Residual period prediction method, system and device for enhancing time sequence prediction and medium

Abstract

The invention discloses a residual period prediction method, system and device for enhancing time sequence prediction and a medium, and aims to solve the problems of low efficiency and limited prediction precision in the prior art in a long time sequence prediction task. According to the method, the periodic residual error is predicted by explicitly modeling the periodic mode in the time sequence data and combining the prediction model, so that the prediction precision and efficiency of the time sequence prediction model are improved. The method comprises the steps of determining the period length of a data set, generating a learnable cycle period, separating a periodic component and a residual component of a time sequence, performing prediction based on a residual, and finally combining a prediction value of the residual component and the corresponding periodic component to form a final prediction result. The method can effectively capture the inherent periodicity in the time sequence, reduce the prediction error, significantly improve the precision of long-time sequence prediction, maintain the simplicity and high efficiency of the model, and is especially suitable for application scenarios with clear periodicity characteristics, such as power consumption, traffic flow, meteorological data and the like.

Description

Technical Field

[0001] The present invention belongs to the technical field of machine learning, and specifically relates to a residual period prediction method, system, device and medium for enhancing time series prediction. Background Art

[0002] Time Series Forecasting plays a vital role in many application areas, such as power demand forecasting, weather forecasting, financial market analysis, and intelligent transportation systems. Accurate time series forecasting can not only improve the operating efficiency of the system, but also provide strong support for decision making. In time series forecasting tasks, especially long-term time series forecasting, the key to accurate prediction lies in whether the model can accurately capture the long-term dependence and inherent periodicity in the data.

[0003] In the existing technology, in order to solve the problem of long time series prediction, many models focus on improving the ability to capture long-range dependencies. For example, Transformer-type models (such as Informer and Autoformer) have been widely used in LTSF tasks by taking advantage of the Transformer's advantages in modeling long-range dependencies. Convolutional neural networks (such as ModernTCN) enhance the model's ability to capture long-range dependencies through large convolution kernel design, while recurrent neural networks (such as SegRNN) improve the processing of long sequences through segmented iteration. However, most of these models extract periodic features in time series by building deep and complex structures.

[0004] This means that existing methods usually require higher computing resources and longer training time, and there are still performance bottlenecks when facing long time series prediction tasks. Therefore, how to accurately model the periodicity in time series while maintaining high efficiency has become a major challenge in the current field of time series prediction.

[0005] Based on this, the present invention proposes a new time series forecasting method, namely the residual cycle forecasting method (RCF). This method explicitly models the periodic pattern in the time series data and predicts the periodic residual on this basis, thereby significantly improving the accuracy and efficiency of the model in long time series forecasting tasks. Summary of the invention

[0006] The main purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art and to provide a residual period prediction method, system, device and medium for enhancing time series prediction, which improves prediction accuracy and significantly reduces the computational overhead of the model by explicitly modeling the periodic patterns in time series data and predicting the periodic residuals on this basis.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] In a first aspect, the present invention provides a residual period prediction method for enhancing time series prediction, comprising the following steps:

[0009] Determining a period length W of a data set; the data set includes time series data;

[0010] Generate learnable cycles for time series data with D variables By cyclically replicating the cycle period Q, a period component sequence C having the same length as the time series X is obtained;

[0011] Take a sample x from the time series X t-L+1:t , where t is the time index of the sample, L is the length of the historical lookback window of the sample; the periodic component c corresponding to the sample is intercepted from the periodic component sequence C t-L+1:t ;

[0012] By transforming the original input sequence x t-L+1:t Subtract the periodic component c t-L+1:t Get the residual component x , t-L+1:t ;

[0013] The residual component x , t-L+1:t Input into the main prediction model for residual prediction to obtain the predicted value of the residual component Where H is the prediction window length of the sample; the periodic component c corresponding to the prediction window of the sample is intercepted from the periodic component sequence C t+1:t+H ;

[0014] The predicted value of the residual component and the corresponding periodic component c t+1:t+H Add together to get the final time series prediction result

[0015] As a preferred technical solution, the period length W of the data set is determined by artificially reasoning about the characteristics of the time series data set or calculating the autocorrelation within the data set.

[0016] As a preferred technical solution, the cycle period Q is trained together with the backbone prediction model through gradient back propagation during the training process, so as to learn the feature representation that reflects the intrinsic periodic pattern of the time series.

