Multi-energy scheduling method and device based on new energy consumption and storage medium

Abstract

The invention discloses a multi-energy scheduling method and device based on new energy consumption and a storage medium, and the method comprises the steps: determining a scheduling period, and dividing the scheduling period into a plurality of scheduling time periods; according to the first meteorological data corresponding to the target scheduling time period, predicting first power supply power probability distribution corresponding to the target scheduling time period based on a first neural network model; predicting second power supply power probability distribution corresponding to the target scheduling time period based on a second neural network model according to second meteorological data corresponding to the target scheduling time period; determining third power supply power probability distribution based on the first power supply power probability distribution and the second power supply power probability distribution; according to the power consumption data corresponding to the target scheduling time period, predicting corresponding power consumption power probability distribution based on an RNN model; and predicting the power supply power of the thermal power equipment based on the third power supply power probability distribution and the power utilization power probability distribution, and scheduling the power supply power of the thermal power equipment based on a prediction result.

Description

Technical Field

[0001] The present application relates to the field of new energy technology, and in particular to a method, device and storage medium for scheduling multiple energy sources based on new energy consumption. Background Art

[0002] As the world attaches great importance to environmental protection and sustainable development, the development and utilization of new energy, especially renewable energy such as wind and solar energy, has become an important part of the energy strategy of countries around the world. However, due to the intermittent, random and volatile characteristics of new energy generation such as wind and solar energy, their large-scale access to the power grid has also brought new challenges to the safe and stable operation of the power system, especially putting forward higher requirements on the dispatching capacity of the power system.

[0003] The power supply of traditional power systems mainly relies on traditional energy sources such as thermal power and hydropower. The power generation methods of these energy sources are relatively stable and controllable, and can better meet the load requirements of the power system. However, with the rapid increase in the installed capacity of new energy, the proportion of traditional energy in the power system has gradually decreased, which has put great pressure on the dispatching capacity and flexibility of the power system. Especially when the output of new energy fluctuates greatly, it is impossible to reasonably coordinate and optimize the dispatching of multiple energy sources, resulting in low utilization of multiple energy sources.

[0004] With regard to the technical problem in the above-mentioned prior art that when the output of new energy sources fluctuates greatly, it is impossible to reasonably coordinate and optimize the scheduling of multiple energy sources, resulting in low energy utilization efficiency, no effective solution has been proposed so far. Summary of the invention

[0005] The embodiments of the present disclosure provide a method, device and storage medium for scheduling multiple energy sources based on new energy consumption, so as to at least solve the technical problem in the prior art that when the output of new energy fluctuates greatly, multiple energy sources cannot be reasonably coordinated and optimized, resulting in low energy utilization efficiency.

[0006] According to one aspect of an embodiment of the present disclosure, a method for scheduling multiple energy sources based on new energy consumption is provided, including: determining a scheduling cycle and dividing the scheduling cycle into multiple scheduling periods; predicting a first power supply probability distribution corresponding to the target scheduling period based on first meteorological data corresponding to a target scheduling period and based on a first neural network model, wherein the first power supply probability distribution corresponds to a photovoltaic device, and the target scheduling period is any one or more scheduling periods among multiple scheduling periods; predicting a second power supply probability distribution corresponding to the target scheduling period based on second meteorological data corresponding to the target scheduling period and based on a second neural network model, wherein the second power supply probability distribution corresponds to a wind turbine device; determining a third power supply probability distribution based on the first power supply probability distribution and the second power supply probability distribution, wherein the third power supply probability distribution corresponds to a new energy device, and the new energy device includes a photovoltaic device and a wind turbine device; predicting a power consumption probability distribution corresponding to the target scheduling period based on power consumption data corresponding to the target scheduling period and based on an RNN model; and predicting the power supply of thermal power equipment based on the third power supply probability distribution and the power consumption probability distribution, and scheduling the power supply of the thermal power equipment based on the prediction result.

[0007] According to another aspect of an embodiment of the present disclosure, a storage medium is further provided, the storage medium including a stored program, wherein when the program is running, a processor executes any one of the methods described above.

[0008] According to another aspect of the embodiment of the present disclosure, a multi-energy scheduling device based on new energy consumption is also provided, including: a scheduling period determination module, used to determine the scheduling period and divide the scheduling period into multiple scheduling periods; a first power supply power probability distribution prediction module, used to predict the first power supply power probability distribution corresponding to the target scheduling period based on the first meteorological data corresponding to the target scheduling period and based on the first neural network model, wherein the first power supply power probability distribution corresponds to the photovoltaic equipment, and the target scheduling period is any one or more scheduling periods among the multiple scheduling periods; a second power supply power probability distribution prediction module, used to predict the first power supply power probability distribution corresponding to the target scheduling period based on the second meteorological data corresponding to the target scheduling period and based on the second neural network model. a second power supply probability distribution corresponding to the target scheduling period, wherein the second power supply probability distribution corresponds to the wind turbine equipment; a third power supply probability distribution prediction module, used to determine the third power supply probability distribution based on the first power supply probability distribution and the second power supply probability distribution, wherein the third power supply probability distribution corresponds to the new energy equipment, and the new energy equipment includes photovoltaic equipment and wind turbine equipment; an electric power probability distribution prediction module, used to predict the electric power probability distribution corresponding to the target scheduling period according to the power consumption data corresponding to the target scheduling period and based on the RNN model; and a scheduling module, used to predict the power supply of the thermal power equipment based on the third power supply probability distribution and the power consumption probability distribution, and schedule the power supply of the thermal power equipment based on the prediction result.

[0009] According to another aspect of the embodiment of the present disclosure, a multi-energy scheduling device based on new energy consumption is also provided, including: a processor; and a memory connected to the processor, for providing the processor with instructions for processing the following processing steps: determining a scheduling period, and dividing the scheduling period into multiple scheduling periods; predicting a first power supply power probability distribution corresponding to the target scheduling period based on first meteorological data corresponding to the target scheduling period and based on a first neural network model, wherein the first power supply power probability distribution corresponds to a photovoltaic device, and the target scheduling period is any one or more scheduling periods among the multiple scheduling periods; predicting a first power supply power probability distribution corresponding to the target scheduling period based on second meteorological data corresponding to the target scheduling period and based on a second neural network model; A network model is used to predict a second power supply probability distribution corresponding to a target scheduling period, wherein the second power supply probability distribution corresponds to wind turbine equipment; a third power supply probability distribution is determined based on the first power supply probability distribution and the second power supply probability distribution, wherein the third power supply probability distribution corresponds to new energy equipment, and the new energy equipment includes photovoltaic equipment and wind turbine equipment; according to the power consumption data corresponding to the target scheduling period and based on the RNN model, a power consumption probability distribution corresponding to the target scheduling period is predicted; and based on the third power supply probability distribution and the power consumption probability distribution, the power supply of thermal power equipment is predicted, and the power supply of thermal power equipment is scheduled based on the prediction result.

[0010] The present application provides a method for scheduling multiple energy sources based on the consumption of new energy. First, the scheduling platform determines the scheduling cycle and divides the scheduling cycle into multiple scheduling periods. Then, the scheduling platform predicts the first power supply probability distribution corresponding to the target scheduling period based on the first meteorological data corresponding to the target scheduling period and based on the first neural network model. After that, the scheduling platform predicts the second power supply probability distribution corresponding to the target scheduling period based on the second meteorological data corresponding to the target scheduling period and based on the second neural network model. Further, the scheduling platform determines the third power supply probability distribution based on the first power supply probability distribution and the second power supply probability distribution. Then, the scheduling platform predicts the power consumption probability distribution corresponding to the target scheduling period based on the power consumption data corresponding to the target scheduling period and based on the RNN model. Finally, the scheduling platform predicts the power supply of the thermal power equipment based on the third power supply probability distribution and the power consumption probability distribution, and schedules the power supply of the thermal power equipment based on the prediction result.

[0011] Since the scheduling platform in the present application predicts the first power supply probability distribution (corresponding to the photovoltaic equipment) corresponding to the target scheduling period based on the first meteorological data corresponding to the target scheduling period and the pre-set first neural network model, and predicts the second power supply probability distribution (corresponding to the wind turbine equipment) corresponding to the target scheduling period based on the second meteorological data corresponding to the target scheduling period and the pre-set second neural network model, the scheduling platform can predict the power supply probability distribution of the new energy equipment (i.e., the third power supply probability distribution) based on the first power supply probability distribution and the second power supply probability distribution.

[0012] Since the scheduling platform in this application predicts the probability distribution of electricity consumption corresponding to the target scheduling period based on the electricity consumption data of the target scheduling period, it is possible to predict the power supply of thermal power equipment based on the power supply probability distribution and power consumption probability distribution of new energy equipment, and schedule the power supply of thermal power equipment based on the prediction results.

