Model-based multi-scene optimization method and device, storage medium and electronic equipment

Abstract

The invention relates to a model-based multi-scene optimization method and device, a storage medium and electronic equipment, and the method comprises the steps: collecting market operation data of a target industrial chain, and setting a multi-scene operation parameter based on the variation of the market operation data; for each scene operation parameter, adjusting a constraint value corresponding to each constraint parameter in the obtained constraint parameter set according to a target industry chain mapping relation library and a change value of the scene operation parameter, an associated scene operation parameter value corresponding to each associated scene operation parameter in an associated scene operation parameter set obtained by querying the scene operation parameter mapping relation library is adjusted; and according to the number of the scene operation parameters, the virtualized crude oil industry chain optimization model is the number of optimization sub-models, and according to the adjusted constraint value and the associated scene operation parameter value corresponding to each scene operation parameter, the optimization sub-models are operated in parallel, and an operation optimization scheme corresponding to each scene operation parameter is obtained. The accuracy of optimizing the operation scheme can be improved.

Description

Technical Field

[0001] This invention relates to the field of digital industry chain technology, and in particular to a model-based multi-scenario optimization method, apparatus, storage medium, and electronic device. Background Technology

[0002] The industrial chain encompasses the entire process from upstream raw material production to midstream product processing and downstream end-market sales, and is a crucial component of the energy industry. Data-driven approaches are a computing paradigm driven by data. By constructing an integrated optimization model of the entire industrial chain (the industrial chain model), and leveraging its powerful data processing capabilities and algorithms, it analyzes and processes massive amounts of data, extracting valuable information to obtain optimized operational plans containing data patterns and predictive trends to support decision-making.

[0003] When market conditions and plans change, it is necessary to construct multi-scenario solutions to address these changes. This allows the industry chain model to analyze and predict based on these multi-scenario solutions, thereby obtaining optimized operational plans for each scenario. However, current integrated industry chain optimization models require manual calculation of scenario parameters (variable indicators) based on the market conditions and historical experience corresponding to each scenario. The parameters associated with these variable indicators are then deployed to hundreds of nodes within the integrated industry chain optimization model to complete the model calculations and obtain optimized operational plans. However, this method, which involves manually matching parameters associated with changing indicators, requires traversing each node and setting corresponding associated parameter values. Due to the large number of nodes and the numerous constraints between the associated parameters of each node, taking the sales end of the crude oil industry chain model as an example, for a single scenario calculation parameter, it is necessary to adjust more than 2,000 parameters (indicators) across various sales methods such as retail, wholesale, exchange, and special sales for nearly 100 major crude oils and more than 120 processing indicators from 27 refineries to more than 10 types of oil products in 31 provinces and cities. This results in long debugging time and low efficiency. Furthermore, due to the omission of parameter values ​​during the process of traversing and setting the corresponding associated parameter values, the accuracy of the final output optimization operation plan will also be low. Summary of the Invention

[0004] In view of this, the present invention provides a model-based multi-scenario optimization method, apparatus, storage medium, and electronic device.

[0005] Specifically, the present invention is achieved through the following technical solution:

[0006] According to a first aspect of the present invention, a model-based multi-scenario optimization method is provided, the model-based multi-scenario optimization method comprising:

[0007] Collect market operation data of the target industry chain. If the change in the market operation data is greater than the change threshold, determine multi-scenario calculation parameters based on the change in the market operation data. The market operation data includes data corresponding to multiple pre-set target indicators.

[0008] For each scenario operation parameter, the constraint parameter set mapped to each scenario operation parameter is obtained through a pre-stored target industry chain mapping relationship library, and the constraint value corresponding to each constraint parameter in the constraint parameter set is adjusted according to the change value of the scenario operation parameter.

[0009] For each scenario operation parameter, the associated scenario operation parameter set mapped by the scenario operation parameter is obtained through a pre-stored scenario operation parameter mapping relationship library. The associated scenario operation parameter value corresponding to each associated scenario operation parameter in the associated scenario operation parameter set is adjusted according to the change value of the scenario operation parameter.

[0010] Based on the number of scenario operation parameters, and using the crude oil industry chain optimization model, the virtualized crude oil industry chain optimization model consists of the number of optimization sub-models. The optimization sub-models are run in parallel according to the constraint values ​​and associated scenario operation parameter values ​​adjusted for each scenario operation parameter, and the operation optimization schemes corresponding to each scenario operation parameter are obtained respectively.

[0011] Optionally, if the change in market operation data of the target industry chain exceeds a threshold, multi-scenario calculation parameters are set based on the change in market operation data, including:

[0012] Collect market situation data of the target industry chain within a pre-set collection period;

[0013] For each preset target indicator, the maximum value corresponding to the target indicator in the market situation data is obtained. If the difference between the maximum value corresponding to any target indicator and the preset base value is greater than the change threshold set for the target indicator, based on the difference, the multi-scenario operation parameters corresponding to the target indicator are set. The scenario operation parameters are the market situation data corresponding to the target indicator with different values ​​assigned based on the difference.

