Green hydrogen production prediction scheduling system and equipment

By using the green hydrogen production prediction and scheduling system, combined with big data models and scheduling optimization modules, the problem of high green hydrogen production costs has been solved, achieving real-time optimization and cost reduction.

CN119047736APending Publication Date: 2024-11-29THREE GORGES GRP YUNNAN ENERGY INVESTMENT CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411022069.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-29
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

The operation and management of green hydrogen production plants are difficult to optimize, resulting in high production costs and unclear electricity and hydrogen supply, which leads to production inconveniences.

Method used

A green hydrogen production prediction and scheduling system is adopted, which combines big data models to predict hydrogen consumption, formulate detailed production plans, optimize hydrogen production capacity, and reduce production costs.

Benefits of technology

It enables real-time optimization and cost reduction of the green hydrogen production process, improves production efficiency and prediction accuracy, and supports multi-source data access and flexible expansion.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119047736A_ABST
    Figure CN119047736A_ABST
Patent Text Reader

Abstract

The invention provides a green hydrogen production prediction scheduling system, and the system comprises a data collection module which is used for collecting the hydrogen selling quantity and hydrogen energy vehicle data in real time; the prediction model module is used for predicting the future hydrogen production demand quantity according to the data acquired by the data acquisition module in real time and historical data; and the scheduling optimization module obtains the hydrogen production demand, the electricity price and the relationship between the carbon transaction and the hydrogen production cost in the future by establishing a cost calculation model, and formulates an optimal scheduling scheme to enable the hydrogen production cost to be the lowest. According to the invention, data is collected and processed in real time, and a prediction and scheduling scheme is adjusted according to latest data; through the scheduling optimization module, optimization and collaboration of the green hydrogen production process are realized, the production efficiency is improved, and the cost is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of integrated energy production, and in particular to a green hydrogen production prediction and scheduling system and equipment. Background Art

[0002] my country is facing the arduous task of energy revolution and industrial restructuring. The development of the hydrogen energy industry is not only an important part of my country's energy security strategy, but also an important way to optimize the energy consumption structure and realize the interconnection of power grids and gas grids. The development of the hydrogen energy industry can also effectively drive the development of high-end equipment manufacturing industries such as new materials, new energy vehicles, and hydrogen storage and transportation. It is of great significance for my country to accelerate the adjustment of industrial structure and achieve high-quality development. The integration of new energy vehicles and big data is a general trend and a model of the deep integration of industrialization and informatization. Intelligent new energy vehicles based on big data will be the strategic focus of the transformation and upgrading of my country's automobile industry.

[0003] At present, the production of green hydrogen relies on the electrolysis of water. Due to the imperfect application scenarios in the domestic market and the fact that the production of green hydrogen requires a large amount of electricity, the operation and management of green hydrogen production plants is difficult in this situation where the identities of electricity consumption and hydrogen supply are unclear. Summary of the invention

[0004] In response to the problems existing in the prior art, a green hydrogen production prediction and scheduling system and equipment are provided. The system combines the big data model to predict the hydrogen consumption, and formulates a detailed production plan based on the electricity consumption period to adjust the corresponding hydrogen preparation power, thereby optimizing and reducing the green hydrogen production cost.

[0005] The first aspect of the present invention provides a green hydrogen production prediction and scheduling system, comprising:

[0006] Data collection module, used to collect hydrogen sales quantity and hydrogen vehicle data in real time;

[0007] The prediction model module predicts the future demand for hydrogen production based on the real-time data collected by the data acquisition module and historical data;

[0008] The scheduling optimization module establishes a cost estimation model to obtain the relationship between future hydrogen production demand, electricity prices, carbon trading and unit hydrogen production costs, and formulates the optimal scheduling plan to minimize the unit hydrogen production cost.

[0009] As a preferred solution, it also includes a data processing module for clarifying, integrating and standardizing the real-time collected hydrogen sales quantity and hydrogen vehicle data.

[0010] As a preferred solution, it also includes a user interface module, which provides a human-computer interaction interface for viewing real-time data, prediction results and scheduling plans.

[0011] As a preferred solution, the prediction model module realizes the prediction of future hydrogen production demand based on machine learning or deep learning algorithm.