[0013] In summary, the dispatching platform can predict the power supply of new energy equipment (i.e., the power supply of photovoltaic equipment and the power supply of wind turbine equipment) in advance, and determine the power supply of thermal power equipment to be dispatched based on the power supply of new energy equipment to meet the power consumption of users. Therefore, in the actual dispatching process, the coordinated dispatching of multiple energy sources can be realized based on the above operations, ensuring the rationality of energy dispatching and improving the utilization rate of multiple energy sources.

[0014] This solves the technical problem in the prior art that when the output of new energy sources fluctuates greatly, multiple energy sources cannot be reasonably coordinated and optimized, resulting in low energy utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of the present application. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure. In the drawings:

[0016] Figure 1 is a hardware structure block diagram of a computing device for implementing the method according to Embodiment 1 of the present disclosure;

[0017] Figure 2 It is a schematic diagram of a multi-energy dispatching system based on new energy consumption according to Example 1 of the present application;

[0018] Figure 3 It is a flow chart of a method for dispatching multiple energies based on new energy consumption according to Example 1 of the present application;

[0019] Figure 4 is a curve diagram of the first power supply probability distribution according to Embodiment 1 of the present application;

[0020] Figure 5 is a curve diagram of the second power supply probability distribution according to Embodiment 1 of the present application;

[0021] Figure 6 is a curve diagram of the third power supply probability distribution according to Embodiment 1 of the present application;

[0022] Figure 7 is a curve diagram of the probability distribution of electric power consumption according to Example 1 of the present application;

[0023] Fig. 8A It is a first comparison diagram between the probability distribution of total power supply when the power supply power of the thermal power equipment is not increased according to the predetermined step length as described in Example 1 of the present application and the probability distribution of power consumption;

[0024] Figure 8B It is a second comparison diagram between the probability distribution of total power supply after increasing the power supply power of the thermal power equipment according to a predetermined step length and the probability distribution of power consumption according to Example 1 of the present application;

[0025] Figure 8C A third comparison diagram between the probability distribution of total power supply after increasing the power supply power of the thermal power equipment according to a predetermined step length and the probability distribution of total power consumption according to Embodiment 1 of the present application;

[0026] Fig.8D is a schematic diagram of the first probability and the second probability according to Example 1 of the present application;

[0027] Fig. 9 is a schematic diagram of a multi-energy dispatching device based on new energy consumption according to Example 2 of the present application; and

[0028] Fig.10 It is a schematic diagram of a multi-energy dispatching device based on new energy consumption as described in Example 3 of the present application. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only embodiments of a part of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present disclosure.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0031] Example 1

[0032] According to this embodiment, an embodiment of a multiple energy scheduling method based on new energy consumption is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0033] The method embodiment provided in this embodiment can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computing device for implementing a variety of energy scheduling methods based on new energy consumption. Figure 1As shown, the computing device may include one or more processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory for storing data, a transmission device for communication functions, and an input / output interface. The memory, the transmission device, and the input / output interface are connected to the processor via a bus. In addition, it may also include: a display, a keyboard, and a cursor control device connected to the input / output interface. A person skilled in the art can understand that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0034] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuitry may be a single independent processing module, or may be incorporated in whole or in part into any of the other components of the computing device. As involved in the embodiments of the present disclosure, the data processing circuitry acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0035] The memory can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the multiple energy scheduling method based on new energy consumption in the embodiment of the present disclosure. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, the multiple energy scheduling method based on new energy consumption of the above-mentioned application program is realized. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computing device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0036] The transmission device is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computing device. In one example, the transmission device includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet wirelessly.

[0037] The display may be, for example, a touch screen liquid crystal display (LCD) that may enable a user to interact with a user interface of the computing device.

[0038] It should be noted that, in some optional embodiments, the above Figure 1 The computing device shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware elements and software elements. Figure 1 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the computing devices described above.

[0039] Figure 2 Schematic diagram of a multi-energy dispatching system based on new energy consumption according to this embodiment. Figure 2 As shown, the system can be used to implement the dispatching of regional power grids. Specifically, the system includes: a dispatching platform 110, a national power grid 120, and a regional power grid 130. The regional power grid 130 can be, for example, a power grid in a city area, and the regional power grid 130 can be powered by power generation equipment 140 of different energy types, such as photovoltaic equipment 141, wind turbine equipment 142, and thermal power units 143.

[0040] In addition, the power load 150 may include, for example, residential power, industrial power, commercial power, agricultural power, and transportation power.

[0041] Furthermore, the dispatching platform 110 can communicate and connect with the photovoltaic device 141, the wind turbine device 142, the thermal power device 143 and the power load 150 through the Internet of Things, so as to obtain the power supply of the photovoltaic device 141, the power supply of the wind turbine device 142, the power supply of the thermal power unit 143, and the power consumption of the power load 150. Thus, through power dispatching, the balance between the power consumption of the power load 150 and the total power supply power is achieved in the regional power grid 130 (wherein the total power supply power includes the power supply power of the photovoltaic device 141, the power supply power of the wind turbine device 142 and the power supply power of the thermal power unit 143). And wherein, relative to the photovoltaic device 141 and the wind turbine device 142, the thermal power unit 143 is relatively stable and controllable. In addition, when the power supply power of the power supply device 140 of the regional power grid 130 cannot meet the power consumption of the power load 150, electricity can be purchased from the national power grid 120. That is, the dispatching platform 110 can balance the power supply and the power load 150 by controlling the thermal power units 143 and purchasing electricity from the national power grid 120 .

[0042] It should be noted that the dispatching platform 110, power supply equipment 140, regional power grid 130 and national power grid 120 in the system can all be applicable to the hardware structure described above.

[0043] Under the above operating environment, according to the first aspect of this embodiment, a method for scheduling multiple energy sources based on new energy consumption is provided. The method comprises: Figure 2 The scheduling platform 110 shown in FIG. Figure 3 A schematic diagram showing the process of the method is shown in FIG. Figure 3 As shown, the method includes:

[0044] S302: Determine a scheduling period, and divide the scheduling period into a plurality of scheduling periods;

[0045] S304: predicting a first power supply probability distribution corresponding to the target scheduling period according to first meteorological data corresponding to the target scheduling period and based on a first neural network model, wherein the first power supply probability distribution corresponds to the photovoltaic device, and the target scheduling period is any one of the multiple scheduling periods;

[0046] S306: predicting a second power supply probability distribution corresponding to the target scheduling period according to the second meteorological data corresponding to the target scheduling period and based on the second neural network model, wherein the second power supply probability distribution corresponds to the wind turbine equipment;

[0047] S308: Determine a third power supply probability distribution based on the first power supply probability distribution and the second power supply probability distribution, wherein the third power supply probability distribution corresponds to new energy equipment, and the new energy equipment includes photovoltaic equipment and wind turbine equipment;

[0048] S310: predicting the probability distribution of power consumption corresponding to the target scheduling period based on the power consumption data corresponding to the target scheduling period and the RNN model; and

[0049] S312: Based on the third power supply probability distribution and the power consumption probability distribution, predict the power supply of the thermal power equipment, and schedule the power supply of the thermal power equipment based on the prediction result.

[0050] Before the scheduling platform 110 schedules multiple energy sources, it is also necessary to clarify the scheduling principles. In this embodiment, the scheduling principles followed by the scheduling platform 110 mainly include the economic benefit principle and the carbon emission reduction principle. The economic benefit principle means that since the price of purchasing electricity from the national power grid 120 is different during different periods of the day, it is necessary to purchase electricity when the electricity price is low and avoid purchasing electricity when the electricity price is high. For example, different time periods within 24 hours a day can be divided into four different types of time periods, namely peak power purchase, peak power purchase, flat power purchase and valley power purchase. And the power purchase cost attributes corresponding to different types of time periods are also different, and the maximum difference can even be more than 3 times. Therefore, the scheduling platform needs to purchase electricity as much as possible during low electricity price periods, and avoid purchasing electricity during high electricity price periods.

[0051] The carbon emission reduction principle means that since the use of thermal power units 143 may have a certain impact on the environment, the use of thermal power units 143 should be minimized during the scheduling process, and full use should be made of new energy equipment such as photovoltaic equipment 141 and wind turbine equipment 142 to supply power and reduce the occurrence of wind and solar power abandonment.

[0052] It is worth noting that when the power demand of the regional power grid 130 cannot be met by only using new energy equipment, and when it is possible to choose to use the thermal power unit 143 for power supply or to purchase power from the national power grid 120, the principle of economic benefit should be given priority. That is, the priority of the principle of economic benefit is higher than the priority of carbon emission reduction.