[0014] Optionally, the process of collecting market operation data from the target industry chain, when the change in market operation data exceeds a pre-set threshold, involves setting multi-scenario calculation parameters based on the change in market operation data, including:

[0015] Obtain the market adjustment plan for the target industry chain, and set the multi-scenario calculation parameters corresponding to the target indicators based on the change values ​​of the target indicators involved in the market adjustment plan.

[0016] Optionally, if the change in market operation data of the target industry chain exceeds a threshold, multi-scenario calculation parameters are set based on the change in market operation data, including:

[0017] Within a pre-set collection period, market data of the target industry chain is captured from the Internet. For each target indicator, the target indicator value corresponding to the target indicator in the market data is obtained. If the target indicator value exceeds the stored value range of the target indicator, the value closest to the target indicator value in the value range is updated based on the target indicator value. If the range difference of the updated value range is greater than the change threshold set for the target indicator, the multi-scenario calculation parameters corresponding to the target indicator are set based on the range difference.

[0018] Optionally, obtaining the scenario operation parameter mapping relationship library includes:

[0019] Input the pre-set set of input parameters into the crude oil industry chain optimization model to obtain the first set of output parameters contained in the optimized operation plan output by the crude oil industry chain optimization model;

[0020] By modifying the value of one target parameter in the input parameter set while keeping the values ​​of other parameters unchanged, and inputting it into the crude oil industry chain optimization model, a second output parameter set containing the optimized operation scheme output by the crude oil industry chain optimization model is obtained.

[0021] From the second output parameter set, obtain the model parameters that have changed relative to the first output parameter set. Based on the target parameter and the obtained changed model parameters, construct and store the scenario operation parameter mapping relationship library.

[0022] Optionally, adjusting the constraint value corresponding to each constraint parameter in the constraint parameter set based on the change value of the scenario calculation parameter includes:

[0023] For each constraint parameter in the constraint parameter set, the constraint value corresponding to the constraint parameter is updated according to the constraint value change rule of the constraint parameter, based on the change value of the scenario operation parameter and the constraint value change rule.

[0024] Optionally, the method further includes:

[0025] The optimization data corresponding to the operation optimization schemes for each scenario's calculation parameters are extracted separately. Based on the pre-set analysis strategy, the optimization data is statistically analyzed, and a multi-scenario scheme result report is generated based on the statistical and analysis results.

[0026] The model-based multi-scenario optimization method in this technical solution collects market operation data of the target industry chain. When the change in market operation data exceeds a pre-set change threshold, multi-scenario calculation parameters are set based on the change in market operation data. The market operation data includes data corresponding to multiple pre-set target indicators. For each scenario calculation parameter, a set of constraint parameters mapped to that scenario calculation parameter is obtained according to a pre-stored target industry chain mapping relationship library. The constraint values ​​corresponding to each constraint parameter in the set of constraint parameters are adjusted according to the change value of the scenario calculation parameter. For each scenario calculation parameter, a set of associated scenario calculation parameters mapped to that scenario calculation parameter is obtained according to a pre-stored scenario calculation parameter mapping relationship library. The associated scenario calculation parameter values ​​corresponding to each associated scenario calculation parameter in the set of associated scenario calculation parameters are adjusted according to the change value of the scenario calculation parameter. Based on the number of scenario calculation parameters, the virtualized crude oil industry chain optimization model consists of the number of optimization sub-models. Based on the adjusted constraint values ​​and associated scenario calculation parameter values ​​corresponding to each scenario calculation parameter, the optimization sub-models are run in parallel to obtain the operation optimization scheme corresponding to each scenario calculation parameter. Each optimization sub-model operates on one scenario calculation parameter. In this way, by using market operation data to drive the setting of multi-scenario calculation parameters, and based on the pre-acquired target industry chain mapping relationship library and scenario calculation parameter mapping relationship library, the constraint parameters and related scenario calculation parameters corresponding to the scenario calculation parameters are obtained. Thus, based on the number of multi-scenario calculation parameter values, the crude oil industry chain optimization model is virtualized, and the corresponding optimization sub-model is obtained for parallel operation. This effectively reduces the omissions that are easily caused by manually searching for constraint parameters and related scenario calculation parameters based on scenario calculation parameters, and effectively improves the accuracy of the optimized operation plan output by the optimization sub-model.

[0027] According to a second aspect of the present invention, a model-based multi-scenario optimization apparatus is provided, the model-based multi-scenario optimization apparatus comprising:

[0028] The scenario calculation parameter determination module is used to collect market operation data of the target industry chain. If the change in the market operation data is greater than the change threshold, multiple scenario calculation parameters are set based on the change in the market operation data. The market operation data includes data corresponding to multiple pre-set target indicators.

