Bus load prediction method and device, electronic equipment and storage medium

Abstract

The present disclosure provides a bus load prediction method and device, electronic equipment and storage medium, which relates to the technical field of industrial big data. The method comprises: obtaining the bus load of the historical similar day of the day to be predicted and the corresponding correction coefficient; determining the similar day load prediction value based on the bus load of the historical similar day and the corresponding correction coefficient; obtaining the periodic load prediction value of the day to be predicted, and the periodic load prediction value is used to represent the periodic change characteristic of the bus load; and determining the bus load prediction value of the day to be predicted based on the similar day load prediction value and the periodic load prediction value. In the technical scheme of the present disclosure, the load similarity between the historical similar day and the day to be predicted is considered, and the periodic change of the load is predicted according to the historical load level. Since the change law of the similar day and the historical load is considered at the same time, the prediction result accuracy can be improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of industrial big data, and particularly relates to a busbar load prediction method and device, electronic equipment and a storage medium. BACKGROUND

[0002] Short-term load prediction of a power system is an important work of the power department, and the accuracy of short-term load prediction has an important influence on the normal operation, safety and economy of the power grid. In the aspect of short-term load prediction, the load characteristics of holidays are obviously different from those of normal days, and the load data of holidays are usually less than those of normal days. Therefore, a general model cannot meet the actual production needs of the power system due to the poor accuracy in prediction and the lack of sufficient and effective sample sets. SUMMARY

[0003] The present disclosure provides a busbar load prediction method and device, electronic equipment and a storage medium.

[0004] According to an aspect of the present disclosure, a busbar load prediction method is provided, comprising:

[0005] obtaining busbar loads of historical similar days of a to-be-predicted day and corresponding correction coefficients;

[0006] determining similar day load prediction values based on the busbar loads of the historical similar days and the corresponding correction coefficients;

[0007] obtaining a periodic load prediction value of the to-be-predicted day, the periodic load prediction value being used to represent a periodic variation characteristic of the busbar load;

[0008] determining a busbar load prediction value of the to-be-predicted day based on the similar day load prediction values and the periodic load prediction value.

[0009] According to another aspect of the present disclosure, a busbar load prediction device is provided, comprising:

[0010] a first obtaining module configured to obtain busbar loads of historical similar days of a to-be-predicted day and corresponding correction coefficients;

[0011] a first determining module configured to determine similar day load prediction values based on the busbar loads of the historical similar days and the corresponding correction coefficients;

[0012] a second obtaining module configured to obtain a periodic load prediction value of the to-be-predicted day, the periodic load prediction value being used to represent a periodic variation characteristic of the busbar load;

[0013] a second determining module configured to determine a busbar load prediction value of the to-be-predicted day based on the similar day load prediction values and the periodic load prediction value.

[0014] According to another aspect of the present disclosure, an electronic device is provided, comprising:

[0015] at least one processor; and

[0016] a memory connected with the at least one processor in communication; wherein

[0017] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method in any embodiment of the present disclosure.

[0018] According to another aspect of the present disclosure, a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method in any embodiment of the present disclosure is provided.

[0019] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method in any embodiment of the present disclosure.

[0020] The embodiments of the present disclosure can improve the accuracy of load prediction results.

[0021] It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0022] The accompanying drawings are used to better understand the present scheme, and do not limit the present disclosure. Among them:

[0023] Figure 1 a flowchart of a bus load prediction method in an embodiment of the present disclosure;

[0024] Figure 2 a flowchart of a bus load prediction method in an embodiment of the present disclosure;

[0025] Figure 3 a schematic diagram of a bus load prediction device in an embodiment of the present disclosure;

[0026] Figure 4 a schematic diagram of a first acquisition module in an embodiment of the present disclosure;

[0027] Figure 5 a block diagram of an electronic device for implementing a bus load prediction method in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] Exemplary embodiments of the present disclosure are described herein with reference to the accompanying drawings, which are meant to be exemplary in nature, and include various details intended to facilitate understanding of the present disclosure. Thus, it should be apparent to those skilled in the art that various modifications and changes can be made in the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, it should be apparent to those skilled in the art that the descriptions set forth in this specification are meant to be illustrative only and should not be taken as restrictive.

