset power dispatching information generation model to obtain power dispatching information, wherein the above power dispatching information includes a power dispatching quantity sequence; according to the above power dispatching quantity sequence, perform power dispatching on the electric energy storage device corresponding to the above power supply node identifier.

[0013] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

[0014] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.

[0015] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the power dispatching method of some embodiments of the present disclosure, the waste of storage resources of the electric storage device is reduced. Specifically, the reason for the waste of storage resources of the electric storage device is that the power resources are dispatched according to the preset power demand, and the potential supply of renewable energy (for example, solar energy and wind energy) is not taken into account in the power dispatching process. When the renewable energy is abundant, the power resource dispatching according to the preset power demand may lead to the waste of storage resources of the electric storage device. Based on this, the power dispatching method of some embodiments of the present disclosure, first, obtains the power supply node identification set. Thus, the power supply node identification set characterizing each area requiring power supply can be obtained. Then, for each power supply node identification in the above power supply node identification set, the following power dispatching processing is performed: the power flow condition information of the day corresponding to the above power supply node identification and the environmental information of the day corresponding to the above power supply node identification are obtained. Thus, the power flow condition information of the day and the environmental information of the day for determining the similar date can be obtained. Then, the historical power flow condition information set corresponding to the above power supply node identifier and the historical environment information set corresponding to the above power supply node identifier are obtained, wherein one historical power flow condition information in the above historical power flow condition information set corresponds to a historical date, and one historical environment information in the above historical environment information set corresponds to a historical date. Thus, the historical power flow condition information set and the historical environment information set for determining the similar date can be obtained. Then, the similar date is determined according to the above power flow condition information of the day, the above environmental information of the day, the above historical power flow condition information set and the above historical environment information set. Thus, the similar date can be obtained. Then, the similar day data corresponding to the above similar date is obtained, wherein the above similar day data includes at least one of the following: an electricity value sequence, a new energy power generation sequence, and a load sequence. Thus, similar day data for predicting the electricity value of each time period of the day can be obtained. Then, according to the above similar day data, the above power flow condition information of the day and the environmental information of the day, the predicted electricity value sequence of the day, the predicted new energy power generation sequence of the day and the predicted load sequence of the day corresponding to the above power supply node identifier are generated. Thus, it is possible to predict the current day's predicted electricity value sequence, the current day's predicted new energy power generation sequence that characterizes the potential supply of renewable energy (for example, solar energy and wind energy), and the current day's predicted load sequence that characterizes the electricity demand. Next, obtain the controllable load information corresponding to the above-mentioned power supply node identifier. Thus, the controllable load information used to generate the power dispatch quantity sequence can be obtained. Next, the above-mentioned controllable load information, the above-mentioned current day's predicted electricity value sequence, the above-mentioned current day's predicted new energy power generation sequence, and the above-mentioned current day's predicted load sequence are input into the preset power dispatch information generation model to obtain the power dispatch information, wherein the above-mentioned power dispatch information includes the power dispatch quantity sequence.Thus, a power dispatching sequence can be generated based on the controllable load information, the daily predicted electricity value sequence, the daily predicted new energy generation sequence that characterizes the potential supply of renewable energy (e.g., solar energy and wind energy), and the daily predicted load sequence. According to the above power dispatching sequence, the electric energy storage device corresponding to the above power supply node identifier is dispatched. Thus, power dispatching can be performed on the basis of generating the power dispatching sequence. Also, because the potential supply of renewable energy (e.g., solar energy and wind energy) is taken into account before power dispatching, a power dispatching sequence is generated based on the controllable load information, the daily predicted electricity value sequence, the daily predicted new energy generation sequence that characterizes the potential supply of renewable energy (e.g., solar energy and wind energy), and the daily predicted load sequence. The possibility of power dispatching according to the preset power demand when renewable energy is abundant is reduced, and the waste of storage resources of the power storage device is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0017] Figure 1 is a flow chart of some embodiments of the power dispatching method according to the present disclosure;

[0018] Figure 2 is a schematic diagram of the structure of some embodiments of the power dispatching device according to the present disclosure;

[0019] Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0020] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0021] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0022] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0023] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0024] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0025] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0026] Figure 1 The process 100 of some embodiments of the power dispatching method according to the present disclosure is shown. The power dispatching method comprises the following steps:

[0027] Step 101: Obtain a power supply node identification set.

[0028] In some embodiments, the execution subject (e.g., a computing device) of the power dispatching method may obtain a power supply node identification set from a preset database. The power supply node identification in the power supply node identification set may be an identification name used to indicate a power supply area. The identification name may be a region name. The execution subject may be a server used to manage and dispatch power resources of a power plant.

[0029] Step 102: for each power supply node identifier in the power supply node identifier set, perform the following power dispatching process:

[0030] Step 1021, obtaining the current day power flow condition information corresponding to the power supply node identification and the current day environment information corresponding to the power supply node identification.

[0031] In some embodiments, the execution subject may obtain the power flow condition information of the day corresponding to the power supply node identifier and the environmental information of the day corresponding to the power supply node identifier. In practice, the execution subject may obtain the power flow condition information of the day corresponding to the power supply node identifier and the environmental information of the day from a preset database. Among them, the power flow condition information of the day may represent the power flow condition information of the current date. The power flow condition information may represent the restrictive conditions affecting the power flow. The power flow condition information includes but is not limited to at least one of the following: unified load information, new energy output information. The unified load information may represent the total power load corresponding to the power supply node identifier. The new energy output information may represent the maximum total power that can be generated by each new energy power generation device corresponding to the power supply node identifier in one day (the new energy output information may represent the maximum total power that can be generated by each new energy power generation device, rather than the actual total power generated). The environmental information of the day may represent the environmental information corresponding to the current date. The environmental information may represent the environmental conditions of a day. The environmental information may include but is not limited to at least one of the following: reference average environmental temperature, reference average relative humidity, reference average solar radiation intensity, and reference sunshine duration. The reference average environmental temperature, the reference average relative humidity, the reference average solar radiation intensity, and the reference sunshine duration may be predicted by a large meteorological model. For example, the large meteorological model may be a Pangu meteorological model.

[0032] Step 1022, obtaining a historical power flow condition information set corresponding to the power supply node identifier and a historical environment information set corresponding to the power supply node identifier.

