Data volume prediction method of time series data, electronic equipment, storage medium and computer program product

Abstract

The invention discloses a data volume prediction method of time series data, electronic equipment, a storage medium and a computer program product. The method comprises the steps of determining an output demand side of one or more time sequence data processing units included in a to-be-predicted module according to a time sequence flow direction; determining a data demand of an output demand side of each time sequence data processing unit; obtaining the data size of a data item input into each time sequence data processing unit; and according to the data size of the data item input into the time sequence data processing unit and the data demand of the output demand side of the time sequence data processing unit, predicting the necessary storage data size of each to-be-predicted module. According to the method, necessary storage is identified based on the system model and the data model, and a basis for estimating the data storage scale is constructed, so that the necessary storage data volume is accurately estimated in the system planning and design stage according to the system model and the data model.

Description

Technical Field

[0001] The present invention relates to the technical field related to data storage, and in particular to a method for predicting the data volume of time series data, an electronic device, a storage medium and a computer program product. Background Art

[0002] Cloud-controlled connected autonomous driving is a technology that connects vehicles to the Internet to enable communication and collaboration between vehicles and between vehicles and infrastructure. By using devices such as sensors, cameras, radars and lasers, connected autonomous driving can collect and analyze data around the vehicle to achieve autonomous driving functions. This technology can improve road safety, traffic efficiency and driving comfort, and lay the foundation for future intelligent transportation systems.

[0003] In the context of cloud-controlled connected autonomous driving, the system stores and generates a large amount of time series data. According to statistics from a certain project, the daily data volume of a single project can reach hundreds of TB, of which time series data accounts for more than 90% of the total data volume. However, the value of this big data decays quickly over time, and it is necessary to accurately estimate the amount of data required to store it.

[0004] However, the existing methods for estimating the amount of stored data are generally tested after use, and the estimation is based on the a posteriori test results, but the storage scale cannot be determined in the forward planning and design stage. At the same time, the processing of time series data is generally continuous frame / window, so the data requirements of each link are affected by the finer-grained frame situation, and the data volume estimation of the existing technology is usually a general consideration of the coarse-grained dependency between data. Therefore, the existing technology does not take into account the specifications and characteristics of time series data, but simply classifies it as data in general, which cannot adapt to the characteristics of time series data. Summary of the invention

[0005] Based on this, it is necessary to provide a method for predicting the data volume of time series data, an electronic device, a storage medium and a computer program product to address the technical problem that the existing technology is unable to determine the storage scale of time series data in the planning and design stage.

[0006] The present invention provides a method for predicting the amount of time series data, comprising:

[0007] Determine the output demand side of one or more time series data processing units included in the module to be predicted according to the time series flow direction;

[0008] Determine the data demand of the output demander of each of the time series data processing units;

[0009] Acquire the data size of the data item input into each of the time series data processing units;

[0010] The necessary storage data size of each module to be predicted is predicted according to the data size of the data item input to the time series data processing unit and the data demand of the output demander of the time series data processing unit.

[0011] Furthermore, the determining of the data demand of the output demander of each of the time series data processing units includes:

[0012] Determine the data granularity requirement and data length requirement of the output demand side of each of the time series data processing units.

[0013] Furthermore, the determining of the data granularity requirement and the data length requirement of the output demand side of each of the time series data processing units includes:

[0014] Determine the maximum value of the data granularity requirements of all output demand parties of each of the time series data processing units as the data granularity requirement of the output demand party of the time series data processing unit;

[0015] A maximum value among the data length requirements of all output demanders of each of the time series data processing units is determined as the data length requirement of the output demander of the time series data processing unit.

[0016] Furthermore, the step of predicting the necessary storage data size of each module to be predicted according to the data size of the data item input to the time series data processing unit and the data demand of the output demander of the time series data processing unit includes:

[0017] According to business requirements, selecting a storage time series data processing unit for storage from the time series data processing units included in each of the modules to be predicted;

[0018] Calculating the necessary storage data size of each of the storage time series data processing units;

[0019] The necessary storage data size of each module to be predicted is predicted according to the necessary storage data size of the storage time series data processing unit included in each module to be predicted.

[0020] Furthermore, the calculating of the necessary storage data size of each storage time series data processing unit includes:

[0021] The necessary storage data size of each storage timing data processing unit is calculated as: the sum of the data sizes of the data items input to the storage timing data processing unit, the product of the data granularity requirement and the data length requirement of the output demand side of the storage timing data processing unit.