[0012] As a preferred solution, the specific working process of the prediction model module includes:

[0013] Determine the forecast data of hydrogen production for the next month through big data deep learning of historical data;

[0014] The hydrogen production forecast data for the next month is corrected based on the hydrogen production data for the current month to obtain the actual hydrogen production demand for the next month.

[0015] As a preferred solution, the hydrogen production forecast data for the next month is corrected according to the hydrogen production data for the current month, specifically including:

[0016] The forecasted hydrogen production data for the next month is recorded as A, the hydrogen production data for the current month is recorded as B, and the actual hydrogen production demand for the next month is recorded as C;

[0017] If BA>0, and BA<0.5*A, then C=A+(BA)*0.5;

[0018] If BA>0, and BA>0.5*A, then C=B*1.05;

[0019] If BA<0, and AB<0.5*B, then C=B+(AB)*0.5;

[0020] If BA<0, and AB>0.5*B, then C=A*0.95.

[0021] As a preferred solution, the scheduling optimization module determines whether the future hydrogen production demand exceeds the maximum production threshold or the minimum production threshold before formulating the scheduling plan. If it exceeds, production is directly carried out according to the maximum production threshold or the minimum production threshold. If it does not exceed, a scheduling plan is formulated based on the unit hydrogen production cost.

[0022] As a preferred solution, the cost estimation model is established to obtain the relationship between future hydrogen production demand, electricity price, carbon trading and hydrogen production cost, which specifically includes:

[0023] Obtain operating costs;

[0024] Obtain the power during peak hours, off-peak hours, normal hours, peak hours and maximum power, and calculate the electricity price cost based on the electricity prices during peak hours, off-peak hours, normal hours and peak hours of the month;

[0025] Based on the production demand data of the month, the carbon trading amount of the month is simulated and calculated through the plug-in carbon trading software;

[0026] The unit hydrogen production cost for the month is calculated based on operating costs, electricity prices and carbon trading amounts.

[0027] A second aspect of the present invention proposes a device, including the green hydrogen production prediction and scheduling system described in the first aspect.

[0028] Compared with the prior art, the beneficial effects of adopting the above technical solution are:

[0029] (1) Real-time: The system can collect and process data in real time and adjust forecasting and scheduling plans based on the latest data.

[0030] (2) Accuracy: Use advanced forecasting algorithms and models to improve forecast accuracy and reliability.

[0031] (3) Optimization: Through the scheduling optimization module, the green hydrogen production process can be optimized and coordinated to improve production efficiency and reduce costs.

[0032] (4) Scalability: The system supports multi-source data access and multiple prediction algorithms, and has good scalability and flexibility.

[0033] (5) Cost estimation can be realized: the electricity price and carbon trading calculation modules are introduced to realize the dual functions of production scheduling and cost estimation. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 Schematic diagram of the green hydrogen production prediction and scheduling system proposed in the present invention.

[0035] Figure 2 This is a schematic diagram of predicting future hydrogen production demand in one embodiment of the present invention.

[0036] Figure 3 It is a schematic diagram of scheduling optimization in one embodiment of the present invention. DETAILED DESCRIPTION

[0037] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar modules or modules with the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be construed as limitations on the present application. On the contrary, the embodiments of the present application include all changes, modifications and equivalents that fall within the spirit and connotation of the appended claims.

[0038] In order to achieve green hydrogen production prediction and establish the lowest cost scheduling plan, the embodiment of the present invention proposes a green hydrogen production prediction and scheduling system, which mainly includes data collection, prediction model module and scheduling optimization module. Figure 1 , specifically:

[0039] The data collection module is mainly used to collect the hydrogen sales quantity and hydrogen vehicle data in real time. In this embodiment, the data collected mainly include the hydrogen refueling volume (i.e., hydrogen sales quantity) and hydrogen usage measurement data of hydrogen users in a certain city within one year. Among them, the hydrogen sales quantity can be obtained from the hydrogen production plant, and the hydrogen vehicle data can be obtained through the AI ​​camera arranged at the hydrogen refueling station.

[0040] The prediction model module is mainly used to predict the future hydrogen production demand based on the real-time data collected by the data acquisition module and historical data.