[0033] In some embodiments, the execution subject may obtain a historical power flow condition information set corresponding to the power supply node identifier and a historical environment information set corresponding to the power supply node identifier. Among them, one historical power flow condition information in the historical power flow condition information set corresponds to a historical date, and one historical environment information in the historical environment information set corresponds to a historical date. The historical power flow condition information may represent power flow condition information corresponding to a historical date. The historical date may refer to a date corresponding to a past day. One historical environment information in the historical environment information set may represent environment information corresponding to a historical date.

[0034] Step 1023, determining a similar day date based on the current day's power flow condition information, current day's environmental information, a historical power flow condition information set, and a historical environmental information set.

[0035] In some embodiments, the execution entity may determine a similar day date based on the current day power flow condition information, the current day environmental information, the historical power flow condition information set, and the historical environmental information set.

[0036] In some optional implementations of some embodiments, the execution subject may determine the similar day date according to the current day power flow condition information, the current day environment information, the historical power flow condition information set, and the historical environment information set through the following steps:

[0037] The first step is to map and convert the above-mentioned power flow condition information of the day to obtain the power flow condition vector information of the day corresponding to the above-mentioned power flow condition information of the day. In practice, first, the above-mentioned execution subject can convert each of the power flow condition sub-information of the day in the above-mentioned power flow condition information of the day into each vector through word embedding technology. Then, the above-mentioned execution subject can determine the above-mentioned each vector as the power flow condition vector information of the day.

[0038] The second step is to map and transform the above-mentioned daily environmental information to obtain the daily environmental vector information corresponding to the above-mentioned daily environmental information. In practice, first, the above-mentioned execution subject can convert each daily environmental sub-information in the above-mentioned daily environmental information into each vector corresponding to each daily environmental sub-information through word embedding technology. Then, the above-mentioned execution subject can determine each vector corresponding to each daily environmental sub-information as the daily environmental vector information.

[0039] The third step is to determine the similar day date based on the above-mentioned current day power flow condition vector information, the above-mentioned current day environment vector information, the above-mentioned historical power flow condition information set and the above-mentioned historical environment information set.

[0040] In some optional implementations of some embodiments, the execution subject may determine the similar day date according to the current day power flow condition vector information, the current day environment vector information, the historical power flow condition information set, and the historical environment information set through the following steps:

[0041] In the first step, for each piece of historical power flow condition information in the above historical power flow condition information set, the following generation steps are performed:

[0042] The first sub-step is to convert the above historical power flow condition information into historical power flow condition vector information corresponding to the above historical power flow condition information. In practice, the above execution subject can input the above historical power flow condition information into a word embedding model to obtain the historical power flow condition vector information corresponding to the above historical power flow condition information. The above historical power flow condition vector information can be a vector matrix representing the historical power flow condition information.

[0043] In the second sub-step, the historical date corresponding to the above-mentioned historical power flow condition information is determined as the target historical date.

[0044] The third sub-step is to determine the similarity between the current day power flow condition vector information and the historical power flow condition vector information as the first similarity to be screened. The first similarity to be screened may be the cosine similarity between the current day power flow condition vector information and the historical power flow condition vector information.

[0045] The fourth sub-step is to determine the historical environment information corresponding to the target historical date in the historical environment information set as the historical environment information to be converted.

[0046] The fifth sub-step is to convert the historical context information to be converted into historical context vector information corresponding to the historical context information to be converted. In practice, the execution subject may input the historical context information to be converted into the word embedding model to obtain the historical context vector information corresponding to the historical context information to be converted.

[0047] The sixth sub-step is to determine the similarity between the current day environment vector information and the historical environment vector information as a second screening similarity, wherein the second screening similarity may be the cosine similarity between the current day environment vector information and the historical environment vector information.

[0048] The seventh sub-step is to generate a screening similarity according to the preset weight coefficient information, the first similarity to be screened and the second screening similarity. The screening similarity corresponds to the target historical date. The preset weight coefficient information may include a first weight coefficient corresponding to the first screening similarity and a second weight coefficient corresponding to the second screening similarity. In practice, first, the execution subject may determine the product of the first weight coefficient in the preset weight coefficient information and the first similarity to be screened as a first value. Then, the execution subject may determine the product of the second weight coefficient in the preset weight coefficient information and the second similarity to be screened as a second value. Then, the execution subject may determine the sum of the first value and the second value as the screening similarity. It should be noted that the sum of the first weight coefficient and the second weight coefficient is equal to 1. The first weight coefficient is greater than 0 and less than 1. The first weight coefficient is greater than 0 and less than 1.

[0049] In the second step, each generated screening similarity is determined as a screening similarity set.

[0050] The third step is to determine the screening similarity in the screening similarity set that meets the preset screening condition as the target screening similarity. The preset screening condition may be the maximum similarity value.

[0051] In the fourth step, the target historical date corresponding to the above target screening similarity is determined as the similar date.

[0052] Step 1024, obtaining similar day data corresponding to the similar day date.

[0053] In some embodiments, the execution subject may obtain similar day data corresponding to the similar day date. The similar day data may include at least one of the following: an electricity value sequence, a new energy power generation sequence, and a load sequence. In practice, the execution subject may obtain similar day data corresponding to the similar day date from the preset database. One of the electricity values ​​in the electricity value sequence may be an electricity value corresponding to a time period. For example, the electricity value may be 25 yuan / kWh corresponding to the time period from 00:00 on March 25, 2024 to 00:15 on March 25, 2024. One of the new energy power generation in the new energy power generation sequence may be a new energy power generation corresponding to a time period. The new energy power generation may be the total amount of electricity generated by new energy in a period of time. The new energy power generation may include but is not limited to at least one of the following: wind power generation, solar power generation, and hydropower generation. For example, the new energy power generation may be 100,000 kWh of new energy power generation in the time period from 00:00 on March 25, 2024 to 00:15 on March 25, 2024. The above period of time may be one of 96 time periods of equal length divided into 24 hours in the current date.

[0054] Step 1025, based on similar day data, the power flow condition information of the day and the environmental information of the day, generate the daily predicted electricity value sequence, the daily predicted new energy power generation sequence and the daily predicted load sequence corresponding to the power supply node identifier.

