An energy demand prediction method, device, equipment and storage medium

Abstract

The application provides an energy demand prediction method and device, equipment and a storage medium, relates to the technical field of energy demand prediction, and aims to solve the problem of low energy demand prediction accuracy. The energy demand prediction method comprises the following steps: obtaining a prediction factor set of each energy consumption field in a plurality of energy consumption fields, wherein the prediction factor set comprises at least one prediction factor which dynamically changes in value with external conditions; the prediction factor is used to represent a factor affecting the energy consumption of the energy consumption field; predicting the energy consumption of the energy consumption field according to the corresponding relationship between the prediction factor set of each energy consumption field and the energy consumption; and predicting the total energy demand according to the energy consumption of each energy consumption field.

Description

Technical Field

[0001] This application relates to the field of energy demand forecasting technology, and in particular to an energy demand forecasting method, apparatus, equipment and storage medium. Background Technology

[0002] Energy (such as refined oil products) demand forecasting is a crucial basis for energy policy formulation, refining and chemical enterprise production planning, and market analysis. Currently, most common refined oil product demand forecasting methods adopt macroeconomic aggregate extrapolation models, that is, based on macroeconomic indicators such as GDP, total population, or historical total consumption, time series models or regression models are established for forecasting.

[0003] However, commonly used energy demand forecasting methods have relatively low accuracy. Therefore, how to accurately forecast energy demand is a pressing technical problem that needs to be solved. Summary of the Invention

[0004] This disclosure provides an energy demand forecasting method, apparatus, device, and storage medium to address the problem of low accuracy in energy demand forecasting.

[0005] To achieve the above objectives, this application adopts the following technical solution: In a first aspect, an energy demand forecasting method is provided, comprising: acquiring a set of predictive factors for each of multiple energy consumption sectors, wherein the set of predictive factors includes at least one predictive factor whose value dynamically changes with external conditions; the predictive factor is used to represent factors affecting the energy consumption of the energy consumption sector; predicting the energy consumption of the energy consumption sector based on the correspondence between the set of predictive factors for each energy consumption sector and the energy consumption; and predicting the total energy demand based on the energy consumption of each energy consumption sector.

[0006] As can be seen from the above, by breaking down energy consumption into multiple independent consumption areas and establishing a correspondence between the predictor and energy consumption for each area, the embodiments of this application can calculate the energy consumption of each area separately, avoiding the defect of macro-aggregate models that confuse different areas, thereby improving the accuracy of medium- and long-term energy demand forecasts.

[0007] Secondly, the predictor set includes at least one predictor whose value changes dynamically with changes in external conditions. This means that when external conditions such as policies, technological approaches, or market environments change, only the values ​​of the corresponding predictors need to be adjusted to output new prediction results, without having to rebuild the entire prediction system. This gives the method in this application embodiment good dynamic adaptability.

[0008] Furthermore, the embodiments of this application, through the logic of first predicting by sector and then summing up, enable the consumption of each energy consumption sector to be traced back to its set of predictive factors and corresponding relationships, which facilitates the adjustment of parameters for specific sectors according to actual conditions and improves the interpretability of prediction results.

[0009] Secondly, an energy demand forecasting device is provided, comprising: a communication unit and a processing unit; the communication unit is configured to acquire a set of forecasting factors for each of multiple energy consumption sectors, the set of forecasting factors including at least one forecasting factor whose value dynamically changes with external conditions; the forecasting factors are used to represent factors affecting the energy consumption of the energy consumption sector; the processing unit is configured to forecast the energy consumption of the energy consumption sector based on the correspondence between the set of forecasting factors for each energy consumption sector and the energy consumption; the processing unit is further configured to forecast the total energy demand based on the energy consumption of each energy consumption sector.

[0010] Thirdly, an energy demand forecasting device is provided, including a memory and a processor; the memory is used to store computer-executed instructions, and the processor is connected to the memory via a bus; when the energy demand forecasting device is running, the processor executes the computer-executed instructions stored in the memory, so that the energy demand forecasting device performs the energy demand forecasting method of the first aspect.

[0011] The energy demand forecasting device can be an electronic device or a component of an electronic device, such as a chip system within an electronic device. The chip system supports the electronic device in implementing the functions involved in the first aspect and any of its possible implementations, such as acquiring and determining the data and / or information involved in the aforementioned energy demand forecasting method. The chip system includes a chip, but may also include other discrete devices or circuit structures.

[0012] Fourthly, a computer-readable storage medium is provided, comprising computer-executable instructions that, when executed on a computer, cause the computer to perform the energy demand forecasting method described in the first aspect.

[0013] Fifthly, a computer program product is provided, comprising a computer program or instructions that, when executed on an energy demand forecasting device, cause the energy demand forecasting device to perform the energy demand forecasting method as described in the first aspect above.

[0014] It should be noted that the aforementioned computer instructions may be stored, in whole or in part, on a computer-readable storage medium. This computer-readable storage medium may be packaged together with the processor of the energy demand forecasting device, or it may be packaged separately from the processor of the energy demand forecasting device; this application does not limit this.

[0015] The descriptions of the second, third, fourth, and fifth aspects of this application can be referenced to the detailed description of the first aspect.

[0016] In the embodiments of this application, the name of the aforementioned energy demand forecasting device does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear under other names. For example, the receiving unit may also be called a receiving module, receiver, etc. As long as the function of each device or functional module is similar to that of this application, it falls within the scope of the claims of this application and its equivalents. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the structure of an energy demand forecasting system provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of an energy demand forecasting device provided in an embodiment of this application; Figure 3 A flowchart illustrating an energy demand forecasting method provided in an embodiment of this application; Figure 4 A schematic diagram of the structure of an energy demand forecasting device provided in an embodiment of this application; Figure 5 This is a schematic diagram of the hardware structure of an energy demand forecasting device provided in an embodiment of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] It should be noted that in the embodiments of this application, the words "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0020] To facilitate a clear description of the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish the same or similar items with essentially the same function and effect. Those skilled in the art can understand that the terms "first" and "second" are not intended to limit the quantity or execution order.

[0021] As described in the background section, current forecasts of refined oil demand largely rely on macroeconomic policy guidance or single indicators (such as GDP or historical total consumption) to extrapolate total volume, lacking a refined analysis of downstream segmented consumption structures.

[0022] Especially against the backdrop of economic transformation and development, the characteristics, driving factors, and development trends of oil consumption in different sectors such as transportation, agriculture, forestry, animal husbandry and fishery, and industry, mining and construction are significantly different. Existing models often mix all consumption into one, making it difficult to accurately capture changes in oil consumption trends in each sector.

[0023] Furthermore, most existing methods employ static parameters or fixed weights, lacking the ability to adaptively adjust to dynamic factors such as the replacement of new energy vehicles, the application of biodiesel, and improvements in fuel efficiency. This results in forecasts that fail to reflect structural changes and cannot support refined decision-making under multiple scenarios. Therefore, improving the structural precision of refined oil demand forecasting and its dynamic adaptability to external changes is a pressing technical problem that needs to be solved in this field.

[0024] To address the aforementioned issues, this application provides an energy demand forecasting method that can obtain a set of predictive factors for each of multiple energy consumption sectors. This set of predictive factors includes at least one predictive factor whose value dynamically changes with external conditions, representing factors influencing energy consumption in that sector. Subsequently, based on the correspondence between the set of predictive factors for each energy consumption sector and its energy consumption, the energy consumption of that sector can be predicted, and based on the energy consumption of each sector, the total energy demand can be predicted.