[0041] The scheduling optimization module establishes a cost estimation model to obtain the relationship between future hydrogen production demand, electricity prices, carbon trading and unit hydrogen production costs, and formulates the optimal scheduling plan to minimize the unit hydrogen production cost.

[0042] The specific working process of each module is further explained below.

[0043] The prediction model module mainly combines the big data model to realize the prediction of future hydrogen production demand. In this embodiment, it is preferably implemented by machine learning or deep learning algorithm.

[0044] Please refer to Figure 2 The specific working process of the prediction model module includes: determining the hydrogen production forecast data for the next month through big data deep learning of historical data; correcting the hydrogen production forecast data for the next month based on the hydrogen production data of the current month to obtain the actual hydrogen production demand for the next month.

[0045] The correction process is as follows:

[0046] The forecast data of hydrogen production for the next month is recorded as A, the hydrogen production data for the current month is recorded as B, and the actual hydrogen production demand for the next month is recorded as C;

[0047] If BA>0, and BA<0.5*A, then C=A+(BA)*0.5;

[0048] If BA>0, and BA>0.5*A, then C=B*1.05;

[0049] If BA<0, and AB<0.5*B, then C=B+(AB)*0.5;

[0050] If BA<0, and AB>0.5*B, then C=A*0.95.

[0051] At this point, the hydrogen production demand for the next month can be accurately predicted.

[0052] At present, some regions produce hydrogen through electricity consumption, and the electricity price policy implements the capacity demand policy. After the production system reaches p power for a period of time, the capacity (demand) electricity fee is calculated for the whole month according to p power. For this reason, a suitable production control system is needed to reduce the production power and further reduce the capacity (demand) electricity fee under the condition of meeting the hydrogen production demand, so as to achieve the purpose of optimizing the hydrogen production cost. At the same time, hydrogen energy participating in carbon trading can further reduce production costs, and green hydrogen can be integrated into carbon trading by adding corresponding calculation models.

[0053] Based on this, the scheduling optimization module proposed in this embodiment balances the relationship between green hydrogen review and cost by establishing a cost calculation model to formulate the optimal scheduling plan.

[0054] Please refer to Figure 3 Before formulating the optimal scheduling plan, it is necessary to determine whether the future hydrogen production demand exceeds the maximum production threshold or the minimum production threshold. If it exceeds, production will be carried out directly according to the maximum production threshold or the minimum production threshold. If it does not exceed, a scheduling plan will be formulated based on the unit hydrogen production cost.

[0055] In this embodiment, the relationship between operating costs, electricity price costs, and carbon trading amounts and unit hydrogen production costs is mainly considered.

[0056] First, the operating cost L Y It can be directly obtained according to the actual situation.

[0057] Secondly, for electricity price cost: after obtaining the production demand data C of the current month, we can get the power P at peak time, valley time, normal time and peak time. 1 , P 2 , P 3 , P 4 And the maximum power P M At this time, the electricity price cost can be determined by combining the electricity price of the month. Specifically including:

[0058] Peak electricity price L D1 =P 1 *Peak electricity prices;

[0059] Off-peak electricity price cost L D2 =P 2 *Off-peak electricity prices;

[0060] Normal electricity price cost L D3 =P 3 *Usually electricity prices;

[0061] Peak electricity price cost L D4 =P 4 *Peak electricity prices;

[0062] Maximum power capacity demand price cost L DM =PM *Capacity demand electricity price

[0063] The total cost of electricity price L for the month can be obtained D =L D1 +L D2 +L D3 +L D4 +L DM .

[0064] According to the production demand data C of the month and the power P during peak hours, valley hours, normal hours and peak hours 1 , P 2 , P 3 , P 4 , the production time of each time end can be planned. The specific calculation formula is as follows:

[0065] C=P 1 *T 1 +P 2 *T 2 +P 3 *T 3 +P 4 *T 4

[0066] Among them, T 1 、T 2 、T 3 、T 4 The production time is peak time, off-peak time, normal time and peak time respectively. Therefore, the electricity price cost can be reduced by adjusting the production time and power.

[0067] Finally, for the carbon trading amount, in this embodiment, the monthly trading amount L is calculated by simulating the production demand data of the month through the plug-in carbon trading software. C .

[0068] According to the above calculation, the monthly unit hydrogen production cost L = (L D -L C +L Y ) / C.