[0029] The bus load prediction method provided by the embodiments of the present disclosure, Figure 1 is a flowchart of the bus load prediction method of an embodiment of the present disclosure. The method can be applied to a bus load prediction device. For example, the device can perform bus load prediction when deployed in a terminal device, a server or other processing device. In some possible implementation manners, the method can also be implemented by a processor invoking computer readable instructions stored in a memory. As shown in Figure 1 includes the following steps:

[0030] In step S101, the bus load of a historical similar day of a to-be-predicted day and a corresponding correction coefficient are obtained.

[0031] The to-be-predicted day can be one day or multiple days. The historical similar day can be one day or multiple days. For example, the to-be-predicted day can be a statutory holiday, such as the Spring Festival holiday, the May Day holiday, the National Day holiday, etc. The historical similar day is a historical day similar to the to-be-predicted day. For example, if the to-be-predicted day is the May Day holiday, the historical similar day can be the Saturday or Sunday before the May Day holiday. The bus load of the historical similar day can be the value of the bus load at each time point in the historical similar day. The bus load of the historical similar day and the correction coefficient corresponding to the bus load of each historical similar day are obtained. The correction coefficient is determined based on the difference between the historical similar day and the to-be-predicted day. The correction coefficient can be stored after being calculated in advance, or can be calculated in real time when the bus load is predicted. The embodiments of the present disclosure do not limit this.

[0032] In step S102, a similar day load prediction value is determined based on the bus load of the historical similar day and the corresponding correction coefficient.

[0033] The bus load of the historical similar day is corrected by using the correction coefficient to obtain the similar day load prediction value. In order to improve the prediction accuracy, in addition to considering the historical similar day, other factors are further considered.

[0034] In step S103, a periodic load prediction value of the to-be-predicted day is obtained. The periodic load prediction value is used to represent the periodic variation characteristics of the bus load.

[0035] The periodic load forecast is used to characterize the periodic variation characteristics of the bus load, which may include the periodic increase or decrease of the bus load. The period may include short periods or long periods, and the specific length of the period can be determined according to specific needs.

[0036] Step S104: Based on the similar daily load forecast values ​​and the periodic load forecast values, determine the bus load forecast value for the day to be forecasted.

[0037] The bus load forecast for the day to be predicted is based on the load forecast values ​​of similar days and the periodic variation characteristics of the bus load on the day to be predicted, which takes into account the periodic variation characteristics of the bus load on similar historical days and the bus load on the day to be predicted, resulting in higher accuracy of the forecast results.

[0038] In related technologies, deep neural network prediction models are used for holiday load forecasting. However, due to the scarcity of historical data on fake holidays and insufficient training, prediction accuracy is difficult to guarantee. In short-term load forecasting, neural networks and support vector machines are used, but the lack of sufficient machine learning sample sets makes them difficult to apply to holiday load forecasting. There are also methods for holiday load forecasting based on similar weekends, considering date and meteorological attributes to select similar days. However, these are significantly affected by meteorological, regional, and human factors, resulting in larger errors in other regions. Another approach uses fuzzy inference to predict the highest and lowest loads on special holidays. It uses holidays, seasons, and daily maximum and minimum temperatures as fuzzy input variables, and the changes in daily maximum and minimum loads as output variables. Fuzzy rules are established based on extensive practical experience to ultimately obtain the predicted load for the special holiday. This method utilizes the advantages of fuzzy logic in handling uncertainties; however, the if-then rule correspondence between non-changing quantities and changing quantities is unreasonable, leading to poor prediction accuracy.

[0039] The bus load forecasting method provided in this disclosure obtains the bus load and corresponding correction coefficients for historical similar days of the day to be forecasted; determines the forecast value of the similar day load based on the historical similar day bus load and corresponding correction coefficients; obtains the periodic load forecast value of the day to be forecasted, which is used to characterize the periodic variation characteristics of the bus load; and determines the forecast value of the bus load for the day to be forecasted based on the similar day load forecast value and the periodic load forecast value. This technical solution considers the load similarity between historical similar days and the day to be forecasted, and predicts the periodic variation of the load based on historical load levels. Because it simultaneously considers the variation patterns of similar days and historical loads, the accuracy of the forecast results can be improved.