[0025] As can be seen from the above, by breaking down energy consumption into multiple independent consumption areas and establishing a correspondence between the predictor and energy consumption for each area, the embodiments of this application can calculate the energy consumption of each area separately, avoiding the defect of macro-aggregate models that confuse different areas, thereby improving the accuracy of medium- and long-term energy demand forecasts.

[0026] Secondly, the predictor set includes at least one predictor whose value changes dynamically with changes in external conditions. This means that when external conditions such as policies, technological approaches, or market environments change, only the values ​​of the corresponding predictors need to be adjusted to output new prediction results, without having to rebuild the entire prediction system. This gives the method in this application embodiment good dynamic adaptability.

[0027] Furthermore, the embodiments of this application, through the logic of first predicting by sector and then summing up, enable the consumption of each energy consumption sector to be traced back to its set of predictive factors and corresponding relationships, which facilitates the adjustment of parameters for specific sectors according to actual conditions and improves the interpretability of prediction results.

[0028] The embodiments of this application are applicable to multiple scenarios such as energy policy formulation (e.g., refining capacity layout and carbon emission reduction target setting), refining and chemical enterprise production planning (e.g., crude oil procurement and equipment capacity configuration), refined oil market analysis (e.g., supply and demand pattern assessment and trade strategy formulation), and energy supply chain collaborative management.

[0029] The implementation environment for the above-mentioned energy demand forecasting method can be the energy demand forecasting system provided in the embodiments of this application.

[0030] Figure 1 This is a schematic diagram of the structure of an energy demand forecasting system provided in an embodiment of this application. Figure 1 As shown, the energy demand forecasting system includes an energy demand forecasting device 101 and a data storage device 102.

[0031] The energy demand forecasting device 101 and the data storage device 102 are connected in communication.

[0032] In this embodiment, the data storage device 102 is used to provide the energy demand forecasting device 101 with data required for energy demand forecasting, such as a set of forecasting factors for each of multiple energy consumption sectors. The energy demand forecasting device 101 is used to forecast energy demand based on the data provided by the data storage device 102.

[0033] In practical applications, the energy demand forecasting device 101 can be connected to any number of data storage devices 102. For ease of understanding, Figure 1 The following is an example of an energy demand forecasting device 101 connected to a data storage device 102.

[0034] Optionally, the physical device of the energy demand forecasting device 101 can be a server, a terminal, or other types of electronic devices, and this application embodiment does not limit this.

[0035] Optionally, the aforementioned terminal may be a device that provides voice and / or data connectivity to a user, a handheld device with wireless connectivity, or other processing device connected to a wireless modem. The wireless terminal may communicate with one or more core networks via a radio access network (RAN). The wireless terminal may be a mobile terminal, such as a mobile phone (or "cellular" phone) and a computer with a mobile terminal, or a portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted mobile device that exchanges voice and / or data with the radio access network, such as a mobile phone, tablet computer, laptop computer, netbook, or personal digital assistant (PDA).

[0036] Optionally, the server mentioned above can be one of the servers in a server cluster (composed of multiple servers), a chip in the server, a system-on-a-chip in the server, or a virtual machine (VM) deployed on a physical machine. This application embodiment does not limit this.

[0037] Optionally, the energy demand forecasting device 101 and the data storage device 102 can be two independent devices, or they can be integrated into the same device. When the energy demand forecasting device 101 and the data storage device 102 are integrated into the same device, the data storage device 102 can be the database of the energy demand forecasting device 101.

[0038] It is easy to understand that when the energy demand forecasting device 101 and the data storage device 102 are integrated into the same device, the communication method between the energy demand forecasting device 101 and the data storage device 102 is the same as the communication method between internal modules of the device. In this case, the communication process between the two is the same as when the energy demand forecasting device 101 and the data storage device 102 are independent of each other.

[0039] It should be noted that the system architecture and application scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems. For ease of understanding, this application uses the example of energy demand forecasting device 101 and data storage device 102 operating independently as an example for illustration.

[0040] When executing the energy demand forecasting method provided in this application embodiment, the energy demand forecasting device 101 can divide the device into multiple logical levels according to the method execution logic. For example, as shown... Figure 2 As shown, the energy demand forecasting device 101 may include a data input layer, a model calculation layer, and a result output layer; The data input layer is used to obtain a set of predictive factors for each of the multiple energy consumption sectors. The set of predictive factors includes at least one predictive factor whose value changes dynamically with external conditions. The predictive factors are used to represent the factors that affect the energy consumption of the energy consumption sector.

[0041] The data input layer specifically includes a public database, a product database, a policy and expert database, and a dynamic update interface.

[0042] The public database provides data on GDP, population, and industrial structure; the product database provides data on vehicle ownership, fuel consumption, and average annual mileage; the policy and expert database provides data on carbon targets, industry planning targets, and energy efficiency standards; and the dynamic update interface ensures the timeliness of each database.

[0043] The model calculation layer is used to predict the energy consumption of each energy consumption sector based on the correspondence between the set of predictor factors for each energy consumption sector and the energy consumption, and to predict the total energy demand based on the energy consumption of each energy consumption sector.

[0044] The model computation layer specifically includes a domain partitioning module, a logic transmission module, a factor calculation module, a cross-validation module, and a correction mechanism module.

[0045] The domain segmentation module is used to divide energy consumption into multiple energy consumption domains; the logic transmission module is used to establish the correspondence between the set of prediction factors for each energy consumption domain and the energy consumption; the factor calculation module is used to calculate the corresponding energy consumption based on the value of the prediction factor; the cross-validation module is used to cross-validate the prediction results; the correction mechanism module is used to dynamically adjust the value of the prediction factor based on external conditions; and the model calculation layer outputs the prediction results.

[0046] The results output layer is used to output the predicted total energy demand.

[0047] The results output layer specifically includes prediction result tables, visualization charts, and multi-scenario comparative analysis; the results output layer is used to provide decision support to decision-makers or planners.

[0048] The specific implementation process of the functions of each module in the above-mentioned levels can be found in the following description, and will not be repeated here.

[0049] It should be pointed out that,Figure 2 The hierarchical architecture shown does not constitute a limitation on the internal structure of the energy demand forecasting device 101, except... Figure 2 In addition to the various levels and modules shown, the energy demand forecasting device 101 may include more or fewer levels and / or modules than shown, or combine certain levels and / or modules, or have different arrangements of levels and / or modules.

[0050] The energy demand forecasting method provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0051] The energy demand forecasting method provided in this application embodiment is applied to... Figure 1 The energy demand forecasting device 101 in the energy demand forecasting system shown is, for example Figure 3 As shown in the embodiments of this application, an energy demand forecasting method includes: S301. Obtain the set of predictive factors for each of the multiple energy consumption sectors.

[0052] The predictor set includes at least one predictor whose value dynamically changes with external conditions. Predictors are used to represent factors influencing energy consumption in the energy sector.

[0053] When performing energy demand forecasting, it is first necessary to obtain a set of forecasting factors for each of the multiple energy consumption sectors. These multiple energy consumption sectors are defined according to industry classification standards, based on the end-use destinations of refined oil products, specifically including transportation, agriculture, forestry, animal husbandry and fishery, industry and mining, construction, and commercial and residential use.

[0054] For each energy consumption sector, its predictive factor set includes at least one predictive factor whose value dynamically changes with external conditions. Predictive factors represent the factors influencing energy consumption in that sector. Specifically, a predictive factor whose value dynamically changes with external conditions refers to a factor whose value can be dynamically adjusted based on external conditions (such as industry development trends, user-chosen development scenarios, industry report trends, or expert opinions).