[0017] As a preferred technical solution, the backbone prediction model is a backbone model for residual prediction.

[0018] As a preferred technical solution, the backbone prediction model is a single-layer linear model or a double-layer MLP model.

[0019] As a preferred technical solution, the periodic component c t-L+1:t The generation of includes the following steps:

[0020] Shift the cycle Q to the left by tmodW positions to get Q (t) ;

[0021] Q (t) copy times and splice Get the periodic component c of length L t-++1:t .

[0022] As a preferred technical solution, the periodic component c t+1:t+H The generation of includes the following steps:

[0023] Shift the cycle Q to the left by (t+L) mod W positions to get Q (t+t) ;

[0024] Q (t+L) copy times and splice Get the periodic component c of length H t+1:t+H .

[0025] In a second aspect, the present invention provides a residual period prediction system for enhanced time series prediction, which is applied to the residual period prediction method for enhanced time series prediction, including a period determination module, a cycle generation module, a period component acquisition module, a residual component calculation module, a residual component prediction module and a time series prediction module;

[0026] The period determination module is used to determine the period length W of a data set; the data set includes time series data;

[0027] The cycle generation module is used to generate a learnable cycle for time series data with D variables. By cyclically replicating the cycle period Q, a period component sequence C having the same length as the time series X is obtained;

[0028] The periodic component acquisition module is used to intercept samples x from the time series X t-L+1:t , where t is the time index of the sample, L is the length of the historical lookback window of the sample; the periodic component c corresponding to the sample is intercepted from the periodic component sequence C t-L+1:t ;

[0029] The residual component calculation module is used to convert the original input sequence x t-L+1:t Subtract the periodic component c t-L+1:t Get the residual component x , t-L+1:t ;

[0030] The residual component prediction module is used to convert the residual component x , t-L+1:t Input into the main prediction model for residual prediction to obtain the predicted value of the residual component Where H is the prediction window length of the sample; the periodic component c corresponding to the prediction window of the sample is intercepted from the periodic component sequence C t+1:t+H ;

[0031] The time series prediction module is used to convert the predicted value of the residual component and the corresponding periodic component c t+1:t+H Add together to get the final time series prediction result

[0032] In a third aspect, the present invention provides an electronic device, the electronic device comprising:

[0033] at least one processor; and,

[0034] a memory communicatively connected to the at least one processor; wherein,

[0035] The memory stores computer program instructions that can be executed by the at least one processor, and the computer program instructions are executed by the at least one processor to enable the at least one processor to perform the residual period prediction method for enhanced time series prediction.

[0036] In a fourth aspect, the present invention provides a computer-readable storage medium storing a program, which, when executed by a processor, implements the residual period prediction method for enhanced time series prediction.

[0037] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0038] (1) Effectiveness: The present invention can more accurately capture the periodic characteristics of data, thereby improving the accuracy of long time series prediction tasks.

[0039] (2) High efficiency: Compared with traditional complex deep models, the present invention can achieve high-precision prediction by only combining a simple backbone model for residual prediction, which greatly reduces the computational cost of the model and improves prediction efficiency.

[0040] (3) Universality: The method proposed in this invention can be combined with a variety of existing time series prediction models to further improve the prediction accuracy of existing models.

[0041] (4) Interpretability: The present invention explicitly models the periodic patterns in time series data by constructing learnable cycles. The fully trained cycles can accurately reflect the periodic characteristics existing in the data, providing a clear explanation basis for the prediction results.

[0042] In summary, the present invention provides an efficient and accurate solution for the long time series prediction task of time series through the residual period prediction method, which has broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 It is a flow chart of a residual period prediction method for enhancing time series prediction in an embodiment of the present invention;

[0045] Figure 2 Schematic diagram of using Linear and MLP as the backbone prediction model in an embodiment of the present invention;

[0046] Figure 3 is a schematic diagram of a periodic component generation process in an embodiment of the present invention;

[0047] Figure 4 A comparison diagram of prediction accuracy and parameter efficiency in a user power consumption prediction task in an embodiment of the present invention;

[0048] Figure 5 A comparison chart of the improvement in prediction accuracy of a user power consumption prediction task based on an existing prediction model in an embodiment of the present invention;

[0049] Figure 6 The cyclical pattern obtained from the modeling result in the user power consumption prediction task in the embodiment of the present invention;

[0050] Figure 7It is a structural schematic diagram of a residual period prediction system for enhancing time series prediction in an embodiment of the present invention;

[0051] Figure 8 Schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.