[0029] The constraint value adjustment module is used to obtain the constraint parameter set mapped to each scenario operation parameter according to the pre-stored target industry chain mapping relationship library, and adjust the constraint value corresponding to each constraint parameter in the constraint parameter set according to the change value of the scenario operation parameter.

[0030] The parameter value adjustment module is used to obtain the associated scenario operation parameter set mapped to each scenario operation parameter according to the pre-stored scenario operation parameter mapping relationship library, and adjust the associated scenario operation parameter value corresponding to each associated scenario operation parameter in the associated scenario operation parameter set according to the change value of the scenario operation parameter.

[0031] The parallel computing module is used to virtualize the crude oil industry chain optimization model into a number of optimization sub-models based on the number of scenario computing parameters. Based on the constraint values ​​and associated scenario computing parameter values ​​adjusted for each scenario computing parameter, the optimization sub-models are run in parallel to obtain the operation optimization schemes corresponding to each scenario computing parameter. Each optimization sub-model runs one scenario computing parameter.

[0032] According to a third aspect of the present invention, a storage medium is provided having a computer program stored thereon, wherein when the program is executed by a processor, it implements the steps of the model-based multi-scenario optimization method in any possible implementation of the first aspect.

[0033] According to a fourth aspect of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the model-based multi-scenario optimization method in any possible implementation of the first aspect. Attached Figure Description

[0034] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0035] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0036] Figure 1 A flowchart illustrating a model-based multi-scenario optimization method provided in an embodiment of the present invention;

[0037] Figure 2 This is a schematic diagram of a model-based multi-scenario optimization device provided in an embodiment of the present invention;

[0038] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] In related technologies, the integrated optimization model for the entire industry chain, for multi-scenario solutions, requires manual adjustment based on the market situation and historical experience corresponding to each scenario. This involves manually setting the associated parameters of each variable indicator for each scenario and deploying them to hundreds of nodes within the integrated optimization model to complete the model calculation and obtain the optimized operation plan for that scenario. However, this method requires manual parameter tuning, which necessitates setting associated parameters for each node corresponding to the variable indicators. Due to the large number of nodes and the numerous constraints between indicators, the debugging time is long and inefficient. Furthermore, the accuracy of the final optimized operation plan can be low due to missed parameter values ​​during the iterative setting process. Additionally, since multiple scenarios need to be calculated, the integrated optimization model needs to be run sequentially for each scenario, resulting in long computation and result processing times.

[0041] To address the aforementioned issues, this embodiment provides a method for acquiring optimized operation schemes for a rapid multi-scenario optimization model that integrates the entire industry chain, in order to predict and evaluate the optimization performance under various scenarios. Specifically, by employing technologies such as data-driven approaches, multi-threaded concurrent processing, intelligent analysis, and visualization, and based on manually set or market-driven indicators, the method calculates scenario operation parameters for each production and sales node, including production and sales volume data and price data, thereby enabling rapid calculation and analysis of multi-scenario schemes based on a data-driven crude oil industry chain model.

[0042] See Figure 1 This invention provides a model-based multi-scenario optimization method, which may include the following steps:

[0043] S101. Collect market operation data of the target industry chain. If the change in market operation data is greater than the change threshold, the change is preset. Determine multi-scenario calculation parameters based on the change in market operation data. The market operation data includes data corresponding to multiple preset target indicators.

[0044] In this embodiment, the target industry chain is the entire crude oil industry chain. For details on constructing an integrated optimization model for the entire crude oil industry chain, please refer to relevant technical literature; details are omitted here. As an optional embodiment, market operation data of the target industry chain is collected. If the change in market operation data exceeds a pre-set change threshold, multi-scenario calculation parameters are set based on the change in market operation data, including:

[0045] Collect market situation data of the target industry chain within a pre-set collection period;

[0046] For each preset target indicator, the maximum value corresponding to the target indicator in the market situation data is obtained. If the difference between the maximum value corresponding to any target indicator and the preset base value is greater than the change threshold set for the target indicator, based on the difference, the multi-scenario operation parameters corresponding to the target indicator are set. The scenario operation parameters are the market situation data corresponding to the target indicator with different values ​​assigned based on the difference.

[0047] In this embodiment, if the difference between multiple target indicators is greater than the change threshold set for the corresponding target indicator, then each scenario calculation parameter includes different values ​​for the multiple target indicators.

[0048] In this embodiment, as another optional embodiment, market operation data of the target industry chain is collected. If the change in market operation data exceeds a preset change threshold, multi-scenario calculation parameters are set based on the change in market operation data, including:

[0049] Obtain the market adjustment plan for the target industry chain, and set the multi-scenario calculation parameters corresponding to the target indicators based on the change values ​​of the target indicators involved in the market adjustment plan.