[0053] Specifically, first, the scheduling platform 110 determines a scheduling period T and divides the scheduling period T into a plurality of scheduling periods S 1 ~S 24 (S302). For example, the scheduling platform 110 may determine 24 hours a day as a scheduling cycle T, and divide the 24 hours a day into 24 scheduling periods S 1 ~S 24 That is, each hour is a scheduling period. Of course, the above-mentioned 24 hours a day is determined as a scheduling cycle T, and the 24 hours a day is divided into 24 scheduling periods S 1 ~S 24It is just an example listed in this application. It should be noted by those skilled in the art that the scheduling platform 110 can determine the scheduling period based on actual conditions and divide the scheduling period, which will not be described in detail here.

[0054] Then, the scheduling platform 110 calculates the time interval S according to the target scheduling period. k The corresponding first meteorological data, and based on the first neural network model, predict the target scheduling period S k The corresponding first power supply probability distribution (S304). The first power supply probability distribution corresponds to the photovoltaic device 141. And the target scheduling period S k Any one or more scheduling periods among the multiple scheduling periods.

[0055] Specifically, first, the scheduling platform 110 collects the target scheduling period S k The corresponding first meteorological data such as sunshine intensity data, cloud cover data, temperature data and wind speed. Then, the scheduling platform 110 converts the collected first meteorological data into the corresponding first feature vector, and inputs the first feature vector into the pre-set first neural network model, so as to predict the probability of different power intervals generated by the photovoltaic device 141. For example, the probability corresponding to the power interval of 9000W to 8000W is 10%, the probability corresponding to the power interval of 8000W to 7000W is 20%, the probability corresponding to the power interval of 7000W to 6000W is 30%, the probability corresponding to the power interval of 6000W to 5000W is 20%, and the probability corresponding to the power interval of 5000W to 4000W is 10%.

[0056] Thus, the scheduling platform 110 can generate the target scheduling period S based on the above-predicted probabilities of different power intervals generated by the photovoltaic device 141. k The corresponding first power supply probability distribution. Figure 4 is a curve diagram of the first power supply probability distribution according to the embodiment of the present application. Figure 4 As shown, with power as the horizontal axis and probability as the vertical axis, and based on the above prediction results, a normal distribution curve is obtained.

[0057] And it is worth noting that the target scheduling period S k It can be the above multiple scheduling periods S 1 ~S 24 For example, the target scheduling period S k It can be the scheduling period S 1 , target scheduling period S k It can be the scheduling period S 2 ,......, target scheduling period S kIt can be the scheduling period S 24 . I will not go into details here.

[0058] Target scheduling period S k It can also be the above multiple scheduling periods S 1 ~S 24 For example, the target scheduling period S k It can be the scheduling period S 1 ~S 3 For another example, the target scheduling period S k It can be the scheduling period S 1 ~S 24 .

[0059] In the scheduling platform 110, the prediction and target scheduling period S k In the case of the corresponding first power supply probability distribution, further according to the target scheduling period S k The corresponding second meteorological data, and based on the second neural network model, predict the target scheduling period S k The corresponding second power supply probability distribution ( S306 ) corresponds to the wind turbine device 142 .

[0060] Specifically, first, the scheduling platform 110 collects the target scheduling period S k The corresponding second meteorological data such as wind speed, wind turbine wind direction angle (i.e., wind turbine wind direction angle after wind turbine adjustment), temperature and air pressure. Then the scheduling platform 110 converts the collected second meteorological data into corresponding second feature vectors, and inputs the second feature vectors into a pre-set second neural network model, so as to predict the probabilities of different power intervals generated by the wind turbine equipment 142. For example, the probability corresponding to the power interval of 8000W to 7500W is 10%, the probability corresponding to the power interval of 7500W to 7000W is 20%, the probability corresponding to the power interval of 7000W to 6500W is 30%, the probability corresponding to the power interval of 6500W to 6000W is 20%, and the probability corresponding to the power interval of 6000W to 5500W is 10%.

[0061] Thus, the scheduling platform 110 can determine the target scheduling period S based on the predicted probabilities of different power intervals generated by the wind turbine device 142. k The corresponding second power supply probability distribution. Figure 5 is a curve diagram of the second power supply probability distribution according to the embodiment of the present application. Figure 5 As shown, with power as the horizontal axis and probability as the vertical axis, and based on the above prediction results, a normal distribution curve is obtained.

[0062] Then, the scheduling platform 110 determines the third power supply probability distribution based on the first power supply probability distribution and the second power supply probability distribution (S308). The third power supply probability distribution corresponds to the new energy equipment. And the new energy equipment includes photovoltaic equipment 141 and wind turbine equipment 142. Specifically, first, the scheduling platform 110 can determine the third power supply probability based on the following formula:

[0063] Q l =Q g +Q f

[0064] Among them, Q g represents the first power supply probability, Q f represents the second power supply probability, Q l represents the third power supply probability.

[0065] That is, the scheduling platform 110 can be based on the target scheduling period S k In the target scheduling period S, a plurality of first power supply probabilities corresponding to a plurality of different power intervals are k The target scheduling period S is determined by combining multiple second power supply probabilities corresponding to multiple different power intervals. k In determining the target scheduling period S k In the case of multiple third power supply power probabilities corresponding to multiple different power intervals, the third power supply power probability distribution corresponding to the new energy equipment can be determined with power as the horizontal coordinate and probability as the vertical coordinate. For example, the probability corresponding to the power interval of 17000W to 15500W is 10%, the probability corresponding to the power interval of 15500W to 14000W is 20%, the probability corresponding to the power interval of 14000W to 13500W is 30%, the probability corresponding to the power interval of 13500W to 11000W is 20%, and the probability corresponding to the power interval of 11000W to 9500W is 10%.

[0066] Figure 6 is a curve diagram of the third power supply probability distribution according to the embodiment of the present application. Figure 6 As shown, with power as the horizontal axis and probability as the vertical axis, and based on the above prediction results, a normal distribution curve is obtained.

[0067] Then the scheduling platform 110 calculates the target scheduling period S k The corresponding power consumption data is used to predict the target scheduling period S based on the RNN model. k First, the scheduling platform 110 collects the target scheduling period S kThe electricity consumption data may include, for example, geographic information data, time factor data, and social activity index data. The geographic information data may include, for example, the area of ​​the urban area and the topographical characteristics. The time factor data may include, for example, the season, and whether the current time status is a working day or a holiday. The social activity index data may include, for example, the population contained in the city and the level of economic activity.

[0068] Then, the scheduling platform 110 will be connected with the target scheduling period S k The power consumption characteristic vector corresponding to the previous scheduling period and the target scheduling period S k The corresponding power consumption data is input into the RNN model, so as to output the target scheduling period S k The corresponding power consumption feature vector. For example, in the target scheduling period S k is the scheduling period S 1 In the case of 1 The power consumption data of the RNN model is input into the RNN model, so as to output the scheduling period S 1 The corresponding power consumption feature vector I 1 For another example, in the target scheduling period S k is the scheduling period S 2 In the case of 2 Power consumption data and dispatch period S 1 The electricity consumption characteristic vector I 1 The output is the same as the scheduling period S. 2 The corresponding power consumption feature vector I 2 Therefore, it should be clear to those skilled in the art that in the target scheduling period S k is another scheduling period S in the multiple scheduling periods 3 ~S 24 In this case, the scheduling platform 110 can determine the power consumption feature vector based on the same method as above.

[0069] Furthermore, the scheduling platform 110 sets the target scheduling period S k The power consumption feature vector is input to the softmax classifier connected to the RNN model, thereby outputting multiple probabilities corresponding to multiple different power consumption intervals. Finally, the scheduling platform 110 generates a target scheduling period S based on the predicted multiple probabilities corresponding to multiple different power consumption intervals. k The corresponding probability distribution of electrical power.

[0070] For example, the probability corresponding to the power range of 16000W to 15500W is 10%, the probability corresponding to the power range of 15500W to 15000W is 20%, the probability corresponding to the power range of 15000W to 14500W is 30%, the probability corresponding to the power range of 14500W to 14000W is 20%, and the probability corresponding to the power range of 14000W to 13500W is 10%.

[0071] Figure 7 is a curve diagram of the probability distribution of power consumption according to the embodiment of the present application. Figure 7 As shown, with power as the horizontal axis and probability as the vertical axis, and based on the above prediction results, a normal distribution curve is obtained.

[0072] Finally, the scheduling platform 110 predicts the power supply of the thermal power equipment 143 based on the third power supply probability distribution and the power consumption probability distribution, and schedules the power supply of the thermal power equipment 143 based on the prediction result (S312). There are two situations in which the scheduling platform 110 predicts the power supply of the thermal power equipment 143 based on the third power supply probability distribution and the power consumption probability distribution: first, when the minimum value of the total power generation of the new energy equipment ≥ the maximum value of the total power consumption (that is, only relying on the new energy equipment can be in the target scheduling period S k The power demand of the power load 150 is absolutely met within the target scheduling period S), and there is no need to use the thermal power equipment 143 for power supply, nor is there a need to purchase power from the national power grid 120. Second, when the minimum value of the total power generation of the new energy equipment is less than the maximum value of the total power consumption (that is, relying solely on the new energy equipment, it is impossible to meet the target scheduling period S with a certain probability). k The dispatching platform 110 needs to further predict the power supply of the thermal power equipment 143, and dispatch the power supply of the thermal power equipment 143 based on the prediction result. The above content will be described in detail later, so it will not be repeated here.