[0055] In some embodiments, external conditions include: industry development trends and / or user-selected development scenarios.

[0056] Predictive factors are specific factors that quantify and describe the energy consumption in a particular energy consumption sector. Each predictive factor has a clear physical or economic meaning, and its value directly affects the calculated energy consumption for that sector.

[0057] Optionally, the predictive factors reflect the core drivers of energy consumption in the sector. For example, in the transportation sector, the pure gasoline vehicle fleet factor characterizes the quantity of fuel-powered vehicles, while the pure gasoline vehicle fuel consumption factor characterizes the average fuel consumption intensity of each vehicle. The product of the two represents the total gasoline consumption of this segment of vehicles.

[0058] Optionally, the predictive factors support independent modeling across different sectors, meaning that the fuel consumption mechanisms differ significantly across sectors, and the selection of predictive factors is customized to the end-consumer behavior of each sector. For example, in the agriculture, forestry, animal husbandry and fishery sector, the total power factor of agricultural machinery and the fuel consumption factor per unit power are used to characterize the relationship between the degree of agricultural mechanization and fuel consumption intensity; in the industry and mining sector, the industrial added value factor and the gasoline consumption factor per unit added value are used to characterize the correlation between industrial output scale and fuel consumption per unit output; and in the commercial and residential sector, the tertiary industry added value factor and the fuel consumption factor per unit added value are used to characterize the relationship between the development level of the service industry and fuel consumption.

[0059] The predictor set includes at least one predictor whose value changes dynamically with external conditions (hereinafter referred to as a dynamic predictor). The value of a dynamic predictor is not fixed but can be dynamically adjusted based on external conditions (such as industry development trends, user-selected development scenarios, industry report trends, or expert opinions). Common dynamic predictors include: new energy substitution rate, biodiesel substitution ratio, and unit energy consumption reduction rate.

[0060] The new energy substitution rate refers to the proportion of traditional fuel vehicles replaced by new energy vehicles (such as pure electric vehicles, plug-in hybrid vehicles, LNG vehicles, etc.) in the transportation sector. This factor changes dynamically with technological advancements and market penetration.

[0061] The biodiesel substitution ratio refers to the proportion of conventional diesel fuel that is replaced by biodiesel in diesel consumption. This factor is influenced by factors such as raw material supply, blending policies, and cost competitiveness, and can be dynamically adjusted.

[0062] The rate of decrease in unit energy consumption refers to the percentage decrease in fuel consumption per unit of activity (such as vehicle mileage or unit industrial added value) year by year due to technological advancements or improved energy efficiency. The value of this factor changes dynamically as energy-saving technologies become more widespread.

[0063] Each predictive factor corresponds to a specific data source or predictive basis. For example, static predictive factors (such as historical vehicle ownership and total agricultural machinery power) can be directly obtained from public or product databases or derived through trend extrapolation; dynamic predictive factors, on the other hand, need to be assigned values ​​based on the development scenario selected by the user (such as a baseline scenario or an aggressive scenario) or industry development trends. When the prediction results need to be adjusted, decision-makers can locate the specific predictive factor, modify its value, and recalculate, thereby achieving refined human-computer interaction and strategy analysis.

[0064] Since the values ​​of dynamic forecasting factors can change with external conditions, users can obtain a set of corresponding dynamic forecasting factor values ​​by setting different development scenarios (such as baseline scenario, aggressive scenario, or custom scenario), and thus obtain the total energy demand forecast results under different scenarios. For example, under the aggressive scenario, the value of the renewable energy substitution rate is higher than that under the baseline scenario, resulting in a lower predicted value for gasoline consumption in the transportation sector than under the baseline scenario.

[0065] In summary, predictive factors serve as a bridge connecting raw data with energy consumption, and are also a core element for achieving sector-specific, dynamic, and multi-scenario forecasting. By rationally selecting predictive factor sets for each sector and clarifying the adjustment mechanism of dynamic predictive factors, this application can accurately and flexibly complete the task of medium- and long-term energy demand forecasting.

[0066] In practice, the above-mentioned predictive factor set is obtained through methods including: reading static or historical data from public databases (such as GDP, population, and industrial structure data), product databases (such as vehicle ownership, fuel consumption, and average annual mileage data), and industry and expert databases (such as industry planning targets and energy efficiency standards data); and dynamically determining the specific values ​​of predictive factors that change with external conditions based on the user-selected development scenario (such as a baseline scenario, an aggressive scenario, or a user-defined scenario) and industry development trends. For example, in an aggressive scenario, the value of the new energy substitution rate is higher than that in the baseline scenario.

[0067] By using the above methods, a complete and dynamically adjustable set of predictive factors for each energy consumption sector can be obtained, providing a data foundation for subsequent sector-specific energy consumption predictions.

[0068] S302. Based on the correspondence between the set of predictive factors for each energy consumption sector and the energy consumption, predict the energy consumption of each energy consumption sector.

[0069] After obtaining the predictor set for each energy consumption sector, the energy consumption of each sector can be calculated based on the correspondence between the predictor set for each sector and the energy consumption of that sector.

[0070] The aforementioned correspondence refers to the pre-established quantitative mapping rule between each predictor in the predictor set and the energy consumption of each energy consumption sector. This quantitative mapping rule reflects the actual physical or economic processes of end-use oil activities in that sector.

[0071] Specifically, the establishment of the correspondence follows a bottom-up end-consumer driven logic, that is, starting from the oil-consuming equipment or activities at the very end of each field, the total energy consumption of that field is obtained by summarizing the multiplication and addition operations between predictive factors.

[0072] In practice, the energy consumption of each energy consumption sector is predicted based on the correspondence between the set of predictive factors and the energy consumption. This includes the following sub-steps: S1. Determine the specific form of the correspondence.

[0073] For each energy consumption sector, the corresponding relationship is usually represented by one or more mathematical formulas. Each formula takes one or more predictors for that sector as input variables and outputs the consumption of a certain type of energy (such as gasoline, diesel, or kerosene) for that sector through arithmetic operations such as multiplication (representing the product of the scale factor and the intensity factor) or addition (representing the sum of consumption of different subcategories).

[0074] For example, in sectors where vehicle operation is the primary mode of fuel consumption, the corresponding relationship can be expressed as the product of the vehicle ownership factor and the fuel consumption factor per vehicle; in sectors where equipment operation is the primary mode of fuel consumption, the corresponding relationship can be expressed as the product of the total power factor of the equipment and the fuel consumption factor per unit power; and in sectors where economic output is the primary related indicator, the corresponding relationship can be expressed as the product of the industrial added value factor and the fuel consumption factor per unit added value.

[0075] S2. Obtain or determine the values ​​of each predictor at the target time point.

[0076] Before performing calculations based on the correspondence, it is necessary to obtain the specific value of each predictor in the target prediction year. For static predictors that do not change with external conditions (such as vehicle ownership and power derived from historical trend extrapolation), their predicted values ​​can be obtained through time series analysis, regression models, or direct reading from a database. For predictors that dynamically change with external conditions (such as the new energy substitution rate, biodiesel substitution ratio, and unit energy consumption reduction rate), their specific values ​​at the target time point are determined based on the user-selected development scenario (such as a baseline scenario, an aggressive scenario, or a custom scenario) or industry development trends.

[0077] S3. Substitute the values ​​of the predictor factors into the corresponding relationships for calculation.

[0078] Substitute the predicted factor values ​​determined in S2 into the correspondence (i.e., mathematical calculation formula) determined in S1, and perform arithmetic operations according to the order of operations defined in the formula (multiplication and division first, then addition and subtraction) to obtain the energy consumption of this energy consumption sector at the target time point. If this sector involves multiple energy types (such as gasoline and diesel), calculate the consumption of each energy type separately according to their respective correspondences.