[0022] Furthermore, the calculating of the necessary storage data size of each storage time series data processing unit includes:

[0023] For each of the storage time series data processing units, the necessary storage data size of the storage time series data processing unit is calculated as: where s i is the single frame data size of the i-th data item in the storage timing data processing unit, N is the number of data items input into the storage timing data processing unit, maxf is the maximum data granularity requirement of the output demand side of the storage timing data processing unit, and maxl is the maximum data length requirement of the output demand side of the storage timing data processing unit.

[0024] Furthermore, before determining the output demand side of one or more time series data processing units included in the module to be predicted according to the time series flow direction, the method further includes:

[0025] According to business needs, the module to be predicted is determined from multiple modules.

[0026] The present invention provides an electronic device, comprising:

[0027] at least one processor; and,

[0028] a memory communicatively connected to at least one of the processors; wherein,

[0029] The memory stores instructions that can be executed by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the data volume prediction method for time series data as described above.

[0030] The present invention provides a storage medium, which stores computer instructions. When a computer executes the computer instructions, it is used to execute all steps of the data volume prediction method for time series data as described above.

[0031] The present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the data volume prediction method for time series data as described above.

[0032] The present invention determines the output demand side of one or more time series data processing units included in the module to be predicted according to the time series flow direction, determines the data demand of the output demand side of each of the time series data processing units, obtains the data size of the data item input to each of the time series data processing units, and thus predicts the necessary storage data size of each of the modules to be predicted. The present invention identifies necessary storage based on the system model and the data model, and constructs a basis for estimating the data storage scale, so that according to the system model and the data model, the necessary storage data volume can be accurately estimated in the system planning and design stage. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a workflow diagram of a method for predicting the amount of time series data according to an embodiment of the present invention;

[0034] Figure 2 This is a workflow diagram of a method for predicting the amount of time series data according to another embodiment of the present invention;

[0035] Figure 3 A time series data flow diagram of a system in an example of the present invention;

[0036] Figure 4 The figure is a schematic diagram of the hardware structure of an electronic device of the present invention. DETAILED DESCRIPTION

[0037] The specific embodiments of the present invention are further described below in conjunction with the accompanying drawings. The same components are represented by the same reference numerals. It should be noted that the words "front", "rear", "left", "right", "upper" and "lower" used in the following description refer to directions in the accompanying drawings, and the words "inner" and "outer" refer to directions toward or away from the geometric center of a specific component, respectively.

[0038] like Figure 1 The flowchart of a method for predicting the amount of time series data according to an embodiment of the present invention is shown, comprising:

[0039] Step S101, determining the output demand side of one or more time series data processing units included in the module to be predicted according to the time series flow direction;

[0040] Step S102, determining the data demand of the output demander of each of the time series data processing units;

[0041] Step S103, obtaining the data size of the data item input into each of the time series data processing units;

[0042] Step S104, predicting the necessary storage data size of each module to be predicted according to the data size of the data item input to the time series data processing unit and the data demand of the output demander of the time series data processing unit.

[0043] Specifically, the present invention can be applied to electronic devices with processing capabilities. The present invention predicts the amount of time series data and can be used in the prediction of the amount of time series data in a data storage system. In particular, the prediction of the amount of time series data in a data storage system for cloud-controlled, networked, and autonomous driving.

[0044] First, step S101 is executed to determine the output demand side of one or more time series data processing units included in the module to be predicted according to the time series flow direction.

[0045] The whole system may include multiple modules, from which one or more modules are selected as modules to be predicted. Each module includes one or more time series data processing units, each of which processes the input time series data (hereinafter referred to as time series data) and outputs it to the next time series data processing unit or system output according to the time series flow. Therefore, the output demand side of one or more time series data processing units included in the module to be predicted can be determined according to the time series flow.

[0046] Among them, the output demand side is the system output, and the output demand side of the time series data processing unit is the system output to which the time series data processing unit is finally connected.

[0047] like Figure 3 The diagram shows a time series data flow diagram of a system in an example of the present invention, wherein the system includes modules 31 and 32, 4 inputs and 2 outputs, and three time series data processing units c31 to c33.

