Energy demand prediction method, device, equipment, medium and product

Abstract

The invention discloses an energy demand prediction method and device, equipment, a medium and a product. The invention relates to the technical field of big data. The method comprises the following steps: acquiring historical steam consumption data of a target factory, wherein the historical steam consumption data comprises daily steam consumption of the factory; performing wavelet decomposition on the historical steam consumption data to obtain high-frequency steam consumption data and low-frequency steam consumption data; respectively inputting the high-frequency steam consumption data and the low-frequency steam consumption data into a pre-trained steam consumption prediction model to obtain a high-frequency steam consumption prediction result corresponding to the high-frequency steam consumption data and a low-frequency steam consumption prediction result corresponding to the low-frequency steam consumption data; and performing inverse wavelet transform on the high-frequency steam consumption prediction result and the low-frequency steam consumption prediction result to obtain a target steam consumption prediction result of the target factory. According to the technical scheme, through the wavelet transform and the steam consumption prediction model, the accurate prediction of the future steam consumption amount of the factory is realized.

Description

Technical Field

[0001] The present disclosure relates to the field of big data technology, and in particular, to an energy demand prediction method, apparatus, device, medium, and product. Background Art

[0002] In order to achieve more efficient and accurate energy management and planning, a thermal power plant needs to accurately predict the energy demand of a factory that supplies steam to the thermal power plant, so as to avoid unnecessary resource waste and help the thermal power plant improve energy utilization efficiency.

[0003] Currently, when formulating the current steam supply plan, the steam consumption of the factory in the future time period is usually predicted or formulated by the staff based on experience, and there is a problem of inaccurate prediction of steam consumption. Summary of the Invention

[0004] The present disclosure provides an energy demand prediction method, apparatus, device, medium, and product, which realizes accurate prediction of the future steam consumption of a factory.

[0005] According to one aspect of the present disclosure, an energy demand prediction method is provided, including:

[0006] Obtaining historical steam consumption data of a target factory, where the historical steam consumption data includes the daily steam consumption of the factory;

[0007] Performing wavelet decomposition on the historical steam consumption data to obtain high-frequency steam consumption data and low-frequency steam consumption data;

[0008] Inputting the high-frequency steam consumption data and the low-frequency steam consumption data into a pre-trained steam consumption prediction model respectively to obtain a high-frequency steam consumption prediction result corresponding to the high-frequency steam consumption data and a low-frequency steam consumption prediction result corresponding to the low-frequency steam consumption data;

[0009] Performing inverse wavelet transform on the high-frequency steam consumption prediction result and the low-frequency steam consumption prediction result to obtain a target steam consumption prediction result of the target factory.

[0010] According to another aspect of the present disclosure, an energy demand prediction apparatus is provided, including:

[0011] A historical steam consumption data acquisition module, configured to obtain historical steam consumption data of a target factory, where the historical steam consumption data includes the daily steam consumption of the factory;

[0012] A steam consumption data wavelet decomposition module, configured to perform wavelet decomposition on the historical steam consumption data to obtain high-frequency steam consumption data and low-frequency steam consumption data;

[0013] A steam consumption prediction module, configured to input the high-frequency steam consumption data and the low-frequency steam consumption data into a pre-trained steam consumption prediction model respectively, so as to obtain a high-frequency steam consumption prediction result corresponding to the high-frequency steam consumption data and a low-frequency steam consumption prediction result corresponding to the low-frequency steam consumption data;

[0014] A high-low frequency inverse wavelet transform module, configured to perform an inverse wavelet transform on the high-frequency steam consumption prediction result and the low-frequency steam consumption prediction result to obtain a target steam consumption prediction result of a target factory.

[0015] According to another aspect of the present disclosure, there is provided an electronic device, including:

[0016] At least one processor;

[0017] And a memory communicatively connected to the at least one processor;

[0018] Wherein, the memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the energy demand prediction method according to any embodiment of the present disclosure.

[0019] According to another aspect of the present disclosure, there is provided a computer-readable storage medium storing computer instructions for enabling a processor to implement the energy demand prediction method according to any embodiment of the present disclosure when executed.

[0020] According to another aspect of the present disclosure, there is provided a computer program product including a computer program, which when executed by a processor implements the energy demand prediction method according to any one of the embodiments of the present disclosure.

[0021] The technical solution of the embodiment of the present disclosure obtains the historical steam consumption data of a target factory, where the historical steam consumption data includes the daily steam consumption of the factory; performs wavelet decomposition on the historical steam consumption data to obtain high-frequency steam consumption data and low-frequency steam consumption data; inputs the high-frequency steam consumption data and the low-frequency steam consumption data into a pre-trained steam consumption prediction model respectively to obtain a high-frequency steam consumption prediction result corresponding to the high-frequency steam consumption data and a low-frequency steam consumption prediction result corresponding to the low-frequency steam consumption data; performs an inverse wavelet transform on the high-frequency steam consumption prediction result and the low-frequency steam consumption prediction result to obtain a target steam consumption prediction result of the target factory. In the above technical solution, through wavelet transform and a steam consumption prediction model, an accurate prediction of the future steam consumption of the factory is realized.

[0022] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present disclosure. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0024] Figure 1 is a flowchart of an energy demand prediction method provided according to an embodiment of the present disclosure;

[0025] Figure 2 is a flowchart of another energy demand prediction method provided according to an embodiment of the present disclosure;

[0026] Figure 3 is a schematic structural diagram of a wavelet decomposition provided according to an embodiment of the present disclosure;

[0027] Figure 4 is a flowchart of another energy demand prediction method provided according to an embodiment of the present disclosure;

[0028] Figure 5 is a flowchart of another energy demand prediction method provided according to an embodiment of the present disclosure;

[0029] Figure 6 is a schematic structural diagram of an energy demand prediction device provided according to an embodiment of the present disclosure;

[0030] Figure 7 is a schematic structural diagram of an electronic device for implementing the energy demand prediction method of the embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] In order to enable those skilled in the art to better understand the solutions of the present disclosure, the following clearly and completely describes the technical solutions in the embodiments of the present disclosure in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only some embodiments of the present disclosure, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present disclosure without creative efforts shall fall within the scope of protection of the present disclosure.

