Methods and related equipment for predicting electricity substitution

Abstract

This invention provides a method and related equipment for predicting electricity substitution, relating to the field of electricity substitution technology. The method includes: predicting the total energy consumption for a prediction period based on an energy consumption prediction model, obtaining the predicted total energy consumption for the prediction period; the energy consumption prediction model is constructed based on system dynamics; predicting the electricity consumption for the prediction period based on an electricity consumption prediction model, obtaining the predicted electricity consumption for the prediction period; the electricity consumption prediction model is constructed based on the grey prediction method; and obtaining the predicted electricity substitution amount for the prediction period based on the total predicted energy consumption and the predicted electricity consumption amount. This invention avoids directly applying historical electricity substitution data, achieving accurate prediction of electricity substitution amount and accurate understanding of regional electricity substitution trends.

Description

Technical Field

[0001] This invention relates to the field of electricity substitution technology, and in particular to a method and related equipment for predicting electricity substitution volume. Background Technology

[0002] The development of electricity substitution has now entered a critical stage, making it essential to predict the electricity substitution situation in different regions and to understand the regional energy consumption situation.

[0003] Traditional methods for predicting electricity substitution include single prediction models and combined prediction models. These traditional methods all rely on a certain amount of historical data on electricity substitution. However, due to the short development time of electricity substitution and the limited amount of data, the prediction results obtained from a small amount of historical data are not ideal. Summary of the Invention

[0004] This invention provides a method and related equipment for predicting electricity substitution, which solves the defects of unsatisfactory electricity substitution prediction results in the prior art, and realizes accurate prediction of electricity substitution and accurate knowledge of the changing trend of electricity substitution in a region.

[0005] This invention provides a method for predicting electricity substitution, comprising:

[0006] Based on the energy consumption forecasting model, the total predicted energy consumption for the forecast period is obtained; the energy consumption forecasting model is constructed based on system dynamics.

[0007] Based on the electricity consumption forecasting model, the predicted electricity consumption for the forecast period is obtained; the electricity consumption forecasting model is constructed based on the grey forecasting method.

[0008] Based on the total energy consumption forecast and the electricity consumption forecast, the electricity substitution forecast for the forecast period is obtained.

[0009] In some embodiments, obtaining the predicted electricity substitution amount for the forecast period based on the total predicted energy consumption and the predicted electricity consumption includes:

[0010] Determine the electrification rate for a preset reference time period; the electrification rate for the preset reference time period is the proportion of electricity consumption during the preset reference time period to the total energy consumption during the preset reference time period.

[0011] Calculate the electrification rate for the forecast period; the electrification rate for the forecast period is the proportion of the forecasted electricity consumption to the total forecasted energy consumption.

[0012] The predicted amount of electricity substitution for the predicted period is obtained based on the total predicted energy consumption, the electrification rate of the preset benchmark period, and the electrification rate of the predicted period.

[0013] In some embodiments, before obtaining the total predicted energy consumption for the forecast period based on the energy consumption forecasting model, the method further includes:

[0014] Based on the factors affecting total energy consumption, the subsystems of the energy consumption system are determined;

[0015] Identify the impact indicators affecting the total energy consumption within each subsystem, and determine the type of the impact indicators;

[0016] The energy consumption forecasting model is constructed based on the correlation between the various influencing indicators and the types of the indicators.

[0017] In some embodiments, before obtaining the predicted electricity consumption for the predicted period based on the electricity consumption prediction model, the method further includes:

[0018] Historical energy consumption data starting from a preset baseline time period is obtained, and the historical energy consumption data is sorted in chronological order according to the time period to obtain a historical energy consumption sequence.

[0019] The historical energy consumption data in the historical energy consumption series are accumulated according to the sorting value to obtain the accumulated energy consumption series.

[0020] The electricity consumption prediction model is obtained based on the historical electricity consumption series and the cumulative electricity consumption series.

[0021] In some embodiments, obtaining the predicted electricity consumption for the predicted period based on the electricity consumption prediction model includes:

[0022] Obtain the cumulative value of electricity consumption prediction for the predicted period output by the electricity consumption prediction model, and the cumulative value of electricity consumption prediction for the period preceding the predicted period.

[0023] The difference between the cumulative predicted electricity consumption value corresponding to the predicted period and the cumulative predicted electricity consumption value corresponding to the previous period is taken as the predicted electricity consumption amount for the predicted period.

[0024] In some embodiments, the expression for the predicted amount of electricity substitution is as follows:

[0025]

[0026] In the formula, t represents the prediction period, and D e,t Y represents the predicted amount of electricity substitution for the forecast period. t S represents the total predicted energy consumption for the forecast period. t This represents the electrification rate for the predicted period, where t0 represents the preset baseline period. This indicates the electrification rate for the predicted baseline period.

[0027] The present invention also provides an electricity substitution quantity prediction device, comprising:

[0028] The first acquisition module is used to acquire the total predicted energy consumption for the forecast period based on the energy consumption forecasting model; the energy consumption forecasting model is constructed based on system dynamics.

[0029] The second acquisition module is used to acquire the predicted amount of electricity consumption for the prediction period based on the electricity consumption prediction model; the electricity consumption prediction model is constructed based on the grey prediction method.

[0030] The third acquisition module is used to obtain the predicted amount of electricity substitution for the forecast period based on the predicted total energy consumption and the predicted amount of electricity consumption.

[0031] The present invention also provides an electronic device, 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 electricity substitution prediction method as described above.

[0032] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the electricity substitution prediction method as described above.

[0033] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the electricity substitution prediction method as described above.