[0048] System input data: including i31~i34;

[0049] System output data: including data d35 to system output o31, data d37 to system output o32;

[0050] All data d31 to d37 are time series data, and the goal is to estimate the minimum amount of time series data that must be stored in the storage s31 and s32 of the two modules. Module 31 and module 32 are both modules to be predicted.

[0051] The system output o31 and the system output o32 are the output demand sides. The system output o31 is the output demand side of the time series data processing unit c1, and the system output o32 is the output demand side of the time series data processing units c2 and c3.

[0052] After the output demand side of the time series data processing unit is determined, step S102 is executed to determine the data demand of the output demand side of each of the time series data processing units.

[0053] Specifically, the data requirements of the output demander can be determined according to the data specification requirements.

[0054] Then, step S103 is executed to obtain the data size of the data item input into each of the time series data processing units.

[0055] Specifically, each time series data processing unit has input time series data. One or more data items are input to the time series data processing unit for processing, and the data size of the data items input to the time series data processing unit can be determined according to data specification requirements.

[0056] Finally, step S104 is executed to predict the necessary storage data size of each module to be predicted according to the data size of the data item input to the time series data processing unit and the data demand of the output demander of the time series data processing unit.

[0057] This embodiment constructs an estimation model to accurately estimate the necessary storage data volume, which has practical economic significance and reference value for system optimization.

[0058] The present invention determines the output demand side of one or more time series data processing units included in the module to be predicted according to the time series flow direction, determines the data demand of the output demand side of each of the time series data processing units, obtains the data size of the data item input to each of the time series data processing units, and thus predicts the necessary storage data size of each of the modules to be predicted. The present invention identifies necessary storage based on the system model and the data model, and constructs a basis for estimating the data storage scale, so that according to the system model and the data model, the necessary storage data volume can be accurately estimated in the system planning and design stage.

[0059] like Figure 2 FIG. 1 is a flowchart of a method for predicting the amount of time series data in another embodiment of the present invention, comprising:

[0060] Step S201, according to the time series flow direction, determine the output demand side of one or more time series data processing units included in the module to be predicted.

[0061] In one embodiment, before determining the output demand side of one or more time series data processing units included in the module to be predicted according to the time series flow direction, the method further includes:

[0062] According to business needs, the module to be predicted is determined from multiple modules.

[0063] Step S202, determining the data granularity requirement and data length requirement of the output demand side of each of the time series data processing units.

[0064] In one embodiment, determining the data granularity requirement and data length requirement of the output demand side of each of the time series data processing units includes:

[0065] Determine the maximum value of the data granularity requirements of all output demand parties of each of the time series data processing units as the data granularity requirement of the output demand party of the time series data processing unit;

[0066] A maximum value among the data length requirements of all output demanders of each of the time series data processing units is determined as the data length requirement of the output demander of the time series data processing unit.

[0067] Step S203, obtaining the data size of the data item input into each of the time series data processing units.

[0068] Step S204: selecting a storage time series data processing unit from the time series data processing units included in each of the modules to be predicted according to business requirements.

[0069] Step S205, calculating the necessary storage data size of each of the storage time series data processing units.

[0070] In one embodiment, the step of calculating the necessary storage data size of each storage time series data processing unit includes:

[0071] The necessary storage data size of each storage timing data processing unit is calculated as: the sum of the data sizes of the data items input to the storage timing data processing unit, the product of the data granularity requirement and the data length requirement of the output demand side of the storage timing data processing unit.

[0072] In one embodiment, the step of calculating the necessary storage data size of each storage time series data processing unit includes:

[0073] For each of the storage time series data processing units, the necessary storage data size of the storage time series data processing unit is calculated as: where s i is the single frame data size of the i-th data item in the storage timing data processing unit, N is the number of data items input into the storage timing data processing unit, maxf is the maximum data granularity requirement of the output demand side of the storage timing data processing unit, and maxl is the maximum data length requirement of the output demand side of the storage timing data processing unit.

[0074] Step S206, predicting the necessary storage data size of each module to be predicted according to the necessary storage data size of the storage time series data processing unit included in each module to be predicted.

[0075] Specifically, step S201 is first executed to determine the output demand side of one or more time series data processing units included in the module to be predicted according to the time series flow direction.

[0076] The module to be predicted can be determined according to business needs.