[0073] As described in the background technology, the power supply of traditional power systems mainly relies on traditional energy sources such as thermal power and hydropower. The power generation methods of these energy sources are relatively stable and controllable, and can better meet the load requirements of the power system. However, with the rapid increase in the installed capacity of new energy, the proportion of traditional energy in the power system has gradually decreased, which has put tremendous pressure on the dispatching capacity and flexibility of the power system. Especially when the output of new energy fluctuates greatly, it is impossible to reasonably coordinate and optimize the dispatching of multiple energy sources, resulting in low utilization rates of multiple energy sources.

[0074] In view of this, the present application provides a method for scheduling multiple energy sources based on new energy consumption. And because the scheduling platform 110 predicts the first power supply probability distribution (corresponding to the photovoltaic device) corresponding to the target scheduling period based on the first meteorological data corresponding to the target scheduling period and the first neural network model, and predicts the second power supply probability distribution (corresponding to the wind turbine device) corresponding to the target scheduling period based on the second meteorological data corresponding to the target scheduling period and the second neural network model, the scheduling platform 110 can predict the power supply probability distribution (i.e., the third power supply probability distribution) of the new energy device based on the first power supply probability distribution and the second power supply probability distribution.

[0075] Since the scheduling platform 110 predicts the power consumption probability distribution corresponding to the target scheduling period based on the power consumption data of the target scheduling period, the scheduling platform 110 can predict the power supply of the thermal power equipment 143 based on the power supply power probability distribution and power consumption probability distribution of the new energy equipment, and schedule the power supply of the thermal power equipment 143 based on the prediction result.

[0076] In summary, the scheduling platform 110 can predict the power supply of new energy equipment (i.e., the power supply of photovoltaic equipment 141 and the power supply of wind turbine equipment 142) in advance, and determine the power supply of thermal power equipment 142 to be scheduled based on the power supply of new energy equipment to meet the power demand. Therefore, in the actual scheduling process, the coordinated scheduling of multiple energy sources can be achieved based on the above operations to ensure the rationality of energy scheduling and improve the utilization rate of multiple energy sources. This solves the technical problem that when the output of new energy fluctuates greatly, it is impossible to reasonably coordinate and optimize the scheduling of multiple energy sources in the prior art, resulting in low energy utilization efficiency.

[0077] Optionally, based on the third power supply probability distribution and the power consumption probability distribution, the power supply of the thermal power equipment is predicted, and the power supply of the thermal power equipment is scheduled based on the prediction result, including: determining the minimum power supply of the new energy equipment based on the third power supply probability distribution; determining the maximum power consumption based on the power consumption probability distribution; and predicting the power supply of the thermal power equipment based on the minimum power supply of the new energy equipment and the maximum power consumption of the user, and scheduling the power supply of the thermal power equipment based on the prediction result.

[0078] Specifically, first, the scheduling platform 110 determines the minimum power supply power of the new energy equipment based on the third power supply power probability distribution. Then, the scheduling platform 110 determines the maximum power consumption based on the power consumption probability distribution. Finally, the scheduling platform 110 predicts the power supply power of the thermal power equipment 143 based on the minimum power supply power and the maximum power consumption of the new energy equipment.

[0079] It is worth noting that when the scheduling platform 110 determines the minimum power supply power and the maximum power consumption of the new energy equipment, two scheduling situations may occur. First, when the minimum value of the total power generation of the new energy equipment is ≥ the maximum value of the total power consumption (that is, only the new energy equipment can be used in the target scheduling period S k The power demand of the power load 150 is absolutely met within the target scheduling period S), and there is no need to use the thermal power equipment 143 for power supply, nor is there any need to purchase power from the national power grid 120. Second, when the minimum value of the total power generation of the new energy equipment is less than the maximum value of the total power consumption (that is, relying solely on the new energy equipment, it is impossible to meet the target scheduling period S with a certain probability). k In order to meet the electricity demand of the power load 150), it is necessary to further predict the power supply power of the thermal power equipment 143.

[0080] For example, refer to Figure 6 as well as Figure 7 As shown, the scheduling platform 110 determines that the minimum power supply power of the new energy equipment is 9500W based on the third power supply power probability distribution. And the scheduling platform 110 determines that the maximum power consumption is 16000W based on the power consumption probability distribution. Then the scheduling platform 110 determines that in the target scheduling period S k There is a certain probability that the power demand of the power load 150 cannot be met by using only new energy equipment. Therefore, in the above case, the dispatching platform 110 needs to further predict the power supply of the thermal power equipment 143. And in the actual dispatching process, there may be a certain probability that power will be purchased from the national power grid 120.

[0081] For another example, if the scheduling platform 110 determines that the minimum power supply power of the new energy equipment is 14000W based on the third power supply power probability distribution, and the scheduling platform 110 determines that the maximum power consumption is 13000W based on the power consumption probability distribution, then the scheduling platform 110 determines that in the target scheduling period S k Within the scope, the electricity demand of 150% of the electricity load can be absolutely met by using only new energy equipment.

[0082] For another example, if the scheduling platform 110 determines that the minimum power supply power of the new energy equipment is 10000W based on the third power supply probability distribution, and the scheduling platform 110 determines that the maximum power consumption is 10000W based on the power consumption probability distribution, then the scheduling platform 110 determines that in the target scheduling period S k Within the scope, the electricity demand of 150% of the electricity load can be absolutely met by using only new energy equipment.

[0083] Therefore, the scheduling platform 110 can predict the power supply of the thermal power equipment based on the predicted third power supply probability distribution and the power consumption probability distribution, and schedule the power supply of the thermal power equipment 143 based on the prediction result. This ensures that the power demand of the power load 150 can be met and the normal work and life of the user can be guaranteed.

[0084] Optionally, based on the minimum power supply power of the new energy equipment and the maximum power consumption of the user, the power supply power of the thermal power equipment is predicted, and the power supply power of the thermal power equipment is scheduled based on the prediction result, including: when the minimum power supply power of the new energy equipment is greater than or equal to the maximum power consumption, the thermal power equipment is not used for power supply.

[0085] Specifically, referring to the above content, when the minimum value of the total power generated by the new energy equipment is greater than or equal to the maximum value of the total power consumed (that is, only the new energy equipment can be used in the target scheduling period S k The power demand of the power load 150 is absolutely met within the power grid), and neither the thermal power equipment 143 is needed to supply power, nor is it needed to purchase power from the national power grid 120. That is, at this time, the thermal power equipment 134 does not need to be used to supply power, and the power demand of the power load 150 can be met by only using new energy equipment.

[0086] Therefore, since the power demand of the power load 150 can be fully met by using only the new energy equipment, there is no need to use the thermal power equipment 134 to supply power. This can achieve the technical effect of reducing carbon emissions and protecting the environment while ensuring the normal work and life of users.

[0087] Optionally, based on the minimum power supply power and the maximum power consumption of the new energy equipment, the power supply power of the thermal power equipment is predicted, and the power supply power of the thermal power equipment is scheduled based on the prediction result, including: when the minimum power supply power of the new energy equipment is less than the maximum power consumption, determining the time period type corresponding to the target scheduling time period, wherein the time period types include peak power purchase, peak power purchase, flat power purchase and valley power purchase, and based on the time period type corresponding to the target scheduling time period, predicting the power supply power of the thermal power equipment, and scheduling the power supply power of the thermal power equipment based on the prediction result.

[0088] Specifically, referring to the above content, when the minimum power supply power of the new energy equipment is less than the maximum power consumption power, the scheduling platform 110 needs to further determine the target scheduling period S k The corresponding time period type. Among them, the target scheduling period S k The corresponding time period types include peak power purchase, peak power purchase, flat power purchase and valley power purchase. Then, the scheduling platform 110 can also kThe corresponding time period type determines the corresponding electricity purchase cost attribute.

[0089] For example, the scheduling platform 110 may determine the target scheduling period S based on Table 1 below: k The corresponding time period type and electricity purchase cost attributes.