[0032] It should be noted that the terms "first", "second", etc. in the description, claims and the above-mentioned drawings of the present disclosure are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of data in the technical solution of the present disclosure all comply with the relevant provisions of national laws and regulations.

[0033] Figure 1 FIG. is a flowchart of an energy demand prediction method provided by an embodiment of the present disclosure. This embodiment is applicable to the situation of predicting the steam consumption of a factory in the future. This method can be executed by an energy demand prediction device, which can be implemented in the form of hardware and / or software, and the energy demand prediction device can be configured in electronic devices such as terminals and servers. As Figure 1 shown, the method includes:

[0034] S110. Obtain the historical steam consumption data of the target factory, where the historical steam consumption data includes the daily steam consumption of the factory.

[0035] Among them, the target factory refers to the factory to be predicted for future steam consumption. The steam consumption is the amount of steam used in the production or operation of the factory, and its measurement unit can be tons or other units.

[0036] Exemplarily, the historical steam consumption data of the target factory can be read from a preset storage path of an electronic device, or can also be downloaded from other devices or the cloud that are communicatively connected to the electronic device.

[0037] S120. Perform wavelet decomposition on the historical steam consumption data to obtain high-frequency steam consumption data and low-frequency steam consumption data.

[0038] Among them, the high-frequency steam consumption data is the high-frequency information in the historical steam consumption data, which is the part with rapid changes and reflects the local changes and short-term fluctuations of the steam consumption data. The low-frequency steam consumption data is the low-frequency information in the historical steam consumption data, which is the part with slow changes and reflects the overall trend and long-term changes of the steam consumption data.

[0039] Exemplarily, the number of high-frequency steam consumption data may be one or more, and the number of low-frequency steam consumption data may be one or more. Specifically, by performing wavelet decomposition on historical steam consumption data, one or more high-frequency steam consumption data and one or more low-frequency steam consumption data can be obtained.

[0040] It should be noted that by performing wavelet decomposition on historical steam consumption data, the historical steam consumption data is decomposed into components of different scales, providing more reliable data detail information for the subsequent steam consumption prediction model.

[0041] S130. Input the high-frequency steam consumption data and the low-frequency steam consumption data into a pre-trained steam consumption prediction model respectively, to obtain a high-frequency steam consumption prediction result corresponding to the high-frequency steam consumption data and a low-frequency steam consumption prediction result corresponding to the low-frequency steam consumption data.

[0042] Among them, the steam consumption prediction model is a pre-trained neural network model. The network architecture of the neural network model can be any network, and no specific limitation is made here. The steam consumption prediction model can be used to predict the steam consumption of a factory in a future time period. The future time period can be one day, one week, one month, etc.

[0043] Exemplarily, the high-frequency steam consumption data and the low-frequency steam consumption data are used as input data. Then, the high-frequency steam consumption data is input into a pre-trained steam consumption prediction model, and the steam consumption prediction model outputs a high-frequency steam consumption prediction result. The low-frequency steam consumption data is input into a pre-trained steam consumption prediction model, and the steam consumption prediction model outputs a low-frequency steam consumption prediction result.

[0044] S140. Perform inverse wavelet transform on the high-frequency steam consumption prediction result and the low-frequency steam consumption prediction result to obtain a target steam consumption prediction result of the target factory.

[0045] In the embodiment of the present disclosure, by performing inverse wavelet transform on the high-frequency steam consumption prediction result and the low-frequency steam consumption prediction result to restore the prediction result, thereby obtaining the target steam consumption prediction result of the target factory. The target steam consumption prediction result refers to the steam consumption amount that the target factory is predicted to consume in a future time period.

[0046] In the technical solution of the embodiment of the present disclosure, by obtaining the historical steam consumption data of the target factory, where the historical steam consumption data includes the daily steam consumption of the factory; performing wavelet decomposition on the historical steam consumption data to obtain high-frequency steam consumption data and low-frequency steam consumption data; inputting the high-frequency steam consumption data and the low-frequency steam consumption data into a pre-trained steam consumption prediction model respectively to obtain a high-frequency steam consumption prediction result corresponding to the high-frequency steam consumption data and a low-frequency steam consumption prediction result corresponding to the low-frequency steam consumption data; performing inverse wavelet transform on the high-frequency steam consumption prediction result and the low-frequency steam consumption prediction result to obtain the target steam consumption prediction result of the target factory. In the above technical solution, through wavelet transform and the steam consumption prediction model, accurate prediction of the future steam consumption required by the factory is realized.

[0047] Figure 2 FIG. is a flowchart of another energy demand prediction method provided by an embodiment of the present disclosure. The method of this embodiment can be combined with each optional solution in the energy demand prediction method provided in the above embodiment. On the basis of the above embodiments, this embodiment further refines the steps of wavelet decomposition of historical steam consumption data.

[0048] As Figure 2 shown, the method includes:

[0049] S210. Obtain the historical steam consumption data of the target factory, where the historical steam consumption data includes the daily steam consumption of the factory.

[0050] S220. Perform the first-layer decomposition on the historical steam consumption data to obtain first high-frequency steam consumption data and first low-frequency steam consumption data.

[0051] S230. Perform the second-layer decomposition on the first high-frequency steam consumption data to obtain second high-frequency steam consumption data and second low-frequency steam consumption data.

[0052] S240. Perform the third-layer decomposition on the second high-frequency steam consumption data to obtain third high-frequency steam consumption data and third low-frequency steam consumption data.

[0053] S250. Input the first low-frequency steam consumption data into a pre-trained steam consumption prediction model to obtain a low-frequency steam consumption prediction result corresponding to the first low-frequency steam consumption data.

[0054] S260. Input the second low-frequency steam consumption data into a pre-trained steam consumption prediction model to obtain a low-frequency steam consumption prediction result corresponding to the second low-frequency steam consumption data.

[0055] S270. Input the third low-frequency steam consumption data into the pre-trained steam consumption prediction model to obtain the low-frequency steam consumption prediction result corresponding to the third low-frequency steam consumption data.