[0040] In one possible implementation, the correction coefficients corresponding to historically similar days are obtained, including:

[0041] obtaining a time interval between the historical similar day and the day to be predicted;

[0042] determining a correction coefficient corresponding to the historical similar day based on the time interval;

[0043] The longer the time interval, the smaller the correction coefficient corresponding to the historical similar day.

[0044] In actual application, a similar evaluation analysis method is used to select several similar days from historical days, and the load of the similar days is corrected, and then the load of the day to be predicted is predicted on this basis. The time factor matching coefficient is used as the correction coefficient to quantify the similarity degree of the historical similar day and the day to be predicted in the time factor. The time factor matching coefficient considers the time factor when being configured, and can be the number of days from the historical similar day to the day to be predicted. The farther the historical similar day is from the day to be predicted, the smaller the similarity degree, and then a smaller time factor matching coefficient is configured. The configuration of the time factor matching coefficient embodies the principle of "near large and far small".

[0045] The correction coefficient corresponding to the historical similar day is set according to the time interval between the historical similar day and the day to be predicted. For example, the first Saturday before the May Day holiday is taken as a historical similar day, and the time interval from the first Saturday to the May Day holiday is 7 days. The second Saturday before the May Day holiday is taken as a historical similar day, and the time interval from the second Saturday to the May Day holiday is 14 days. The busbar load at 8 pm on the first Saturday before the May Day holiday is A1, and the corresponding correction coefficient is (0.9) 7 The busbar load at 8 pm on the second Saturday before the May Day holiday is A2, and the corresponding correction coefficient is (0.9) 14 The correction coefficient can be configured according to the configuration mode that the longer the time interval, the smaller the correction coefficient corresponding to the historical similar day. The specific configuration mode is not limited in the present disclosure.

[0046] In the embodiment of the present disclosure, the correction coefficient is determined according to the time interval between the historical similar day and the day to be predicted, which can better reflect the similarity degree of the busbar load of the historical similar day and the busbar load of the day to be predicted, thereby improving the accuracy of the busbar load.

[0047] The busbar load has the characteristics of "periodicity", which not only shows the periodicity of short-term change rules, such as "weekly" periodicity, but also shows the periodicity of long-term change rules, such as "yearly" periodicity. Therefore, it is necessary to distinguish similar weekends and annual holidays according to the type of similar days.

[0048] In one possible implementation, the periodic load prediction value of the day to be predicted is obtained, including:

[0049] If the day to be predicted is a statutory holiday, and the periodic load prediction value is a weekly prediction value, the bus load corresponding to the historical statutory holiday of the day to be predicted is obtained, and the bus load corresponding to the weekend of the historical statutory holiday is obtained;

[0050] The weekly prediction value is determined based on the bus load of the historical statutory holiday and the bus load of the weekend corresponding to the historical statutory holiday.

[0051] In actual application, the weekly prediction value is used to represent the "weekly" periodic variation characteristics of the bus load. The historical statutory holiday corresponding to the prediction day, for example, if the day to be predicted is the National Day holiday, the historical statutory holiday corresponding to the day to be predicted can be the National Day holiday of the previous year, or the National Day holiday of the previous two years. The weekend corresponding to the historical statutory holiday can be the first Saturday or Sunday before the National Day holiday of the previous year, the second Saturday or Sunday before the National Day holiday of the previous year, and so on.

[0052] In the embodiments of the present disclosure, the weekly prediction value is determined based on the bus load of the historical statutory holiday and the bus load of the weekend corresponding to the historical statutory holiday, which can represent the "weekly" periodic variation rule of the bus load.

[0053] In a possible implementation, the weekly prediction value is determined based on the bus load of the historical statutory holiday and the bus load of the weekend corresponding to the historical statutory holiday, comprising:

[0054] The weekly correction coefficient is determined based on the bus load of the historical statutory holiday and the bus load of the weekend corresponding to the historical statutory holiday.

[0055] The weekly prediction value is determined based on the bus load of the weekend corresponding to the historical statutory holiday and the weekly correction coefficient.

[0056] In actual application, the ratio of the historical statutory holiday to the corresponding weekend load is obtained as the weekly correction coefficient, and each weekly correction coefficient is used to correct the bus load of each weekend corresponding to the statutory holiday to be predicted, to obtain the weekly prediction value. For example, if the day to be predicted is the National Day holiday, the bus load of the previous year's National Day holiday and the bus load of each weekend before the National Day holiday are obtained, the weekly correction coefficient corresponding to each weekend is obtained, and the bus load of each weekend before the National Day holiday to be predicted is corrected by using the weekly correction coefficient corresponding to each weekend, to obtain the weekly prediction value.