[0079] S4 outputs the energy consumption of each energy consumption sector.

[0080] The energy consumption (and consumption by product category) of each energy consumption sector calculated above will be used as the output of this step for subsequent aggregation steps.

[0081] Through the above methods, this step achieves independent and refined prediction of energy consumption in each energy consumption sector. Since the correspondences for each sector are designed based on end-user consumption behavior within that sector, the prediction results accurately reflect the oil consumption characteristics and trends of each sector, avoiding the problem of mutual masking between different sectors in macro-level total forecasts. Furthermore, because the correspondences include predictive factors that dynamically change with external conditions, when external conditions change, only the values ​​of the corresponding factors need to be adjusted and recalculated to obtain updated prediction results, without modifying the correspondences themselves. This ensures the flexibility and adaptability of the prediction model.

[0082] S303. Based on the energy consumption of each energy consumption sector, predict the total energy demand.

[0083] After obtaining the energy consumption in each energy consumption sector, the energy consumption in all energy consumption sectors can be summed up to obtain the final total energy demand.

[0084] Specifically, the energy consumption in each energy consumption sector may involve multiple energy types. In this application, energy consumption includes at least one or more of gasoline, diesel, and kerosene consumption. For each energy consumption sector, the energy consumption output in S302 can be the consumption of a single type or the consumption of multiple types. For example, some sectors may consume both gasoline and diesel, while others may consume only a single type of oil.

[0085] Next, the consumption of the same energy type in each energy consumption sector is summed up to obtain the total consumption of that energy type.

[0086] Optionally, the total consumption of the aforementioned energy type specifically includes: summing up the gasoline consumption in all energy consumption sectors to obtain the total gasoline consumption; summing up the diesel consumption in all energy consumption sectors to obtain the total diesel consumption; and summing up the kerosene consumption in all energy consumption sectors to obtain the total kerosene consumption.

[0087] Next, based on the total consumption of each of the aforementioned energy types, the final total energy demand is determined. In some implementations, the total energy demand is the sum of the total consumption of gasoline, diesel, and kerosene, i.e., the total consumption of refined oil products. In some implementations, the total consumption of only one or a few types of oil products may be output as needed.

[0088] Next, the predicted total energy demand (and the total consumption of each energy type) will be output in a structured format. Output methods may include generating forecast result tables, creating visualization charts, and providing interfaces for multi-scenario comparative analysis. The output forecast results can be used by decision-makers or planners in scenarios such as energy policy formulation, production planning, and market analysis.

[0089] Furthermore, the reasonableness of the forecast results can be verified before outputting them. Verification methods include: comparing the forecast results with historical data trends to determine if there are any abnormal fluctuations; cross-validating the forecast results with values ​​obtained from other methods (such as time series models and econometric models); or benchmarking the forecast results against industry reports and expert experience. If the verification finds that the forecast results deviate from a reasonable range, the values ​​of the dynamic forecast factors in the forecast factor set can be adjusted based on the verification feedback, and S302 and S303 can be re-executed until the forecast results meet the reasonableness requirements.

[0090] Through the above methods, this step aggregates the energy consumption of various sectors into a unified total energy demand, completing the entire forecasting chain from the decomposition of end-consumer spending to the integration of total demand. Because the aggregation process is based on the independent forecasts of each sector, any structural changes in any sector will be directly reflected in its consumption, thus affecting the total energy demand. This ensures the sensitivity and accuracy of the total demand forecast to structural changes.

[0091] The following section, using specific energy consumption areas as examples, introduces the specific implementation method for predicting energy consumption in each energy consumption area based on the correspondence between the set of predictive factors and energy consumption.

[0092] In some embodiments, where the energy consumption sector includes the transportation sector, the predictive factors for the transportation sector include: pure gasoline vehicle ownership factor, pure gasoline vehicle fuel consumption per vehicle factor, new energy hybrid vehicle ownership factor, new energy hybrid vehicle fuel consumption per vehicle factor, diesel heavy truck ownership factor, diesel heavy truck fuel consumption per vehicle factor, biodiesel substitution rate factor, civil aviation passenger volume factor, fuel consumption per unit passenger volume factor, civil aviation cargo volume factor, and fuel consumption per unit cargo volume factor. Energy consumption in the transportation sector includes: gasoline consumption, diesel consumption, and kerosene consumption.

[0093] Based on the correspondence between the predictor set of each energy consumption sector and energy consumption, the energy consumption of each sector is predicted, including: The gasoline consumption of a pure gasoline vehicle is determined by multiplying the pure gasoline vehicle ownership factor by the pure gasoline vehicle fuel consumption factor per vehicle.

[0094] The pure gasoline vehicle ownership factor represents the number of vehicles in the transportation sector that use only gasoline as fuel at the target time point, while the pure gasoline vehicle fuel consumption factor represents the average gasoline consumption of each pure gasoline vehicle within a unit of time (usually one year). Multiplying the two together yields the total gasoline consumption of all pure gasoline vehicles.

[0095] The gasoline consumption of new energy hybrid vehicles is determined by multiplying the number of new energy hybrid vehicles by the fuel consumption factor of each new energy hybrid vehicle.

[0096] Among them, the new energy hybrid vehicle ownership factor represents the number of vehicles using hybrid technology (such as hybrid electric vehicles and plug-in hybrid electric vehicles) in the transportation sector at the target time point, and the new energy hybrid vehicle fuel consumption factor represents the average gasoline consumption of each new energy hybrid vehicle per unit time. Multiplying the two together yields the total gasoline consumption of all new energy hybrid vehicles.

[0097] The gasoline consumption in the transportation sector is determined by summing the gasoline consumption of pure gasoline vehicles and the gasoline consumption of new energy hybrid vehicles.

[0098] The summation result reflects the total gasoline consumption of all road vehicles (including pure gasoline vehicles and new energy hybrid vehicles) in the transportation sector.

[0099] The diesel consumption of a diesel heavy-duty truck is determined by multiplying the diesel heavy-duty truck inventory factor by the diesel heavy-duty truck fuel consumption factor per vehicle.

[0100] The diesel heavy-duty truck inventory factor represents the number of heavy-duty trucks using diesel fuel in the transportation sector at the target time point, while the diesel heavy-duty truck per vehicle fuel consumption factor represents the average diesel consumption of each diesel heavy-duty truck per unit time. Multiplying the two together yields the total diesel consumption of all diesel heavy-duty trucks.

[0101] Based on the diesel consumption of diesel heavy-duty trucks and the biodiesel substitution rate factor, the diesel consumption in the transportation sector after biodiesel substitution correction is determined.

[0102] The biodiesel substitution rate factor represents the proportion of total diesel consumption where biodiesel replaces conventional diesel. Multiplying the diesel consumption of heavy-duty trucks obtained in the first step by (1 minus the biodiesel substitution rate factor), or subtracting the replaced portion according to the substitution logic, yields the corrected diesel consumption. This correction reflects the reduction in conventional diesel consumption caused by biodiesel as an alternative fuel.

[0103] The kerosene consumption of civil aviation passenger transport is determined by multiplying the civil aviation passenger volume factor and the fuel consumption factor per unit passenger volume.

[0104] The civil aviation passenger volume factor represents the passenger turnover (e.g., passenger-kilometers) of civil aviation transportation at the target time point, while the fuel consumption per unit passenger volume factor represents the amount of kerosene consumed per unit of passenger turnover. Multiplying the two together yields the total kerosene consumption for the civil aviation passenger segment.