[0034] The method and related equipment for predicting electricity substitution provided by this invention obtain the total predicted energy consumption through system dynamics, obtain the predicted electricity consumption through grey prediction, and then indirectly obtain the predicted electricity substitution through the total predicted energy consumption and the predicted electricity consumption. This avoids directly applying historical data on electricity substitution, and achieves accurate prediction of electricity substitution and accurate knowledge of the changing trend of electricity substitution in a region. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0036] Figure 1 This is one of the flowcharts of an exemplary embodiment of the present invention for predicting electricity substitution.

[0037] Figure 2 This is a second schematic flowchart of an exemplary embodiment of the present invention for predicting electricity substitution quantities.

[0038] Figure 3 This is the third flowchart of an exemplary embodiment of the present invention for predicting electricity substitution quantities;

[0039] Figure 4 This is the fourth flowchart of an exemplary embodiment of the present invention for predicting electricity substitution quantities;

[0040] Figure 5 This is the fifth flowchart of an exemplary embodiment of the present invention for predicting electricity substitution quantities;

[0041] Figure 6 This is a schematic diagram of the structure of an energy substitution prediction device provided in an exemplary embodiment of the present invention;

[0042] Figure 7 This is a schematic diagram of the physical structure of an electronic device provided in an exemplary embodiment of the present invention. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. It should be noted that, unless otherwise specified, the embodiments and features of the embodiments of this invention can be combined with each other. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0045] It should be further noted that, in this document, 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 limitation, 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.

[0046] In this invention, "at least one" means one or more, and "more than one" means two or more. The terms "first," "second," "third," "fourth," etc. (if present) in this invention are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0047] In embodiments of the present invention, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" or "for example" in embodiments of the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0048] Please refer to Figure 1 , Figure 1 This is one of the flowcharts illustrating an exemplary embodiment of the electricity substitution prediction method provided by the present invention. The present invention provides an electricity substitution prediction method, the execution subject of which can be a terminal device or a server. The terminal device can be, but is not limited to, various personal computers, laptops, and tablets, etc., and the server can be a standalone server or a server cluster composed of multiple servers. The following description uses a terminal device as the execution subject of the method. The electricity substitution prediction method provided in this embodiment includes the following steps:

[0049] Step 110: Based on the energy consumption forecasting model, obtain the total predicted energy consumption for the forecast period; the energy consumption forecasting model is constructed based on system dynamics.

[0050] Specifically, given the numerous factors influencing energy consumption, terminal equipment employs system dynamics to construct energy consumption prediction models. System dynamics builds the system structure framework using a loop approach, describes the logical relationships between systems using causal diagrams and flow graphs, describes the quantitative relationships between systems using equations, and uses computer simulation software for simulation analysis.

[0051] The terminal equipment inputs historical energy consumption data into the energy consumption prediction model and selects the prediction period to obtain the total energy consumption for the prediction period.

[0052] In some embodiments, a time period is the time interval between two moments, such as a month, two months, a year, or two years. The prediction time period can be a prediction month, a prediction year, or the like.

[0053] Step 120: Based on the electricity consumption forecast model, obtain the predicted electricity consumption for the forecast period; the electricity consumption forecast model is constructed based on the grey forecasting method.

[0054] Specifically, since there is sufficient historical data on electricity consumption, the terminal equipment uses the grey prediction method to construct an electricity consumption prediction model. The grey prediction method is a prediction method for grey systems. It identifies the degree of difference in development trends among system factors (i.e., performs correlation analysis), processes the original data to find patterns in system changes, generates data sequences with strong regularity, and then establishes corresponding differential equation models to predict future development trends.

[0055] The terminal equipment inputs historical electricity consumption data into the electricity consumption prediction model and selects the prediction period to obtain the predicted electricity consumption for that period.

[0056] Step 130: Based on the total energy consumption forecast and the electricity consumption forecast, obtain the electricity substitution forecast for the forecast period.

[0057] Specifically, the terminal equipment links the amount of electricity substitution with the total energy consumption and the amount of electricity consumption, thereby indirectly obtaining the predicted amount of electricity substitution through the predicted total energy consumption and the predicted amount of electricity consumption, thus realizing the prediction of the amount of electricity substitution in the region.

[0058] The method for predicting electricity substitution provided in this embodiment obtains the total predicted energy consumption through system dynamics, obtains the predicted electricity consumption through grey prediction, and then indirectly obtains the predicted electricity substitution through the total predicted energy consumption and the predicted electricity consumption. This avoids directly applying historical data on electricity substitution, and achieves accurate prediction of electricity substitution and accurate knowledge of the changing trend of electricity substitution in a region.

[0059] Please refer to Figure 2 , Figure 2 This is a second schematic flowchart of an exemplary embodiment of the present invention for predicting electricity substitution. This embodiment further illustrates the foregoing embodiment, mainly describing the specific process of obtaining the predicted electricity substitution amount for a prediction period based on the total predicted energy consumption and the predicted electricity consumption. The electricity substitution prediction method provided in this embodiment includes the following steps:

[0060] Step 210: Determine the electrification rate for the preset reference period; the electrification rate for the preset reference period is the proportion of electricity consumption in the preset reference period to the total energy consumption in the preset reference period.

[0061] Specifically, in some embodiments, the preset reference time period can be a period before the predicted time period and also a period within the historical time period. For example, if the preset time period is 2035 and the historical time period is from 2012 to 2022, then the preset reference time period can be 2015.

[0062] After determining the preset reference time period, the terminal equipment obtains the electricity consumption and total energy consumption of the preset reference time period, and determines the electrification rate of the preset reference time period based on the electricity consumption and total energy consumption of the preset reference time period.

[0063] The expression for the electrification rate during the preset reference time period is as follows:

[0064]

[0065] Where t0 represents the preset baseline time period, This indicates the electrification rate for a preset reference time period. This indicates the electricity consumption during a preset reference period. This represents the total energy consumption for the preset baseline period. Step 220: Calculate the electrification rate for the forecast period; the electrification rate for the forecast period is the proportion of the forecasted electricity consumption to the total forecasted energy consumption.