[0069] The scheduling optimization module can adjust the production plan to minimize the unit hydrogen production cost by looking at the relationship between the unit hydrogen production cost and operating cost, the electricity price cost and the carbon trading amount. The specific constraint formula is as follows:

[0070] C≦P 1 *T 1 +P 2 *T 2 +P 3 *T 3 +P 4 *T 4

[0071] L min =(L D -L C+ L Y ) / C

[0072] Among them, L min For the lowest unit hydrogen production cost for the month, the output at this time is: P1, T1, P2, T2, P3, T3, P4, T4, C, and the production plan is completed.

[0073] In order to ensure the accuracy of the data, the green hydrogen production prediction and scheduling system also includes a data processing module, which is used to clarify, integrate and standardize the real-time collected hydrogen sales quantity and hydrogen vehicle data.

[0074] Similarly, for ease of use, the green hydrogen production prediction and scheduling system also includes a user interface module that provides a human-computer interaction interface for viewing real-time data, prediction results and scheduling plans.

[0075] The green hydrogen production prediction and scheduling system proposed in the present invention has the following advantages:

[0076] (1) Real-time: The system can collect and process data in real time and adjust forecasting and scheduling plans based on the latest data.

[0077] (2) Accuracy: Use advanced forecasting algorithms and models to improve forecast accuracy and reliability.

[0078] (3) Optimization: Through the scheduling optimization module, the green hydrogen production process can be optimized and coordinated to improve production efficiency and reduce costs.

[0079] (4) Scalability: The system supports multi-source data access and multiple prediction algorithms, and has good scalability and flexibility.

[0080] (5) Cost estimation can be realized: the electricity price and carbon trading calculation modules are introduced to realize the dual functions of production scheduling and cost estimation.

[0081] Example 1

[0082] This embodiment proposes a green hydrogen production prediction and scheduling system, including:

[0083] Data collection module, used to collect hydrogen sales quantity and hydrogen vehicle data in real time;

[0084] The prediction model module predicts the future demand for hydrogen production based on the real-time data collected by the data acquisition module and historical data;

[0085] The scheduling optimization module establishes a cost estimation model to obtain the relationship between future hydrogen production demand, electricity prices, carbon trading and unit hydrogen production costs, and formulates the optimal scheduling plan to minimize the unit hydrogen production cost.

[0086] Example 2

[0087] Based on Example 1, it also includes a data processing module for clarifying, integrating and standardizing the real-time collected hydrogen sales quantity and hydrogen vehicle data.

[0088] Example 3

[0089] Based on Example 2, it also includes a user interface module, which provides a human-computer interaction interface for viewing real-time data, prediction results and scheduling plans.

[0090] Example 4

[0091] Based on Example 3, the prediction model module realizes the prediction of future hydrogen production demand based on machine learning or deep learning algorithm.

[0092] Example 5

[0093] Based on Example 4, the specific working process of the prediction model module includes:

[0094] Determine the forecast data of hydrogen production for the next month through big data deep learning of historical data;

[0095] The hydrogen production forecast data for the next month is corrected based on the hydrogen production data for the current month to obtain the actual hydrogen production demand for the next month.

[0096] Example 6

[0097] On the basis of Example 5, the hydrogen production forecast data for the next month is corrected according to the hydrogen production data of the current month, specifically including:

[0098] The forecasted hydrogen production data for the next month is recorded as A, the hydrogen production data for the current month is recorded as B, and the actual hydrogen production demand for the next month is recorded as C;

[0099] If BA>0, and BA<0.5*A, then C=A+(BA)*0.5;

[0100] If BA>0, and BA>0.5*A, then C=B*1.05;

[0101] If BA<0, and AB<0.5*B, then C=B+(AB)*0.5;

[0102] If BA<0, and AB>0.5*B, then C=A*0.95.

[0103] Example 7

[0104] Based on Example 6, before formulating a scheduling plan, the scheduling optimization module determines whether the future hydrogen production demand exceeds the maximum production threshold or the minimum production threshold. If it exceeds, production is directly carried out according to the maximum production threshold or the minimum production threshold. If it does not exceed, a scheduling plan is formulated based on the unit hydrogen production cost.