[0105] The kerosene consumption for civil aviation cargo is determined by multiplying the civil aviation cargo volume factor and the fuel consumption factor per unit cargo volume.

[0106] The civil aviation cargo volume factor represents the cargo turnover (e.g., ton-kilometers) of civil aviation transportation at the target time point, while the fuel consumption factor per unit cargo volume represents the amount of kerosene consumed per unit of cargo turnover. Multiplying the two together yields the total kerosene consumption for the civil aviation cargo segment.

[0107] The kerosene consumption in the transportation sector is determined by the sum of the kerosene consumption for civil aviation passenger flights and the kerosene consumption for civil aviation cargo flights.

[0108] The summation result reflects the total kerosene consumption of all civil aviation transport activities (including passenger and freight transport) in the transportation sector.

[0109] Using the methods described above, gasoline consumption, diesel consumption (adjusted for biodiesel substitution), and kerosene consumption were calculated for the transportation sector. These consumption figures for each product type will be used as the energy consumption output for this sector, and will be subsequently aggregated to obtain the total energy demand.

[0110] In some embodiments, where the energy consumption sector includes agriculture, forestry, animal husbandry, and fishery, the predictive factor set for this sector includes: total power factor for agricultural machinery, fuel consumption per unit power, and total power factor for motorized fishing vessels. Energy consumption in the agriculture, forestry, animal husbandry, and fishery sector includes: gasoline consumption and diesel consumption.

[0111] Based on the correspondence between the predictor set of each energy consumption sector and energy consumption, the energy consumption of each sector is predicted, including: The gasoline consumption in the agricultural, forestry, animal husbandry and fishery sectors is determined by multiplying the total power factor of agricultural machinery with the fuel consumption factor per unit power.

[0112] The total power factor of agricultural machinery represents the total power output of all agricultural machinery (such as tractors, harvesters, and agricultural transport vehicles) in the agricultural, forestry, animal husbandry, and fishery sectors at the target time point, usually expressed in kilowatts. The unit power fuel consumption factor represents the average gasoline consumption per unit of power per unit of time. Multiplying the two yields the total gasoline consumption of agricultural machinery in the agricultural, forestry, animal husbandry, and fishery sectors. It should be noted that in the agricultural, forestry, animal husbandry, and fishery sectors, gasoline consumption mainly comes from small agricultural machinery and agricultural transport vehicles, while large agricultural machinery and fishing boats typically use diesel as their primary fuel. Therefore, gasoline consumption is calculated only by multiplying the total power of agricultural machinery by the unit power fuel consumption, without additionally adding the fuel consumption of motorized fishing boats.

[0113] The diesel consumption of agricultural machinery is determined by multiplying the total power factor of agricultural machinery by the fuel consumption factor per unit power.

[0114] The total power factor of agricultural machinery also represents the total power scale of all agricultural machinery in the fields of agriculture, forestry, animal husbandry and fishery, but the unit power fuel consumption factor here uses the unit power fuel consumption value corresponding to diesel. Multiplying the two together yields the total diesel consumption of agricultural machinery.

[0115] The diesel fuel consumption of motorized fishing vessels is determined by multiplying the total power factor of the vessel by the fuel consumption factor per unit power.

[0116] The total power factor of motorized fishing vessels represents the total power capacity of all motorized fishing vessels in the agricultural, forestry, animal husbandry and fishery sectors at the target time point, while the unit power fuel consumption factor represents the average diesel consumption per unit of power per unit of time. Multiplying the two together yields the total diesel consumption of motorized fishing vessels.

[0117] The diesel consumption in the agricultural, forestry, animal husbandry and fishery sectors is determined by summing the diesel consumption of agricultural machinery and diesel consumption of motorized fishing vessels.

[0118] The summation result reflects the total diesel consumption of all equipment in the agricultural, forestry, animal husbandry and fishery sectors (including land-based agricultural machinery and offshore motorized fishing vessels).

[0119] Using the methods described above, gasoline and diesel consumption were calculated separately for the agriculture, forestry, animal husbandry, and fishery sectors. These consumption figures for each product category will be used as the energy consumption output for that sector, and will be subsequently aggregated to obtain the total energy demand.

[0120] In some embodiments, where the energy consumption sector includes the industrial and mining sector, the predictive factors for the industrial and mining sector include: an industrial value-added factor, a gasoline consumption factor per unit value-added, a total power factor for construction equipment, and a diesel consumption factor per unit power. Energy consumption in the industrial and mining sector includes: gasoline consumption and diesel consumption.

[0121] Based on the correspondence between the predictor set of each energy consumption sector and energy consumption, the energy consumption of each sector is predicted, including: The gasoline consumption in the industrial and mining sectors is determined by multiplying the industrial added value factor by the gasoline consumption factor per unit added value.

[0122] The industrial value-added factor represents the new value created by industrial enterprises in the mining sector through production activities at the target time point, usually measured in monetary units (e.g., 100 million yuan), reflecting the economic scale and output level of the mining sector. The gasoline consumption per unit of value-added represents the average amount of gasoline consumed in the mining sector to create one unit of industrial value-added, reflecting the efficiency of gasoline use in production activities in the mining sector. Multiplying the two factors yields the total gasoline consumption generated by industrial production activities in the mining sector. This calculation method is applicable to gasoline-powered scenarios in the mining sector, such as vehicle transportation and small equipment operation.

[0123] The diesel consumption in the industrial and mining sector is determined by multiplying the total power factor of the construction equipment by the diesel consumption factor per unit power.

[0124] The total power factor of construction equipment represents the total power output of all construction equipment (such as excavators, loaders, drilling rigs, and mining transport vehicles) in the mining sector at the target time point, typically expressed in kilowatts. The diesel consumption factor per unit power represents the average diesel consumption per unit of power per unit of time. Multiplying the two factors yields the total diesel consumption of all construction equipment in the mining sector. This calculation method is applicable to scenarios in the mining sector where large machinery, heavy transport vehicles, and other equipment primarily use diesel fuel.

[0125] Using the methods described above, the gasoline and diesel consumption for the industrial and mining sectors were calculated separately. These consumption figures for each product type will be used as the energy consumption output for this sector, and will be subsequently aggregated to obtain the total energy demand.

[0126] In some embodiments, where the energy consumption sector includes the construction sector, the predictive factors for the construction sector include: a total power factor for construction equipment, a gasoline consumption factor per unit power, and a diesel consumption factor per unit power. Energy consumption in the construction sector includes: gasoline consumption and diesel consumption.

[0127] Based on the correspondence between the predictor set of each energy consumption sector and energy consumption, the energy consumption of each sector is predicted, including: The gasoline consumption in the construction sector is determined by multiplying the total power factor of construction equipment by the gasoline consumption factor per unit power.

[0128] The total power factor of construction equipment represents the total power output of all construction equipment (such as excavators, bulldozers, road rollers, concrete mixer trucks, cranes, etc.) within the construction sector at the target time point, typically expressed in kilowatts. The unit power gasoline consumption factor represents the average gasoline consumption per unit of power per unit of time, reflecting the energy intensity of construction equipment using gasoline as fuel. Multiplying the two factors yields the total gasoline consumption of all construction equipment within the construction sector. This calculation method is applicable to fuel-consuming scenarios such as small equipment and light transport vehicles using gasoline as fuel on construction sites.

[0129] The diesel consumption in the construction sector is determined by multiplying the total power factor of construction equipment by the diesel consumption factor per unit power.