[0090] Table 1

[0091] Time Period Type Power purchase cost attributes 0:00～8:00 Lows lowest 8:00～10:00 peak high 10:00～12:00 peak Highest 12:00～17:00 Flat section Higher 17:00～19:00 peak high 19:00～21:00 peak Highest 21:00～23:00 peak high 23:00～00:00 Lows lowest

[0092] Table 1 shows a table of time period-time period type-power purchase cost attributes. Referring to Table 1, for example, if the target scheduling time period S k is 0:00~1:00, then the target scheduling period S k The time period type is off-peak electricity purchase, and the target scheduling period S k The power purchase cost is the lowest. If the target dispatch period S k is 8:00~9:00, then the target scheduling period S k The time period type is peak power purchase, and the target scheduling period S k The electricity purchase cost is high. If the target dispatch period S k is 11:00~12:00, then the target scheduling period S k The time period type is peak power purchase, and the target scheduling period S k The electricity purchase cost is the highest. If the target dispatch period S k is 12:00~13:00, then the target scheduling period S k The time period type is flat-term power purchase, and the target scheduling period S k The electricity purchase cost is high. It is worth noting that the size relationship between the various types of electricity purchase cost attributes shown in Table 1 is: highest > high > relatively high > lowest.

[0093] Therefore, the scheduling platform 110 can determine the target scheduling period S based on the above Table 1. k The corresponding time period type.

[0094] Finally, the scheduling platform 110 calculates the target scheduling period S based on the target scheduling period S. k The power supply of the thermal power equipment 143 is predicted according to the time period type. For example, in the target scheduling period S kWhen the time period type is peak power purchase, peak power purchase or flat power purchase, since the power purchase price of the national power grid 120 is relatively high at this time, power is not purchased from the national power grid 120, but the power supply equipment 140 of the regional power grid 130 is relied on for power supply. In this case, the dispatching platform 110 predicts the power supply power of the thermal power unit 143 to be dispatched, and makes the minimum value of the total power supply power ≥ the maximum value of the total power consumption, so that the power demand of the power load 150 can be absolutely met by relying only on the power supply equipment 140 of the regional power grid 130. Among them, the minimum value of the total power supply power is equal to the sum of the maximum value of the total power generation of the new energy equipment and the minimum value of the total power generation of the thermal power equipment 143.

[0095] For another example, in the target scheduling period S k When the time period type is off-peak electricity purchase, since the electricity purchase price of the national power grid 120 is the lowest at this time, it is allowed to purchase electricity from the national power grid within a certain probability range. The above content will be described in detail later, so it will not be repeated here.

[0096] Therefore, since the present application chooses not to purchase electricity from the national power grid 120 when the power purchase cost is high, but chooses to purchase electricity from the national power grid 120 when the power purchase cost is the lowest, it can achieve the technical effect of saving costs to the greatest extent while absolutely meeting the power demand of the power load.

[0097] Optionally, based on the time period type corresponding to the target scheduling period, the power supply of the thermal power equipment is predicted, and the power supply of the thermal power equipment is scheduled based on the prediction result, including: when the time period type corresponding to the target scheduling period is peak power purchase, peak power purchase or flat power purchase, only new energy equipment and thermal power equipment are used for power supply, and the minimum value of the total power supply is greater than or equal to the maximum power consumption, wherein the total power supply includes the power supply of the new energy equipment and the power supply of the thermal power equipment; and when the time period type corresponding to the target scheduling period is valley power purchase, the power supply of the thermal power equipment is predicted, and the power supply of the thermal power equipment is scheduled based on the prediction result.

[0098] Specifically, based on the above Table 1, it can be seen that due to the target scheduling period S k When the corresponding time period type is peak power purchase, peak power purchase or flat power purchase, it is consistent with the target scheduling period S k The corresponding electricity purchase cost is high, so in this case, only new energy equipment and thermal power equipment are used for power supply, and the minimum total power supply power is greater than or equal to the maximum power consumption power. The total power supply power includes the power supply power of new energy equipment and the power supply power of thermal power equipment.

[0099] For example, refer to Figure 6 and Figure 7 As shown, Figure 6 The minimum power supply of the new energy equipment shown in the table is 9500W. Figure 7 The maximum value of the power consumption shown in is 16000W. This shows that in this case, there is a certain probability that the new energy equipment cannot absolutely meet the power demand of the power load 150. In other words, in order to absolutely meet the power demand of the power load 150, it is necessary to use the thermal power equipment 143 to supply power, and make the minimum value of the total power supply greater than or equal to the maximum value of the power consumption, so that the power demand of the power load 150 can be absolutely met.

[0100] Therefore, the minimum value of the power supply of the thermal power equipment 143 is 6500 W. That is, only when the power supply of the thermal power equipment 143 is 6500 W can the minimum value of the total power supply be absolutely equal to the maximum value of the total power consumption.

[0101] Furthermore, in the target scheduling period S k When the corresponding time period type is off-peak power purchase, the dispatching platform 110 predicts the power supply of the thermal power equipment 143 and dispatches the power supply of the thermal power equipment 143 based on the prediction result. In addition, based on the above Table 1, it can be seen that due to the target dispatching period S k When the corresponding time period type is off-peak power purchase, it is consistent with the target scheduling period S k The corresponding electricity purchase cost is the lowest, so in this case, it is allowed to purchase electricity from the national power grid 120 within a certain probability range.

[0102] However, it should be noted that the above-mentioned permission to purchase electricity from the national power grid 120 only refers to the situation where the actual demand of the power load 150 cannot be met according to the prediction result of the dispatching platform 110. k The power supply of the internal thermal power equipment 143 is P k However, due to some influencing factors, the thermal power equipment 143 cannot reach the predicted power supply, or the prediction result is wrong. Even if the power supply power of the thermal power equipment 143 is P k , and the power demand of the power load 150 cannot be absolutely met. Then, at this time, the dispatching platform 110 can purchase electricity from the national power grid 120, and the probability of purchasing electricity from the national power grid 120 needs to be less than a preset probability threshold.

[0103] Therefore, in the target scheduling period S kWhen the corresponding time period type is peak power purchase, peak power purchase or flat power purchase, only new energy equipment and thermal power equipment are used to supply power, and no power is purchased from the national power grid 120, and during the target dispatch period S k When the corresponding time period type is off-peak electricity purchase, it can be allowed to purchase electricity from the national power grid 120 within a certain probability range, which can achieve the technical effect of saving economic costs.

[0104] Optionally, when the time period type corresponding to the target scheduling period is off-peak electricity purchase, the power supply of the thermal power equipment is predicted, and the power supply of the thermal power equipment is scheduled based on the prediction result, including: determining whether the maximum value of the total power supply is greater than or equal to the maximum power consumption; if not, increasing the power supply of the thermal power equipment according to a predetermined step size until the maximum value of the total power supply is greater than or equal to the maximum power consumption.

[0105] Specifically, in the target scheduling period S k When the corresponding time period type is off-peak power purchase, the dispatching platform 110 first determines whether the maximum value of the total power supply is greater than or equal to the maximum value of the power consumption. If the dispatching platform 110 determines that the maximum value of the total power supply is less than the maximum value of the power consumption, it means that under a certain probability, the total power supply cannot meet the power demand of the power load 150. Therefore, the dispatching platform 110 increases the power supply of the thermal power equipment 143 according to the predetermined step size until the maximum value of the total power supply is greater than or equal to the maximum value of the power consumption. Among them, the predetermined step size can be determined by the dispatching platform 110 based on actual conditions, and is not limited here.

[0106] In addition, it is worth noting that when the dispatching platform 110 does not dispatch the thermal power equipment 143 to supply power, the power supply power of the new energy equipment is the total power supply power.

[0107] For example, Fig. 8A It is a first comparison diagram between the probability distribution of total power supply when the power supply power of the thermal power equipment is not increased according to a predetermined step size as described in an embodiment of the present application and the probability distribution of power consumption. Figure 8B It is a second comparison diagram between the probability distribution of total power supply after increasing the power supply power of the thermal power equipment according to a predetermined step size as described in an embodiment of the present application and the probability distribution of power consumption.

[0108] refer to Fig. 8A As shown in FIG. 1 , when the power supply of the thermal power equipment 143 is not increased according to the predetermined step length, the maximum value of the total power supply is less than the maximum value of the power consumption. Therefore, the scheduling platform 110 determines that the power supply of the thermal power equipment 143 needs to be increased according to the predetermined step length until the maximum value of the total power supply is greater than or equal to the maximum value of the power consumption. Figure 8B shown.

[0109] Optionally, when the maximum value of the total power supply is greater than or equal to the maximum value of the power consumption, the power supply of the thermal power equipment is predicted, and the power supply of the thermal power equipment is scheduled based on the prediction result, including: determining the minimum power consumption based on the power consumption probability distribution; and determining whether the minimum value of the total power supply is greater than or equal to the minimum power consumption; if not, increasing the power supply of the thermal power equipment according to a predetermined step size until the minimum value of the total power supply is greater than or equal to the minimum power consumption.