[0056] S280. Input the third high-frequency steam consumption data into the pre-trained steam consumption prediction model to obtain the high-frequency steam consumption prediction result corresponding to the third high-frequency steam consumption data.

[0057] S290. Perform inverse wavelet transform on the low-frequency steam consumption prediction result corresponding to the first low-frequency steam consumption data, the low-frequency steam consumption prediction result corresponding to the second low-frequency steam consumption data, the low-frequency steam consumption prediction result corresponding to the third low-frequency steam consumption data, and the high-frequency steam consumption prediction result corresponding to the third high-frequency steam consumption data to obtain the target steam consumption prediction result of the target factory.

[0058] Exemplarily, Figure 3 is a schematic structural diagram of wavelet decomposition provided by an embodiment of the present disclosure. As Figure 3 shown, the number of decomposition layers of the present disclosure is 3 layers. S represents historical steam consumption data, A1 represents the first high-frequency steam consumption data, D1 represents the first low-frequency steam consumption data, A2 represents the second high-frequency steam consumption data, D2 represents the second low-frequency steam consumption data, A3 represents the third high-frequency steam consumption data, and D3 represents the third low-frequency steam consumption data.

[0059] Further, D1, D2, D3, and A3 can be respectively input into the pre-trained steam consumption prediction model, and D1 ′ , D2 ′ , D3 ′ , and A3 ′ can be predicted, where D1 ′ represents the low-frequency steam consumption prediction result corresponding to the first low-frequency steam consumption data, D2 ′ represents the low-frequency steam consumption prediction result corresponding to the second low-frequency steam consumption data, D3 ′ represents the low-frequency steam consumption prediction result corresponding to the third low-frequency steam consumption data, and A3 ′ represents the high-frequency steam consumption prediction result corresponding to the third high-frequency steam consumption data.

[0060] Further, perform inverse wavelet transform on D1 ′ , D2 ′ , D3 ′ , and A3 ′ to obtain the target steam consumption prediction result of the target factory.

[0061] Based on the above embodiments, optionally, after performing the third-layer decomposition on the second high-frequency steam consumption data to obtain the third high-frequency steam consumption data and the third low-frequency steam consumption data, the following steps are further included: determining the data length of the historical steam consumption data; determining the wavelet coefficient denoising threshold based on the data length of the historical steam consumption data; based on the wavelet coefficient denoising threshold, performing noise reduction processing on the first low-frequency steam consumption data, the second low-frequency steam consumption data, the third low-frequency steam consumption data, and the third high-frequency steam consumption data to obtain the denoised first low-frequency steam consumption data, the denoised second low-frequency steam consumption data, the denoised third low-frequency steam consumption data, and the denoised third high-frequency steam consumption data; correspondingly, inputting the high-frequency steam consumption data and the low-frequency steam consumption data into a pre-trained steam consumption prediction model respectively to obtain the high-frequency steam consumption prediction result corresponding to the high-frequency steam consumption data and the low-frequency steam consumption prediction result corresponding to the low-frequency steam consumption data, including: inputting the denoised first low-frequency steam consumption data into the pre-trained steam consumption prediction model to obtain the low-frequency steam consumption prediction result corresponding to the first low-frequency steam consumption data; inputting the denoised second low-frequency steam consumption data into the pre-trained steam consumption prediction model to obtain the low-frequency steam consumption prediction result corresponding to the second low-frequency steam consumption data; inputting the denoised third low-frequency steam consumption data into the pre-trained steam consumption prediction model to obtain the low-frequency steam consumption prediction result corresponding to the third low-frequency steam consumption data; inputting the denoised third high-frequency steam consumption data into the pre-trained steam consumption prediction model to obtain the high-frequency steam consumption prediction result corresponding to the third high-frequency steam consumption data.

[0062] In the embodiments of the present disclosure, the historical steam consumption data includes the steam consumption for multiple days, and its data length can be the date length. The wavelet coefficient denoising threshold refers to the threshold used for denoising the wavelet coefficients. It should be noted that through noise reduction processing, the quality of the steam consumption data can be effectively improved.

[0063] Exemplarily, the calculation formula for the wavelet coefficient denoising threshold can be:

[0064] λ = σ√(2lnN);

[0065] where λ represents the wavelet coefficient denoising threshold, σ represents the noise standard deviation, and N represents the data length of the historical steam consumption data. If the first low-frequency steam consumption data, the second low-frequency steam consumption data, the third low-frequency steam consumption data, or the third high-frequency steam consumption data is less than the wavelet coefficient denoising threshold, the steam consumption data less than the wavelet coefficient denoising threshold is set to zero. For example, if the first low-frequency steam consumption data is less than the first low-frequency steam consumption data, the first low-frequency steam consumption data is set to zero.

[0066] The technical solution of the embodiment of the present disclosure realizes the accurate prediction of the future steam consumption required by the factory through three-layer wavelet decomposition, a steam consumption prediction model, and inverse wavelet transform.

[0067] Figure 4 FIG. is a flowchart of another energy demand prediction method provided by the embodiment of the present disclosure. The method of this embodiment can be combined with each optional solution in the energy demand prediction method provided in the above embodiment. On the basis of the above embodiments, optionally, before obtaining the historical steam consumption data of the target factory, the method further includes: obtaining historical steam consumption sample data of at least one factory; performing wavelet decomposition on the historical steam consumption sample data to obtain high-frequency steam consumption sample data and low-frequency steam consumption sample data; inputting the high-frequency steam consumption sample data and the low-frequency steam consumption sample data into a steam consumption prediction model to be trained respectively, to obtain a steam consumption prediction result corresponding to the high-frequency steam consumption sample data and a steam consumption prediction result corresponding to the low-frequency steam consumption sample data; performing inverse wavelet transform on the steam consumption prediction result corresponding to the high-frequency steam consumption sample data and the steam consumption prediction result corresponding to the low-frequency steam consumption sample data to obtain a steam consumption prediction result corresponding to the historical steam consumption sample data; determining a model loss based on the steam consumption prediction result corresponding to the historical steam consumption sample data and the actual steam consumption, and updating the model parameters of the steam consumption prediction model to be trained based on the model loss until the model training stop condition is met, to obtain a trained steam consumption prediction model.