[0053] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0054] like Figure 1 As shown, this embodiment provides a residual period prediction method for enhancing time series prediction, which improves prediction accuracy and significantly reduces the computational overhead of the model by explicitly modeling the periodic pattern in the time series data and predicting the periodic residual on this basis. The method specifically includes the following steps:

[0055] (1) Determine the period length W of the data set;

[0056] Specifically, the cycle length W can be obtained by manually reasoning about the characteristics of the time series data set or calculating the autocorrelation within the data set.

[0057] (2) For time series data with D variables, generate learnable cycles By cyclically replicating the cycle period Q, a periodic component sequence C with the same length as the time series X can be obtained.

[0058] It is understandable that the cycle period Q will be trained together with the backbone prediction model through gradient back propagation during the training process, so as to learn the feature representation that reflects the intrinsic periodic pattern of the time series.

[0059] (3) Extract sample x from time series X t-L+1:t , where t is the time index of the sample, L is the length of the historical lookback window of the sample; the periodic component c corresponding to the sample is intercepted from the periodic component sequence Ct-L+1:t .

[0060] Specifically, the periodic component c t-L+1:t The generation of includes the following steps:

[0061] (31) By shifting the cycle period q to the left by tmodW positions, we get q (t) ;

[0062] (32) Then Q (t) copy times and splice Get the periodic component c of length L t-L+1:t ;

[0063] (4) By transforming the original input sequence x t-L+1:t Subtract the periodic component c t-L+1:t Get the residual component x , t-L+1:t ;

[0064] (5) The residual component x , t-L+1:t Input into the main prediction model for residual prediction to obtain the predicted value of the residual component Where H is the prediction window length of the sample, and the backbone prediction model is a backbone model for residual prediction, including but not limited to a basic neural network model and an existing time series prediction model. At the same time, the periodic component c corresponding to the prediction window of the sample is intercepted from the periodic component sequence C. t+1:t+H .

[0065] Specifically, the periodic component c t+1:t+H The generation of includes the following steps:

[0066] (51) By translating the cycle Q to the left by (t+L) modW positions, we get Q (t+L) ;

[0067] (52) Q (t+L) copy times and splice Get the periodic component c of length H t+1:t+H .

[0068] (6) The predicted value of the residual component and the corresponding periodic component c t+1:t+H Add together to get the final time series prediction result

[0069] In another specific embodiment of the present application, the technical solution of this patent is used to further explain the electricity consumption of users in the power industry.

[0070] Accurately predicting the user's power consumption curve is crucial for the planning of the power system. To this end, the industry is in urgent need of a more accurate user power consumption prediction technology to assist in the long-term scheduling and planning of the power system. There is power consumption data of 321 users in a certain area, with a recording interval of 1 hour. It is necessary to model based on these historical data, and use the user's historical power consumption curve for the past 4 days (96 data points) to predict the user's power consumption curve for the next month (720 data points). The method of the present invention is now used to model this user power consumption prediction task:

[0071] First, these historical training data are standardized. Since the power consumption data patterns and value ranges of different users are different, each variable (user's power consumption) needs to be standardized to ensure data consistency. The specific method is to calculate the mean and standard deviation of each variable, and then divide each variable by its own mean and standard deviation to achieve standardization.

[0072] Furthermore, the cycle length W of the data is determined. Electricity data usually has a daily cycle (different patterns during the day and night) and a weekly cycle (different patterns during weekdays and weekends). Combined with the recording interval of the data, it can be inferred that the cycle length of the power consumption curve is one week, that is, W=168.

[0073] Furthermore, for the user power consumption data with D=321 variables, a learnable cycle is generated By cyclically replicating the cycle period Q, a periodic component sequence C of equal length to the time series X can be obtained. The cycle period Q will be trained together with the backbone prediction model through gradient backpropagation during the training process, so as to learn the feature representation that reflects the intrinsic periodic pattern of the time series.