[0057] In the embodiments of the present disclosure, the weekly prediction value is determined based on the bus load of the weekend corresponding to the historical statutory holiday and the weekly correction coefficient, which can improve the accuracy of the prediction.

[0058] In a possible implementation, the periodic load prediction value of the day to be predicted is obtained, comprising:

[0059] If the forecast date is a statutory holiday and the periodic load forecast value is the annual forecast value, then obtain the bus load for the preset time period before the forecast date in the current year, as well as the bus load for the preset time period before the historical statutory holidays corresponding to the forecast date.

[0060] The annual forecast value is determined based on the bus load of the preset time period before the forecast date and the bus load of the preset time period before the corresponding historical statutory holidays.

[0061] In practical applications, annual forecast values ​​are used to characterize the annual cyclical variation of bus load. A preset time period preceding the forecast date is used; for example, if the forecast date falls on the National Day holiday (October 1st), the preset time period could be the three months preceding that year's National Day holiday. Similarly, the preset time period preceding a historical statutory holiday corresponding to the forecast date could be the three months preceding the National Day holiday of the previous year.

[0062] In this embodiment of the disclosure, the annual forecast value is determined based on the bus load of a preset time period before the date to be predicted and the bus load of a preset time period before the historical statutory holidays corresponding to the date to be predicted, which can characterize the "annual" periodic change pattern of the bus load.

[0063] In one possible implementation, the annual forecast value is determined based on the bus load for a preset period prior to the forecast date and the bus load for a preset period prior to the corresponding historical statutory holidays, including:

[0064] The annual correction factor is determined based on the bus load of the preset time period before the predicted date and the bus load of the preset time period before the corresponding historical statutory holiday.

[0065] The annual forecast value is determined based on the bus load of the preset period before the historical statutory holiday corresponding to the forecast date and the annual correction factor.

[0066] In practical applications, the bus load and annual correction factor for a preset period of time preceding the historical statutory holidays corresponding to the forecast date are obtained. The annual correction factor is then used to adjust the bus load for the historical statutory holidays corresponding to the forecast date to obtain the annual forecast value. For example, if the forecast date is the National Day holiday, the annual correction factor is the ratio of the average bus load of the three months preceding the National Day holiday to the average bus load of the three months preceding the National Day holiday of the previous year. The annual forecast value is the bus load of the previous year's National Day holiday multiplied by the annual correction factor.

[0067] In this embodiment of the disclosure, the annual forecast value is determined based on the bus load and annual correction factor for a preset period of time before the historical statutory holiday corresponding to the date to be predicted, which can improve the accuracy of the forecast.

[0068] Optionally, the periodic load prediction value can be determined according to the weekly prediction value and the annual prediction value, for example, weights corresponding to the weekly prediction value and the annual prediction value are respectively set, and the periodic load prediction value is obtained through weighted calculation.

[0069] In a possible implementation, the bus load prediction value of the to-be-predicted day is determined based on the similar-day load prediction value and the periodic load prediction value, and the method comprises the following steps of:

[0070] The weights corresponding to the similar-day load prediction value and the periodic load prediction value are respectively determined.

[0071] The bus load prediction value of the to-be-predicted day is determined based on the similar-day load prediction value, the periodic load prediction value, and the weights corresponding thereto.

[0072] In the embodiments of the present disclosure, the bus load prediction value of the to-be-predicted day is determined based on the similar-day load prediction value, the periodic load prediction value, and the weights corresponding thereto, which takes into account the load similarity between the historical similar days and the to-be-predicted day, and predicts the periodic change of the load according to the historical load level, and takes into account the change rule of the similar days and the historical load, so that the prediction result has high accuracy.

[0073] Figure 2 A flowchart of a bus load prediction method in an embodiment of the present disclosure is shown in FIG. 2. Figure 2 As shown in FIG. 2, the method comprises the following steps of:

[0074] In step S201, the bus load of the historical similar day of the to-be-predicted day is obtained.