[0130] The total power factor of construction equipment represents the total power output of all construction equipment in the construction sector. The diesel consumption factor per unit power represents the average diesel consumption per unit of power per unit of time, reflecting the energy intensity of construction equipment using diesel as fuel. Multiplying the two factors yields the total diesel consumption of all construction equipment in the construction sector. This calculation method is applicable to diesel-fueled scenarios on construction sites, including heavy equipment and large transport vehicles.

[0131] Using the methods described above, the gasoline and diesel consumption figures for the construction sector were calculated separately. These consumption figures for each product type will be used as the energy consumption output for this sector, and will be subsequently aggregated to obtain the total energy demand.

[0132] In some embodiments, where the energy consumption sector includes both commercial and residential sectors, the predictive factor set for the commercial and residential sectors includes: a tertiary industry value-added factor, a gasoline consumption factor per unit value-added, and a diesel consumption factor per unit value-added. Energy consumption in the commercial and residential sectors includes: gasoline consumption and diesel consumption.

[0133] Based on the correspondence between the predictor set of each energy consumption sector and energy consumption, the energy consumption of each sector is predicted, including: The gasoline consumption in the commercial and civilian sectors is determined by multiplying the added value factor of the tertiary industry with the gasoline consumption factor per unit added value.

[0134] The tertiary sector added value factor represents the total added value created by the tertiary sector (such as wholesale and retail, accommodation and catering, transportation support, and residential services) in the commercial and civilian sectors at the target time point. It is usually measured in monetary units (e.g., 100 million yuan) and reflects the scale and development level of economic activities in the commercial and civilian sectors. The unit added value gasoline consumption factor represents the average amount of gasoline consumed per unit of tertiary sector added value created in the commercial and civilian sectors. This factor reflects the correlation between economic activity in this sector and gasoline consumption intensity. Multiplying the two factors yields the total gasoline consumption generated by commercial activities and residential life in the commercial and civilian sectors. This calculation method is applicable to gasoline consumption scenarios in the commercial and civilian sectors, such as small commercial vehicles, residential vehicles, taxis, and ride-hailing services, where gasoline is the primary fuel.

[0135] The diesel consumption in the commercial and civilian sectors is determined by multiplying the added value factor of the tertiary industry with the diesel consumption factor per unit added value.

[0136] The tertiary sector added value factor also represents the total added value of the tertiary sector in the commercial and residential sectors at the target time point. The diesel consumption factor per unit added value represents the average amount of diesel consumed per unit of tertiary sector added value created in the commercial and residential sectors. Multiplying the two together yields the total diesel consumption generated by commercial activities and residential life in the commercial and residential sectors. This calculation method is applicable to diesel consumption scenarios in the commercial and residential sectors, such as activities using diesel as the primary fuel, including logistics and delivery vehicles, city buses, tourist buses, sanitation vehicles, and residential heating oil.

[0137] Using the methods described above, gasoline and diesel consumption were calculated separately for both commercial and residential sectors. These consumption figures for each product type will be used as the energy consumption output for that sector, and will be subsequently aggregated to obtain the total energy demand.

[0138] The energy demand forecasting method and system provided in this application will be further explained below with specific forecasting examples and industrial application scenarios.

[0139] Taking the demand forecast of refined oil products in a certain region from 2025 to 2040 as an example, the energy demand forecasting method provided in this application is applied.

[0140] In this example, firstly, following the aforementioned steps, refined oil consumption is divided into the transportation sector, agriculture, forestry, animal husbandry and fishery sector, industrial and mining sector, construction sector, and commercial and residential sector. Then, the predictive factor set for each sector is obtained, where the values ​​of dynamic predictive factors (such as the new energy substitution rate and the biodiesel substitution ratio) are set according to two different external conditions: the baseline scenario and the aggressive scenario. Next, based on the correspondence between the predictive factor set for each sector and energy consumption, the gasoline consumption, diesel consumption, and kerosene consumption for each sector in the target year are calculated. Finally, the consumption of all sectors is summarized by oil type to obtain the total demand for refined oil.

[0141] The forecasts show that from 2025 to 2040, the total demand for refined oil products in the region will decline under both the baseline and aggressive scenarios. Specifically, the total demand for refined oil products in 2030 is 368 million tons under the baseline scenario and 367 million tons under the aggressive scenario; the total demand in 2040 is 245 million tons under the baseline scenario and 244 million tons under the aggressive scenario.

[0142] The above forecast results are largely consistent with the forecasts of several authoritative energy research institutions. However, because this application employs a multi-dimensional domain decomposition and dynamic factor correction mechanism, it can present the consumption trends of each domain and each oil product separately. Therefore, compared with traditional macro-level total forecasting methods, the forecast results provided by this application have clearer structured information and stronger decision-making guidance significance. Users can use the forecast results to determine which domains have experienced the fastest decline in oil consumption and which oil product demand structures have changed, thereby developing more targeted response strategies.

[0143] The energy demand forecasting method provided in this application, by constructing a multi-dimensional dynamic analysis model, can be widely applied in the petrochemical industry and can provide quantitative support for various decision-making processes.

[0144] Specifically, this application can provide energy authorities with consumption trend analysis results by energy type and consumption sector to support the planning of refining capacity layout, the design of the promotion schedule for new energy vehicles, and the setting of carbon emission reduction targets. For example, when forecasts show that gasoline demand in the transportation sector is entering a rapid decline, energy authorities can correspondingly reduce regional gasoline production quotas while accelerating the deployment of charging or gas refueling infrastructure.

[0145] Secondly, by predicting changes in the demand structure of refined oil products in the regional market over the next 3 to 5 years, this application can guide refineries to adjust their unit capacity configuration, optimize crude oil procurement strategies, and product blending plans, thereby reducing the risk of inventory backlog and improving operational efficiency. For example, if the forecast shows that diesel demand continues to decline while the demand for chemical feedstocks increases, refineries can shift some of their catalytic cracking units towards chemical production in advance.

[0146] Furthermore, this application can provide demand-side data support for cross-regional refined oil pipeline transportation and storage base construction, assisting in the formulation of dynamic logistics scheduling plans and improving supply chain response speed and resource utilization. For example, based on the predicted demand for each region and each type of oil, pipeline operators can rationally arrange transportation batches and volumes to avoid wasting transportation capacity or supply interruptions.

[0147] Furthermore, the consumption trend analysis results provided in this application by product type and by region can provide a fundamental reference for the pricing of financial derivatives such as energy futures and options, and assist trading institutions in judging the market supply and demand pattern and formulating hedging strategies.

[0148] In summary, this application accurately breaks down the demand for refined oil products into multi-dimensional sub-sectors and establishes a dynamic correlation model, solving the technical bottlenecks of traditional methods in data fusion, weight allocation, and adaptability to structural changes. It achieves accurate, dynamic, and multi-scenario prediction of the medium- and long-term demand for refined oil products, which has significant industrial application value and strategic significance.

[0149] The foregoing mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, it includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0150] This application embodiment can divide the energy demand forecasting device into functional modules according to the above method example. For example, each function can be divided into its own functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. Optionally, the module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0151] Figure 4 This is a schematic diagram of the structure of an energy demand forecasting device provided in an embodiment of this application. Figure 4 As shown, the energy demand forecasting device includes: a communication unit 401 and a processing unit 402; Communication unit 401 is used to acquire a set of predictive factors for each of multiple energy consumption areas. The set of predictive factors includes at least one predictive factor whose value changes dynamically with changes in external conditions. The predictive factors are used to represent the factors that affect the energy consumption of the energy consumption area. Processing unit 402 is used to predict the energy consumption of each energy consumption area based on the correspondence between the set of predictive factors for each energy consumption area and the energy consumption. The processing unit 402 is also used to predict the total energy demand based on the energy consumption of each energy consumption sector.