[0066] Specifically, after obtaining the predicted electricity consumption and total energy consumption, the terminal equipment determines the electrification rate for the forecast period based on the predicted electricity consumption and total energy consumption.

[0067] The expression for the electrification rate during the forecast period is as follows:

[0068]

[0069] Where t represents the prediction period, S t Q represents the electrification rate for the forecast period. t Y represents the electricity consumption for the predicted period. t This indicates the total energy consumption for the forecast period.

[0070] Step 230: Based on the total energy consumption forecast, the electrification rate of the preset baseline period, and the electrification rate of the forecast period, obtain the predicted amount of electricity substitution for the forecast period.

[0071] Specifically, the proportion of electricity consumption to total energy consumption can reflect whether electricity has replaced other energy sources in the energy consumption process.

[0072] If the proportion of electricity consumption in total energy consumption increases, it means that electricity has replaced other energy sources in the energy consumption process; if the proportion of electricity consumption in total energy consumption remains unchanged or decreases, it means that electricity has not been replaced by other energy sources in the energy consumption process.

[0073] The terminal equipment compares the electrification rate of the preset base period with the electrification rate of the predicted period to obtain the difference in electrification rate. Then, it multiplies the difference in electrification rate with the total predicted energy consumption to obtain the predicted amount of electricity substitution for the predicted period.

[0074] In some embodiments, the expression for the predicted amount of electricity substitution is as follows:

[0075]

[0076] In the formula, t represents the prediction period, and D e,t Y represents the predicted amount of electricity substitution for the forecast period. t S represents the total predicted energy consumption for the forecast period. t This represents the electrification rate for the predicted period, where t0 represents the preset baseline period. This indicates the electrification rate for the predicted baseline period.

[0077] The electricity substitution prediction method provided in this embodiment achieves accurate acquisition of the predicted electricity substitution amount by multiplying the difference between the electrification rate of the preset benchmark period and the electrification rate of the predicted period by the total predicted energy consumption. Please refer to... Figure 3 , Figure 3 This is the third flowchart illustrating the electricity substitution prediction method provided in an exemplary embodiment of the present invention. This embodiment further explains the foregoing embodiments, mainly illustrating the specific process of constructing an energy consumption prediction model.

[0078] Step 310: Determine the subsystems of the energy consumption system based on the factors affecting total energy consumption.

[0079] Specifically, an energy consumption system is constructed based on the region's energy consumption situation. The energy consumption system includes all factors that affect total energy consumption.

[0080] In some embodiments, the terminal equipment quantifies the degree of influence of influencing factors on total energy consumption, and the influencing factors with the highest quantified values ​​are determined as the boundary of the energy consumption system, that is, the subsystem of the energy consumption system.

[0081] For example, the economy, energy, and environment are the leading influencing factors in terms of quantifiable values. Therefore, the energy consumption system is defined within the three subsystems of energy, economy, and environment.

[0082] Step 320: Determine the impact indicators on total energy consumption within each subsystem, and determine the type of the impact indicators.

[0083] Specifically, each subsystem includes many indicators that are related to the corresponding influencing factors, that is, indicators that have an impact on the corresponding influencing factors, but these indicators do not necessarily have an impact on the total energy consumption.

[0084] The terminal equipment identifies the indicators that affect total energy consumption from the indicators included in each subsystem, and defines the identified indicators that affect total energy consumption as the influencing indicators.

[0085] In some embodiments, the terminal device determines the impact indicators within each subsystem based on the principles of system dynamics, dynamism, scientificity, operability, regionality, and local characteristics.

[0086] After determining the impact indicators within each subsystem, the terminal device determines the indicator type for each impact indicator. Indicator types include: state variables, rate variables, auxiliary variables, and constants.

[0087] As a cumulative quantity, the state variable is expressed in the state equation as follows:

[0088] IL.K = Initial + DT * (R1) in .JK-R2 out .JK)

[0089] Where IL.K is the output of the state equation at time K, DT is the difference step size within the system, Initial represents the initial value of the state variable, J and K represent two adjacent time points within the system, and R1 in .JK represents the input rate of the state variable during the time interval between time K and time J, that is, the increase in the state variable during the time interval between time K and time J, R2 out .JK represents the output rate equation of the state variable during the time interval between time K and time J, that is, the decrease of the state variable during the time interval between time K and time J.

[0090] The auxiliary equation is used in the decision-making process to calculate the output of the state equation. The expression of the auxiliary equation is as follows:

[0091] A1 = f(IL, Constant.C1)

[0092] Where A1 is the output of the auxiliary equation, IL represents the output of the state equation, and C1 is a constant.

[0093] The rate equation is used to calculate the changing patterns of the state equation decision process. The expression for the rate equation is shown below:

[0094] R1 in =f(A1,Constant.C2)

[0095] Among them, R1 in A1 represents the increase in the state variable, A2 is the output of the auxiliary equation, and C2 is a constant.

[0096] Step 330: Construct an energy consumption forecasting model based on the correlation between various influencing indicators and the types of indicators.

[0097] Specifically, the construction of energy consumption forecasting models includes the creation of causal loop diagrams and flow graphs. Terminal devices clarify the chain reactions between various influencing indicators by identifying their correlations, thereby creating causal loop diagrams and flow graphs.

[0098] Based on the determined causal loop diagram, flow graph, and index types, equations relating the various influencing indicators are constructed to obtain an initial energy consumption forecasting model. After obtaining the initial energy consumption forecasting model, it is necessary to perform model validation.

[0099] The verification process includes checking the model parameters, logical structure, model dimensions, and whether the model can operate normally. Only when the verification passes is the constructed energy consumption forecasting model obtained, which can then be used to predict total energy consumption. If the verification fails, the process returns to the model building steps to modify the error-prone parts.