[0075] In step S202, the time interval between the historical similar day and the to-be-predicted day is obtained, and a correction coefficient corresponding to the historical similar day is determined based on the time interval.

[0076] In step S203, the similar-day load prediction value is determined based on the bus load of the historical similar day and the correction coefficient corresponding thereto.

[0077] In step S204, the periodic load prediction value of the to-be-predicted day is obtained.

[0078] In step S205, the weights corresponding to the similar-day load prediction value and the periodic load prediction value are respectively determined.

[0079] In step S206, the bus load prediction value of the to-be-predicted day is determined based on the similar-day load prediction value, the periodic load prediction value, and the weights corresponding thereto.

[0080] The bus load forecasting method provided in this disclosure obtains the bus load and corresponding correction coefficients for historical similar days of the day to be forecasted; determines the forecast value of the similar day load based on the historical similar day bus load and corresponding correction coefficients; obtains the periodic load forecast value of the day to be forecasted, which is used to characterize the periodic variation characteristics of the bus load; and determines the forecast value of the bus load for the day to be forecasted based on the similar day load forecast value and the periodic load forecast value. This technical solution considers the load similarity between historical similar days and the day to be forecasted, and predicts the periodic variation of the load based on historical load levels. Because it simultaneously considers the variation patterns of similar days and historical loads, the accuracy of the forecast results can be improved.

[0081] Figure 3 This is a schematic diagram of a bus load prediction device according to an embodiment of this disclosure. Figure 3 As shown, the bus load forecasting device may include:

[0082] The first acquisition module 301 is used to acquire the bus load and corresponding correction coefficient of historical similar days of the day to be predicted;

[0083] The first determining module 302 is used to determine the predicted load value for similar days based on the bus load of historical similar days and the corresponding correction coefficient;

[0084] The second acquisition module 303 is used to acquire the periodic load forecast value for the day to be predicted. The periodic load forecast value is used to characterize the periodic variation characteristics of the bus load.

[0085] The second determining module 304 is used to determine the bus load forecast value for the day to be predicted based on the similar daily load forecast value and the periodic load forecast value.

[0086] The bus load forecasting device provided in this disclosure acquires the bus load and corresponding correction coefficients of historical similar days for the day to be forecasted; determines the predicted load value for similar days based on the historical similar day bus load and corresponding correction coefficients; acquires the predicted periodic load value for the day to be forecasted, which characterizes the periodic variation characteristics of the bus load; and determines the predicted bus load value for the day to be forecasted based on the predicted load value for similar days and the predicted periodic load value. This technical solution considers the load similarity between historical similar days and the day to be forecasted, and predicts the periodic variation of the load based on historical load levels. Because it simultaneously considers the variation patterns of similar days and historical loads, the accuracy of the forecast results can be improved.

[0087] Figure 4 This is a schematic diagram of the first acquisition module in one embodiment of this disclosure. Figure 4 As shown, in one possible implementation, the first acquisition module includes a first acquisition unit 401 and a first determination unit 402;

[0088] The first obtaining unit 401 is configured to obtain a time interval between a historical similar day and the day to be predicted.

[0089] The first determining unit 402 is configured to determine a correction coefficient corresponding to the historical similar day based on the time interval.

[0090] The longer the time interval, the smaller the correction coefficient corresponding to the historical similar day.

[0091] In a possible implementation, the second obtaining module 303 includes a second obtaining unit and a second determining unit.

[0092] The second obtaining unit is configured to, if the day to be predicted is a statutory holiday and the periodic load prediction value is a weekly prediction value, obtain busbar load of a historical statutory holiday corresponding to the day to be predicted, and busbar load of a weekend corresponding to the historical statutory holiday.

[0093] The second determining unit is configured to determine the weekly prediction value based on the busbar load of the historical statutory holiday and the busbar load of the weekend corresponding to the historical statutory holiday.

[0094] In a possible implementation, the second determining unit is configured to:

[0095] determine a weekly correction coefficient based on the busbar load of the historical statutory holiday and the busbar load of the weekend corresponding to the historical statutory holiday;

[0096] determine the weekly prediction value based on the busbar load of the weekend corresponding to the historical statutory holiday and the weekly correction coefficient.

[0097] In a possible implementation, the second obtaining module 303 includes a third obtaining unit and a third determining unit.