[0068] As Figure 4 shown, the method includes:

[0069] S310. Obtain historical steam consumption sample data of at least one factory.

[0070] The historical steam consumption sample data refers to the sample data for model training, and may include the steam consumption of multiple factories on multiple dates.

[0071] Exemplarily, the historical steam consumption sample data can be read from a preset storage path of an electronic device, or can be downloaded from other devices or the cloud that are communicatively connected to the electronic device.

[0072] S320. Perform wavelet decomposition on the historical steam consumption sample data to obtain high-frequency steam consumption sample data and low-frequency steam consumption sample data.

[0073] Among them, the high-frequency steam consumption sample data is the high-frequency information in the historical steam consumption sample data. It is the part that changes rapidly and reflects the local changes and short-term fluctuations of the steam consumption sample data. The low-frequency steam consumption sample data is the low-frequency information in the historical steam consumption sample data. It is the part that changes slowly and reflects the overall trend and long-term changes of the steam consumption sample data.

[0074] Exemplarily, wavelet decomposition can be performed on the steam consumption sample data, and one or more high-frequency steam consumption sample data and one or more low-frequency steam consumption sample data can be obtained.

[0075] S330: Respectively input the high-frequency steam consumption sample data and the low-frequency steam consumption sample data into the steam consumption prediction model to be trained, and obtain the steam consumption prediction result corresponding to the high-frequency steam consumption sample data and the steam consumption prediction result corresponding to the low-frequency steam consumption sample data.

[0076] Exemplarily, take the high-frequency steam consumption sample data and the low-frequency steam consumption sample data as input data. Then input the high-frequency steam consumption sample data into the steam consumption prediction model to be trained. The steam consumption prediction model outputs the steam consumption prediction result corresponding to the high-frequency steam consumption sample data. Input the low-frequency steam consumption sample data into the steam consumption prediction model to be trained. The steam consumption prediction model outputs the steam consumption prediction result corresponding to the low-frequency steam consumption sample data.

[0077] S340: Perform inverse wavelet transform on the steam consumption prediction result corresponding to the high-frequency steam consumption sample data and the steam consumption prediction result corresponding to the low-frequency steam consumption sample data to obtain the steam consumption prediction result corresponding to the historical steam consumption sample data.

[0078] In the embodiments of the present disclosure, through inverse wavelet transform, the prediction result is restored to obtain the steam consumption prediction result corresponding to the historical steam consumption sample data.

[0079] S350: Determine the model loss based on the steam consumption prediction result corresponding to the historical steam consumption sample data and the actual steam consumption. Update the model parameters of the steam consumption prediction model to be trained based on the model loss until the model training stop condition is met, and obtain the trained steam consumption prediction model.

[0080] S360: Obtain the historical steam consumption data of the target factory, where the historical steam consumption data includes the daily steam consumption of the factory.

[0081] S370: Perform wavelet decomposition on the historical steam consumption data to obtain high-frequency steam consumption data and low-frequency steam consumption data.

[0082] S380. Input the high-frequency steam consumption data and the low-frequency steam consumption data into a pre-trained steam consumption prediction model respectively, to obtain a high-frequency steam consumption prediction result corresponding to the high-frequency steam consumption data and a low-frequency steam consumption prediction result corresponding to the low-frequency steam consumption data.

[0083] S390. Perform an inverse wavelet transform on the high-frequency steam consumption prediction result and the low-frequency steam consumption prediction result to obtain a target steam consumption prediction result of the target factory.

[0084] Based on the above embodiments, optionally, the performing a wavelet decomposition on the historical steam consumption sample data to obtain high-frequency steam consumption sample data and low-frequency steam consumption sample data includes: performing a first-layer decomposition on the historical steam consumption sample data to obtain first high-frequency steam consumption sample data and first low-frequency steam consumption sample data; performing a second-layer decomposition on the first high-frequency steam consumption sample data to obtain second high-frequency steam consumption sample data and second low-frequency steam consumption sample data; performing a third-layer decomposition on the second high-frequency steam consumption sample data to obtain third high-frequency steam consumption sample data and third low-frequency steam consumption sample data; correspondingly, inputting the high-frequency steam consumption sample data and the low-frequency steam consumption sample data into a steam consumption prediction model to be trained respectively, to obtain a steam consumption prediction result corresponding to the high-frequency steam consumption sample data and a steam consumption prediction result corresponding to the low-frequency steam consumption sample data includes: inputting the first low-frequency steam consumption sample data into the steam consumption prediction model to be trained to obtain a steam consumption prediction result corresponding to the first low-frequency steam consumption sample data; inputting the second low-frequency steam consumption sample data into the steam consumption prediction model to be trained to obtain a steam consumption prediction result corresponding to the second low-frequency steam consumption sample data; inputting the third low-frequency steam consumption sample data into the steam consumption prediction model to be trained to obtain a steam consumption prediction result corresponding to the third low-frequency steam consumption sample data; inputting the third high-frequency steam consumption sample data into the steam consumption prediction model to be trained to obtain a steam consumption prediction result corresponding to the third high-frequency steam consumption sample data; correspondingly, performing an inverse wavelet transform on the steam consumption prediction result corresponding to the high-frequency steam consumption sample data and the steam consumption prediction result corresponding to the low-frequency steam consumption sample data to obtain a steam consumption prediction result corresponding to the historical steam consumption sample data includes: performing an inverse wavelet transform on the steam consumption prediction result corresponding to the first low-frequency steam consumption sample data, the steam consumption prediction result corresponding to the second low-frequency steam consumption sample data, the steam consumption prediction result corresponding to the third low-frequency steam consumption sample data, and the steam consumption prediction result corresponding to the third high-frequency steam consumption sample data to obtain a steam consumption prediction result corresponding to the historical steam consumption sample data.