[0050] In this embodiment, as another optional embodiment, market operation data of the target industry chain is collected. If the change in market operation data is greater than a preset change threshold, multi-scenario calculation parameters are set based on the change in market operation data, including:

[0051] Within a pre-set collection period, market data of the target industry chain is captured from the Internet using pre-set packet capture software. For each target indicator, the target indicator value corresponding to the target indicator in the market data is obtained. If the target indicator value exceeds the stored value range of the target indicator, the value closest to the target indicator value in the value range is updated based on the target indicator value. If the range difference of the updated value range is greater than the change threshold set for the target indicator, the multi-scenario calculation parameters corresponding to the target indicator are set based on the range difference.

[0052] In this embodiment, multi-scenario calculations and forecasts are performed based on market conditions and plans. Data, such as market situation data, market operation data, and market data, are analyzed. As an optional embodiment, data changes can be manually edited or analyzed using pre-set intelligent analysis algorithms to automatically generate multi-scenario calculation parameters. For example, when international crude oil prices fluctuate significantly, the intelligent analysis algorithm determines the magnitude of changes in refinery-processed crude oil prices based on actual changes in international crude oil price data. For example, when the Brent crude oil futures price drops by $6 per barrel from $81 per barrel (base price) to $75 per barrel, the intelligent analysis algorithm infers the impact on future oil prices based on the current price volatility, such as a decrease of $4 per barrel, a decrease of $2 per barrel, or a decrease of $6 per barrel. Based on this, it sets multiple scenario calculation parameters. The first scenario parameter corresponds to a decrease of $4 per barrel, the second scenario parameter to a decrease of $2 per barrel, and the third scenario parameter to a decrease of $6 per barrel. The base scenario is set to maintain the predicted oil price unchanged. The algorithm then predicts optimized operational plans for the first scenario parameter (a decrease of $4 per barrel), the third scenario parameter (a decrease of $6 per barrel), and the second scenario parameter (a decrease of $2 per barrel), thus forming three scenario calculation parameters. These parameters are then used in subsequent steps to calculate the processing prices of different crude oils for all refineries according to the pricing rules for domestically produced crude oil, mutually supplied crude oil, and imported crude oil.

[0053] In this embodiment, the integrated optimization model of the entire industry chain is used as an example of the crude oil industry chain optimization model. This crude oil industry chain includes three main links (scenarios): crude oil production, processing, and product sales. Taking the product sales link as an example, the domestic sales link includes, but is not limited to: gasoline retail sales (gas station retail), gasoline wholesale sales (sales to large customers), diesel retail sales, and diesel wholesale sales. As an optional embodiment, three scenarios are set for the above-mentioned crude oil industry chain, and the corresponding scenario calculation parameters are as follows: The first scenario calculation parameter is set to: increase diesel wholesale sales by 5%; the second scenario calculation parameter is set to: decrease diesel wholesale sales by 5%; the third scenario calculation parameter is set to: reduce diesel retail price by 200 yuan / ton and increase sales by 5%, etc. For each scenario calculation parameter, operations such as adding, modifying, and deleting are supported. For example, taking the calculation parameters of the refined oil sales end as an example, if the diesel sales situation in the autumn market is good, the intelligent analysis algorithm predicts an increase of 10% in diesel wholesale sales, and can automatically generate a series of scenario calculation parameters between 1% and 10%.

[0054] Table 1 is a schematic table of multi-scenario operation parameter settings.

[0055] Table 1

[0056]

[0057]

[0058] S102. For each scenario operation parameter, obtain the constraint parameter set mapped to each scenario operation parameter through the pre-stored target industry chain mapping relationship library, and adjust the constraint value corresponding to each constraint parameter in the constraint parameter set according to the change value of the scenario operation parameter.

[0059] S103. For each scenario operation parameter, obtain the associated scenario operation parameter set mapped by each scenario operation parameter through the pre-stored scenario operation parameter mapping relationship library, and adjust the associated scenario operation parameter value corresponding to each associated scenario operation parameter in the associated scenario operation parameter set according to the change value of the scenario operation parameter.

[0060] In this embodiment, a model constraint function containing the scenario calculation parameters is obtained from the model constraint function of the crude oil industry chain optimization model, and the value range of the constraint parameters in the obtained model constraint function is adjusted accordingly.

[0061] In this embodiment, each scenario calculation parameter corresponds to a target index, and the index value corresponding to the scenario calculation parameter is split across all the corresponding constraint nodes. For example, for the scenario where the sales volume of pure diesel fuel increases by 5%, the crude oil industry chain optimization model proportionally adjusts more than 400 constraints on the sales volume of pure diesel fuel in the sales volume, adjusting the maximum value to 1.05 times the original value.

[0062] In this embodiment, as an optional embodiment, obtaining the scenario operation parameter mapping relationship library includes:

[0063] Input the pre-set set of input parameters into the crude oil industry chain optimization model to obtain the first set of output parameters contained in the optimized operation plan output by the crude oil industry chain optimization model;

[0064] By modifying the value of one target parameter in the input parameter set while keeping the values ​​of other parameters unchanged, and inputting it into the crude oil industry chain optimization model, a second output parameter set containing the optimized operation scheme output by the crude oil industry chain optimization model is obtained.