[0100] In some embodiments, after obtaining the constructed energy consumption forecasting model, known data from historical periods are acquired, a benchmark period is selected from the historical periods, and values ​​are assigned to each influencing indicator based on the data of the benchmark period. The assigned values ​​are based on the values ​​of the benchmark period, thereby the constructed energy consumption forecasting model outputs the total predicted energy consumption for the forecast period.

[0101] The electricity substitution prediction method provided in this embodiment constructs a subsystem by considering the factors affecting total energy consumption, and then uses the indicators affecting total energy consumption within each subsystem to construct an energy consumption prediction model. This avoids data unrelated to total energy consumption from participating in the model construction, thereby improving the accuracy of the energy consumption prediction model and further enhancing the accuracy of total energy consumption prediction.

[0102] Please refer to Figure 4 , Figure 4 This is the fourth flowchart illustrating the electricity substitution prediction method provided in an exemplary embodiment of the present invention. This embodiment further explains the foregoing embodiments, mainly illustrating the specific process of constructing an electricity consumption prediction model. The electricity substitution prediction method provided in this embodiment includes the following steps:

[0103] Step 410: Obtain historical electricity consumption data starting from a preset base period, and sort the historical electricity consumption data according to the chronological order of the time periods to obtain a historical electricity consumption sequence.

[0104] Specifically, the terminal device acquires historical energy consumption data for a preset reference time period and subsequent periods, with one energy consumption data point corresponding to each time period. The terminal device then arranges the acquired historical energy consumption data in chronological order, with the energy consumption data for the preset reference time period appearing first, the energy consumption data for the period immediately following the preset reference time period appearing second, and so on, to obtain a historical energy consumption sequence.

[0105] Historical electricity consumption series X (0) The expression is as follows:

[0106] X (0) ={X (0) (i),i=1,2,…,n}={X (0) (1), X (0) (2), ..., X (0) (n)}

[0107] In the formula, X (0) X represents a series of historical electricity consumption data. (0) (i) represents the i-th electricity consumption data in the historical electricity consumption series, and n represents the permutation value of the last data in the series.

[0108] Step 420: Accumulate the historical electricity consumption data in the historical electricity consumption series according to the sorting value to obtain the accumulated electricity consumption series.

[0109] Specifically, the terminal device will store the historical electricity consumption data series X. (0) The historical electricity consumption data of the first few values ​​are summed to obtain the cumulative electricity consumption series X. (1) The sorted value is the cumulative electricity consumption data.

[0110] For example, if the sorting value is 1, then the first historical electricity consumption data in the historical electricity consumption series will be used as the first cumulative electricity consumption data in the cumulative electricity consumption series.

[0111] For example, if the sort value is 2, then the first and second historical electricity consumption data in the historical electricity consumption series will be summed, and the sum will be used as the second accumulated electricity consumption data in the accumulated electricity consumption series.

[0112] The expression for the k-th cumulative energy consumption data in the cumulative energy consumption sequence is shown below:

[0113]

[0114] In the formula, X (1) (k) represents the k-th cumulative energy consumption data in the cumulative energy consumption sequence, x (0)(i) represents the i-th electricity consumption data in the historical electricity consumption series, and n represents the permutation value of the last data in the series.

[0115] The expression for the cumulative electricity consumption sequence is as follows:

[0116] X (1) ={X (1) (k),k=1,2,…,n}={X (1) (1), X (1) (2), ..., X (1) (n)}

[0117] ={X (0) (1), X (0) (1)+X (0) (2), ..., X (0) (1)+…+X (0) (n-1)+X (0) (n)}

[0118] In the formula, X (1) X represents a cumulative electricity consumption sequence. (1) (k) represents the kth cumulative energy consumption data in the cumulative energy consumption sequence, and n represents the permutation value of the last data in the sequence.

[0119] Step 430: Based on the historical electricity consumption series and the cumulative electricity consumption series, obtain the electricity consumption prediction model.

[0120] Specifically, based on the grey prediction method, the expression for the initial electricity consumption prediction model is as follows:

[0121]

[0122] in,

[0123]

[0124]

[0125]

[0126] Y n =(X (0) (2), X (0) (3), ..., X (0) (n)) T

[0127] In the formula, a and u are the parameters of the electricity consumption prediction model. X represents (1) The predicted value of (k).

[0128] Yn For historical electricity consumption series X (0) The sequence starting from the second data point is based on the cumulative electricity consumption sequence X. (1) The data in the middle can determine B, and then based on Y n Together with B, we can obtain a two-row, two-column matrix. get Then, the values ​​of a and u can be obtained according to the principle of least squares, thus obtaining the electricity consumption prediction model.

[0129] The electricity substitution prediction method provided in this embodiment obtains historical electricity consumption data starting from a preset benchmark period, obtains historical electricity consumption series and cumulative electricity consumption series based on the historical electricity consumption data, and finally determines the parameters of the electricity consumption prediction model through the historical electricity consumption series and cumulative electricity consumption series, thereby improving the accuracy of constructing the electricity consumption prediction model and further improving the accuracy of the cumulative value of electricity consumption prediction.

[0130] Please refer to Figure 5 , Figure 5 This is the fifth flowchart illustrating an exemplary embodiment of the present invention for predicting electricity substitution. This embodiment further explains the foregoing embodiments, primarily illustrating the specific process of obtaining the predicted electricity consumption for a given period based on an electricity consumption prediction model. The electricity substitution prediction method provided in this embodiment includes the following steps:

[0131] Step 510: Obtain the cumulative value of electricity consumption forecast for the forecast period corresponding to the forecast period output by the electricity consumption forecast model, and the cumulative value of electricity consumption forecast for the period preceding the forecast period.