[0055] In some embodiments, the above-mentioned execution entity can generate the daily predicted electricity value sequence, the daily predicted new energy power generation sequence and the daily predicted load sequence corresponding to the above-mentioned power supply node identifier based on the above-mentioned similar day data, the above-mentioned daily power flow condition information and the daily environmental information.

[0056] In some optional implementations of some embodiments, the execution subject may generate a daily predicted electricity value sequence, a daily predicted new energy power generation sequence, and a daily predicted load sequence corresponding to the power supply node identifier according to the similar day data, the daily power flow condition information, and the daily environmental information through the following steps:

[0057] The first step is to determine the electricity value sequence included in the similar day data, the electricity flow condition information of the day, and the environmental information of the day as the first input data.

[0058] In the second step, the first input data is input into the pre-trained electricity value prediction model to obtain the current predicted electricity value sequence corresponding to the first input data. The electricity value prediction model can be a neural network model with the first input data as input data and the current predicted electricity value sequence as output data. For example, the neural network model can be a long short-term memory network (LSTM, Long Short-Term Memory) model. As an example, a plurality of sample first input data and a sample current predicted electricity value sequence corresponding to each sample first input data in the plurality of sample first input data can be first obtained. Then, each sample first input data of the plurality of sample first input data is used as input, and the current predicted electricity value sequence corresponding to each sample first input data in the plurality of sample first input data is used as the expected output to train the electricity value prediction model. The current predicted electricity value in the current predicted electricity value sequence can be the predicted electricity value corresponding to a time period. The above period of time can be one of the 96 time periods of equal length that divides the 24 hours in the current date. It should be noted that there are certain objective laws between the daily environmental information in the first input data (for example, reference average sunshine radiation intensity, reference sunshine duration) and the power generation of new energy (for example, solar power generation). As an example, the higher the average sunshine radiation intensity, the corresponding increase in solar power generation. A higher average sunshine radiation intensity means that solar panels can receive more solar radiation energy, thereby generating more electrical energy. The reference sunshine duration refers to the length of time from sunrise to sunset, which directly affects the total amount of solar radiation that the solar power generation system can receive every day, and thus affects the total amount of solar power generation. There are also certain objective laws between the power generation of new energy and the value of electricity. The increase in the power generation of new energy will affect the power supply, and thus affect the value of electricity.

[0059] The third step is to determine the new energy power generation sequence included in the above similar day data, the above power flow condition information on the day, and the above environmental information on the day as the second input data.

[0060] The fourth step is to input the second input data into the pre-trained new energy output prediction model to obtain the predicted new energy power generation sequence for the day corresponding to the second input data. The new energy output prediction model can be a neural network model with the second input data as input data and the predicted new energy power generation sequence for the day as output data. For example, the neural network model can be a recurrent neural network (RNN) model. As an example, a plurality of sample second input data and a sample predicted new energy power generation sequence corresponding to each sample second input data in the plurality of sample second input data can be first obtained. Then, each sample second input data in the plurality of sample second input data is used as input, and the predicted new energy power generation sequence for the day corresponding to each sample second input data in the plurality of sample second input data is used as the expected output to train the new energy output prediction model. One of the predicted new energy power generation for the day in the predicted new energy power generation sequence for the day can be the predicted new energy power generation corresponding to a time period.

[0061] The fifth step is to determine the load sequence included in the similar day data and the power flow condition information of the day as the third input data.

[0062] The sixth step is to input the third input data into a pre-trained load forecasting model to obtain a predicted load sequence for the day corresponding to the third input data. The load forecasting model may be a neural network model with the third input data as input data and the predicted load sequence for the day as output data. For example, the neural network model may be a long short-term memory network (LSTM, Long Short-Term Memory) model. As an example, a plurality of sample third input data and a sample predicted load sequence for the day corresponding to each of the plurality of third input data may be first obtained. Then, each of the plurality of third input data is used as input, and a sample predicted load sequence for the day corresponding to each of the plurality of third input data is used as the expected output to train a load forecasting model. A predicted load for the day in the predicted load sequence for the day may be a predicted load for a time period. The load may be the amount of electricity provided by the power system to a region.

[0063] In some optional implementations of some embodiments, the execution subject may input the first input data into a pre-trained electricity value prediction model through the following steps to obtain a current predicted electricity value sequence corresponding to the first input data:

[0064] The first step is to input the current day power flow condition information in the first input data into the mapping conversion layer of the electricity value prediction model to obtain the current day power flow condition characteristic information corresponding to the current day power flow condition information. The electricity value prediction model includes the mapping conversion layer, feature merging layer, feature time series dependency capture layer, current predicted power value layer, and output layer. The mapping conversion layer can be an embedding layer that converts the current day power flow condition information into a continuous representation. The current day power flow condition characteristic information can be a vector representing the current day power flow condition information.

[0065] The second step is to input the daily environmental information in the first input data into the mapping conversion layer of the electricity value prediction model to obtain the daily environmental feature information corresponding to the daily environmental information. The daily environmental feature information can be a vector representing the daily environmental information.

[0066] The third step is to input the above-mentioned current-day power flow condition characteristic information and the above-mentioned current-day environmental characteristic information into the above-mentioned characteristic merging layer to obtain the merged characteristic information. The above-mentioned characteristic merging layer may be a concatenate layer that merges the above-mentioned current-day power flow condition characteristic information and the above-mentioned current-day environmental characteristic information. The above-mentioned merged characteristic information may be a characteristic vector obtained by merging the above-mentioned current-day power flow condition characteristic information and the above-mentioned current-day environmental characteristic information.

[0067] In the fourth step, the electricity value sequence and the merged feature information in the first input data are input into the feature time series dependency capture layer to obtain the time series dependency feature information. The feature time series dependency capture layer can be an LSTM layer that learns the time dependency in the sequence data, the electricity value sequence and the merged feature information dependency.

[0068] The fifth step is to input the above time-series dependent feature information into the above current predicted electricity value layer to obtain the value prediction information corresponding to the above time-series dependent feature information. The above current predicted electricity value layer can be a fully connected layer that predicts the electricity value based on the time-series dependent feature information. The above value prediction information can be a vector that represents the current predicted electricity value sequence.