[0074] Furthermore, in each specific prediction process, we first extract a sample x from the time series X. t-L+1:t , where t is the time index of the sample, L = 96 is the historical lookback window length of the sample; at the same time, the periodic component c corresponding to the sample is intercepted from the periodic component sequence C t-L+1:t Specifically, Q can be obtained by shifting the cycle period Q to the left by tmodW positions. (t) , and then Q (t) copy times and splice Get the periodic component c of length L t-L+1:t .

[0075] Furthermore, by transforming the original input sequence x t-L+1:t Subtract the periodic component c t-L+1:t Get the residual component x , t-L+1:t .

[0076] Furthermore, the residual component x , t-L+1:t Input into the main prediction model for residual prediction to obtain the predicted value of the residual component Where H=720 is the prediction window length of the sample. The backbone prediction model is a backbone model for residual prediction, including but not limited to a basic neural network model and an existing time series prediction model. In this embodiment, a single-layer linear model and a double-layer MLP model are used as the backbone prediction model, and two specific prediction models, CycleNet / Linear and CycleNet / MLP, are constructed.

[0077] Further, the periodic component c corresponding to the prediction window of the sample is intercepted from the periodic component sequence C t+1:t+H Specifically, Q is obtained by translating the cycle Q to the left by (t+L) mod W positions. (t+L) , and then Q (t+L) copy times and splice Get the periodic component c of length H t+1:t+H .

[0078] Further, the predicted value of the residual component and the corresponding periodic component c t+1:t+H Add together to get the final time series prediction result

[0079] To clearly show the overall process of this embodiment, Figure 1 A flowchart showing a residual period prediction method for enhanced time series forecasting is shown. Figure 2 A schematic diagram showing the use of Linear and MLP as the backbone prediction model. Figure 3 The schematic diagram of the periodic component generation process after adopting the method of the present invention is further shown.

[0080] In order to verify the effective performance of the present invention, this embodiment will use the CycleNet / Linear and CycleNet / MLP of the present invention to compare with the existing prediction models. Figure 4 The comparison results of the original direct modeling method and the method of the present invention in the prediction accuracy and parameter amount of user power consumption prediction modeling are shown. It can be found that the present invention achieves higher prediction accuracy at a smaller parameter scale.

[0081] Further, Figure 5The present invention, namely the residual cycle forecasting method (RCF), is combined with the existing time series forecasting model to improve the forecasting accuracy. It can be found that the present invention can significantly improve the forecasting accuracy of the existing model.

[0082] Further, Figure 6 The invention shows the periodic features of the data learned in the cycle period after the training. It can be found that the invention fully captures the periodic features existing in the user's power consumption curve, including daily and weekly cycle patterns, which provides further explainability for the accurate prediction of time series.

[0083] In summary, the residual period prediction method for enhanced time series prediction proposed in the present invention can effectively improve the prediction accuracy of user power consumption prediction tasks, provide an important basis for realizing power supply scheduling of power systems, and provide important guarantees for the safe and stable operation of power systems.

[0084] It should be noted that, for the sake of convenience, the aforementioned method embodiments are all expressed as a series of action combinations, but those skilled in the art should know that the present invention is not limited to the described order of actions, because according to the present invention, certain steps can be performed in other orders or simultaneously.

[0085] Based on the same idea as the residual period prediction method for enhanced time series prediction in the above-mentioned embodiment, the present invention also provides a residual period prediction system for enhanced time series prediction, which can be used to execute the residual period prediction method for enhanced time series prediction. For ease of explanation, the structural schematic diagram of the residual period prediction system embodiment for enhanced time series prediction only shows the parts related to the embodiment of the present invention. Those skilled in the art can understand that the illustrated structure does not constitute a limitation on the device, and may include more or fewer components than shown in the diagram, or combine certain components, or arrange the components differently.