[0065] From the second output parameter set, obtain the model parameters that have changed relative to the first output parameter set. Based on the target parameter and the obtained changed model parameters, construct and store the scenario operation parameter mapping relationship library.

[0066] In this embodiment, the scenario calculation parameter is one of the model parameters. Taking the integrated crude oil industry chain model as an example, the model parameters include, but are not limited to: crude oil purchase quantity parameters, refined oil production parameters, refining minor product parameters, chemical product parameters, provincial and municipal parameters, refined oil grade parameters, refined oil sales method parameters, and oil quantity upper and lower limit parameters and price parameters. For example, taking the oil price parameter as the scenario calculation parameter corresponding to the target indicator, if the oil price increases by 5%, the integrated crude oil industry chain model (crude oil industry chain optimization model) obtains the constraint parameter set of the oil price parameter mapping based on the pre-stored target industry chain mapping relationship library, thereby automatically obtaining more than 400 constraint parameters for more than 10 grades in 31 provinces and cities, and updating the upper limit value of each constraint parameter to 1.05 times the original value.

[0067] Crude oil procurement parameters include, but are not limited to: upper limit parameters, lower limit parameters, and procurement price parameters. As an optional embodiment, crude oil includes, but is not limited to, multiple major categories such as self-produced crude oil, mutually supplied crude oil, and imported crude oil. The self-produced crude oil category can be further divided into multiple subcategories, such as Daqing oil. For the Daqing oil subcategory, the corresponding procurement quantity parameters include, but are not limited to: minimum oil procurement value, maximum oil procurement value, and procurement price. As an optional embodiment, self-produced crude oil involves multiple conventionally processed crude oils from multiple refineries.

[0068] The parameters for refined oil production include, but are not limited to, the upper and lower limits of gasoline, kerosene and diesel production for multiple enterprises, the upper and lower limits of diesel-gasoline ratio (diesel production / gasoline production), and the upper and lower limits of refined oil yield (refined oil production / crude oil processing volume).

[0069] For parameters of minor oil refining products, including but not limited to: the upper and lower limits of production volume and sales price of specialty products such as asphalt, paraffin wax, and lubricating oil;

[0070] In this embodiment, the provincial and municipal parameters include 31 provinces and municipalities such as Heilongjiang, Gansu, Sichuan, Guangdong, Beijing, and Tianjin;

[0071] In this embodiment, the refined oil grade parameters include, but are not limited to, 14 specific grades such as 92# gasoline, 95# gasoline, 0# diesel, and -35# diesel;

[0072] In this embodiment, the sales methods include, but are not limited to, four methods: retail, wholesale, special sales, and exchange. The sales prices of different sales methods correspond to different arrival rates and calculation rules.

[0073] In this embodiment, as an optional embodiment, adjusting the constraint value corresponding to each constraint parameter in the constraint parameter set based on the change value of the scenario calculation parameter includes:

[0074] For each constraint parameter in the constraint parameter set, the constraint value corresponding to the constraint parameter is updated according to the constraint value change rule of the constraint parameter, based on the change value of the scenario operation parameter and the constraint value change rule.

[0075] In this embodiment, constraint parameters can be configured with constraint value adjustment rules that adjust the constraint values ​​according to changes in the operation parameters of each scenario. Similarly, for associated scenario operation parameters, associated value adjustment rules can be configured to adjust the associated value according to changes in the operation parameters of the scenario.

[0076] S104. Based on the number of scenario operation parameters, the virtualized crude oil industry chain optimization model consists of the number of optimization sub-models. The optimization sub-models are run in parallel according to the constraint values ​​and associated scenario operation parameter values ​​adjusted for each scenario operation parameter. Each optimization sub-model runs one scenario operation parameter and obtains the operation optimization scheme corresponding to each scenario operation parameter.

[0077] The virtualized crude oil industry chain optimization model, which refers to the number of optimization sub-models, should be understood as virtualizing the crude oil industry chain optimization model into multiple optimization sub-models, with the number of optimization sub-models being equal to the number of scenario operation parameters.

[0078] In this embodiment, N scenario models (optimized sub-models) are generated based on data-driven methods, where N is a natural number greater than 1. The number of model parameters in each optimized sub-model is the same as that in the crude oil industry chain optimization model, and each optimized sub-model is a copy of the crude oil industry chain optimization model. In this embodiment, each scenario calculation parameter corresponds to an optimized sub-model containing approximately 2000 model parameters. Each optimized sub-model is assigned a different identifier and saved as a calculation model.

[0079] In this embodiment, each scenario model is computed in parallel. As an optional embodiment, the computation logs of all scenario models are displayed in real time.

[0080] In this embodiment, after the scenario model completes the calculation, the calculation results are automatically saved, and the operational optimization plan data of the scenario model are stored sequentially to avoid data entry conflicts.