[0132] Specifically, the electricity consumption forecasting model is based on the cumulative electricity consumption series X. (1) The data in the model is used for prediction; therefore, the output of the electricity consumption prediction model is the cumulative value of electricity consumption predictions, which can be used to form a cumulative electricity consumption prediction series.

[0133] The terminal device determines the ranking value corresponding to the predicted period based on a preset base period. For example, if the preset base period is 2012 and the preset period is 2021, then the ranking value corresponding to the predicted period is 10.

[0134] After determining the ranking value g corresponding to the forecast period, the cumulative value of electricity consumption forecast for the forecast period is the cumulative electricity consumption forecast series. The cumulative electricity consumption forecast sequence is the sum of the electricity consumption forecasts for the previous period corresponding to the g-th data point. The (g-1)th data point.

[0135] Electricity consumption forecast cumulative series The g-th data The expression is as follows:

[0136]

[0137] In the formula, X represents (1) The predicted value of (g), X represents (0) The predicted value of (g), X represents (0) The predicted value of (g-1) X represents (0) (1) Predicted value.

[0138] Electricity consumption forecast cumulative series The g-th data The expression is as follows:

[0139]

[0140] In the formula, X represents (1) The predicted value of (g-1) X represents (0) The predicted value of (g-1) X represents (0) The predicted value of (g-2) X represents (0) (1) Predicted value.

[0141] Step 520: The difference between the cumulative predicted electricity consumption value for the predicted period and the cumulative predicted electricity consumption value for the previous period is taken as the predicted electricity consumption amount for the predicted period.

[0142] Specifically, the terminal equipment calculates the difference between the cumulative predicted electricity consumption value for the predicted period and the cumulative predicted electricity consumption value for the previous period, i.e., it calculates... and The difference between them.

[0143] and The expression for the difference between them is as follows:

[0144]

[0145] In the formula, X represents (1) The predicted value of (g-1) X represents (1) The predicted value of (g-1) X represents (0) The predicted value of (g) is the predicted amount of electricity consumption for the predicted period. The electricity substitution prediction method provided in this embodiment obtains the predicted period and the output value of the previous period corresponding to the predicted period from the electricity consumption prediction model, and uses the difference between the two output values ​​as the predicted amount of electricity consumption for the predicted period, thereby achieving accurate acquisition of the predicted amount of electricity consumption.

[0146] The method for predicting electricity substitution provided by the present invention will be applied to specific embodiments below.

[0147] For example, Table 1 shows the influencing indicators and indicator types within the economic subsystem. As shown in Table 1, since the industrial structure has a significant impact on total energy consumption, the influencing indicators within the economic subsystem include: Gross Domestic Product (GDP), GDP growth, output value and energy consumption per 100 million yuan of output value of the tertiary, secondary, and primary industries, energy consumption per unit of GDP, GDP growth rate, output value coefficients and energy consumption coefficients of the tertiary, secondary, and primary industries.

[0148] Among them, GDP is a state variable; GDP growth is a rate variable; the output value of the tertiary industry, secondary industry, and primary industry, as well as the energy consumption per 100 million yuan of output value and the energy consumption per unit of GDP, are auxiliary variables; the GDP growth rate, the output value coefficient of the tertiary industry, secondary industry, and primary industry, and the energy consumption coefficient are constants.

[0149] Table 1. Impact Indicators and Indicator Types within the Economic Subsystem

[0150]

[0151] For example, Table 2 shows the influencing indicators and indicator types within the energy subsystem. As shown in Table 2, since the energy structure has a significant impact on total energy consumption, the influencing indicators within the energy subsystem include: total energy consumption, changes in energy consumption, energy consumption of coal, oil, natural gas, and hydropower, the proportion of energy consumption of coal, oil, natural gas, and hydropower, and the average annual growth rate of energy consumption of coal, oil, and natural gas.

[0152] Among them, total energy consumption is a state variable; change in energy consumption is a rate variable; energy consumption of coal, oil, natural gas and hydropower is an auxiliary variable; the proportion of energy consumption of coal, oil, natural gas and hydropower, and the average annual growth rate of energy consumption of coal, oil and natural gas are constants.

[0153] Table 2. Impact Indicators and Indicator Types within the Energy Subsystem

[0154]

[0155]

[0156] For example, Table 3 shows the impact indicators and indicator types within the environmental subsystem. As shown in Table 3, since carbon dioxide emissions have a significant impact on total energy consumption, the impact indicators within the environmental subsystem include: cumulative carbon dioxide emissions, total carbon dioxide emissions, consumption of raw coal, crude oil, and natural gas, carbon emissions from raw coal, crude oil, and natural gas, per capita energy consumption, population size, birth rate, death rate, carbon emission coefficients of raw coal, crude oil, and natural gas, standardization coefficients of crude oil and natural gas, birth rate, death rate, and ecological and environmental impact factors.

[0157] Among them, cumulative carbon dioxide emissions and population size are state variables; carbon dioxide emissions, births and deaths are rate variables; consumption of raw coal, crude oil and natural gas, carbon emissions of raw coal, crude oil and natural gas, and per capita energy consumption are auxiliary variables; carbon emission coefficients of raw coal, crude oil and natural gas, standardization coefficients of crude oil and natural gas, birth rate, death rate and ecological environment impact factors are constants.

[0158] Table 3. Impact Indicators and Indicator Types within the Energy Subsystem

[0159]

[0160]

[0161] Based on the interactions between the subsystems, a stock-flow map for predicting total energy consumption is established. This system uses 2010 as the starting point and analyzes the next 25 years, simulating energy consumption in region A from 2010 to 2035, with a time interval of one year. To simplify the model, the "total natural gas production" and "total natural gas consumption" in the system only include conventional natural gas, and the system does not consider oil import / export volumes, natural gas import / export volumes, oil prices, coal prices, natural gas prices, electricity prices, or the consumption of intermediate energy conversions.