[0110] Specifically, when the scheduling platform 110 increases the power supply of the thermal power equipment 143 according to a predetermined step size until the maximum value of the total power supply is greater than or equal to the maximum power consumption, the scheduling platform 110 further determines whether the minimum value of the total power supply is greater than or equal to the minimum power consumption.

[0111] If the dispatching platform 110 determines that the minimum value of the total power supply is less than the minimum value of the power consumption, it means that under a certain probability, the total power supply cannot meet the power demand of the power load 150. Therefore, the dispatching platform 110 increases the power supply of the thermal power equipment 143 according to the predetermined step size until the minimum value of the total power supply is greater than or equal to the minimum value of the power consumption. The predetermined step size can be determined by the dispatching platform 110 based on actual conditions, and is not limited here.

[0112] For example, Figure 8C It is a third comparison diagram between the probability distribution of total power supply after increasing the power supply power of the thermal power equipment according to a predetermined step size as described in an embodiment of the present application and the probability distribution of total power consumption.

[0113] refer to Figure 8B As shown, when the dispatching platform 110 has increased the power supply of the thermal power equipment 143 according to the predetermined step length and made the maximum value of the total power supply equal to the maximum value of the power consumption, the dispatching platform 110 further determines whether the minimum value of the total power supply at this time is greater than or equal to the minimum value of the power consumption. Figure 8B It can be seen that the minimum value of the total power supply at this time is less than the minimum value of the power consumption. Therefore, the scheduling platform 110 increases the power supply of the thermal power equipment 143 until the minimum value of the total power supply is greater than or equal to the minimum value of the power consumption. Figure 8C shown.

[0114] When the dispatching platform 110 increases the power supply of the thermal power equipment 143 according to the predetermined step length so that the maximum value of the total power supply is greater than or equal to the maximum value of the power consumption, the minimum value of the total power supply is also greater than or equal to the minimum value of the power consumption. In this case, there is no need to increase the power supply of the thermal power equipment 143.

[0115] Optionally, when the maximum value of the total power supply is greater than or equal to the maximum value of the power consumption, and the minimum value of the total power supply is greater than or equal to the minimum value of the power consumption, the power supply of the thermal power equipment is predicted, and the power supply of the thermal power equipment is scheduled based on the prediction result, including: determining a first probability that the power consumption is within the overlapping interval of a fourth power supply probability distribution and the power consumption probability distribution, wherein the fourth power supply probability distribution corresponds to the total power supply; determining a second probability that the total power supply is within the overlapping interval of the fourth power supply probability distribution and the power consumption probability distribution; determining a third probability based on the first probability and the second probability, wherein the third probability is used to indicate the probability within the overlapping interval of the first probability and the second probability; determining a preset probability threshold based on the power purchase cost attribute corresponding to the target scheduling period; and determining whether the third probability is greater than the preset probability threshold, if not, increasing the power supply of the thermal power equipment according to a predetermined step size until the third probability is less than or equal to the preset probability threshold.

[0116] Specifically, when the scheduling platform 110 has increased the power supply of the thermal power equipment 143 according to a predetermined step length so that the maximum value of the total power supply is greater than or equal to the maximum value of the power consumption, and the minimum value of the total power supply is greater than or equal to the minimum value of the power consumption, the scheduling platform 110 first needs to determine the first probability. The first probability corresponds to the overlapping interval of the power consumption in the fourth power supply power probability distribution and the power consumption probability distribution.

[0117] For example, Fig.8D is a schematic diagram of the first probability and the second probability according to an embodiment of the present application. Fig.8D As shown, the overlapping interval of the fourth power supply probability distribution and the power consumption probability distribution is represented by a dotted line. Thus, for the power consumption, the first probability of the power consumption in the overlapping interval of the fourth power supply probability distribution and the power consumption probability distribution is 100%. For the total power supply, the second probability of the total power supply in the overlapping interval of the fourth power supply probability distribution and the power consumption probability distribution is 95%.

[0118] Further, the scheduling platform 110 determines a third probability based on the first probability and the second probability. A certain power of the third probability is used to indicate a probability that is within both the first probability and the second probability. The specific calculation formula is as follows:

[0119] P 3 =P 1 ×P 2

[0120] Among them, P 3 represents the third probability, P 1 represents the first probability, P 2 represents the second probability.

[0121] Then the scheduling platform 110 calculates the target scheduling period S k Corresponding time period type, determine the preset probability threshold P t The preset probability threshold P t That is, in this embodiment, it is allowed to purchase electricity from the national power grid 120 within a certain probability range, but the maximum probability cannot exceed the preset probability threshold P t If the probability exceeds the preset threshold P t , it means that it is very likely that the national power grid 120 will appear, which is inconsistent with the principle of economic benefit in this embodiment.

[0122] In addition, it is worth noting that the preset probability threshold P t It can change dynamically with the increase of electricity price. For example, the lower the electricity price, the higher the preset probability threshold P t The larger the value, the higher the electricity price. t The smaller the probability is, the smaller the probability is. And the preset probability threshold P t This is a value determined by the regulator based on actual conditions and is not specifically limited here.

[0123] Finally, the scheduling platform 110 determines the third probability P 3 Is it greater than the preset probability threshold P? t If not, the dispatching platform 110 increases the power supply of the thermal power equipment 143 according to a predetermined step length until the third probability P 3 ≤Preset probability threshold P t Until (that is, until the probability of purchasing electricity from the national power grid 120 is less than the preset probability threshold P t until).

[0124] For another example, the above content has mentioned that the first probability P 1 is 100%, the second probability P 2 Then, the scheduling platform 110 can determine the third probability P based on the above formula: 3 is 95%. Therefore, if the preset probability threshold P t The scheduling platform 110 also needs to increase the power supply of the thermal power equipment 143 according to the predetermined step length until the third probability P 3 Less than or equal to the preset probability threshold P t .

[0125] Therefore, after the scheduling platform 110 predicts the power supply of the thermal power equipment 143 based on the above operations, the scheduling platform 110 can schedule the power supply of the thermal power equipment 143 based on the prediction results during the actual operation, which can achieve the technical effect of theoretically absolutely meeting the power demand of the power load 150.

[0126] In addition, in the target scheduling period S k In the present invention, the dispatching platform 110 dispatches the power supply of the thermal power equipment 143 based on the prediction result. However, when the total power supply still cannot absolutely meet the power demand of the power load 150 (for example, the thermal power equipment 143 cannot reach the power supply corresponding to the prediction result), the dispatching platform 110 can also purchase electricity from the national power grid 120 to meet the power demand of the power load 150.

[0127] Therefore, according to the first aspect of this embodiment, it is possible to achieve the technical effect of realizing coordinated scheduling of multiple energy sources based on the above operations during the actual scheduling process, ensuring the rationality of energy scheduling, and improving the utilization rate of multiple energy sources.

[0128] In addition, reference Figure 1 As shown, according to the second aspect of this embodiment, a storage medium is provided, wherein the storage medium includes a stored program, wherein when the program is run, a processor executes any one of the above methods.

[0129] Therefore, according to this embodiment, it is possible to achieve the technical effect of realizing coordinated scheduling of multiple energy sources based on the above operations during the actual scheduling process, ensuring the rationality of energy scheduling, and improving the utilization rate of multiple energy sources.

[0130] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0131] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0132] Example 2

[0133] Fig. 9 FIG. 9 shows a multi-energy scheduling device 900 based on new energy consumption according to this embodiment, and the device 900 corresponds to the method according to Embodiment 1. Fig. 9 As shown, the device 900 includes: a scheduling period determination module 910, which is used to determine the scheduling period and divide the scheduling period into multiple scheduling periods; a first power supply power probability distribution prediction module 920, which is used to predict the first power supply power probability distribution corresponding to the target scheduling period based on the first meteorological data corresponding to the target scheduling period and based on the first neural network model, wherein the first power supply power probability distribution corresponds to the photovoltaic equipment, and the target scheduling period is any one or more scheduling periods among the multiple scheduling periods; a second power supply power probability distribution prediction module 930, which is used to predict the second power supply power probability distribution corresponding to the target scheduling period based on the second meteorological data corresponding to the target scheduling period and based on the second neural network model, wherein The second power supply probability distribution corresponds to the wind turbine equipment; the third power supply probability distribution prediction module 930 is used to determine the third power supply probability distribution based on the first power supply probability distribution and the second power supply probability distribution, wherein the third power supply probability distribution corresponds to the new energy equipment, and the new energy equipment includes photovoltaic equipment and wind turbine equipment; the power consumption probability distribution prediction module 950 is used to predict the power consumption probability distribution corresponding to the target scheduling period according to the power consumption data corresponding to the target scheduling period and based on the RNN model; and the scheduling module 960 is used to predict the power supply of the thermal power equipment based on the third power supply probability distribution and the power consumption probability distribution, and schedule the power supply of the thermal power equipment based on the prediction result.