[0081] In this embodiment, as an optional embodiment, the method further includes:

[0082] Record the computation logs of the optimized sub-model running in parallel.

[0083] In this embodiment, by recording the calculation log, the final calculation log can be viewed, and the results of the multi-scenario solution can be preliminarily checked.

[0084] In this embodiment, as another optional embodiment, the method further includes:

[0085] The optimization data corresponding to the operation optimization schemes for each scenario's calculation parameters are extracted separately. Based on the pre-set analysis strategy, the optimization data is statistically analyzed, and a multi-scenario scheme result report is generated based on the statistical and analysis results.

[0086] In this embodiment, by performing data statistics and analysis on the optimization data in each operational optimization plan, a multi-scenario plan result report is automatically generated. As an optional embodiment, the multi-scenario plan result report includes, but is not limited to: a multi-scenario plan result comparison table, a Business Intelligence (BI) display report, and a multi-scenario plan analysis report. Thus, by combining the BI display report and the multi-scenario plan analysis report, adjustment strategies for production and operation in the industrial chain can be proposed.

[0087] The data-driven multi-scenario rapid calculation method for the industry chain model provided in this embodiment can quickly set model parameters according to changes in market conditions. It can quickly and automatically debug and model detailed parameters of the industry chain, which can greatly improve the response speed of the industry chain model to market changes. It can effectively reduce the omissions that are easily caused by manually finding constraint parameters and related scenario calculation parameters based on scenario calculation parameters, and effectively improve the accuracy of the optimized operation plan output by the optimized sub-model. At the same time, the data-driven decomposition of parameters of each node avoids the errors that may occur in manual operation. Furthermore, the scenario parameters of multiple industry chain models are directly established, reducing the space occupation caused by the overall model replication. Moreover, the calculation tasks that need to be completed sequentially are carried out simultaneously, and the multi-scenario scheme is used for parallel calculation, which improves the computational efficiency. In addition, the results of the operation optimization scheme are automatically compared and analyzed and displayed on the page, which improves the intelligence level of industry chain optimization.

[0088] Based on the same inventive concept, such as Figure 2 As shown, this embodiment of the invention also provides a model-based multi-scenario optimization device, the device comprising:

[0089] The scenario calculation parameter determination module is used to collect market operation data of the target industry chain. If the change in the market operation data is greater than the pre-set change threshold, multiple scenario calculation parameters are set based on the change in the market operation data. The market operation data includes data corresponding to multiple pre-set target indicators.

[0090] In this embodiment, as an optional embodiment, the scenario calculation parameter determination module is specifically used for:

[0091] Collect market situation data of the target industry chain within a pre-set collection period;

[0092] For each preset target indicator, the maximum value corresponding to the target indicator in the market situation data is obtained. If the difference between the maximum value corresponding to any target indicator and the preset base value is greater than the change threshold set for the target indicator, based on the difference, the multi-scenario operation parameters corresponding to the target indicator are set. The scenario operation parameters are the market situation data corresponding to the target indicator with different values ​​assigned based on the difference.

[0093] In this embodiment, as another optional embodiment, the scenario calculation parameter determination module is specifically used for:

[0094] Obtain the market adjustment plan for the target industry chain, and set the multi-scenario calculation parameters corresponding to the target indicators based on the change values ​​of the target indicators involved in the market adjustment plan.

[0095] In this embodiment, as another optional embodiment, the scenario calculation parameter determination module is specifically used for:

[0096] Within a pre-set collection period, market data of the target industry chain is captured from the Internet using pre-set packet capture software. For each target indicator, the target indicator value corresponding to the target indicator in the market data is obtained. If the target indicator value exceeds the stored value range of the target indicator, the value closest to the target indicator value in the value range is updated based on the target indicator value. If the range difference of the updated value range is greater than the change threshold set for the target indicator, the multi-scenario calculation parameters corresponding to the target indicator are set based on the range difference.

[0097] The constraint value adjustment module is used to obtain the constraint parameter set mapped to each scenario operation parameter according to the pre-stored target industry chain mapping relationship library, and adjust the constraint value corresponding to each constraint parameter in the constraint parameter set according to the change value of the scenario operation parameter.

[0098] In this embodiment, as an optional implementation, the constraint value adjustment module is specifically used for:

[0099] For each constraint parameter in the constraint parameter set, the constraint value corresponding to the constraint parameter is updated according to the constraint value change rule of the constraint parameter, based on the change value of the scenario operation parameter and the constraint value change rule.

[0100] The parameter value adjustment module is used to obtain the associated scenario operation parameter set mapped to each scenario operation parameter according to the pre-stored scenario operation parameter mapping relationship library, and adjust the associated scenario operation parameter value corresponding to each associated scenario operation parameter in the associated scenario operation parameter set according to the change value of the scenario operation parameter.