[0162] By analyzing the causal relationships among various systems in sustainable energy consumption development, system dynamics equations are used to link the various influencing indicators. Due to space limitations, only some of the equations for the influencing indicators are listed here (Units indicate the unit):

[0163] (1) Energy consumption per unit of GDP = Total energy consumption / GDP Units: 10,000 tons of standard coal / 100 million yuan;

[0164] (2) Output value of primary industry = Output value coefficient of primary industry * GDP + 1363.67 Units: 100 million yuan;

[0165] (3) Energy consumption of primary industry = energy consumption coefficient of primary industry * total energy consumption (Units: 10,000 tons of standard coal);

[0166] (4) Energy consumption coefficient of primary industry = 0.02733 Units: Dmnl;

[0167] (5) Energy consumption per 100 million yuan of output value of the primary industry = Energy consumption of the primary industry / Output value of the primary industry (Units: 10,000 tons of standard coal / 100 million yuan)

[0168] (6) Cumulative carbon dioxide emissions = INTEG(emissions, 50000) Units: 10,000 tons;

[0169] (7) Coal energy consumption = Coal energy consumption proportion * Total energy consumption (Units: 10,000 tons of standard coal);

[0170] (8) Coal energy consumption ratio = WITH LOOKUP(time, ([2010, 0) - (2021, 1)], (2010, 0.578), (2011, 0.62), (2012, 0.568), (2013, 0.568), (2014, 0.53), (2015, 0.499), (2016, 0.429)), (2017, 0.451), (2018, 0.484), (2019, 0.473), (2020, 0.483))Units: Dmnl;

[0171] (9) Average annual growth rate of coal energy consumption = 0.032 Units: Dmnl;

[0172] (10) Raw coal carbon emissions = Raw coal carbon emission coefficient * Raw coal consumption * 44 / 12 Units: 10,000 tons;

[0173] (11) Raw coal carbon emission coefficient = 0.7476 Units: kg standard coal / kg;

[0174] (12) Raw coal consumption = Coal energy consumption / Raw coal conversion coefficient (Units: 10,000 tons of standard coal);

[0175] (13) Raw coal conversion factor = 0.7143 Units: tons of standard coal;

[0176] (14) Emissions = Carbon emissions from natural gas + Carbon emissions from raw coal + Carbon emissions from crude oil (Units: 10,000 tons)

[0177] (15) Total energy consumption = INTEG(change in energy consumption, 9189.42) Units: 10,000 tons of standard coal;

[0178] (16) GDP = INTEG(GDP growth, 15002.51) Units: RMB 100 million;

[0179] (17) GDP growth = GDP * GDP growth rate (Units: RMB 100 million)

[0180] An energy consumption forecasting model was used to simulate energy consumption in region A from 2010 to 2020. Table 4 compares the simulated values ​​with the actual values ​​obtained from the energy consumption forecasting model. According to Table 4, the relative error of the simulated energy consumption data for region A is less than 5%, which is within an acceptable range. Verification shows that the relative errors of each state variable obtained from the model calculation are all within the allowable range, and subsequent forecasts can be made. Table 5 shows the predicted energy consumption values ​​obtained from the energy consumption forecasting model. The predicted energy consumption from 2021 to 2035 is shown in Table 5.

[0181] Table 4 Comparison of Simulated Values ​​and Actual Values ​​Obtained by the Energy Consumption Forecasting Model

[0182]

[0183] Table 5. Energy consumption forecast values ​​obtained using the energy consumption forecasting model.

[0184]

[0185] A power consumption forecasting model was used to simulate the power consumption of region A from 2010 to 2021. Table 6 compares the simulated values ​​with the actual values ​​obtained from the power consumption forecasting model. According to Table 6, the relative error of the simulated power consumption data for region A is less than 4%, which is within an acceptable range. Verification shows that the relative errors of each state variable obtained from the model calculation are all within the allowable range, and subsequent forecasts can be made. Table 7 shows the predicted power consumption values ​​obtained from the power consumption forecasting model. The predicted power consumption from 2022 to 2035 is shown in Table 7.

[0186] Table 6. Comparison of Simulated Values ​​and Actual Values ​​Obtained from the Electricity Consumption Prediction Model

[0187]

[0188] Table 7. Electricity consumption forecast values ​​obtained using the electricity consumption forecasting model.

[0189]

[0190] The electrification rate was calculated based on historical and forecast data of total electricity consumption and electricity consumption. The results of the electrification rate are shown in Table 8. The table shows that the electrification rate of region A has shown an increasing trend compared with the base year (2010). Therefore, it can be considered that region A has vigorously implemented electricity substitution from 2022 to 2035.

[0191] Table 8 Electrification Rate of Area A

[0192] years Electrification rate years Electrification rate 2010 17.83％ 2023 23.66％ 2011 18.18％ 2024 24.18％ 2012 17.20％ 2025 24.71％ 2013 19.13％ 2026 25.25％ 2014 19.26％ 2027 25.81％ 2015 18.89％ 2028 26.37％ 2016 19.80％ 2029 26.95％ 2017 20.92％ 2030 27.55％ 2018 21.78％ 2031 28.15％ 2019 21.55％ 2032 28.77％ 2020 22.12％ 2033 29.40％ 2021 23.26％ 2034 30.05％ 2022 23.15％ 2035 30.07％

[0193] Based on the projected total energy consumption and electricity consumption in Region A, and using 2010 as the base year, the future electricity substitution situation in Region A is predicted as shown in Table 9. Table 9 shows that as the total energy consumption and electrification rate in Region A continue to increase, the scale of electricity substitution will also maintain continuous growth.