[0105] Example 8

[0106] On the basis of Example 7, the cost estimation model is established to obtain the relationship between future hydrogen production demand, electricity price, carbon trading and hydrogen production cost, specifically including:

[0107] Obtain operating costs;

[0108] Obtain the power during peak hours, off-peak hours, normal hours, peak hours and maximum power, and calculate the electricity price cost based on the electricity prices during peak hours, off-peak hours, normal hours and peak hours of the month;

[0109] Based on the production demand data of the month, the carbon trading amount of the month is simulated and calculated through the plug-in carbon trading software;

[0110] The unit hydrogen production cost for the month is calculated based on operating costs, electricity prices and carbon trading amounts.

[0111] Example 9

[0112] This embodiment proposes a device, including the green hydrogen production prediction and scheduling system described in any one of Embodiments 1 to 8.

[0113] The present invention can be better implemented through Examples 1 to 9.

[0114] For those skilled in the art, the specific meanings of the above terms in the present invention can be understood in specific situations; the drawings in the embodiments are used to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0115] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in the field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A green hydrogen production prediction and scheduling system, characterized in that: include: Data collection module, used to collect hydrogen sales quantity and hydrogen vehicle data in real time; The prediction model module predicts the future demand for hydrogen production based on the real-time data collected by the data acquisition module and historical data; The scheduling optimization module establishes a cost estimation model to obtain the relationship between future hydrogen production demand, electricity prices, carbon trading and unit hydrogen production costs, and formulates the optimal scheduling plan to minimize the unit hydrogen production cost.

2. The green hydrogen production prediction and scheduling system according to claim 1, characterized in that: It also includes a data processing module for clarifying, integrating and standardizing the real-time collected hydrogen sales quantity and hydrogen vehicle data.

3. The green hydrogen production prediction and scheduling system according to claim 1, characterized in that: It also includes a user interface module that provides a human-computer interaction interface for viewing real-time data, forecast results and scheduling plans.

4. The green hydrogen production prediction and scheduling system according to claim 1, characterized in that: The prediction model module realizes the prediction of future hydrogen production demand based on machine learning or deep learning algorithms.

5. The green hydrogen production prediction and scheduling system according to any one of claims 1 to 4, characterized in that: The specific working process of the prediction model module includes: Determine the forecast data of hydrogen production for the next month through big data deep learning of historical data; The hydrogen production forecast data for the next month is corrected based on the hydrogen production data for the current month to obtain the actual hydrogen production demand for the next month.

6. The green hydrogen production prediction and scheduling system according to claim 5, characterized in that: The correction of the hydrogen production forecast data for the next month based on the hydrogen production data for the current month specifically includes: The forecasted hydrogen production data for the next month is recorded as A, the hydrogen production data for the current month is recorded as B, and the actual hydrogen production demand for the next month is recorded as C; If BA>0, and BA<0.5*A, then C=A+(BA)*0.5; If BA>0, and BA>0.5*A, then C=B*1.05; If BA<0, and AB<0.5*B, then C=B+(AB)*0.5; If BA<0, and AB>0.5*B, then C=A*0.

95.

7. The green hydrogen production prediction and scheduling system according to claim 1, characterized in that: Before formulating a scheduling plan, the scheduling optimization module determines whether the future hydrogen production demand exceeds the maximum production threshold or the minimum production threshold. If it exceeds, production is directly carried out according to the maximum production threshold or the minimum production threshold. If it does not exceed, a scheduling plan is formulated based on the unit hydrogen production cost.

8. The green hydrogen production prediction and scheduling system according to claim 1 or 7, characterized in that: The cost estimation model is established to obtain the relationship between future hydrogen production demand, electricity price, carbon trading and hydrogen production cost, specifically including: Obtain operating costs; Obtain the power during peak hours, off-peak hours, normal hours, peak hours and maximum power, and calculate the electricity price cost based on the electricity prices during peak hours, off-peak hours, normal hours and peak hours of the month; Based on the production demand data of the month, the carbon trading amount of the month is simulated and calculated through the plug-in carbon trading software; The unit hydrogen production cost for the month is calculated based on operating costs, electricity prices and carbon trading amounts.

9. A device, characterized in that: Comprising the green hydrogen production prediction and scheduling system as described in any one of claims 1 to 8.