[0101] In this embodiment, as an optional embodiment, the parameter value adjustment module is further used for:

[0102] Input the pre-set set of input parameters into the crude oil industry chain optimization model to obtain the first set of output parameters contained in the optimized operation plan output by the crude oil industry chain optimization model;

[0103] By modifying the value of one target parameter in the input parameter set while keeping the values ​​of other parameters unchanged, and inputting it into the crude oil industry chain optimization model, a second output parameter set containing the optimized operation scheme output by the crude oil industry chain optimization model is obtained.

[0104] From the second output parameter set, obtain the model parameters that have changed relative to the first output parameter set. Based on the target parameter and the obtained changed model parameters, construct and store the scenario operation parameter mapping relationship library.

[0105] The parallel computing module is used to virtualize the crude oil industry chain optimization model into a number of optimization sub-models based on the number of scenario computing parameters. Based on the constraint values ​​and associated scenario computing parameter values ​​adjusted for each scenario computing parameter, the optimization sub-models are run in parallel to obtain the operation optimization schemes corresponding to each scenario computing parameter. Each optimization sub-model runs one scenario computing parameter.

[0106] In this embodiment, as an optional embodiment, the device further includes:

[0107] The operation optimization scheme generation module (not shown in the figure) is used to extract the optimization data from the operation optimization schemes corresponding to the operation optimization parameters of each scenario, perform statistical analysis on the optimization data according to the pre-set analysis strategy, and generate a multi-scenario scheme result report based on the statistical analysis results.

[0108] Based on the same inventive concept, embodiments of the present invention also provide a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the model-based multi-scenario optimization method in any of the above possible implementations.

[0109] Alternatively, the storage medium may be a non-transitory computer-readable storage medium, such as a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.

[0110] Based on the same inventive concept, see [link to inventive concept] Figure 3This invention also provides an electronic device, including a memory (e.g., non-volatile memory), a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of the model-based multi-scenario optimization method described in any of the possible implementations above, which can be equivalent to the aforementioned model-based multi-scenario optimization device. Of course, the processor can also be used to process other data or perform calculations. This electronic device can be a PC, server, terminal, or other similar device.

[0111] like Figure 3 As shown, this electronic device may also include: memory, network interface, and internal bus. In addition to these components, other hardware may be included, which will not be elaborated further.

[0112] It should be noted that the aforementioned model-based multi-scenario optimization device can be implemented in software. As a logical device, it is formed by the processor of the electronic device in which it is located reading the computer program instructions stored in the non-volatile memory into the memory for execution.

[0113] The embodiments of the subject matter and functional operation described in this specification can be implemented in the following ways: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or combinations thereof. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier for execution by a data processing apparatus or for controlling the operation of a data processing apparatus. Alternatively or additionally, the program instructions may be encoded on artificially generated propagation signals, such as machine-generated electrical, optical, or electromagnetic signals, which are generated to encode information and transmit it to a suitable receiving device for execution by the data processing apparatus. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or combinations thereof.

[0114] The processing and logic flow described in this specification can be executed by one or more programmable computers that execute one or more computer programs to perform corresponding functions by operating on input data and generating output. The processing and logic flow can also be executed by special-purpose logic circuitry—such as FPGAs (Field-Programmable Gate Arrays) or ASICs (Application-Specific Integrated Circuits), and the device can also be implemented as special-purpose logic circuitry.

[0115] Suitable computers for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit receives instructions and data from read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as disks, magneto-optical disks, or optical disks, or the computer will be operatively coupled to such mass storage devices to receive data from or transfer data to them, or both. However, a computer is not required to have such devices. Furthermore, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.

[0116] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0117] While this specification contains numerous specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily used to describe features of specific embodiments of a particular invention. Certain features described in the various embodiments herein may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation thereof.

[0118] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0119] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0120] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0121] The above are merely specific embodiments of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A model-based multi-scenario optimization method, characterized in that, include: Collect market operation data of the target industry chain. If the change in the market operation data is greater than the change threshold, determine multi-scenario calculation parameters based on the change in the market operation data. The market operation data includes data corresponding to multiple pre-set target indicators. For each scenario operation parameter, the constraint parameter set mapped to each scenario operation parameter is obtained through a pre-stored target industry chain mapping relationship library, and the constraint value corresponding to each constraint parameter in the constraint parameter set is adjusted according to the change value of the scenario operation parameter. For each scenario operation parameter, the associated scenario operation parameter set mapped by the scenario operation parameter is obtained through a pre-stored scenario operation parameter mapping relationship library. The associated scenario operation parameter value corresponding to each associated scenario operation parameter in the associated scenario operation parameter set is adjusted according to the change value of the scenario operation parameter. Based on the number of scenario operation parameters, the virtualized crude oil industry chain optimization model consists of the number of optimization sub-models. The optimization sub-models are run in parallel according to the constraint values ​​and associated scenario operation parameter values ​​adjusted for each scenario operation parameter, and the operation optimization schemes corresponding to each scenario operation parameter are obtained respectively.