[0085] Exemplarily, W represents the historical steam consumption sample data, M1 represents the first high-frequency steam consumption sample data, N1 represents the first low-frequency steam consumption sample data, M2 represents the second high-frequency steam consumption sample data, N2 represents the second low-frequency steam consumption sample data, M3 represents the third high-frequency steam consumption sample data, and N3 represents the third low-frequency steam consumption sample data.

[0086] Further, N1, N2, N3, and M3 can be respectively input into the steam consumption prediction model to be trained, and N1 can be predicted. ′ , N2 ′ , N3 ′ and M3 ′ , where N1 ′ represents the steam consumption prediction result corresponding to the first low-frequency steam consumption sample data, N2 ′ represents the steam consumption prediction result corresponding to the second low-frequency steam consumption sample data, N3 ′ represents the steam consumption prediction result corresponding to the third low-frequency steam consumption sample data, and M3 ′ represents the steam consumption prediction result corresponding to the third high-frequency steam consumption sample data.

[0087] Further, perform inverse wavelet transform on N1 ′ , N2 ′ , N3 ′ and M3 ′ to obtain the steam consumption prediction result corresponding to the historical steam consumption sample data. Further, determine the model loss based on the steam consumption prediction result corresponding to the historical steam consumption sample data and the actual steam consumption, and update the model parameters of the steam consumption prediction model to be trained based on the model loss until the model training stop condition is satisfied, and obtain the trained steam consumption prediction model.

[0088] The technical solution of the embodiments of the present disclosure lays a reliable model foundation for subsequent steam consumption prediction by training the steam consumption prediction model.

[0089] Figure 5 is a flowchart of another energy demand prediction method provided by the embodiments of the present disclosure, and the method of this embodiment is a preferred example of the above embodiment. The steam consumption prediction model is a deep learning model based on time series prediction. For example, the steam consumption prediction model can be a deep learning model based on DeepAR (Deep Autoregressive). As Figure 5 shown, the method includes:

[0090] S410. Obtain the historical steam consumption data of the target factory, where the historical steam consumption data includes the daily steam consumption of the factory.

[0091] S420. Perform the first - layer decomposition on the historical steam consumption data to obtain the first high - frequency steam consumption data and the first low - frequency steam consumption data.

[0092] S430. Perform the second - layer decomposition on the first high - frequency steam consumption data to obtain the second high - frequency steam consumption data and the second low - frequency steam consumption data.

[0093] S440. Perform the third - layer decomposition on the second high - frequency steam consumption data to obtain the third high - frequency steam consumption data and the third low - frequency steam consumption data.

[0094] S450. Input the first low - frequency steam consumption data into the pre - trained DeepAR model to obtain the low - frequency steam consumption prediction result corresponding to the first low - frequency steam consumption data.

[0095] S460. Input the second low - frequency steam consumption data into the pre - trained DeepAR model to obtain the low - frequency steam consumption prediction result corresponding to the second low - frequency steam consumption data.

[0096] S470. Input the third low - frequency steam consumption data into the pre - trained DeepAR model to obtain the low - frequency steam consumption prediction result corresponding to the third low - frequency steam consumption data.

[0097] S480. Input the third high - frequency steam consumption data into the pre - trained DeepAR model to obtain the high - frequency steam consumption prediction result corresponding to the third high - frequency steam consumption data.

[0098] S490. Perform the inverse wavelet transform on the low - frequency steam consumption prediction result corresponding to the first low - frequency steam consumption data, the low - frequency steam consumption prediction result corresponding to the second low - frequency steam consumption data, the low - frequency steam consumption prediction result corresponding to the third low - frequency steam consumption data, and the high - frequency steam consumption prediction result corresponding to the third high - frequency steam consumption data to obtain the target steam consumption prediction result of the target factory.

[0099] The technical solution of the embodiments of the present disclosure realizes the accurate prediction of the future steam consumption required by the factory through wavelet transform and the DeepAR model.

[0100] Figure 6 It is a schematic structural diagram of an energy demand prediction device provided by the embodiments of the present disclosure. As Figure 6 shown, the device includes:

[0101] A historical steam consumption data acquisition module 510, configured to acquire the historical steam consumption data of the target factory, where the historical steam consumption data includes the daily steam consumption of the factory;

[0102] The wavelet decomposition module 520 for steam consumption data is used to perform wavelet decomposition on the historical steam consumption data to obtain high-frequency steam consumption data and low-frequency steam consumption data;

[0103] The steam consumption prediction module 530 is used to respectively input the high-frequency steam consumption data and the low-frequency steam consumption data into a pre-trained steam consumption prediction model to obtain a high-frequency steam consumption prediction result corresponding to the high-frequency steam consumption data and a low-frequency steam consumption prediction result corresponding to the low-frequency steam consumption data;

[0104] The inverse wavelet transform module 540 for high and low frequencies is used to perform inverse wavelet transform on the high-frequency steam consumption prediction result and the low-frequency steam consumption prediction result to obtain a target steam consumption prediction result of the target factory.

[0105] The technical solution of the embodiment of the present disclosure, by obtaining the historical steam consumption data of the target factory, where the historical steam consumption data includes the daily steam consumption of the factory; performing wavelet decomposition on the historical steam consumption data to obtain high-frequency steam consumption data and low-frequency steam consumption data; respectively inputting the high-frequency steam consumption data and the low-frequency steam consumption data into a pre-trained steam consumption prediction model to obtain a high-frequency steam consumption prediction result corresponding to the high-frequency steam consumption data and a low-frequency steam consumption prediction result corresponding to the low-frequency steam consumption data; performing inverse wavelet transform on the high-frequency steam consumption prediction result and the low-frequency steam consumption prediction result to obtain a target steam consumption prediction result of the target factory. In the above technical solution, through wavelet transform and the steam consumption prediction model, accurate prediction of the future steam consumption required by the factory is realized.

