Load response method, system and device based on time-of-use electricity price and medium

Abstract

The invention provides a time-of-use electricity price-based load response method, system and device and a medium, and the method comprises the steps: carrying out the load prediction of each electricity utilization department based on the pre-calculated historical load feature information of each electricity utilization department, and obtaining the load prediction information of each electricity utilization department; according to the load prediction information of each electricity utilization department, determining electricity price elasticity characteristic information of each electricity utilization department in different time-of-use electricity price periods; according to the electricity price elasticity feature information, performing load response on each electricity utilization department by using a pre-constructed load response model, and outputting response load data of each electricity utilization department in different time-of-use electricity price periods; according to the method, load response is carried out based on the electricity price elasticity characteristics of different time-of-use electricity price periods, direct and indirect influences of electricity price changes in different periods on load behaviors of electricity utilization departments can be effectively identified, and therefore electricity price response behaviors of different electricity utilization departments are achieved.

Description

Technical Field

[0001] This invention relates to the field of load management technology, and specifically to a load response method, system, device, and medium based on time-of-use pricing. Background Technology

[0002] Currently, with the increasing proportion of distributed and renewable energy sources integrated into the power system, load volatility is increasing, posing a greater challenge to balancing power supply and demand. To improve system regulation capabilities and operational efficiency, time-of-use pricing, as a tool to guide users to optimize their electricity consumption behavior, has been promoted and applied in many regions. By setting different pricing periods such as peak, flat, and valley, users are guided to increase load during off-peak hours and reduce load during peak hours, thereby achieving peak shaving and valley filling and operational optimization of the power system.

[0003] However, during the implementation of time-of-use pricing, it is usually necessary to analyze user load response behavior to determine the impact of price changes on the load curve. Current technologies often employ load response analysis based on empirical parameters or macroscopic assumptions, leading to significant deviations in the results and failing to accurately reflect different types of electricity consumption behavior. Summary of the Invention

[0004] To address the problem that existing load response methods often exhibit significant deviations and fail to accurately reflect different types of electricity consumption behavior, this invention proposes a load response method based on time-of-use pricing, comprising:

[0005] Based on the pre-calculated historical load characteristics of each electricity-consuming sector, load forecasting is performed on each electricity-consuming sector to obtain load forecasting information for each electricity-consuming sector;

[0006] Based on the load forecast information of each electricity-consuming sector, determine the electricity price elasticity characteristics of each electricity-consuming sector during different time-of-use pricing periods;

[0007] Based on the electricity price elasticity characteristic information, the pre-built load response model is used to perform load response on each electricity-consuming sector, and the response load data of each electricity-consuming sector during different time-of-use electricity price periods are output.

[0008] Optionally, the step of performing load forecasting on each electricity consumer based on pre-calculated historical load characteristic information of each electricity consumer to obtain load forecasting information for each electricity consumer includes:

[0009] Based on the pre-calculated historical load characteristics of each electricity-consuming sector, the intraday fluctuation characteristics of each electricity-consuming sector are calculated.

[0010] Based on the intraday fluctuation characteristics of each electricity-consuming sector, calculate the load percentage information of each electricity-consuming sector;

[0011] Based on the load percentage information of each electricity-consuming sector, load forecasting is performed on each electricity-consuming sector to obtain load forecasting information for each electricity-consuming sector;

[0012] The load percentage information includes: average load percentage information and hourly load percentage information.

[0013] Optionally, calculating the load percentage information of each electricity-consuming sector based on its intraday fluctuation characteristics includes:

[0014] Based on the intraday fluctuation characteristics of each electricity-consuming sector, the load change amplitude information of each electricity-consuming sector is obtained;

[0015] Based on the load change information of each electricity-consuming sector, calculate the average load percentage information of each electricity-consuming sector;

[0016] Based on the average load share information of each electricity-consuming sector, the hourly load share information of each electricity-consuming sector is calculated. Optionally, the expression for the load forecast information of each electricity-consuming sector is as follows:

[0017] L i (D) (h)=L0 (D) (h)·p i (D) (h);

[0018] in, This represents the load forecast information for electricity consumer i at time h in year D; This represents the total load forecast information for all electricity-consuming sectors at time h in year D; This represents the hourly load percentage information for electricity-consuming sector i at time h in year D.