[0086] See also Figure 7 In another embodiment of the present application, a residual period prediction system 100 for enhancing time series prediction is provided, the system comprising a period determination module 101, a cycle generation module 102, a period component acquisition module 103, a residual component calculation module 104, a residual component prediction module 105 and a time series prediction module 106;

[0087] The period determination module 101 is used to determine the period length W of a data set; the data set includes time series data;

[0088] The cycle generation module 102 is used to generate a learnable cycle for time series data with D variables. By cyclically replicating the cycle period Q, a period component sequence C having the same length as the time series X is obtained;

[0089] The periodic component acquisition module 103 is used to extract samples x from the time series X. t-L+1:t , where t is the time index of the sample, L is the length of the historical lookback window of the sample; the periodic component c corresponding to the sample is intercepted from the periodic component sequence C t-L+1:t ;

[0090] The residual component calculation module 104 is used to calculate the original input sequence x t-L+1:t Subtract the periodic component c t-L+1:t Get the residual component x , t-L+1:t ;

[0091] The residual component prediction module 105 is used to convert the residual component x , t-L+1:t Input into the main prediction model for residual prediction to obtain the predicted value of the residual component Where H is the prediction window length of the sample; the periodic component c corresponding to the prediction window of the sample is intercepted from the periodic component sequence C t+1:t+H ;

[0092] The time series prediction module 106 is used to convert the predicted value of the residual component and the corresponding periodic component c t+1:t+H Add together to get the final time series prediction result

[0093] It should be noted that the residual period prediction system for enhanced time series prediction of the present invention corresponds one-to-one to the residual period prediction method for enhanced time series prediction of the present invention. The technical features and beneficial effects described in the embodiment of the residual period prediction method for enhanced time series prediction mentioned above are applicable to the embodiment of the residual period prediction for enhanced time series prediction. For specific contents, please refer to the description in the embodiment of the method of the present invention, which will not be repeated here. This is hereby declared.

[0094] In addition, in the implementation of the residual period prediction system for enhanced time series prediction in the above-mentioned embodiment, the logical division of each program module is only an example. In actual applications, the above-mentioned functions can be assigned to different program modules as needed, for example, for the configuration requirements of the corresponding hardware or the convenience of software implementation. That is, the internal structure of the residual period prediction system for enhanced time series prediction is divided into different program modules to complete all or part of the functions described above.

[0095] See also Figure 8In one embodiment, an electronic device for implementing a residual period prediction method for enhanced time series prediction is provided. The electronic device 200 may include a first processor 201, a first memory 202 and a bus, and may also include a computer program stored in the first memory 202 and executable on the first processor 201, such as a residual period prediction program 203 for enhanced time series prediction.

[0096] The first memory 202 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the first memory 202 may be an internal storage unit of the electronic device 200, such as a mobile hard disk of the electronic device 200. In other embodiments, the first memory 202 may also be an external storage device of the electronic device 200, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 200. Further, the first memory 202 may also include both an internal storage unit of the electronic device 200 and an external storage device. The first memory 202 may not only be used to store application software and various types of data installed in the electronic device 200, such as the code of the residual period prediction program 203 for enhanced time series prediction, but also be used to temporarily store data that has been output or is to be output.

[0097] In some embodiments, the first processor 201 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The first processor 201 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes various functions and processes data of the electronic device 200 by running or executing programs or modules stored in the first memory 202, and calling data stored in the first memory 202.

[0098] Figure 8 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 8The structure shown does not constitute a limitation on the electronic device 200 , and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0099] The residual period prediction program 203 for enhanced time series prediction stored in the first memory 202 in the electronic device 200 is a combination of multiple instructions, and when executed in the first processor 201, it can achieve:

[0100] Determining a period length W of a data set; the data set includes time series data;

[0101] Generate learnable cycles for time series data with D variables By cyclically replicating the cycle period Q, a period component sequence C having the same length as the time series X is obtained;

[0102] Take a sample x from the time series X t-L+1:t , where t is the time index of the sample, L is the length of the historical lookback window of the sample; the periodic component c corresponding to the sample is intercepted from the periodic component sequence C t-L+1:t ;

[0103] By transforming the original input sequence x t-L+1:t Subtract the periodic component c t-L+1:t Get the residual component x , t-L+1:t ;

[0104] The residual component x , t-L+1:t Input into the main prediction model for residual prediction to obtain the predicted value of the residual component Where H is the prediction window length of the sample; the periodic component c corresponding to the prediction window of the sample is intercepted from the periodic component sequence C t+1:t+H ;

[0105] The predicted value of the residual component and the corresponding periodic component c t+1:t+H Add together to get the final time series prediction result

[0106] Furthermore, if the module / unit integrated in the electronic device 200 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0107] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0108] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0109] The above embodiments are preferred implementation modes of the present invention, but the implementation modes of the present invention are not limited to the above embodiments. Any other changes, modifications, substitutions, combinations, and simplifications that do not deviate from the spirit and principles of the present invention should be equivalent replacement methods and are included in the protection scope of the present invention.