[0069] Step 6: Input the value prediction information into the output layer to obtain the current predicted electricity value sequence corresponding to the value prediction information. The output layer may be a neural network layer that converts the output information of the fully connected layer into information in a preset format. Here, the preset format information may be a sequence. The output layer may arrange the elements in the vector according to their order in the vector to form a sequence.

[0070] The above technical scheme and its related contents, as an inventive point of the embodiments of the present disclosure, solve the second technical problem mentioned in the background technology, "electricity dispatching according to preset electricity demand, renewable energy generation and historical electricity value, lack of real-time performance of electricity dispatching using historical electricity value, historical electricity value cannot accurately reflect the supply and demand situation of the electricity circulation market at the current moment, if there is a large difference between electricity supply and actual demand, resulting in low accuracy of the generated electricity dispatching quantity sequence, and electricity dispatching according to the low-accuracy electricity dispatching quantity sequence may cause waste or shortage of electricity resources". The factors that lead to waste and shortage of electricity resources are often as follows: electricity dispatching according to preset electricity demand, renewable energy generation and historical electricity value, lack of real-time performance of electricity dispatching using historical electricity value, historical electricity value cannot accurately reflect the supply and demand situation of the electricity circulation market at the current moment, if there is a large difference between electricity supply and actual demand, resulting in low accuracy of the generated electricity dispatching quantity sequence, and electricity dispatching according to the low-accuracy electricity dispatching quantity sequence may cause waste or shortage of electricity resources. If the above factors are solved, the effect of reducing waste and shortage of electricity resources can be achieved. In order to achieve this effect, first, the power flow condition information of the day in the above-mentioned first input data is input into the mapping conversion layer of the above-mentioned electricity value prediction model to obtain the power flow condition characteristic information of the day corresponding to the power flow condition information of the day, wherein the above-mentioned electricity value prediction model includes the above-mentioned mapping conversion layer, feature merging layer, feature time series dependency capture layer, current predicted electricity value layer, and output layer. Thus, the power flow condition characteristic information of the day used to generate the merged characteristic information can be obtained. Then, the daily environmental information in the above-mentioned first input data is input into the mapping conversion layer of the above-mentioned electricity value prediction model to obtain the daily environmental characteristic information corresponding to the above-mentioned daily environmental information. Thus, the daily environmental characteristic information used to generate the merged characteristic information can be obtained. Then, the power flow condition characteristic information of the day and the daily environmental characteristic information of the day are input into the above-mentioned feature merging layer to obtain the merged characteristic information. Thus, the power flow condition characteristic information of the day and the daily environmental characteristic information of the day can be merged. Then, the electric value sequence in the above-mentioned first input data and the above-mentioned merged characteristic information are input into the above-mentioned feature time series dependency capture layer to obtain the time series dependency characteristic information. Thus, the time-dependent characteristic information that characterizes the dependency relationship between the electricity value sequence and time, the electricity value sequence and the combined characteristic information can be obtained. Then, the above-mentioned time-dependent characteristic information is input into the above-mentioned current predicted electricity value layer to obtain the value prediction information corresponding to the above-mentioned time-dependent characteristic information. Thus, the current predicted electricity value sequence can be predicted. After that, the above-mentioned value prediction information is input into the above-mentioned output layer to obtain the current predicted electricity value sequence corresponding to the above-mentioned value prediction information. Thus, the current predicted electricity value sequence can be obtained.The current predicted electricity value sequence is real-time and can more accurately reflect the supply and demand situation of the electricity circulation market at the current moment. Combined with step 1027, the above-mentioned controllable load information, the above-mentioned daily predicted electricity value sequence, the above-mentioned daily predicted new energy power generation sequence and the above-mentioned daily predicted load sequence are input into the preset power dispatch information generation model to obtain power dispatch information, wherein the above-mentioned power dispatch information includes a power dispatch quantity sequence. Thus, a power dispatch quantity sequence with higher accuracy can be generated according to the controllable load information, the above-mentioned daily predicted electricity value sequence, the above-mentioned daily predicted new energy power generation sequence and the above-mentioned daily predicted load sequence. Combined with step 1028, according to the above-mentioned power dispatch quantity sequence, the electric energy storage device corresponding to the above-mentioned power supply node identifier is dispatched. Power dispatch is performed according to a power dispatch quantity sequence with higher accuracy, which reduces the waste of power resources and the occurrence of power shortages.

[0071] Step 1026, obtaining controllable load information corresponding to the power supply node identifier.

[0072] In some embodiments, the execution subject may obtain controllable load information corresponding to the power supply node identifier. In practice, the execution subject may obtain controllable load information corresponding to the power node identifier from a preset database. The controllable load information may be relevant data and parameters of controllable loads that can be adjusted by external control means in the power system. The controllable load may include but is not limited to at least one of the following: a curtailable load, a shiftable load, and an interruptible load. For example, the controllable load information may be P cut (t) = (1-γ cut (t))P(t). The above P cut (t) can be the load after the reduction in time period t. The above P(t) can be the load before the reduction in time period t. The above γ cut (t) can be the load reduction ratio in time period t, and the above γ cut (t) can be a value between 0 and 1. cut (t) is γ cut A load ratio that can be reduced in the load ratio sequence. The above t can represent one of the 96 time periods. The above γ cut It can be a sequence of load reduction ratios corresponding to the above 96 time periods. A load reduction ratio in the above load reduction ratio sequence can be a load reduction ratio corresponding to a time period. As an example, the above t can be 00:00 on March 25, 2024-00:15 on March 25, 2024. Then the above γ cut (t) can be the above γ cutThe load reduction ratio corresponding to the above 00:00 on March 25, 2024-00:15 on March 25, 2024. The above load reduction ratio is a value between 0 and 1.

[0073] Step 1027, input the controllable load information, the daily predicted electricity value sequence, the daily predicted new energy power generation sequence and the daily predicted load sequence into the preset power dispatch information generation model to obtain the power dispatch information.