[0194] Table 9. Forecast of Electricity Substitution in Region A

[0195]

[0196]

[0197] The following describes the electricity substitution prediction device provided by the present invention. The electricity substitution prediction device described below can be referred to in correspondence with the electricity substitution prediction method described above.

[0198] Figure 6 This is a schematic diagram of the structure of an electricity substitution quantity prediction device provided in an exemplary embodiment of the present invention, as shown below. Figure 6 As shown, the electricity substitution quantity prediction device includes: a first acquisition module 610, a second acquisition module 620, and a third acquisition module 630. Wherein:

[0199] The first acquisition module 610 is used to acquire the total predicted energy consumption for a prediction period based on an energy consumption prediction model; the energy consumption prediction model is constructed based on system dynamics.

[0200] The second acquisition module 620 is used to acquire the predicted amount of electricity consumption for the prediction period based on the electricity consumption prediction model; the electricity consumption prediction model is constructed based on the grey prediction method.

[0201] The third acquisition module 630 is used to obtain the predicted amount of electricity substitution for the prediction period based on the predicted total energy consumption and the predicted amount of electricity consumption.

[0202] In some embodiments, the third acquisition module 630 includes: a determining unit, a calculating unit, and an acquisition unit, wherein:

[0203] The determining unit is used to determine the electrification rate of a preset reference time period; the electrification rate of the preset reference time period is the proportion of the electricity consumption of the preset reference time period to the total energy consumption of the preset reference time period.

[0204] The calculation unit is used to calculate the electrification rate for the forecast period; the electrification rate for the forecast period is the proportion of the predicted electricity consumption to the total predicted energy consumption.

[0205] The first acquisition unit is used to obtain the predicted amount of electricity substitution for the predicted period based on the predicted total energy consumption, the electrification rate of the preset benchmark period, and the electrification rate of the predicted period.

[0206] In some embodiments, the electricity substitution quantity prediction device further includes: a first determining module, a second determining module, and a first constructing module, wherein:

[0207] The first determining module is used to determine the subsystems of the energy consumption system based on the factors affecting the total energy consumption.

[0208] The second determining module is used to determine the impact indicators affecting the total energy consumption within each subsystem, and to determine the type of the impact indicators;

[0209] The first construction module is used to construct the energy consumption prediction model based on the correlation between various influencing indicators and the type of the indicators.

[0210] In some embodiments, the electricity substitution quantity prediction device further includes: a fourth acquisition module, an accumulation module, and a fifth acquisition module, wherein:

[0211] The fourth acquisition module is used to acquire historical energy consumption data starting from a preset benchmark time period, and sort the historical energy consumption data according to the time period to obtain a historical energy consumption sequence.

[0212] The accumulation module is used to accumulate the historical energy consumption data in the historical energy consumption sequence according to the sorting value to obtain the accumulated energy consumption sequence.

[0213] The fifth acquisition module is used to obtain the electricity consumption prediction model based on the historical electricity consumption series and the cumulative electricity consumption series.

[0214] In some embodiments, the second acquisition module 620 includes: a second acquisition unit and a difference unit, wherein:

[0215] The second acquisition unit is used to acquire the cumulative value of electricity consumption prediction for the predicted period output by the electricity consumption prediction model, and the cumulative value of electricity consumption prediction for the period preceding the predicted period.

[0216] The difference unit is used to take the difference between the cumulative value of electricity consumption forecast corresponding to the forecast period and the cumulative value of electricity consumption forecast corresponding to the previous period as the electricity consumption forecast amount for the forecast period.

[0217] In some embodiments, the expression for the predicted amount of electricity substitution is as follows:

[0218]

[0219] In the formula, t represents the prediction period, and D e,t Y represents the predicted amount of electricity substitution for the forecast period. t S represents the total predicted energy consumption for the forecast period. t This represents the electrification rate for the predicted period, where t0 represents the preset baseline period. This indicates the electrification rate for the predicted baseline period.

[0220] It should be noted that the above-mentioned electricity substitution prediction device provided by the present invention can realize all the method steps implemented in the above method embodiments and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiments and the beneficial effects will not be described in detail.

[0221] Figure 7 This is a schematic diagram of the physical structure of an electronic device provided in an exemplary embodiment of the present invention, as shown below. Figure 7 As shown, the electronic device may include a processor 710, a communications interface 720, a memory 730, and a communication bus 740, wherein the processor 710, communications interface 720, and memory 730 communicate with each other via the communication bus 740. The processor 710 can call logic instructions in the memory 730 to execute an electricity substitution prediction method. This method includes: obtaining the total predicted energy consumption for a prediction period based on an energy consumption prediction model (the energy consumption prediction model is constructed based on system dynamics); obtaining the predicted electricity consumption for a prediction period based on an electricity consumption prediction model (the electricity consumption prediction model is constructed based on a grey prediction method); and obtaining the predicted electricity substitution for a prediction period based on the total predicted energy consumption and the predicted electricity consumption.

[0222] Furthermore, the logical instructions in the aforementioned memory 730 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0223] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the electricity substitution prediction method provided by the above methods. The method includes: obtaining the total predicted energy consumption for a prediction period based on an energy consumption prediction model; the energy consumption prediction model is constructed based on system dynamics; obtaining the predicted electricity consumption for a prediction period based on an electricity consumption prediction model; the electricity consumption prediction model is constructed based on a grey prediction method; and obtaining the predicted electricity substitution for a prediction period based on the total predicted energy consumption and the predicted electricity consumption.

[0224] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the electricity substitution prediction method provided by the above methods. The method includes: obtaining the total predicted energy consumption for a prediction period based on an energy consumption prediction model; the energy consumption prediction model being constructed based on system dynamics; obtaining the predicted electricity consumption for a prediction period based on an electricity consumption prediction model; the electricity consumption prediction model being constructed based on a grey prediction method; and obtaining the predicted electricity substitution for a prediction period based on the total predicted energy consumption and the predicted electricity consumption.