[0134] Optionally, the scheduling module 960 includes: a first power supply determination module, used to determine the minimum power supply power of the new energy equipment based on the third power supply probability distribution; a first power consumption determination module, used to determine the maximum power consumption based on the power consumption probability distribution; and a first scheduling sub-module, used to predict the power supply power of the thermal power equipment based on the minimum power supply power and the maximum power consumption of the new energy equipment, and schedule the power supply power of the thermal power equipment based on the prediction result.

[0135] Optionally, the first scheduling submodule includes: a first prediction result determination module, which is used to not use thermal power equipment to supply power when the minimum power supply power of the new energy equipment is greater than or equal to the maximum power consumption power.

[0136] Optionally, the first scheduling submodule includes: a time period type determination module, which is used to determine the time period type corresponding to the target scheduling time period when the minimum power supply power of the new energy equipment is less than the maximum power consumption power, wherein the time period types include peak power purchase, peak power purchase, flat power purchase and valley power purchase; and a second prediction result determination module, which is used to predict the power supply power of the thermal power equipment based on the time period type corresponding to the target scheduling time period, and schedule the power supply power of the thermal power equipment based on the prediction result.

[0137] Optionally, the first scheduling submodule includes: a third prediction result determination module, which is used to only use new energy equipment and thermal power equipment to supply power when the time period type corresponding to the target scheduling period is peak power purchase, peak power purchase or flat power purchase, and make the minimum value of the total power supply power greater than or equal to the maximum power consumption, wherein the total power supply power includes the power supply power of the new energy equipment and the power supply power of the thermal power equipment; and a fourth prediction result determination module, which is used to predict the power supply power of the thermal power equipment when the time period type corresponding to the target scheduling period is valley power purchase, and schedule the power supply power of the thermal power equipment based on the prediction result.

[0138] Optionally, the fourth prediction result determination module includes: a first power supply increase module, used to determine whether the maximum value of the total power supply is greater than or equal to the maximum power consumption; if not, increase the power supply of the thermal power equipment according to a predetermined step size until the maximum value of the total power supply is greater than or equal to the maximum power consumption.

[0139] Optionally, when the maximum value of the total power supply power is greater than or equal to the maximum value of the power consumption, the fourth prediction result determination module includes: a second power consumption determination module, used to determine the minimum power consumption based on the power consumption probability distribution; and a second power supply increase module, used to determine whether the minimum value of the total power supply power is greater than or equal to the minimum power consumption value; if not, increasing the power supply of the thermal power equipment according to a predetermined step size until the minimum value of the total power supply power is greater than or equal to the minimum power consumption value.

[0140] Optionally, when the maximum value of the total power supply power is greater than or equal to the maximum value of the power consumption, and the minimum value of the total power supply power is greater than or equal to the minimum value of the power consumption, the fourth prediction result determination module includes: a first probability determination module, used to determine the first probability of the power consumption within the overlapping interval of the fourth power supply power probability distribution and the power consumption probability distribution, wherein the fourth power supply power probability distribution corresponds to the total power supply power; a second probability determination module, used to determine the second probability of the total power supply power within the overlapping interval of the fourth power supply power probability distribution and the power consumption probability distribution; a third probability determination module, used to determine the third probability based on the first probability and the second probability; a preset probability threshold determination module, used to determine the preset probability threshold based on the time period type corresponding to the target scheduling time period; and a third power supply increase module, used to determine whether the third probability is greater than the preset probability threshold, and if not, increase the power supply of the thermal power equipment according to a predetermined step size until the third probability is less than or equal to the preset probability threshold.

[0141] Therefore, according to this embodiment, it is possible to achieve the technical effect of realizing coordinated scheduling of multiple energy sources based on the above operations during the actual scheduling process, ensuring the rationality of energy scheduling, and improving the utilization rate of multiple energy sources.

[0142] Example 3

[0143] Fig.10 FIG. 1 shows a multi-energy scheduling device 1000 based on new energy consumption according to this embodiment, and the device 1000 corresponds to the method according to Embodiment 1. Fig.10As shown, the device 1000 includes: a processor 1010; and a memory 1020, connected to the processor 1010, for providing the processor 1010 with instructions for processing the following processing steps: determining a scheduling period, and dividing the scheduling period into a plurality of scheduling periods; predicting a first power supply power probability distribution corresponding to the target scheduling period based on first meteorological data corresponding to the target scheduling period and based on a first neural network model, wherein the first power supply power probability distribution corresponds to the photovoltaic device, and the target scheduling period is any one or more scheduling periods among the plurality of scheduling periods; predicting a first power supply power probability distribution corresponding to the target scheduling period based on second meteorological data corresponding to the target scheduling period and based on a second neural network model; Measure a second power supply probability distribution corresponding to the target scheduling period, wherein the second power supply probability distribution corresponds to the wind turbine equipment; determine a third power supply probability distribution based on the first power supply probability distribution and the second power supply probability distribution, wherein the third power supply probability distribution corresponds to the new energy equipment, and the new energy equipment includes photovoltaic equipment and wind turbine equipment; predict the power consumption probability distribution corresponding to the target scheduling period based on the power consumption data corresponding to the target scheduling period and based on the RNN model; and predict the power supply of the thermal power equipment based on the third power supply probability distribution and the power consumption probability distribution, and schedule the power supply of the thermal power equipment based on the prediction result.

[0144] Optionally, based on the third power supply probability distribution and the power consumption probability distribution, the power supply of the thermal power equipment is predicted, and the power supply of the thermal power equipment is scheduled based on the prediction result, including: determining the minimum power supply of the new energy equipment based on the third power supply probability distribution; determining the maximum power consumption based on the power consumption probability distribution; and predicting the power supply of the thermal power equipment based on the minimum power supply and the maximum power consumption of the new energy equipment, and scheduling the power supply of the thermal power equipment based on the prediction result.

[0145] Optionally, based on the minimum power supply power of the new energy equipment and the maximum power consumption of the user, the power supply power of the thermal power equipment is predicted, and the power supply power of the thermal power equipment is scheduled based on the prediction result, including: when the minimum power supply power of the new energy equipment is greater than or equal to the maximum power consumption, the thermal power equipment is not used for power supply.

[0146] Optionally, based on the minimum power supply power and the maximum power consumption of the new energy equipment, the power supply power of the thermal power equipment is predicted, and the power supply power of the thermal power equipment is scheduled based on the prediction result, including: when the minimum power supply power of the new energy equipment is less than the maximum power consumption, determining the time period type corresponding to the target scheduling time period, wherein the time period types include peak power purchase, peak power purchase, flat power purchase and valley power purchase; and based on the time period type corresponding to the target scheduling time period, predicting the power supply power of the thermal power equipment, and scheduling the power supply power of the thermal power equipment based on the prediction result.

[0147] Optionally, based on the time period type corresponding to the target scheduling period, the power supply of the thermal power equipment is predicted, and the power supply of the thermal power equipment is scheduled based on the prediction result, including: when the time period type corresponding to the target scheduling period is peak power purchase, peak power purchase or flat power purchase, only new energy equipment and thermal power equipment are used for power supply, and the minimum value of the total power supply is greater than or equal to the maximum power consumption, wherein the total power supply includes the power supply of the new energy equipment and the power supply of the thermal power equipment; and when the time period type corresponding to the target scheduling period is valley power purchase, the power supply of the thermal power equipment is predicted, and the power supply of the thermal power equipment is scheduled based on the prediction result.

[0148] Optionally, when the time period type corresponding to the target scheduling period is off-peak electricity purchase, the power supply of the thermal power equipment is predicted, and the power supply of the thermal power equipment is scheduled based on the prediction result, including: determining whether the maximum value of the total power supply is greater than or equal to the maximum power consumption; if not, increasing the power supply of the thermal power equipment according to a predetermined step size until the maximum value of the total power supply is greater than or equal to the maximum power consumption.

[0149] Optionally, when the maximum value of the total power supply is greater than or equal to the maximum value of the power consumption, the power supply of the thermal power equipment is predicted, and the power supply of the thermal power equipment is scheduled based on the prediction result, including: determining the minimum power consumption based on the power consumption probability distribution; and determining whether the minimum value of the total power supply is greater than or equal to the minimum power consumption; if not, increasing the power supply of the thermal power equipment according to a predetermined step size until the minimum value of the total power supply is greater than or equal to the minimum power consumption.

[0150] Optionally, when the maximum value of the total power supply is greater than or equal to the maximum value of the power consumption, and the minimum value of the total power supply is greater than or equal to the minimum value of the power consumption, the power supply of the thermal power equipment is predicted, and the power supply of the thermal power equipment is scheduled based on the prediction result, including: determining a first probability that the power consumption is within the overlapping interval of a fourth power supply probability distribution and the power consumption probability distribution, wherein the fourth power supply probability distribution corresponds to the total power supply; determining a second probability that the total power supply is within the overlapping interval of the fourth power supply probability distribution and the power consumption probability distribution; determining a third probability based on the first probability and the second probability; determining a preset probability threshold based on the time period type corresponding to the target scheduling time period; and determining whether the third probability is greater than the preset probability threshold, and if not, increasing the power supply of the thermal power equipment according to a predetermined step size until the third probability is less than or equal to the preset probability threshold.