[0098] The third obtaining unit is configured to, if the day to be predicted is a statutory holiday and the periodic load prediction value is an annual prediction value, obtain busbar load of a preset time period before the day to be predicted, and busbar load of a historical statutory holiday corresponding to the day to be predicted.

[0099] The third determining unit is configured to determine the annual prediction value based on the busbar load of the preset time period before the day to be predicted and the busbar load of the historical statutory holiday corresponding to the day to be predicted.

[0100] In a possible implementation, the third determining unit is configured to:

[0101] determine an annual correction coefficient based on the busbar load of the preset time period before the day to be predicted and the busbar load of the historical statutory holiday corresponding to the day to be predicted.

[0102] The annual prediction value is determined based on the bus load of a preset time period before a historical statutory holiday corresponding to the day to be predicted and an annual correction coefficient.

[0103] In a possible implementation, the second determination module 304 is configured to:

[0104] The weight corresponding to each of the similar day load prediction value and the periodic load prediction value is determined respectively.

[0105] The bus load prediction value of the day to be predicted is determined based on the similar day load prediction value, the periodic load prediction value, and the weight corresponding to each of the similar day load prediction value and the periodic load prediction value.

[0106] In the technical solution of the present disclosure, the acquisition, storage and application of user personal information comply with relevant laws and regulations and do not violate public order and good customs.

[0107] According to another aspect of the present disclosure, an electronic device is provided, comprising:

[0108] at least one processor; and

[0109] a memory connected with the at least one processor in communication; wherein,

[0110] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method in any embodiment of the present disclosure.

[0111] According to another aspect of the present disclosure, a non-transitory computer readable storage medium storing computer instructions is provided, the computer instructions being used to make a computer execute the method in any embodiment of the present disclosure.

[0112] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method in any embodiment of the present disclosure.

[0113] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present disclosure described and / or claimed in this document.

[0114] As Figure 5As shown, the device 500 includes a computing unit 501 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. Various programs and information required for the operation of the device 500 can also be stored in the RAM 503. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0115] Various components in the device 500 are connected to the I / O interface 505, including an input unit 506, such as a keyboard, a mouse, etc., an output unit 507, such as various types of displays, speakers, etc., a storage unit 508, such as a magnetic disk, an optical disk, etc., and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information / information with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0116] The computing unit 501 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 501 performs various methods and processes described above, such as the busbar load prediction method. For example, in some embodiments, the busbar load prediction method can be implemented as a computer software program that is tangibly embodied in a machine-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the busbar load prediction method described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to perform the busbar load prediction method by any other appropriate means, such as by means of firmware.

[0117] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0118] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable information processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or the block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, or entirely on a remote machine or server.

[0119] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0120] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0121] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital information communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0122] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server is generally established by computer programs running on the respective computers and having a client-server relationship to each other. The servers can be cloud servers, servers of a distributed system, or servers combined with a blockchain.

[0123] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the spirit and scope of the present disclosure. For example, the steps recited in the present disclosure can be performed in parallel, in series, or in a different order, as long as the desired results of the present disclosure are achieved, and are not limited herein.

[0124] The specific embodiments described above are not intended to be limiting, and persons skilled in the art will appreciate that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments without departing from the spirit and scope of the disclosure. Any modifications, equivalent substitutions, improvements, and the like, made within the spirit and principles of the disclosure, are intended to be included in the scope of the disclosure.