[0106] Based on any optional technical solution in the embodiment of the present disclosure, optionally, the wavelet decomposition module 520 for steam consumption data includes:

[0107] The first-layer decomposition unit is used to perform the first-layer decomposition on the historical steam consumption data to obtain the first high-frequency steam consumption data and the first low-frequency steam consumption data;

[0108] The second-layer decomposition unit is used to perform the second-layer decomposition on the first high-frequency steam consumption data to obtain the second high-frequency steam consumption data and the second low-frequency steam consumption data;

[0109] The third-layer decomposition unit is used to perform the third-layer decomposition on the second high-frequency steam consumption data to obtain the third high-frequency steam consumption data and the third low-frequency steam consumption data;

[0110] Correspondingly, the steam consumption prediction module 530 is further specifically used for:

[0111] Input the first low-frequency steam consumption data into the pre-trained steam consumption prediction model to obtain the low-frequency steam consumption prediction result corresponding to the first low-frequency steam consumption data;

[0112] Input the second low-frequency steam consumption data into the pre-trained steam consumption prediction model to obtain the low-frequency steam consumption prediction result corresponding to the second low-frequency steam consumption data;

[0113] Input the third low-frequency steam consumption data into the pre-trained steam consumption prediction model to obtain the low-frequency steam consumption prediction result corresponding to the third low-frequency steam consumption data;

[0114] Input the third high-frequency steam consumption data into the pre-trained steam consumption prediction model to obtain the high-frequency steam consumption prediction result corresponding to the third high-frequency steam consumption data;

[0115] Correspondingly, the high-low frequency inverse wavelet transform module 540 is further specifically configured to:

[0116] Perform inverse wavelet transform on the low-frequency steam consumption prediction result corresponding to the first low-frequency steam consumption data, the low-frequency steam consumption prediction result corresponding to the second low-frequency steam consumption data, the low-frequency steam consumption prediction result corresponding to the third low-frequency steam consumption data, and the high-frequency steam consumption prediction result corresponding to the third high-frequency steam consumption data to obtain the target steam consumption prediction result of the target factory.

[0117] Based on any optional technical solution in the embodiments of the present disclosure, optionally, the energy demand prediction device further includes:

[0118] A wavelet coefficient denoising module, configured to determine the data length of the historical steam consumption data; determine a wavelet coefficient denoising threshold based on the data length of the historical steam consumption data; and perform denoising processing on the first low-frequency steam consumption data, the second low-frequency steam consumption data, the third low-frequency steam consumption data, and the third high-frequency steam consumption data based on the wavelet coefficient denoising threshold to obtain the denoised first low-frequency steam consumption data, the denoised second low-frequency steam consumption data, the denoised third low-frequency steam consumption data, and the denoised third high-frequency steam consumption data;

[0119] Correspondingly, the steam consumption prediction module 530 is further specifically configured to:

[0120] Input the denoised first low-frequency steam consumption data into the pre-trained steam consumption prediction model to obtain the low-frequency steam consumption prediction result corresponding to the first low-frequency steam consumption data;

[0121] Input the second low-frequency steam consumption data after noise reduction into the pre-trained steam consumption prediction model to obtain the low-frequency steam consumption prediction result corresponding to the second low-frequency steam consumption data;

[0122] Input the third low-frequency steam consumption data after noise reduction into the pre-trained steam consumption prediction model to obtain the low-frequency steam consumption prediction result corresponding to the third low-frequency steam consumption data;

[0123] Input the third high-frequency steam consumption data after noise reduction into the pre-trained steam consumption prediction model to obtain the high-frequency steam consumption prediction result corresponding to the third high-frequency steam consumption data.

[0124] Based on any optional technical solution in the embodiments of the present disclosure, optionally, the energy demand prediction device further includes:

[0125] A steam consumption prediction model training module, configured to obtain historical steam consumption sample data of at least one factory; perform wavelet decomposition on the historical steam consumption sample data to obtain high-frequency steam consumption sample data and low-frequency steam consumption sample data; input the high-frequency steam consumption sample data and the low-frequency steam consumption sample data into the steam consumption prediction model to be trained respectively to obtain the steam consumption prediction result corresponding to the high-frequency steam consumption sample data and the steam consumption prediction result corresponding to the low-frequency steam consumption sample data; perform inverse wavelet transform on the steam consumption prediction result corresponding to the high-frequency steam consumption sample data and the steam consumption prediction result corresponding to the low-frequency steam consumption sample data to obtain the steam consumption prediction result corresponding to the historical steam consumption sample data; determine the model loss based on the steam consumption prediction result corresponding to the historical steam consumption sample data and the actual steam consumption, and update the model parameters of the steam consumption prediction model to be trained based on the model loss until the model training stop condition is met, and obtain the trained steam consumption prediction model.

[0126] Based on any optional technical solution in the embodiments of the present disclosure, optionally, the steam consumption prediction model training module is specifically configured to:

[0127] Perform the first-layer decomposition on the historical steam consumption sample data to obtain the first high-frequency steam consumption sample data and the first low-frequency steam consumption sample data;

[0128] Perform the second-layer decomposition on the first high-frequency steam consumption sample data to obtain the second high-frequency steam consumption sample data and the second low-frequency steam consumption sample data;

[0129] Perform the third-layer decomposition on the second high-frequency steam consumption sample data to obtain the third high-frequency steam consumption sample data and the third low-frequency steam consumption sample data;

[0130] Input the first low-frequency steam consumption sample data into the steam consumption prediction model to be trained, and obtain the steam consumption prediction result corresponding to the first low-frequency steam consumption sample data;

[0131] Input the second low-frequency steam consumption sample data into the steam consumption prediction model to be trained, and obtain the steam consumption prediction result corresponding to the second low-frequency steam consumption sample data;

[0132] Input the third low-frequency steam consumption sample data into the steam consumption prediction model to be trained, and obtain the steam consumption prediction result corresponding to the third low-frequency steam consumption sample data;

[0133] Input the third high-frequency steam consumption sample data into the steam consumption prediction model to be trained, and obtain the steam consumption prediction result corresponding to the third high-frequency steam consumption sample data;

[0134] Perform inverse wavelet transform on the steam consumption prediction results corresponding to the first low-frequency steam consumption sample data, the second low-frequency steam consumption sample data, the third low-frequency steam consumption sample data, and the third high-frequency steam consumption sample data, and obtain the steam consumption prediction result corresponding to the historical steam consumption sample data.