[0074] In some embodiments, the execution subject may input the controllable load information, the daily predicted electricity value sequence, the daily predicted new energy generation sequence and the daily predicted load sequence into a preset power dispatch information generation model to obtain power dispatch information. The power dispatch information includes a power dispatch quantity sequence. The preset power dispatch information generation model may be a mathematical programming model that solves each optimal power dispatch quantity within a preset time with the maximum value of the total power outflow as the goal, with the controllable load information, the daily predicted electricity value sequence, the daily predicted new energy generation sequence and the daily predicted load sequence as input data. The power dispatch quantity sequence may be a sequence corresponding to each preset time period. One of the power dispatch quantities in the power dispatch quantity sequence may be a power dispatch quantity corresponding to a time period. For example, the power dispatch quantity is the amount of electricity that needs to be dispatched to the electric energy storage device corresponding to the power supply node identifier in the time period from 00:00 on March 28, 2024 to 00:15 on March 28, 2024.

[0075] In some optional implementations of some embodiments, the execution subject may input the controllable load information, the daily predicted electricity value sequence, the daily predicted new energy power generation sequence and the daily predicted load sequence into a preset power dispatch information generation model to obtain power dispatch information through the following steps:

[0076] The first step is to determine the controllable load information, the daily predicted electricity value sequence, the daily predicted new energy power generation sequence, and the daily predicted load sequence as input data.

[0077] The second step is to input the above input data into the preset power dispatch information generation model.

[0078] The third step is to generate a power dispatch quantity sequence according to the preset solver and the preset power dispatch information generation model. In practice, the above-mentioned execution subject can solve the preset power dispatch information generation model through the above-mentioned preset solver to obtain the power dispatch sequence. Finally, the above-mentioned execution subject can determine the above-mentioned power dispatch sequence as power dispatch information. Among them, the above-mentioned preset solver can be a CPLEX solver.

[0079] Step 1028: Perform power dispatch on the electric energy storage device corresponding to the power supply node identifier according to the power dispatch quantity sequence.

[0080] In some embodiments, the execution subject may perform power dispatching on the electric energy storage device corresponding to the power supply node identifier according to the electric power dispatching amount sequence. The electric energy storage device may be a device for storing electric power. For example, the electric energy storage device may be a supercapacitor.

[0081] In some optional implementations of some embodiments, the execution subject may perform power dispatching on the electric energy storage device corresponding to the power supply node identifier according to the power dispatching amount sequence through the following steps:

[0082] In the first step, for the first power dispatch quantity in the power dispatch quantity sequence, the following power dispatch processing is performed:

[0083] In the first sub-step, the time period corresponding to the above-mentioned power dispatching amount is determined as the target time period.

[0084] The second sub-step is to obtain the system time as the current time point.

[0085] The third sub-step is, in response to determining that the current time point is within the target time period and the power dispatch amount is greater than a preset value, transferring the electric energy resources corresponding to the power dispatch amount from the preset power plant to the electric energy storage device. The preset value may be 0. In practice, the execution subject may send information representing the transfer of the electric energy resources corresponding to the power dispatch amount from the preset power plant to the electric energy storage device to the power system. Then, after receiving the information, the power system will control the telecontrol terminal to transfer the electric energy resources corresponding to the power dispatch amount from the preset power plant to the electric energy storage device.

[0086] The fourth sub-step is, in response to determining that the current time point is within the target time period and the power dispatch amount is less than a preset value, releasing the electric energy resources corresponding to the power dispatch amount from the electric energy storage device to the power grid where the electric energy storage device is located. In practice, the execution subject may send information representing the transfer of electric energy resources corresponding to the power dispatch amount from the electric energy storage device to the preset power plant to the power system. Then, after receiving the information, the power system will control the telecontrol terminal to release the electric energy resources corresponding to the power dispatch amount from the electric energy storage device to the power grid.

[0087] The fifth sub-step is to delete the first electric power dispatching amount from the electric power dispatching amount sequence to update the electric power dispatching amount sequence.

[0088] The sixth sub-step is, in response to determining that the updated power dispatching amount sequence is not empty, after a preset time period at the current time point, executing the above-mentioned power dispatching process again according to the above-mentioned updated power dispatching amount sequence.

[0089] In some optional implementations of some embodiments, after performing power dispatching on the electric energy storage device corresponding to the power supply node identifier according to the power dispatching amount sequence, the execution subject may further perform the following steps:

[0090] The first step is to perform the following steps for each power dispatch quantity in the above power dispatch quantity sequence:

[0091] In the first sub-step, the time period corresponding to the above-mentioned power dispatching amount is determined as the dispatching time period.

[0092] In the second sub-step, the daily predicted electricity value corresponding to the above-mentioned scheduling time period in the above-mentioned daily predicted electricity value sequence is determined as the target daily predicted electricity value.

[0093] In the third sub-step, in response to determining that the power dispatch amount is equal to the preset value, information corresponding to the dispatch time period is generated according to the target daily predicted power value. In practice, the execution subject may determine the value range information representing the value greater than or equal to the target daily predicted power value as the value range information corresponding to the dispatch time period.

[0094] The fourth sub-step is, in response to determining that the above-mentioned power dispatch amount is greater than the above-mentioned preset value, generating value range information corresponding to the above-mentioned dispatch time according to the first preset correction coefficient and the above-mentioned target daily predicted electricity value. In practice, first, the above-mentioned execution subject may determine the product of the above-mentioned first preset correction coefficient and the above-mentioned target daily predicted electricity value as the first value. Then, the above-mentioned execution subject may determine the information representing less than or equal to the above-mentioned first value as the value range information.

[0095] The fifth sub-step is, in response to determining that the above-mentioned power dispatch amount is less than the above-mentioned preset value, generating the value range information corresponding to the above-mentioned dispatch time according to the second preset correction coefficient and the above-mentioned target daily predicted electricity value. In practice, the above-mentioned execution subject may determine the product of the above-mentioned second preset correction coefficient and the above-mentioned target daily predicted electricity value as the second value. Then, the above-mentioned execution subject may determine the information representing that it is greater than or equal to the above-mentioned second value as the value range information corresponding to the above-mentioned dispatch time.

[0096] In the second step, each value range information generated is determined as a value range information set.

[0097] The third step is to obtain encryption algorithm information corresponding to the above value range information set from a preset database. The above encryption algorithm information may represent a preset encryption algorithm. For example, the above preset encryption algorithm may be an AES encryption algorithm.

[0098] The fourth step is to generate a key corresponding to the encryption algorithm information according to the encryption algorithm information and the preset pseudo-random number generator. In practice, the execution subject can generate a key corresponding to the encryption algorithm information through the preset pseudo-random number generator. The key can be a parameter used to control the encryption and decryption process.