[0077] In one embodiment, before determining the output demand side of one or more time series data processing units included in the module to be predicted according to the time series flow direction, the method further includes:

[0078] According to business needs, the module to be predicted is determined from multiple modules.

[0079] Specifically, if the business requirement is to only store the actual system output, the module directly connected to the system output will be used as the module to be predicted. Modules not directly connected to the system output have no storage requirements, so modules not directly connected to the system output are not used as modules to be predicted.

[0080] If the business requirement requires the preservation of historical data, all modules that need to save data will be considered as modules to be predicted.

[0081] For example, Figure 3 In the system shown, modules 31 and 32 are directly connected to the system output, so modules 31 and 32 are both modules to be predicted.

[0082] This embodiment determines the module to be predicted according to business requirements to meet customer needs.

[0083] Then, step S202 is executed to determine the data granularity requirement and data length requirement of the output demand side of each of the time series data processing units.

[0084] Specifically, the data requirements of the output demand side include data granularity requirements and data length requirements. The data granularity requirement is the minimum input frequency (Hz) of the system output, and the data length requirement is the minimum historical data (seconds).

[0085] In one embodiment, determining the data granularity requirement and data length requirement of the output demand side of each of the time series data processing units includes:

[0086] Determine the maximum value of the data granularity requirements of all output demand parties of each of the time series data processing units as the data granularity requirement of the output demand party of the time series data processing unit;

[0087] A maximum value among the data length requirements of all output demanders of each of the time series data processing units is determined as the data length requirement of the output demander of the time series data processing unit.

[0088] Specifically, each time series data processing unit can be connected to multiple system outputs, so there can be multiple output demand parties. The connection between the time series data processing unit and the system output includes a direct connection and an indirect connection with the system output after passing through one or more other time series data processing units.

[0089] Therefore, for Figure 3 The data specification requirement analysis of the system shown is shown in Table 1.

[0090] Table 1 Data specification requirement analysis table

[0091]

[0092] Wherein, f31 is the data granularity requirement of system output o31, f32 is the data granularity requirement of system output o32, l31 is the data length requirement of system output o31, and l32 is the data length requirement of system output o32. max() is the maximum value function. For the timing data processing unit c31, it is directly connected to the system output o31, and the timing data processing unit c31 is indirectly connected to the system output o32 through the timing data processing unit c32 and the timing data processing unit c33. Therefore, the data granularity requirement of the timing data processing unit c31 is max(f31,f32), and the data length requirement of the timing data processing unit c31 is max(l31,l32).

[0093] This embodiment determines the maximum value of the data granularity requirements of all output demand parties of each of the timing data processing units as the data granularity requirement of the output demand party of the timing data processing unit, and determines the maximum value of the data length requirements of all output demand parties of each of the timing data processing units as the data length requirement of the output demand party of the timing data processing unit, thereby meeting the output requirements to the greatest extent and ensuring that there is sufficient storage space to store the timing data of the system.

[0094] Then, step S203 is executed to obtain the data size of the data item input into each of the time series data processing units.

[0095] Specifically, the data size of the data item is the single-frame data size of each data item.

[0096] As shown in Table 2 Figure 3 Data specification sheet for the system shown.

[0097] Table 2 Data Specifications

[0098]

[0099]

[0100] Then, step S204 is executed to select a storage time series data processing unit for storage from the time series data processing units included in each of the modules to be predicted according to business requirements.

[0101] Specifically, the time series data processing unit for storage is determined according to business requirements and system models.

[0102] Among them, if the business demand is to only require the actual system output to be stored, the timing data processing unit directly connected to the system output will be used as a storage module, and the timing data processing unit that is not directly connected to the system output will be a timing data processing unit of the intermediate process. The timing data processing unit of the intermediate process has no storage requirement, so the timing data processing unit that is not directly connected to the system output will not be used as a timing data processing unit for storage.

[0103] If the business requirement requires the preservation of historical data, all time series data processing units that need to preserve data will be used as storage time series data processing units.

[0104] Then, step S205 is executed to calculate the necessary storage data size of each of the storage time series data processing units, and to estimate the necessary storage data size of each module of the system.

[0105] In one embodiment, the step of calculating the necessary storage data size of each storage time series data processing unit includes:

[0106] The necessary storage data size of each storage timing data processing unit is calculated as: the sum of the data sizes of the data items input to the storage timing data processing unit, the product of the data granularity requirement and the data length requirement of the output demand side of the storage timing data processing unit.