[0135] Based on any optional technical solution in the embodiments of the present disclosure, optionally, the steam consumption prediction model is a deep learning model based on time series prediction.

[0136] The energy demand prediction device provided by the embodiments of the present disclosure can execute the energy demand prediction method provided by any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects for executing the method.

[0137] Figure 7 FIG. shows a schematic structural diagram of an electronic device 10 that can be used to implement the embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described herein and / or claimed.

[0138] Such as Figure 7As shown, the electronic device 10 includes at least one processor 11 and a memory communicatively connected to the at least one processor 11, such as read-only memory (ROM) 12, random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor. The processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, ROM 12, and RAM 13 are connected to each other through a bus 14. The I / O interface 15 is also connected to the bus 14.

[0139] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0140] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as an energy demand prediction method, which includes:

[0141] Obtaining historical steam consumption data of a target factory, where the historical steam consumption data includes the daily steam consumption of the factory;

[0142] Performing wavelet decomposition on the historical steam consumption data to obtain high-frequency steam consumption data and low-frequency steam consumption data;

[0143] Respectively inputting the high-frequency steam consumption data and the low-frequency steam consumption data into a pre-trained steam consumption prediction model to obtain a high-frequency steam consumption prediction result corresponding to the high-frequency steam consumption data and a low-frequency steam consumption prediction result corresponding to the low-frequency steam consumption data;

[0144] Performing inverse wavelet transform on the high-frequency steam consumption prediction result and the low-frequency steam consumption prediction result to obtain a target steam consumption prediction result of the target factory.

[0145] In some embodiments, the energy demand forecasting method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the energy demand forecasting method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the energy demand forecasting method by any other suitable means (e.g., by means of firmware).

[0146] The various embodiments of the systems and techniques described above in this document may be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), system-on-a-chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs executable and / or interpretable on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0147] The computer programs for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs may be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine, or entirely on the remote machine or server.

[0148] In the context of this disclosure, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0149] To provide for interaction with a user, the systems and techniques described herein can be implemented on an electronic device 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 electronic device. Other kinds of devices can also be used to provide for interaction with the user; 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 input, speech input, or tactile input).

[0150] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0151] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The relationship between the client and the server is created by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0152] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of this disclosure can be achieved, and no limitation is imposed herein.

[0153] The embodiments of this disclosure also provide a computer program product, including a computer program which, when executed by a processor, implements the energy demand prediction method provided in any embodiment of this disclosure.

[0154] In the process of implementing the computer program product, the computer program code for performing the operations of this disclosure can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0155] The above specific implementation manners do not constitute a limitation on the protection scope of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of this disclosure shall be included within the protection scope of this disclosure.

Claims

1. A method for predicting energy demand, characterized in that: include: Acquire historical steam consumption data of a target plant, wherein the historical steam consumption data includes daily steam consumption of the plant; Performing wavelet decomposition on the historical steam consumption data to obtain high-frequency steam consumption data and low-frequency steam consumption data; Inputting the high-frequency steam consumption data and the low-frequency steam consumption data into a pre-trained steam consumption prediction model respectively, to obtain a high-frequency steam consumption prediction result corresponding to the high-frequency steam consumption data and a low-frequency steam consumption prediction result corresponding to the low-frequency steam consumption data; The high-frequency steam consumption prediction result and the low-frequency steam consumption prediction result are subjected to inverse wavelet transformation to obtain a target steam consumption prediction result of a target plant.

2. The method according to claim 1, characterized in that: The wavelet decomposition of the historical steam consumption data to obtain high-frequency steam consumption data and low-frequency steam consumption data includes: Performing a first-level decomposition on the historical steam consumption data to obtain first high-frequency steam consumption data and first low-frequency steam consumption data; Performing a second-level decomposition on the first high-frequency steam consumption data to obtain second high-frequency steam consumption data and second low-frequency steam consumption data; Performing a third-level decomposition on the second high-frequency steam consumption data to obtain third high-frequency steam consumption data and third low-frequency steam consumption data; Accordingly, the high-frequency steam consumption data and the low-frequency steam consumption data are respectively input into a pre-trained steam consumption prediction model to obtain a high-frequency steam consumption prediction result corresponding to the high-frequency steam consumption data and a low-frequency steam consumption prediction result corresponding to the low-frequency steam consumption data, including: Inputting the first low-frequency steam consumption data into a pre-trained steam consumption prediction model to obtain a low-frequency steam consumption prediction result corresponding to the first low-frequency steam consumption data; Inputting the second low-frequency steam consumption data into a pre-trained steam consumption prediction model to obtain a low-frequency steam consumption prediction result corresponding to the second low-frequency steam consumption data; Inputting the third low-frequency steam consumption data into a pre-trained steam consumption prediction model to obtain a low-frequency steam consumption prediction result corresponding to the third low-frequency steam consumption data; Inputting the third high-frequency steam consumption data into a pre-trained steam consumption prediction model to obtain a high-frequency steam consumption prediction result corresponding to the third high-frequency steam consumption data; Accordingly, the high-frequency steam consumption prediction result and the low-frequency steam consumption prediction result are subjected to inverse wavelet transformation to obtain a target steam consumption prediction result of the target plant, including: The low-frequency steam consumption prediction results corresponding to the first low-frequency steam consumption data, the low-frequency steam consumption prediction results corresponding to the second low-frequency steam consumption data, the low-frequency steam consumption prediction results corresponding to the third low-frequency steam consumption data, and the high-frequency steam consumption prediction results corresponding to the third high-frequency steam consumption data are inversely transformed to obtain the target steam consumption prediction results of the target plant.