[0099] The fifth step is to encrypt the value range information set according to the key to obtain the value range encrypted data corresponding to the value range information set. In practice, the execution subject may determine the value range information set as the plaintext to be encrypted. Then, the execution subject may perform encryption operation on the plaintext to be encrypted according to the generated key to obtain the ciphertext corresponding to the plaintext to be encrypted. Afterwards, the execution subject may determine the ciphertext as the value range encrypted data.

[0100] Step 6: Store the encrypted data in a preset storage device. The preset storage device may be a device for storing encrypted data of a value range. For example, the device may be a hard disk.

[0101] The above technical solution and its related contents, as an inventive point of the embodiment of the present disclosure, solve the technical problem three mentioned in the background technology, "directly storing the generated information representing the value range of electricity to a storage device (for example, a hard disk), and not encrypting the stored information during the storage process, resulting in the unencrypted information representing the value range of electricity being vulnerable to hacker attacks or internal personnel leakage, resulting in sensitive information being stolen or tampered with, and then resulting in low storage security of the information representing the value range of electricity". The factors that lead to low storage security of the information of the value range of electricity are often as follows: directly storing the generated information representing the value range of electricity to a storage device (for example, a hard disk), and not encrypting the stored information during the storage process, resulting in the unencrypted information representing the value range of electricity being vulnerable to hacker attacks or internal personnel leakage, resulting in sensitive information being stolen or tampered with, and then resulting in low storage security of the information representing the value range of electricity. If the above factors are solved, the effect of improving the storage security of the information representing the value range of electricity can be achieved. In order to achieve this effect, first, for each power dispatch amount in the above power dispatch amount sequence, the following steps are performed: Then, the time period corresponding to the above power dispatch amount is determined as the dispatch time period. Thus, the dispatch time period for determining the target daily forecast value can be obtained. Afterwards, the predicted electricity value of the day corresponding to the above-mentioned scheduling time period in the above-mentioned predicted electricity value sequence is determined as the target predicted electricity value of the day. Thus, the target predicted electricity value of the day can be obtained. Then, in response to determining that the above-mentioned power dispatch amount is equal to the above-mentioned preset value, the value range information corresponding to the above-mentioned scheduling time period is generated according to the above-mentioned target predicted electricity value of the day. Thus, the value range information when the power dispatch amount is equal to the above-mentioned preset value can be obtained. Then, in response to determining that the above-mentioned power dispatch amount is greater than the above-mentioned preset value, the value range information corresponding to the above-mentioned scheduling time is generated according to the first preset correction coefficient and the above-mentioned target predicted electricity value of the day. Thus, the value range information when the power dispatch amount is greater than the above-mentioned preset value can be obtained. Then, in response to determining that the above-mentioned power dispatch amount is less than the above-mentioned preset value, the value range information corresponding to the above-mentioned scheduling time is generated according to the second preset correction coefficient and the above-mentioned target predicted electricity value of the day. Thus, the value range information when the power dispatch amount is less than the above-mentioned preset value can be obtained. Afterwards, the generated value range information is determined as a value range information set. Thus, the value range information set characterizing the power value range can be obtained. Next, the encryption algorithm information corresponding to the above value range information set is obtained from the preset database. Thus, the encryption algorithm information used to encrypt the value range information set can be obtained. Next, according to the above encryption algorithm information and the preset pseudo-random number generator, a key corresponding to the above encryption algorithm information is generated. Thus, the key used for encryption processing can be obtained.Then, according to the above-mentioned key, the above-mentioned value range information set is encrypted to obtain the value range encrypted data corresponding to the above-mentioned value range information set. In this way, the value range information set can be encrypted to obtain the value range encrypted data. Afterwards, the above-mentioned value range encrypted data is stored in a preset storage device. Also because after the power dispatching, a value range information set representing the value range of electricity that changes with the power dispatching is generated, and the value range information set is encrypted before storing the value range information set, the risk of the value range information set representing the value range of electricity being attacked by hackers or leaked by internal personnel is reduced, and the storage security of the value range information set representing the value range of electricity is improved.

[0102] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the power dispatching method of some embodiments of the present disclosure, the waste of storage resources of the electric storage device is reduced. Specifically, the reason for the waste of storage resources of the electric storage device is that the power resources are dispatched according to the preset power demand, and the potential supply of renewable energy (for example, solar energy and wind energy) is not taken into account in the power dispatching process. When the renewable energy is abundant, the power resource dispatching according to the preset power demand may lead to the waste of storage resources of the electric storage device. Based on this, the power dispatching method of some embodiments of the present disclosure, first, obtains the power supply node identification set. Thus, the power supply node identification set characterizing each area requiring power supply can be obtained. Then, for each power supply node identification in the above power supply node identification set, the following power dispatching processing is performed: the power flow condition information of the day corresponding to the above power supply node identification and the environmental information of the day corresponding to the above power supply node identification are obtained. Thus, the power flow condition information of the day and the environmental information of the day for determining the similar date can be obtained. Then, the historical power flow condition information set corresponding to the above power supply node identifier and the historical environment information set corresponding to the above power supply node identifier are obtained, wherein one historical power flow condition information in the above historical power flow condition information set corresponds to a historical date, and one historical environment information in the above historical environment information set corresponds to a historical date. Thus, the historical power flow condition information set and the historical environment information set for determining the similar date can be obtained. Then, the similar date is determined according to the above power flow condition information of the day, the above environmental information of the day, the above historical power flow condition information set and the above historical environment information set. Thus, the similar date can be obtained. Then, the similar day data corresponding to the above similar date is obtained, wherein the above similar day data includes at least one of the following: an electricity value sequence, a new energy power generation sequence, and a load sequence. Thus, similar day data for predicting the electricity value of each time period of the day can be obtained. Then, according to the above similar day data, the above power flow condition information of the day and the environmental information of the day, the predicted electricity value sequence of the day, the predicted new energy power generation sequence of the day and the predicted load sequence of the day corresponding to the above power supply node identifier are generated. Thus, it is possible to predict the current day's predicted electricity value sequence, the current day's predicted new energy power generation sequence that characterizes the potential supply of renewable energy (for example, solar energy and wind energy), and the current day's predicted load sequence that characterizes the electricity demand. Next, obtain the controllable load information corresponding to the above-mentioned power supply node identifier. Thus, the controllable load information used to generate the power dispatch quantity sequence can be obtained. Next, the above-mentioned controllable load information, the above-mentioned current day's predicted electricity value sequence, the above-mentioned current day's predicted new energy power generation sequence, and the above-mentioned current day's predicted load sequence are input into the preset power dispatch information generation model to obtain the power dispatch information, wherein the above-mentioned power dispatch information includes the power dispatch quantity sequence.Thus, a power dispatching sequence can be generated based on the controllable load information, the daily predicted electricity value sequence, the daily predicted new energy generation sequence that characterizes the potential supply of renewable energy (e.g., solar energy and wind energy), and the daily predicted load sequence. According to the above power dispatching sequence, the electric energy storage device corresponding to the above power supply node identifier is dispatched. Thus, power dispatching can be performed on the basis of generating the power dispatching sequence. Also, because the potential supply of renewable energy (e.g., solar energy and wind energy) is taken into account before power dispatching, a power dispatching sequence is generated based on the controllable load information, the daily predicted electricity value sequence, the daily predicted new energy generation sequence that characterizes the potential supply of renewable energy (e.g., solar energy and wind energy), and the daily predicted load sequence. The possibility of power dispatching according to the preset power demand when renewable energy is abundant is reduced, and the waste of storage resources of the power storage device is reduced.