[0152] Optionally, when the energy consumption sector includes the transportation sector, the predictive factors for the transportation sector include: pure gasoline vehicle ownership factor, pure gasoline vehicle fuel consumption factor, new energy hybrid vehicle ownership factor, new energy hybrid vehicle fuel consumption factor, diesel heavy truck ownership factor, diesel heavy truck fuel consumption factor, biodiesel substitution rate factor, civil aviation passenger volume factor, fuel consumption per unit passenger volume factor, civil aviation freight volume factor, and fuel consumption per unit freight volume factor; the energy consumption in the transportation sector includes: gasoline consumption, diesel consumption, and kerosene consumption; Processing unit 402 is specifically used for: The gasoline consumption of a pure gasoline vehicle is determined by multiplying the pure gasoline vehicle ownership factor and the pure gasoline vehicle fuel consumption factor. The gasoline consumption of new energy hybrid vehicles is determined by multiplying the number of new energy hybrid vehicles by the fuel consumption factor of each new energy hybrid vehicle. The gasoline consumption in the transportation sector is determined by the sum of the gasoline consumption of pure gasoline vehicles and the gasoline consumption of new energy hybrid vehicles. The diesel consumption of a diesel heavy-duty truck is determined by multiplying the diesel heavy-duty truck inventory factor by the diesel heavy-duty truck fuel consumption factor per vehicle. Based on the diesel consumption of diesel heavy-duty trucks and the biodiesel substitution rate factor, the diesel consumption in the transportation sector after biodiesel substitution correction is determined. The kerosene consumption of civil aviation passenger transport is determined by multiplying the civil aviation passenger volume factor and the fuel consumption factor per unit passenger volume. The kerosene consumption for civil aviation cargo is determined by multiplying the civil aviation cargo volume factor and the fuel consumption factor per unit cargo volume. The kerosene consumption in the transportation sector is determined by the sum of the kerosene consumption for civil aviation passenger flights and the kerosene consumption for civil aviation cargo flights.

[0153] Optionally, when the energy consumption sector includes agriculture, forestry, animal husbandry and fishery, the predictive factor set for agriculture, forestry, animal husbandry and fishery includes: total power factor of agricultural machinery, fuel consumption per unit power factor and total power factor of motorized fishing vessels; the energy consumption in agriculture, forestry, animal husbandry and fishery includes: gasoline consumption and diesel consumption. Processing unit 402 is specifically used for: The gasoline consumption in the agricultural, forestry, animal husbandry and fishery sectors is determined by multiplying the total power factor of agricultural machinery with the fuel consumption factor per unit power. The diesel consumption of agricultural machinery is determined by multiplying the total power factor of agricultural machinery by the fuel consumption factor per unit power. The diesel consumption of motorized fishing vessels is determined by multiplying the total power factor of the vessel by the fuel consumption factor per unit power. The diesel consumption in the agricultural, forestry, animal husbandry and fishery sectors is determined by summing the diesel consumption of agricultural machinery and diesel consumption of motorized fishing vessels.

[0154] Optionally, when the energy consumption sector includes the industrial and mining sector, the predictive factors for the industrial and mining sector include: industrial added value factor, gasoline consumption per unit added value factor, total power factor for construction equipment, and diesel consumption per unit power factor; the energy consumption in the industrial and mining sector includes: gasoline consumption and diesel consumption. Processing unit 402 is specifically used for: The gasoline consumption in the industrial and mining sectors is determined by multiplying the industrial added value factor and the gasoline consumption factor per unit added value. The diesel consumption in the industrial and mining sector is determined by multiplying the total power factor of the construction equipment by the diesel consumption factor per unit power.

[0155] Optionally, when the energy consumption sector includes the construction sector, the predictive factors for the construction sector include: total power factor of construction equipment, gasoline consumption factor per unit power, and diesel consumption factor per unit power; the energy consumption in the construction sector includes: gasoline consumption and diesel consumption. Processing unit 402 is specifically used for: The gasoline consumption in the construction sector is determined by multiplying the total power factor of construction equipment by the gasoline consumption factor per unit power. The diesel consumption in the construction sector is determined by multiplying the total power factor of construction equipment by the diesel consumption factor per unit power.

[0156] Optionally, in the case where the energy consumption sector includes both commercial and residential sectors, the predictive factors for the commercial and residential sectors include: the added value factor of the tertiary industry, the gasoline consumption factor per unit added value, and the diesel consumption factor per unit added value; the energy consumption in the commercial and residential sectors includes: gasoline consumption and diesel consumption. Processing unit 402 is specifically used for: The gasoline consumption in the commercial and civilian sectors is determined by multiplying the added value factor of the tertiary industry with the gasoline consumption factor per unit added value. The diesel consumption in the commercial and civilian sectors is determined by multiplying the added value factor of the tertiary industry with the diesel consumption factor per unit added value.

[0157] Optional external conditions include: industry development trends and / or user-selected development scenarios.

[0158] Energy demand forecasting devices in an energy demand forecasting system include, for example: Figure 5 The components included. The following are examples. Figure 5 Taking the energy demand forecasting device shown as an example, the hardware structure of the energy demand forecasting device is introduced.

[0159] Figure 5 This is a schematic diagram of the hardware structure of an energy demand forecasting device provided in an embodiment of this application. Figure 5 As shown, the energy demand forecasting device includes: a processor 501, a memory 502, a communication interface 503, and a bus 504. The processor 501, the memory 502, and the communication interface 503 can be connected via the bus 504.

[0160] Processor 501 is the control center of the energy demand forecasting device. It can be a single processor or a collective term for multiple processing elements. For example, processor 501 can be a general-purpose central processing unit (CPU) or other general-purpose processors. The general-purpose processor can be a microprocessor or any conventional processor.

[0161] As one embodiment, processor 501 may include one or more CPUs, for example Figure 5 CPU0 and CPU1 are shown in the diagram.

[0162] The memory 502 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0163] In one possible implementation, the memory 502 can exist independently of the processor 501. The memory 502 can be connected to the processor 501 via a bus 504 and is used to store instructions or program code. When the processor 501 calls and executes the instructions or program code stored in the memory 502, it can implement the energy demand prediction method provided in the following embodiments of this application.

[0164] In this embodiment, the software programs stored in memory 502 differ for the energy demand forecasting device, resulting in different functions implemented by the energy demand forecasting device. The functions performed by each device will be described in conjunction with the following flowchart.

[0165] In another possible implementation, the memory 502 can also be integrated with the processor 501.

[0166] Communication interface 503 is used for connecting the energy demand forecasting device to other devices via a communication network, such as Ethernet, wireless access network, or wireless local area network (WLAN). Communication interface 503 may include a receiving unit for receiving data and a transmitting unit for sending data.

[0167] Bus 504 can be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, or an extended industry standard architecture (EISA) bus. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0168] It should be pointed out that, Figure 5 The structure shown does not constitute a limitation on the energy demand forecasting device, except ​ In addition to the components shown, the energy demand forecasting device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0169] This application also provides a computer-readable storage medium including computer-executable instructions that, when executed on a computer, cause the computer to perform the energy demand forecasting method provided in the above embodiments.

[0170] This application also provides a computer program that can be directly loaded into a memory and contains software code. After being loaded and executed by a computer, the computer program can realize the energy demand prediction method provided in the above embodiments.

[0171] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in this application can be implemented using hardware, software, firmware, or any combination thereof. When implemented in software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer-readable storage media and communication media, wherein communication media include any medium that facilitates the transmission of a computer program from one place to another. Storage media can be any available medium accessible to a general-purpose or special-purpose computer.