[0151] Therefore, according to this embodiment, it is possible to achieve the technical effect of realizing coordinated scheduling of multiple energy sources based on the above operations during the actual scheduling process, ensuring the rationality of energy scheduling, and improving the utilization rate of multiple energy sources.

[0152] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0153] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0154] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0155] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0156] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0157] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0158] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for dispatching multiple energies based on new energy consumption, characterized in that: include: Determine a scheduling period, and divide the scheduling period into a plurality of scheduling periods; According to the first meteorological data corresponding to the target scheduling period and based on the first neural network model, predicting the first power supply probability distribution corresponding to the target scheduling period, wherein the first power supply probability distribution corresponds to the photovoltaic device, and the target scheduling period is any one or more scheduling periods among the multiple scheduling periods; According to the second meteorological data corresponding to the target scheduling period and based on the second neural network model, predicting the second power supply probability distribution corresponding to the target scheduling period, wherein the second power supply probability distribution corresponds to the wind turbine device; Determine a third power supply probability distribution based on the first power supply probability distribution and the second power supply probability distribution, wherein the third power supply probability distribution corresponds to new energy equipment, and the new energy equipment includes the photovoltaic equipment and the wind turbine equipment; According to the power consumption data corresponding to the target scheduling period and based on the RNN model, predicting the power consumption probability distribution corresponding to the target scheduling period; as well as Based on the third power supply probability distribution and the power consumption probability distribution, the power supply of the thermal power equipment is predicted, and the power supply of the thermal power equipment is scheduled based on the prediction result.

2. The method according to claim 1, characterized in that: The operation of predicting the power supply of the thermal power equipment based on the third power supply probability distribution and the power consumption probability distribution, and scheduling the power supply of the thermal power equipment based on the prediction result includes: Based on the third power supply power probability distribution, determining a minimum power supply power value of the new energy equipment; Determining a maximum power consumption value based on the power consumption probability distribution; and Based on the minimum power supply power of the new energy equipment and the maximum power consumption, the power supply power of the thermal power equipment is predicted, and the power supply power of the thermal power equipment is scheduled based on the prediction result.

3. The method according to claim 2, characterized in that The operation of predicting the power supply of the thermal power equipment based on the minimum power supply of the new energy equipment and the maximum power consumption of the user, and scheduling the power supply of the thermal power equipment based on the prediction result includes: When the minimum power supply power of the new energy equipment is greater than or equal to the maximum power consumption power, the thermal power equipment is not used for power supply.

4. The method according to claim 2, characterized in that: The operation of predicting the power supply of the thermal power equipment based on the minimum power supply of the new energy equipment and the maximum power consumption, and scheduling the power supply of the thermal power equipment based on the prediction result includes: In the case where the minimum power supply power of the new energy equipment is less than the maximum power consumption power, determining a time period type corresponding to the target scheduling time period, wherein the time period type includes peak power purchase, peak power purchase, flat power purchase and valley power purchase; and Based on the time period type corresponding to the target scheduling time period, the power supply of the thermal power equipment is predicted, and the power supply of the thermal power equipment is scheduled based on the prediction result.

5. The method according to claim 4, characterized in that The operation of predicting the power supply of the thermal power equipment based on the time period type corresponding to the target scheduling time period, and scheduling the power supply of the thermal power equipment based on the prediction result includes: In the case where the time period type corresponding to the target scheduling time period is the peak power purchase, the sharp peak power purchase or the flat period power purchase, only the new energy equipment and the thermal power equipment are used to supply power, and the minimum value of the total power supply power is greater than or equal to the maximum power consumption power, wherein the total power supply power includes the power supply power of the new energy equipment and the power supply power of the thermal power equipment; and When the time period type corresponding to the target scheduling time period is the off-peak power purchase, the power supply of the thermal power equipment is predicted, and the power supply of the thermal power equipment is scheduled based on the prediction result, wherein In a case where the time period type corresponding to the target scheduling time period is the off-peak power purchase, the operation of predicting the power supply of the thermal power equipment and scheduling the power supply of the thermal power equipment based on the prediction result includes: Determine whether the maximum value of the total power supply is greater than or equal to the maximum power consumption; if not, increase the power supply power of the thermal power equipment according to a predetermined step size until the maximum value of the total power supply is greater than or equal to the maximum power consumption.

6. The method according to claim 5, characterized in that When the maximum value of the total power supply is greater than or equal to the maximum power consumption, the power supply of the thermal power equipment is predicted, and the power supply of the thermal power equipment is scheduled based on the prediction result, including: Determining a minimum value of electric power based on the electric power probability distribution; and Determine whether the minimum value of the total power supply is greater than or equal to the minimum power consumption. If not, increase the power supply power of the thermal power equipment according to a predetermined step size until the minimum value of the total power supply is greater than or equal to the minimum power consumption.

7. The method according to claim 6, characterized in that When the maximum value of the total power supply is greater than or equal to the maximum power consumption, and the minimum value of the total power supply is greater than or equal to the minimum power consumption, the power supply of the thermal power equipment is predicted, and the power supply of the thermal power equipment is scheduled based on the prediction result, including: Determine a first probability that the power consumption is within an overlapping interval of a fourth power supply power probability distribution and the power consumption power probability distribution, wherein the fourth power supply power probability distribution corresponds to the total power supply power; Determine a second probability that the total power supplied is within an overlapping interval of the fourth power supply probability distribution and the power consumption probability distribution; Determining a third probability based on the first probability and the second probability; Determining a preset probability threshold based on a time period type corresponding to the target scheduling time period; and It is determined whether the third probability is greater than the preset probability threshold; if not, the power supply power of the thermal power equipment is increased according to a predetermined step length until the third probability is less than or equal to the preset probability threshold.

8. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is run, the processor executes the method according to any one of claims 1 to 7.

9. A multi-energy dispatching device based on new energy consumption, characterized in that: include: A scheduling period determination module, used to determine a scheduling period and divide the scheduling period into a plurality of scheduling periods; A first power supply probability distribution prediction module, configured to predict a first power supply probability distribution corresponding to a target scheduling period according to first meteorological data corresponding to the target scheduling period and based on a first neural network model, wherein the first power supply probability distribution corresponds to the photovoltaic device, and the target scheduling period is any one or more scheduling periods among the multiple scheduling periods; a second power supply probability distribution prediction module, configured to predict a second power supply probability distribution corresponding to the target scheduling period according to second meteorological data corresponding to the target scheduling period and based on a second neural network model, wherein the second power supply probability distribution corresponds to the wind turbine device; a third power supply probability distribution prediction module, configured to determine a third power supply probability distribution based on the first power supply probability distribution and the second power supply probability distribution, wherein the third power supply probability distribution corresponds to new energy equipment, and the new energy equipment includes the photovoltaic equipment and the wind turbine equipment; An electric power probability distribution prediction module is used to predict the electric power probability distribution corresponding to the target scheduling period based on the electric power consumption data corresponding to the target scheduling period and based on the RNN model; as well as A scheduling module is used to predict the power supply of the thermal power equipment based on the third power supply probability distribution and the power consumption probability distribution, and schedule the power supply of the thermal power equipment based on the prediction result.

10. A multi-energy dispatching device based on new energy consumption, characterized in that: include: processor; as well as A memory, connected to the processor, configured to provide the processor with instructions for processing the following processing steps: Determine a scheduling period, and divide the scheduling period into a plurality of scheduling periods; According to the first meteorological data corresponding to the target scheduling period and based on the first neural network model, predicting the first power supply probability distribution corresponding to the target scheduling period, wherein the first power supply probability distribution corresponds to the photovoltaic device, and the target scheduling period is any one or more scheduling periods among the multiple scheduling periods; According to the second meteorological data corresponding to the target scheduling period and based on the second neural network model, predicting the second power supply probability distribution corresponding to the target scheduling period, wherein the second power supply probability distribution corresponds to the wind turbine device; Determine a third power supply probability distribution based on the first power supply probability distribution and the second power supply probability distribution, wherein the third power supply probability distribution corresponds to new energy equipment, and the new energy equipment includes the photovoltaic equipment and the wind turbine equipment; According to the power consumption data corresponding to the target scheduling period and based on the RNN model, predicting the power consumption probability distribution corresponding to the target scheduling period; as well as Based on the third power supply probability distribution and the power consumption probability distribution, the power supply of the thermal power equipment is predicted, and the power supply of the thermal power equipment is scheduled based on the prediction result.

Images