2. The model-based multi-scenario optimization method according to claim 1, characterized in that, The process involves collecting market operation data from the target industry chain. If the change in market operation data exceeds a threshold, multi-scenario calculation parameters are set based on the change in market operation data, including: Collect market situation data of the target industry chain within a pre-set collection period; For each preset target indicator, the maximum value corresponding to the target indicator in the market situation data is obtained. If the difference between the maximum value corresponding to any target indicator and the preset base value is greater than the change threshold set for the target indicator, based on the difference, the multi-scenario operation parameters corresponding to the target indicator are set. The scenario operation parameters are the market situation data corresponding to the target indicator with different values ​​assigned based on the difference.

3. The model-based multi-scenario optimization method according to claim 1, characterized in that, The process involves collecting market operation data from the target industry chain. If the change in market operation data exceeds a threshold, multi-scenario calculation parameters are set based on the change in market operation data, including: Obtain the market adjustment plan for the target industry chain, and set the multi-scenario calculation parameters corresponding to the target indicators based on the change values ​​of the target indicators involved in the market adjustment plan.

4. The model-based multi-scenario optimization method according to claim 1, characterized in that, The process involves collecting market operation data from the target industry chain. If the change in market operation data exceeds a threshold, multi-scenario calculation parameters are set based on the change in market operation data, including: Within a pre-set collection period, market data of the target industry chain is captured from the Internet. For each target indicator, the target indicator value corresponding to the target indicator in the market data is obtained. If the target indicator value exceeds the stored value range of the target indicator, the value closest to the target indicator value in the value range is updated based on the target indicator value. If the range difference of the updated value range is greater than the change threshold set for the target indicator, the multi-scenario calculation parameters corresponding to the target indicator are set based on the range difference.

5. The model-based multi-scenario optimization method according to any one of claims 1 to 4, characterized in that, Obtaining the scenario operation parameter mapping relationship library includes: Input the pre-set set of input parameters into the crude oil industry chain optimization model to obtain the first set of output parameters contained in the optimized operation plan output by the crude oil industry chain optimization model; By modifying the value of one target parameter in the input parameter set while keeping the values ​​of other parameters unchanged, and inputting it into the crude oil industry chain optimization model, a second output parameter set containing the optimized operation scheme output by the crude oil industry chain optimization model is obtained. From the second output parameter set, obtain the model parameters that have changed relative to the first output parameter set. Based on the target parameter and the obtained changed model parameters, construct and store the scenario operation parameter mapping relationship library.

6. The model-based multi-scenario optimization method according to any one of claims 1 to 4, characterized in that, The step of adjusting the constraint value corresponding to each constraint parameter in the constraint parameter set based on the change value of the scenario calculation parameter includes: For each constraint parameter in the constraint parameter set, the constraint value corresponding to the constraint parameter is updated according to the constraint value change rule of the constraint parameter, based on the change value of the scenario operation parameter and the constraint value change rule.

7. The model-based multi-scenario optimization method according to any one of claims 1 to 4, characterized in that, The method further includes: The optimization data corresponding to the operation optimization schemes for each scenario's calculation parameters are extracted separately. Based on the pre-set analysis strategy, the optimization data is statistically analyzed, and a multi-scenario scheme result report is generated based on the statistical and analysis results.

8. A model-based multi-scenario optimization device, characterized in that, include: The scenario calculation parameter determination module is used to collect market operation data of the target industry chain. When the change in the market operation data is greater than the change threshold, multiple scenario calculation parameters are set based on the change in the market operation data. The market operation data includes data corresponding to multiple pre-set target indicators. The constraint value adjustment module is used to obtain the constraint parameter set mapped to each scenario operation parameter according to the pre-stored target industry chain mapping relationship library, and adjust the constraint value corresponding to each constraint parameter in the constraint parameter set according to the change value of the scenario operation parameter. The parameter value adjustment module is used to obtain the associated scenario operation parameter set mapped to each scenario operation parameter according to the pre-stored scenario operation parameter mapping relationship library, and adjust the associated scenario operation parameter value corresponding to each associated scenario operation parameter in the associated scenario operation parameter set according to the change value of the scenario operation parameter. The parallel computing module is used to virtualize the crude oil industry chain optimization model into the number of optimization sub-models according to the number of scenario computing parameters. Based on the constraint value and associated scenario computing parameter value adjusted for each scenario computing parameter, the optimization sub-models are run in parallel to obtain the operation optimization scheme corresponding to each scenario computing parameter. Each optimization sub-model runs one scenario computing parameter.

9. A storage medium, characterized in that, The program or instructions are stored on the storage medium, and the program or instructions are executed by the processor to implement the steps of the model-based multi-scenario optimization method as described in any one of claims 1 to 7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the model-based multi-scenario optimization method according to any one of claims 1 to 7.

Images