[0103] Further references Figure 2 As an implementation of the methods shown in the figures, the present disclosure provides some embodiments of a power dispatching device, and these device embodiments are Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0104] like Figure 2As shown, the power dispatching device 200 of some embodiments includes: an acquisition unit 201 and a power dispatching processing unit 202. The acquisition unit 201 is configured to acquire a power supply node identification set; the power dispatching processing unit 202 is configured to perform the following power dispatching processing for each power supply node identification in the above power supply node identification set: acquire the current day power flow condition information corresponding to the above power supply node identification and the current day environment information corresponding to the above power supply node identification; acquire the historical power flow condition information set corresponding to the above power supply node identification and the historical environment information set corresponding to the above power supply node identification, wherein one historical power flow condition information in the above historical power flow condition information set corresponds to a historical date, and one historical environment information in the above historical environment information set corresponds to a historical date; determine similar dates based on the above current day power flow condition information, the above current day environment information, the above historical power flow condition information set and the above historical environment information set; acquire and Similar day data corresponding to the above-mentioned similar day dates, wherein the above-mentioned similar day data include at least one of the following: an electricity value sequence, a new energy power generation sequence, and a load sequence; based on the above-mentioned similar day data, the above-mentioned daily power flow condition information and the daily environmental information, generate the daily predicted electricity value sequence, the daily predicted new energy power generation sequence and the daily predicted load sequence corresponding to the above-mentioned power supply node identifier; obtain the controllable load information corresponding to the above-mentioned power supply node identifier; input the above-mentioned controllable load information, the above-mentioned daily predicted electricity value sequence, the above-mentioned daily predicted new energy power generation sequence and the above-mentioned daily predicted load sequence into a preset power dispatching information generation model to obtain power dispatching information, wherein the above-mentioned power dispatching information includes a power dispatching quantity sequence; according to the above-mentioned power dispatching quantity sequence, perform power dispatching on the electric energy storage device corresponding to the above-mentioned power supply node identifier.

[0105] It is understood that the units described in the device 200 are similar to those described in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 200 and the units contained therein, and will not be described in detail here.

[0106] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0107] like Figure 3As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0108] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0109] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the functions defined in the method of some embodiments of the present disclosure are executed.

[0110] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0111] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0112] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains a power supply node identification set; for each power supply node identification in the above power supply node identification set, performs the following power dispatching processing: obtains the current day power flow condition information corresponding to the above power supply node identification and the current day environment information corresponding to the above power supply node identification; obtains the historical power flow condition information set corresponding to the above power supply node identification and the historical environment information set corresponding to the above power supply node identification, wherein one historical power flow condition information in the above historical power flow condition information set corresponds to a historical date, and one historical environment information in the above historical environment information set corresponds to a historical date; according to the above current day power flow condition information, the above current day environment information, the above historical power flow condition information set and the above historical environment information set, determine Similar day date; obtaining similar day data corresponding to the above similar day date, wherein the above similar day data includes at least one of the following: electricity value sequence, new energy power generation sequence, load sequence; generating the predicted electricity value sequence, predicted new energy power generation sequence and predicted load sequence for the day corresponding to the above power supply node identifier according to the above similar day data, the above power flow condition information for the day and the environmental information for the day; obtaining controllable load information corresponding to the above power supply node identifier; inputting the above controllable load information, the above predicted electricity value sequence for the day, the above predicted new energy power generation sequence for the day and the above predicted load sequence for the day into a preset power dispatching information generation model to obtain power dispatching information, wherein the above power dispatching information includes a power dispatching quantity sequence; performing power dispatching on the electric energy storage device corresponding to the above power supply node identifier according to the above power dispatching quantity sequence.

[0113] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0114] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0115] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The units described may also be provided in a processor, for example, may be described as: a processor including an acquisition unit and a power dispatch processing unit. The names of these units do not, in some cases, constitute limitations on the units themselves, for example, the acquisition unit may also be described as a "unit for acquiring a power supply node identification set".

[0116] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0117] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of technical features, but should also cover other technical solutions formed by any combination of technical features or their equivalent features without departing from the inventive concept. For example, a technical solution formed by replacing the features with (but not limited to) the technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A power dispatching method, comprising: Obtain a power supply node identification set; For each power supply node identifier in the power supply node identifier set, the following power dispatching process is performed: Acquire the current-day power flow condition information corresponding to the power supply node identifier and the current-day environment information corresponding to the power supply node identifier; Acquire a historical power flow condition information set corresponding to the power supply node identifier and a historical environment information set corresponding to the power supply node identifier, wherein one historical power flow condition information in the historical power flow condition information set corresponds to one historical date, and one historical environment information in the historical environment information set corresponds to one historical date; Determining a similar day date according to the current day power flow condition information, the current day environmental information, the historical power flow condition information set and the historical environmental information set; Acquire similar day data corresponding to the similar day date, wherein the similar day data includes at least one of the following: an electricity value sequence, a new energy power generation sequence, and a load sequence; Generate a daily predicted electricity value sequence, a daily predicted new energy power generation sequence, and a daily predicted load sequence corresponding to the power supply node identifier based on the similar day data, the daily power flow condition information, and the daily environmental information; Acquire controllable load information corresponding to the power supply node identifier; Input the controllable load information, the current day predicted electricity value sequence, the current day predicted new energy power generation sequence and the current day predicted load sequence into a preset power dispatch information generation model to obtain power dispatch information, wherein the power dispatch information includes a power dispatch quantity sequence; According to the power dispatch amount sequence, power dispatch is performed on the electric energy storage device corresponding to the power supply node identifier.