[0172] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0173] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and other division methods may exist in actual implementation. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms. Units described as separate components may or may not be physically separate; components shown as units may be one physical unit or multiple physical units, i.e., they may be located in one place or distributed in multiple different places. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0174] Furthermore, the functional units in the various embodiments of this application can be integrated into a single defect detection unit, or each unit can exist physically separately, or two or more units can be integrated into a single unit. The integrated unit can be implemented in hardware or as a software functional unit. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, in essence, or the part that contributes to general technology, or all or part of the technical solution, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0175] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An energy demand forecasting method, characterized in that, include: Obtain a set of predictive factors for each of multiple energy consumption sectors, wherein the set of predictive factors includes at least one predictive factor whose value dynamically changes with external conditions; the predictive factors are used to represent factors affecting the energy consumption of the energy consumption sector. Based on the correspondence between the set of predictive factors for each energy consumption sector and the energy consumption, predict the energy consumption of that energy consumption sector; Based on the energy consumption of each energy consumption sector, the total energy demand is predicted.

2. The method according to claim 1, characterized in that, When the energy consumption sector includes the transportation sector, the predictive factor set for the transportation sector includes: pure gasoline vehicle ownership factor, pure gasoline vehicle fuel consumption factor, new energy hybrid vehicle ownership factor, new energy hybrid vehicle fuel consumption factor, diesel heavy truck ownership factor, diesel heavy truck fuel consumption factor, biodiesel substitution rate factor, civil aviation passenger volume factor, fuel consumption per unit passenger volume factor, civil aviation freight volume factor, and fuel consumption per unit freight volume factor; the energy consumption in the transportation sector includes: gasoline consumption, diesel consumption, and kerosene consumption. The step of predicting the energy consumption of each energy consumption sector based on the correspondence between the predictor set of each energy consumption sector and the energy consumption includes: The gasoline consumption of a pure gasoline vehicle is determined by multiplying the pure gasoline vehicle ownership factor and the pure gasoline vehicle fuel consumption factor. The gasoline consumption of a new energy hybrid vehicle is determined by multiplying the new energy hybrid vehicle ownership factor and the new energy hybrid vehicle fuel consumption factor per vehicle. The gasoline consumption in the transportation sector is determined by the sum of the gasoline consumption of the pure gasoline vehicle and the gasoline consumption of the new energy hybrid vehicle. The diesel consumption of a diesel heavy-duty truck is determined by multiplying the diesel heavy-duty truck inventory factor by the diesel heavy-duty truck fuel consumption factor per vehicle. Based on the diesel consumption of the diesel heavy-duty trucks and the biodiesel substitution rate factor, the diesel consumption in the transportation sector after biodiesel substitution correction is determined. The kerosene consumption for civil aviation passenger transport is determined by multiplying the civil aviation passenger volume factor and the fuel consumption factor per unit passenger volume. The kerosene consumption for civil aviation cargo is determined by multiplying the civil aviation cargo volume factor and the fuel consumption factor per unit cargo volume. The kerosene consumption in the transportation sector is determined by summing the kerosene consumption for civil aviation passenger transport and the kerosene consumption for civil aviation cargo transport.

3. The method according to claim 1, characterized in that, When the energy consumption sector includes agriculture, forestry, animal husbandry and fishery, the predictive factor set for the agriculture, forestry, animal husbandry and fishery sector includes: total power factor of agricultural machinery, fuel consumption per unit power factor and total power factor of motorized fishing vessels; the energy consumption of the agriculture, forestry, animal husbandry and fishery sector includes: gasoline consumption and diesel consumption. The step of predicting the energy consumption of each energy consumption sector based on the correspondence between the predictor set of each energy consumption sector and the energy consumption includes: The gasoline consumption in the agricultural, forestry, animal husbandry and fishery sector is determined by multiplying the total power factor of the agricultural machinery with the fuel consumption factor per unit power. The diesel consumption for agricultural machinery is determined by multiplying the total power factor of the agricultural machinery by the fuel consumption factor per unit power. The diesel fuel consumption of the motorized fishing vessel is determined by multiplying the total power factor of the motorized fishing vessel with the fuel consumption factor per unit power. The diesel consumption in the agricultural, forestry, animal husbandry and fishery sectors is determined by summing the diesel consumption of agricultural machinery and the diesel consumption of motorized fishing vessels.

4. The method according to claim 1, characterized in that, When the energy consumption sector includes the industrial and mining sector, the predictive factor set for the industrial and mining sector includes: industrial added value factor, gasoline consumption per unit added value factor, total power factor for construction equipment, and diesel consumption per unit power factor; the energy consumption in the industrial and mining sector includes: gasoline consumption and diesel consumption. The step of predicting the energy consumption of each energy consumption sector based on the correspondence between the predictor set of each energy consumption sector and the energy consumption includes: The gasoline consumption in the industrial and mining sector is determined by multiplying the industrial added value factor and the gasoline consumption factor per unit added value. The diesel consumption in the industrial and mining sector is determined by multiplying the total power factor of the construction equipment by the diesel consumption factor per unit power.

5. The method according to claim 1, characterized in that, When the energy consumption sector includes the construction sector, the predictive factor set for the construction sector includes: total power factor for construction equipment, gasoline consumption factor per unit power, and diesel consumption factor per unit power; the energy consumption in the construction sector includes: gasoline consumption and diesel consumption. The step of predicting the energy consumption of each energy consumption sector based on the correspondence between the predictor set of each energy consumption sector and the energy consumption includes: The gasoline consumption in the construction field is determined by multiplying the total power factor of the construction equipment by the gasoline consumption factor per unit power. The diesel consumption in the construction sector is determined by multiplying the total power factor of the construction equipment by the diesel consumption factor per unit power.

6. The method according to claim 1, characterized in that, When the energy consumption sector includes both commercial and residential sectors, the predictive factor set for the commercial and residential sectors includes: the added value factor of the tertiary industry, the gasoline consumption factor per unit added value, and the diesel consumption factor per unit added value; the energy consumption in the commercial and residential sectors includes: gasoline consumption and diesel consumption. The step of predicting the energy consumption of each energy consumption sector based on the correspondence between the predictor set of each energy consumption sector and the energy consumption includes: The gasoline consumption in the commercial and civilian sectors is determined by multiplying the added value factor of the tertiary industry with the gasoline consumption factor per unit added value. The diesel consumption in the commercial and civilian sectors is determined by multiplying the added value factor of the tertiary industry with the diesel consumption factor per unit added value.

7. The method according to claim 1, characterized in that, The external conditions include: industry development trends and / or user-selected development scenarios.

8. An energy demand forecasting device, characterized in that, include: Communication unit and processing unit; The communication unit is used to acquire a set of predictive factors for each of multiple energy consumption areas, wherein the set of predictive factors includes at least one predictive factor whose value changes dynamically with changes in external conditions; the predictive factor is used to represent the factors affecting the energy consumption of the energy consumption area. The processing unit is used to predict the energy consumption of each energy consumption area based on the correspondence between the prediction factor set of each energy consumption area and the energy consumption. The processing unit is also used to predict the total energy demand based on the energy consumption of each energy consumption sector.

9. An electronic device, characterized in that, The electronic device includes: processor; A memory configured to store processor-executable instructions; The processor is configured to execute the instructions to implement the method as described in any one of claims 1-7.

10. A non-volatile storage medium, characterized in that, The storage medium stores a computer program, which, when read and executed, implements the method as described in any one of claims 1-7.

Images