Claims

1. A residual period prediction method for enhanced time series prediction, characterized in that: The steps include: Determining a period length W of a data set; the data set includes time series data; Generate learnable cycles for time series data with D variables By cyclically replicating the cycle period Q, a period component sequence C having the same length as the time series X is obtained; Take a sample x from the time series X t-L+1:t , where t is the time index of the sample, L is the length of the historical lookback window of the sample; the periodic component c corresponding to the sample is intercepted from the periodic component sequence C t-L+1:t ; By transforming the original input sequence x t-L+1:t Subtract the periodic component c t-L+1:t Get the residual component x , t-L+1:t ; The residual component x , t-L+1:t Input into the main prediction model for residual prediction to obtain the predicted value of the residual component Where H is the prediction window length of the sample; the periodic component c corresponding to the prediction window of the sample is intercepted from the periodic component sequence C t+1:t+H ; The predicted value of the residual component and the corresponding periodic component c t+1:t+H Add together to get the final time series prediction result 2. The residual period prediction method for enhanced time series prediction according to claim 1, characterized in that: The cycle length W of the data set is determined by manually reasoning about the characteristics of the time series data set or calculating the autocorrelation within the data set.

3. The residual period prediction method for enhanced time series prediction according to claim 1, characterized in that: The cycle period Q is trained together with the backbone prediction model through gradient back propagation during the training process, so as to learn the feature representation that reflects the intrinsic periodic pattern of the time series.

4. The residual period prediction method for enhanced time series prediction according to claim 1, characterized in that: The backbone prediction model is a backbone model used for residual prediction.

5. The residual period prediction method for enhanced time series prediction according to claim 4 is characterized in that: The backbone prediction model is a single-layer linear model or a double-layer MLP model.

6. The residual period prediction method for enhanced time series prediction according to claim 1, characterized in that: The periodic component c t-L+1:t The generation of includes the following steps: Shift the cycle Q to the left by tmodW positions to get Q (t) ; Q (t) copy times and splice Get the periodic component c of length L t-L+1:t .

7. The residual period prediction method for enhanced time series prediction according to claim 1, characterized in that: The periodic component c t+1:t+H The generation of includes the following steps: Shift the cycle Q to the left by (t+L) mod W positions to get Q (t+L) ; Q (t+L) copy times and splice Get the periodic component c of length H t+1:t+H .

8. A residual period prediction system for enhanced time series prediction, characterized in that: A residual period prediction method for enhanced time series prediction applied to any one of claims 1-7, comprising a period determination module, a cycle generation module, a period component acquisition module, a residual component calculation module, a residual component prediction module and a time series prediction module; The period determination module is used to determine the period length W of a data set; the data set includes time series data; The cycle generation module is used to generate a learnable cycle for time series data with D variables. By cyclically replicating the cycle period Q, a period component sequence C having the same length as the time series X is obtained; The periodic component acquisition module is used to intercept samples x from the time series X t-L+1:t , where t is the time index of the sample, L is the length of the historical lookback window of the sample; the periodic component c corresponding to the sample is intercepted from the periodic component sequence C t-L+1:t ; The residual component calculation module is used to convert the original input sequence x t-L+1:t Subtract the periodic component c t-L+1:t Get the residual component x , t-L+1:t ; The residual component prediction module is used to convert the residual component x , t-L+1:t Input into the main prediction model for residual prediction to obtain the predicted value of the residual component Where H is the prediction window length of the sample; the periodic component c corresponding to the prediction window of the sample is intercepted from the periodic component sequence C t+1:t+H ; The time series prediction module is used to convert the predicted value of the residual component and the corresponding periodic component c t+1:t+H Add together to get the final time series prediction result 9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores computer program instructions that can be executed by the at least one processor, and the computer program instructions are executed by the at least one processor so that the at least one processor can execute the residual period prediction method for enhanced time series prediction as described in any one of claims 1-7.

10. A computer-readable storage medium storing a program, characterized in that: When the program is executed by a processor, the residual period prediction method for enhanced time series prediction according to any one of claims 1 to 7 is implemented.

Images