[0107] Specifically, the data sizes of the data items input into each storage time series data processing unit are added together to obtain the total data sizes of the data items input into the storage time series data processing unit.

[0108] Then, the sum of the data sizes of the data items input into the storage time series data processing unit is multiplied by the data granularity requirement and data length requirement of the output demand side of the storage time series data processing unit in sequence to obtain the necessary storage data size of the storage time series data processing unit.

[0109] In one embodiment, the step of calculating the necessary storage data size of each storage time series data processing unit includes:

[0110] For each of the storage time series data processing units, the necessary storage data size of the storage time series data processing unit is calculated as: where s i is the single frame data size of the i-th data item in the storage timing data processing unit, N is the number of data items input into the storage timing data processing unit, maxf is the maximum data granularity requirement of the output demand side of the storage timing data processing unit, and maxl is the maximum data length requirement of the output demand side of the storage timing data processing unit.

[0111] Specifically, for Table 2, it can be calculated that:

[0112] The necessary storage data size of the time series data processing unit c31 is: (s31+s32+s33)×max(f31,f32)×max(l31,l32);

[0113] The required storage data size of the timing data processing unit c33 is: (s33+s34+s36)×f32×l32.

[0114] Finally, step S206 is executed to predict the necessary storage data size of each module to be predicted according to the necessary storage data size of the storage time series data processing unit included in each module to be predicted.

[0115] Specifically, the necessary storage data sizes of all storage time series data processing units included in each module to be predicted may be added together to obtain the necessary storage data size of each module to be predicted.

[0116] For example, for Table 2, the storage time series data processing unit of module 31 is the time series data processing unit c31, and the storage time series data processing unit of module 32 is the time series data processing unit c33, therefore:

[0117] The necessary storage data size of module 31 is: (s31+s32+s33)×max(f31,f32)×max(l31,l32);

[0118] The required storage data size of module 32 is: (s33+s34+s36)×f32×l32.

[0119] During the system design phase, this embodiment estimates the storage data size of each model to be predicted by constructing the storage estimation model of this embodiment, thereby predicting the storage cost in advance. Based on the research and adjustment of the storage estimation model, the estimated scale of the cost can be constructed in combination with the actual storage specifications and prices of each module, and further based on this cost model, the data flow and computing division of each module of the system can be adjusted for cost optimization. Finally, this embodiment takes into account the specification features and characteristics of time series data during modeling and storage estimation. Considering that the processing process of time series data is generally continuous frame / window division, the data requirements of each link are affected by the finer-grained frame division. The calculation is based on the data granularity requirements and data length requirements to meet the needs of time series data.

[0120] It should be noted that the above example is only an example of a basic estimation model, and in actual application it needs to be adjusted according to the specific data processing flow and computing requirements.

[0121] like Figure 4 The figure shows a hardware structure diagram of an electronic device of the present invention, including:

[0122] at least one processor 401; and,

[0123] A memory 402 is communicatively connected to at least one of the processors 401; wherein,

[0124] The memory 402 stores instructions that can be executed by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the data volume prediction method for time series data as described above.

[0125] Figure 4 A processor 401 is taken as an example.

[0126] The electronic device may further include: an input device 403 and a display device 404 .

[0127] The processor 401, the memory 402, the input device 403 and the display device 404 may be connected via a bus or other means, and the figure takes the connection via a bus as an example.

[0128] The memory 402 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the data volume prediction method for time series data in the embodiment of the present application, for example, Figure 1 , Figure 2The processor 401 executes various functional applications and data processing by running the non-volatile software programs, instructions and modules stored in the memory 402, that is, the method for predicting the data volume of time series data in the above embodiment is implemented.

[0129] The memory 402 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created according to the use of the data volume prediction method of time series data, etc. In addition, the memory 402 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 402 may optionally include a memory remotely arranged relative to the processor 401, and these remote memories may be connected to a device for executing the data volume prediction method of time series data 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.

[0130] The input device 403 can receive user clicks and generate signal inputs related to user settings and function control of the method for predicting the amount of time series data. The display device 404 can include display devices such as a display screen.

[0131] The one or more modules are stored in the memory 402 , and when executed by the one or more processors 401 , the method for predicting the data volume of time series data in any of the above method embodiments is executed.