[0225] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0226] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0227] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting electricity substitution, characterized in that, include: Based on the energy consumption forecasting model, the total predicted energy consumption for the forecast period is obtained; the energy consumption forecasting model is constructed based on system dynamics. Based on the electricity consumption forecasting model, the predicted electricity consumption for the forecast period is obtained; the electricity consumption forecasting model is constructed based on the grey forecasting method. Based on the total energy consumption forecast and the electricity consumption forecast, the electricity substitution forecast for the forecast period is obtained. The process of obtaining the predicted electricity substitution amount for the predicted period based on the predicted total energy consumption and the predicted electricity consumption includes: Determine the electrification rate for a preset reference time period; the electrification rate for the preset reference time period is the proportion of electricity consumption during the preset reference time period to the total energy consumption during the preset reference time period. Calculate the electrification rate for the forecast period; the electrification rate for the forecast period is the proportion of the forecasted electricity consumption to the total forecasted energy consumption. Based on the total energy consumption forecast, the electrification rate of the preset benchmark period, and the electrification rate of the forecast period, the predicted amount of electricity substitution for the forecast period is obtained. Before obtaining the total predicted energy consumption for the forecast period based on the energy consumption forecasting model, the method further includes: Based on the factors affecting total energy consumption, the subsystems of the energy consumption system are determined; Identify the impact indicators affecting the total energy consumption within each subsystem, and determine the type of the impact indicators; Based on the correlation between the various influencing indicators and the types of the indicators, the energy consumption forecasting model is constructed. Before obtaining the predicted electricity consumption for the predicted period based on the electricity consumption prediction model, the method further includes: Historical energy consumption data starting from a preset baseline time period is obtained, and the historical energy consumption data is sorted in chronological order according to the time period to obtain a historical energy consumption sequence. The historical energy consumption data in the historical energy consumption series are accumulated according to the sorting value to obtain the accumulated energy consumption series. The electricity consumption prediction model is obtained based on the historical electricity consumption series and the cumulative electricity consumption series. The expression for the predicted amount of electricity substitution is shown below: In the formula, t represents the prediction period, and D e,t Y represents the predicted amount of electricity substitution for the forecast period. t S represents the total predicted energy consumption for the forecast period. t This represents the electrification rate for the predicted period, where t0 represents the preset baseline period. This indicates the electrification rate for the predicted baseline period.

2. The method for predicting electricity substitution volume according to claim 1, characterized in that, The method for obtaining the predicted electricity consumption for the predicted period based on the electricity consumption prediction model includes: Obtain the cumulative value of electricity consumption prediction for the predicted period output by the electricity consumption prediction model, and the cumulative value of electricity consumption prediction for the period preceding the predicted period. The difference between the cumulative predicted electricity consumption value corresponding to the predicted period and the cumulative predicted electricity consumption value corresponding to the previous period is taken as the predicted electricity consumption amount for the predicted period.

3. A device for predicting electricity substitution, characterized in that, include: The first acquisition module is used to acquire the total predicted energy consumption for the forecast period based on the energy consumption forecasting model. The energy consumption forecasting model is based on system dynamics; The second acquisition module is used to acquire the predicted amount of electricity consumption for the prediction period based on the electricity consumption prediction model; the electricity consumption prediction model is constructed based on the grey prediction method. The third acquisition module is used to obtain the predicted amount of electricity substitution for the prediction period based on the predicted total energy consumption and the predicted amount of electricity consumption. The third acquisition module includes: a determination unit, a calculation unit, and an acquisition unit, wherein: The determining unit is used to determine the electrification rate of a preset reference time period; the electrification rate of the preset reference time period is the proportion of the electricity consumption of the preset reference time period to the total energy consumption of the preset reference time period. The calculation unit is used to calculate the electrification rate for the forecast period; the electrification rate for the forecast period is the proportion of the predicted electricity consumption to the total predicted energy consumption. The acquisition unit is used to obtain the predicted amount of electricity substitution for the predicted period based on the predicted total energy consumption, the electrification rate of the preset benchmark period, and the electrification rate of the predicted period. The electricity substitution prediction device further includes: a first determining module, a second determining module, and a first constructing module, wherein: The first determining module is used to determine the subsystems of the energy consumption system based on the factors affecting the total energy consumption. The second determining module is used to determine the impact indicators affecting the total energy consumption within each subsystem, and to determine the type of the impact indicators; The first construction module is used to construct the energy consumption prediction model based on the correlation between the various influencing indicators and the indicator types. The electricity substitution prediction device further includes: a fourth acquisition module, an accumulation module, and a fifth acquisition module, wherein: The fourth acquisition module is used to acquire historical energy consumption data starting from a preset benchmark time period, and sort the historical energy consumption data according to the chronological order of the time periods to obtain a historical energy consumption sequence. The accumulation module is used to accumulate the historical energy consumption data in the historical energy consumption sequence according to the sorting value to obtain the accumulated energy consumption sequence. The fifth acquisition module is used to obtain the electricity consumption prediction model based on the historical electricity consumption series and the cumulative electricity consumption series. The expression for the predicted amount of electricity substitution is shown below: In the formula, t represents the prediction period, and D e,t Y represents the predicted amount of electricity substitution for the forecast period. t S represents the total predicted energy consumption for the forecast period. t This represents the electrification rate for the predicted period, where t0 represents the preset baseline period. This indicates the electrification rate for the predicted baseline period.

4. 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 computer program, it implements the method for predicting electricity substitution as described in any one of claims 1 to 2.

5. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for predicting electricity substitution as described in any one of claims 1 to 2.

6. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for predicting electricity substitution as described in any one of claims 1 to 2.

Images