Claims

1. A bus load prediction method, comprising: obtaining bus loads of historical similar days of a to-be-predicted day; obtaining a time interval between the historical similar day and the day to be predicted, and determining a correction coefficient corresponding to the historical similar day according to a preset calculation rule based on the time interval; wherein the preset calculation rule is that the correction coefficient is negatively correlated with the time interval, and the correction coefficient λ is determined according to a formula λ = e (―β·Δt) , wherein β is a preset attenuation factor, and Δt is the time interval. determining a similar day load prediction value based on the bus loads of the historical similar days and corresponding correction coefficients; obtaining a periodic load prediction value of the to-be-predicted day, the periodic load prediction value being used to represent a periodic variation characteristic of the bus load; wherein the obtaining of the periodic load prediction value of the to-be-predicted day comprises: if the to-be-predicted day is a statutory holiday, then: obtaining daily average busbar load P of the corresponding statutory holidays of the years before the to-be-predicted day holiday_avg , and daily average busbar load P of the corresponding weekends of the years before the to-be-predicted day weekend_avg ; Compute weekly correction factor γ = P holiday_avg / P weekend_avg ; obtaining daily average busbar load P of a corresponding weekend one day before the day to be predicted current_weekend ; The periodic load prediction value is calculated as P period_weekly = P current_weekend * γ; determining a bus load prediction value of the to-be-predicted day based on the similar day load prediction value and the periodic load prediction value; wherein the determining of the bus load prediction value of the to-be-predicted day based on the similar day load prediction value and the periodic load prediction value comprises: determining weights a and (1-a) corresponding to the similar day load prediction value and the periodic load prediction value respectively, wherein the weight a is dynamically adjusted according to a historical prediction error rate; and calculating the bus load prediction value of the to-be-predicted day as: load prediction value = a * similar day load prediction value + (1-a) * periodic load prediction value. The obtaining of the periodic load prediction value of the to-be-predicted day further comprises:

2. The method of claim 1, wherein, if the to-be-predicted day is a statutory holiday and the periodic load prediction value is an annual prediction value, then: obtaining a daily average bus load P_hist_holiday of a historical statutory holiday corresponding to the to-be-predicted day. obtaining daily average busbar load P of a preset time period before the day to be predicted current_year_avg and daily average busbar load P of a preset time period before a historical statutory holiday corresponding to the day to be predicted hist_year_avg ; Calculate annual correction factor η = P current_year_avg / P hist_year_avg ; 3.A bus load prediction device, comprising: The periodic load prediction value is calculated as P yearly = η * P hist_holiday . a first obtaining module configured to obtain bus loads of historical similar days of a to-be-predicted day; a first determining module configured to determine a similar day load prediction value based on the bus loads of the historical similar days and corresponding correction coefficients; obtaining a time interval between the historical similar day and the day to be predicted, and determining a correction coefficient corresponding to the historical similar day according to a preset calculation rule based on the time interval; wherein the preset calculation rule is that the correction coefficient is negatively correlated with the time interval, and the correction coefficient λ is determined according to a formula λ = e (―β·Δt) wherein β is a preset attenuation factor, and Δt is the time interval; a second obtaining module configured to obtain a periodic load prediction value of the to-be-predicted day, the periodic load prediction value being used to represent a periodic variation characteristic of the bus load; wherein the second obtaining module obtains the periodic load prediction value of the to-be-predicted day by: if the to-be-predicted day is a statutory holiday, then: a second determining module configured to determine a bus load prediction value of the to-be-predicted day based on the similar day load prediction value and the periodic load prediction value; wherein the second determining module is specifically configured to: determine weights a and (1-a) corresponding to the similar day load prediction value and the periodic load prediction value respectively, wherein the weight a is dynamically adjusted according to a historical prediction error rate; and calculate the bus load prediction value of the to-be-predicted day as: load prediction value = a * similar day load prediction value + (1-a) * periodic load prediction value. obtaining daily average busbar load P of the statutory holiday corresponding to the to-be-predicted day holiday_avg , and daily average busbar load P of the weekend corresponding to the statutory holiday weekend_avg ; Compute weekly correction factor β = P holiday_avg / P weekend_avg ; obtaining daily average busbar load P of a corresponding weekend one day before the day to be predicted current_weekend ; The periodic load prediction value is calculated as P period_weekly = P current_weekend * γ; wherein, 4. The apparatus of claim 3, wherein, the second obtaining module obtains the periodic load prediction value of the to-be-predicted day by: if the to-be-predicted day is a statutory holiday and the periodic load prediction value is an annual prediction value, then: obtaining a daily average bus load P_hist_holiday of a historical statutory holiday corresponding to the to-be-predicted day. obtaining daily average busbar load P of a preset time period before the day to be predicted current_year_avg and daily average busbar load P of a preset time period before a historical statutory holiday corresponding to the day to be predicted hist_year_avg ; Calculate annual correction factor η = P current_year_avg / P hist_year_avg ; 5.An electronic device, comprising: The periodic load prediction value is calculated as P yearly = η * P hist_holiday . at least one processor; and a memory connected to the at least one processor in communication; wherein, ​ The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-2.

6. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1-2.

7. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-2.

Images