3. The method according to claim 2, characterized in that After performing a third-level decomposition on the second high-frequency steam consumption data to obtain third high-frequency steam consumption data and third low-frequency steam consumption data, the method further includes: Determining the data length of the historical steam consumption data; Determining a wavelet coefficient denoising threshold based on the data length of the historical steam consumption data; Based on the wavelet coefficient denoising threshold, the first low-frequency steam consumption data, the second low-frequency steam consumption data, the third low-frequency steam consumption data and the third high-frequency steam consumption data are subjected to denoising to obtain the first low-frequency steam consumption data after denoising, the second low-frequency steam consumption data after denoising, the third low-frequency steam consumption data after denoising and the third high-frequency steam consumption data after denoising; Accordingly, the high-frequency steam consumption data and the low-frequency steam consumption data are respectively input into a pre-trained steam consumption prediction model to obtain a high-frequency steam consumption prediction result corresponding to the high-frequency steam consumption data and a low-frequency steam consumption prediction result corresponding to the low-frequency steam consumption data, including: Inputting the first low-frequency steam consumption data after noise reduction into a pre-trained steam consumption prediction model to obtain a low-frequency steam consumption prediction result corresponding to the first low-frequency steam consumption data; Inputting the noise-reduced second low-frequency steam consumption data into a pre-trained steam consumption prediction model to obtain a low-frequency steam consumption prediction result corresponding to the second low-frequency steam consumption data; Inputting the third low-frequency steam consumption data after noise reduction into a pre-trained steam consumption prediction model to obtain a low-frequency steam consumption prediction result corresponding to the third low-frequency steam consumption data; The third high-frequency steam consumption data after noise reduction is input into a pre-trained steam consumption prediction model to obtain a high-frequency steam consumption prediction result corresponding to the third high-frequency steam consumption data.

4. The method according to claim 1, characterized in that Before obtaining the historical steam consumption data of the target plant, the method further includes: Obtain historical steam consumption sample data for at least one plant; Performing wavelet decomposition on the historical steam consumption sample data to obtain high-frequency steam consumption sample data and low-frequency steam consumption sample data; Inputting the high-frequency steam consumption sample data and the low-frequency steam consumption sample data into the steam consumption prediction model to be trained respectively, and obtaining the steam consumption prediction result corresponding to the high-frequency steam consumption sample data and the steam consumption prediction result corresponding to the low-frequency steam consumption sample data; Performing inverse wavelet transform on the steam consumption prediction result corresponding to the high-frequency steam consumption sample data and the steam consumption prediction result corresponding to the low-frequency steam consumption sample data to obtain the steam consumption prediction result corresponding to the historical steam consumption sample data; The model loss is determined based on the steam consumption prediction results corresponding to the historical steam consumption sample data and the actual steam consumption, and the model parameters of the steam consumption prediction model to be trained are updated based on the model loss until the model training stop conditions are met, thereby obtaining a trained steam consumption prediction model.

5. The method according to claim 4, characterized in that The wavelet decomposition of the historical steam consumption sample data to obtain high-frequency steam consumption sample data and low-frequency steam consumption sample data includes: Performing a first-level decomposition on the historical steam consumption sample data to obtain first high-frequency steam consumption sample data and first low-frequency steam consumption sample data; Performing a second-level decomposition on the first high-frequency steam consumption sample data to obtain second high-frequency steam consumption sample data and second low-frequency steam consumption sample data; Performing a third-level decomposition on the second high-frequency steam consumption sample data to obtain third high-frequency steam consumption sample data and third low-frequency steam consumption sample data; Accordingly, the high-frequency steam consumption sample data and the low-frequency steam consumption sample data are respectively input into the steam consumption prediction model to be trained, and the steam consumption prediction results corresponding to the high-frequency steam consumption sample data and the steam consumption prediction results corresponding to the low-frequency steam consumption sample data are obtained, including: Inputting the first low-frequency steam consumption sample data into the steam consumption prediction model to be trained to obtain a steam consumption prediction result corresponding to the first low-frequency steam consumption sample data; Inputting the second low-frequency steam consumption sample data into the steam consumption prediction model to be trained to obtain a steam consumption prediction result corresponding to the second low-frequency steam consumption sample data; Inputting the third low-frequency steam consumption sample data into the steam consumption prediction model to be trained to obtain a steam consumption prediction result corresponding to the third low-frequency steam consumption sample data; Inputting the third high-frequency steam consumption sample data into the steam consumption prediction model to be trained to obtain a steam consumption prediction result corresponding to the third high-frequency steam consumption sample data; Accordingly, the steam consumption prediction result corresponding to the high-frequency steam consumption sample data and the steam consumption prediction result corresponding to the low-frequency steam consumption sample data are subjected to inverse wavelet transformation to obtain the steam consumption prediction result corresponding to the historical steam consumption sample data, including: The steam consumption prediction results corresponding to the first low-frequency steam consumption sample data, the steam consumption prediction results corresponding to the second low-frequency steam consumption sample data, the steam consumption prediction results corresponding to the third low-frequency steam consumption sample data, and the steam consumption prediction results corresponding to the third high-frequency steam consumption sample data are inversely transformed to obtain steam consumption prediction results corresponding to the historical steam consumption sample data.

6. The method according to any one of claims 1 to 5, characterized in that: The steam consumption prediction model is a deep learning model based on time series prediction.

7. An energy demand forecasting device, characterized in that: include: A historical steam consumption data acquisition module is used to acquire historical steam consumption data of a target plant, wherein the historical steam consumption data includes the daily steam consumption of the plant; A steam consumption data wavelet decomposition module is used to perform wavelet decomposition on the historical steam consumption data to obtain high-frequency steam consumption data and low-frequency steam consumption data; A steam consumption prediction module, used to input the high-frequency steam consumption data and the low-frequency steam consumption data into a pre-trained steam consumption prediction model, respectively, to obtain a high-frequency steam consumption prediction result corresponding to the high-frequency steam consumption data and a low-frequency steam consumption prediction result corresponding to the low-frequency steam consumption data; The high- and low-frequency inverse wavelet transform module is used to perform inverse wavelet transform on the high-frequency steam consumption prediction result and the low-frequency steam consumption prediction result to obtain the target steam consumption prediction result of the target plant.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the energy demand forecasting method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the energy demand forecasting method according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the energy demand forecasting method according to any one of claims 1 to 6.

Images