[0132] The present invention determines the output demand side of one or more time series data processing units included in the module to be predicted according to the time series flow direction, determines the data demand of the output demand side of each of the time series data processing units, obtains the data size of the data item input to each of the time series data processing units, and thus predicts the necessary storage data size of each of the modules to be predicted. The present invention identifies necessary storage based on the system model and the data model, and constructs a basis for estimating the data storage scale, so that according to the system model and the data model, the necessary storage data volume can be accurately estimated in the system planning and design stage.

[0133] An embodiment of the present invention provides a storage medium, which stores computer instructions. When a computer executes the computer instructions, it is used to execute all steps of the data volume prediction method for time series data as described above.

[0134] In the context of the present disclosure, a storage medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or apparatus. The storage medium may be a machine-readable signal medium or a machine-readable storage medium. Alternatively, the storage medium may be a non-temporary computer-readable storage medium, for example, a non-temporary computer-readable storage medium may be a ROM, a random access memory (Random Access Memory, RAM), a compact disc read-only memory (Compact Disc ROM, CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0135] An embodiment of the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the data volume prediction method for time series data as described above.

[0136] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for predicting the amount of time series data, characterized in that: include: Determine the output demand side of one or more time series data processing units included in the module to be predicted according to the time series flow direction; Determine the data demand of the output demander of each of the time series data processing units; Acquire the data size of the data item input into each of the time series data processing units; The necessary storage data size of each module to be predicted is predicted according to the data size of the data item input to the time series data processing unit and the data demand of the output demander of the time series data processing unit.

2. The method for predicting the amount of time series data according to claim 1, characterized in that: The determining of the data demand of the output demander of each of the time series data processing units includes: Determine the data granularity requirement and data length requirement of the output demand side of each of the time series data processing units.

3. The method for predicting the amount of time series data according to claim 2, characterized in that: The step of determining the data granularity requirement and data length requirement of the output demand side of each of the time series data processing units includes: Determine the maximum value among the data granularity requirements of all output demand parties of each of the time series data processing units as the data granularity requirement of the output demand party of the time series data processing unit; A maximum value among the data length requirements of all output demanders of each of the time series data processing units is determined as the data length requirement of the output demander of the time series data processing unit.

4. The method for predicting the amount of time series data according to claim 2, characterized in that: The step of predicting the necessary storage data size of each module to be predicted according to the data size of the data item input to the time series data processing unit and the data demand of the output demander of the time series data processing unit comprises: According to business requirements, selecting a storage time series data processing unit for storage from the time series data processing units included in each of the modules to be predicted; Calculating the necessary storage data size of each of the storage time series data processing units; The necessary storage data size of each module to be predicted is predicted according to the necessary storage data size of the storage time series data processing unit included in each module to be predicted.

5. The method for predicting the amount of time series data according to claim 4, characterized in that: The step of calculating the necessary storage data size of each storage time series data processing unit includes: The necessary storage data size of each storage timing data processing unit is calculated as: the sum of the data sizes of the data items input to the storage timing data processing unit, the product of the data granularity requirement and the data length requirement of the output demand side of the storage timing data processing unit.

6. The method for predicting the amount of time series data according to claim 5, characterized in that: The step of calculating the necessary storage data size of each storage time series data processing unit includes: For each of the storage time series data processing units, the necessary storage data size of the storage time series data processing unit is calculated as: where s i is the single frame data size of the i-th data item in the storage timing data processing unit, N is the number of data items input into the storage timing data processing unit, maxf is the maximum data granularity requirement of the output demand side of the storage timing data processing unit, and maxl is the maximum data length requirement of the output demand side of the storage timing data processing unit.

7. The method for predicting the amount of time series data according to any one of claims 1 to 6, characterized in that: Before determining the output demand side of one or more time series data processing units included in the module to be predicted according to the time series flow direction, the method further includes: According to business needs, the module to be predicted is determined from multiple modules.

8. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to at least one of the processors; wherein, The memory stores instructions that can be executed by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the data volume prediction method for time series data as described in any one of claims 1 to 7.

9. A storage medium, characterized in that: The storage medium stores computer instructions, which, when executed by a computer, are used to execute all steps of the method for predicting the data volume of time series data as described in any one of claims 1 to 7.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the method for predicting the data volume of time series data as described in any one of claims 1 to 7 is implemented.

Images