2. The method according to claim 1, wherein: The determining of the similar day date according to the current day power flow condition information, the current day environment information, the historical power flow condition information set and the historical environment information set includes: Performing mapping conversion processing on the current day power flow condition information to obtain current day power flow condition vector information corresponding to the current day power flow condition information; Performing mapping conversion processing on the current day environmental information to obtain current day environmental vector information corresponding to the current day environmental information; A similar day date is determined according to the current day power flow condition vector information, the current day environment vector information, the historical power flow condition information set and the historical environment information set.

3. The method according to claim 2, wherein: The determining of the similar day date according to the current day power flow condition vector information, the current day environment vector information, the historical power flow condition information set and the historical environment information set includes: For each piece of historical power flow condition information in the historical power flow condition information set, the following generation steps are performed: converting the historical power flow condition information into historical power flow condition vector information corresponding to the historical power flow condition information; Determining a historical date corresponding to the historical power flow condition information as a target historical date; Determine the similarity between the current day power flow condition vector information and the historical power flow condition vector information as a first similarity to be screened; Determining the historical environmental information corresponding to the target historical date in the historical environmental information set as the historical environmental information to be converted; Converting the historical environment information to be converted into historical environment vector information corresponding to the historical environment information to be converted; Determine the similarity between the current day environment vector information and the historical environment vector information as a second screening similarity; Generate a screening similarity according to preset weight coefficient information, the first similarity to be screened, and the second screening similarity, wherein the screening similarity corresponds to the target historical date; Determine each generated screening similarity as a screening similarity set; Determine the screening similarity in the screening similarity set that meets the preset screening condition as the target screening similarity; The target historical date corresponding to the target screening similarity is determined as the similar date.

4. The method according to claim 1, wherein: The generating of the daily predicted electricity value sequence, the daily predicted new energy power generation sequence and the daily predicted load sequence corresponding to the power supply node identifier according to the similar day data, the daily power flow condition information and the daily environmental information includes: Determine the electricity value sequence included in the similar day data, the electricity flow condition information of the day, and the environmental information of the day as the first input data; Inputting the first input data into a pre-trained electricity value prediction model to obtain a current predicted electricity value sequence corresponding to the first input data; Determine the new energy power generation amount sequence included in the similar day data, the power flow condition information of the day, and the environmental information of the day as the second input data; Inputting the second input data into a pre-trained new energy output prediction model to obtain a daily predicted new energy power generation sequence corresponding to the second input data; Determine the load quantity sequence included in the similar day data and the power flow condition information of the day as the third input data; The third input data is input into a pre-trained load prediction model to obtain a daily predicted load sequence corresponding to the third input data.

5. The method according to claim 1, wherein: The step of performing power dispatching on the electric energy storage device corresponding to the power supply node identifier according to the power dispatching amount sequence includes: For the first power dispatch quantity in the power dispatch quantity sequence, the following power dispatch processing is performed: Determining a time period corresponding to the power dispatching amount as a target time period; Get the system time as the current time point; In response to determining that the current time point is within the target time period and the power dispatch amount is greater than a preset value, transferring electric energy resources corresponding to the power dispatch amount from a preset power plant to the electric energy storage device; In response to determining that the current time point is within the target time period and the power dispatch amount is less than a preset value, releasing electric energy resources corresponding to the power dispatch amount from the electric energy storage device to the power grid where the electric energy storage device is located; Deleting the first electric power dispatch amount from the electric power dispatch amount sequence to update the electric power dispatch amount sequence; In response to determining that the updated power dispatch amount sequence is not empty, after a preset time period at a current time point, the power dispatch process is executed again according to the updated power dispatch amount sequence.

6. The method according to claim 1, wherein: The controllable load information, the current day predicted electricity value sequence, the current day predicted new energy power generation sequence and the current day predicted load sequence are input into a preset power dispatch information generation model to obtain power dispatch information, including: Determine the controllable load information, the current day predicted electricity value sequence, the current day predicted new energy power generation sequence, and the current day predicted load sequence as input data; Inputting the input data into a preset power dispatch information generation model; The power dispatch information is generated according to a preset solver and a preset power dispatch information generation model.

7. A power dispatching device, comprising: An acquisition unit, configured to acquire a power supply node identification set; The power dispatch processing unit is configured to perform the following power dispatch processing for each power supply node identifier in the power supply node identifier set: obtain the current day power flow condition information corresponding to the power supply node identifier and the current day environment information corresponding to the power supply node identifier; obtain the historical power flow condition information set corresponding to the power supply node identifier and the historical environment information set corresponding to the power supply node identifier, wherein one historical power flow condition information in the historical power flow condition information set corresponds to a historical date, and one historical environment information in the historical environment information set corresponds to a historical date; determine a similar day date based on the current day power flow condition information, the current day environment information, the historical power flow condition information set and the historical environment information set; obtain a similar day date corresponding to the similar day date Data, wherein the similar day data includes at least one of the following: an electricity value sequence, a new energy power generation sequence, and a load sequence; based on the similar day data, the power flow condition information of the day and the environmental information of the day, generate a daily predicted electricity value sequence, a daily predicted new energy power generation sequence and a daily predicted load sequence corresponding to the power supply node identifier; obtain the controllable load information corresponding to the power supply node identifier; input the controllable load information, the daily predicted electricity value sequence, the daily predicted new energy power generation sequence and the daily predicted load sequence into a preset power dispatching information generation model to obtain power dispatching information, wherein the power dispatching information includes a power dispatching quantity sequence; according to the power dispatching quantity sequence, perform power dispatching on the electric energy storage device corresponding to the power supply node identifier.

8. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images