[0019] Optionally, determining the electricity price elasticity characteristics of each electricity consumer during different time-of-use pricing periods based on the load forecast information of each electricity consumer includes:

[0020] Based on the load forecast information of each electricity-consuming sector, calculate the self-elasticity coefficient and cross-elasticity coefficient of each electricity-consuming sector;

[0021] Based on the self-elasticity coefficient of each electricity-consuming sector, calculate the self-elasticity matrix of each electricity-consuming sector under different time-of-use electricity price periods;

[0022] Based on the cross elasticity coefficients of each electricity-consuming sector, calculate the cross elasticity matrix of each electricity-consuming sector under different time-of-use pricing periods;

[0023] The self-elasticity matrix and the cross-elasticity matrix are used as the electricity price elasticity characteristic information of each electricity-consuming sector;

[0024] The time-of-use electricity pricing periods include peak hours, normal hours, and valley hours.

[0025] Optionally, the expression for the self-elasticity matrix of each electricity-consuming sector under different time-of-use pricing periods is as follows:

[0026]

[0027] Among them, Λ ff (i0,j0) represents the self-elasticity matrix of the load in the j0th time period when the electricity price changes in the i0th time period; k f E represents the rate of change in electricity prices during peak hours. ff T represents the self-elasticity coefficient during the peak period; f Indicates peak period; Λ pp (i1,j1) represents the self-elasticity matrix of the load in the j1st time period when the electricity price changes in the i1th time period; T p Indicates the normal segment; Λ gg (i2,j2) represents the self-elasticity matrix of the load in the j2th time period when the electricity price changes in the i2th time period; k g E represents the rate of change in electricity prices during off-peak hours. gg T represents the self-elasticity coefficient during the valley period; g Indicates the valley period.

[0028] Optionally, the expression for the cross-elasticity matrix of each electricity-consuming sector under different time-of-use pricing periods is as follows:

[0029]

[0030] Among them, Λ fp (i3,j3) represents the cross-elasticity matrix of the load in the j3rd time period when the electricity price changes in the i3th time period; T f Indicates peak period; T p Indicates a normal time period; T g Indicates the valley period; k f E represents the rate of change in electricity prices during peak hours. fp This represents the cross-elasticity coefficient between peak and off-peak periods; Λ fg (i4,j4) represents the cross-elasticity matrix of the load in the j4th time period when the electricity price changes in the i4th time period; k g E represents the rate of change in electricity prices during off-peak hours. fg This represents the cross-elasticity coefficient between peak and trough periods; Λ gp (i5,j5) represents the cross-elasticity matrix of the load in the j5th time period when the electricity price changes in the i5th time period; E gp This represents the cross-elasticity coefficient of the valley period to the normal period.

[0031] Optionally, the expression for the load response model is as follows:

[0032]

[0033] Among them, L′ f (i0) represents the response load data for the i0th time period; L′ p (i1) represents the response load data for the i1th time period; L′ g (i2) represents the response load data for the i2th time period; T f Indicates peak period; T p Indicates a normal time period; T g Indicates the valley period; K f (i0) represents the load data before the response in the i0th time period; K p (i1) represents the load data before the response in the i1th time period; K g (i2) represents the load data before the response in the i2th time period; Υ ff This indicates information about the price elasticity characteristics of electricity during peak hours; Υ fp This indicates the price elasticity characteristics of electricity during peak hours compared to normal hours; Υ fg This indicates the price elasticity of electricity during peak hours relative to off-peak hours; Υ pp This indicates the elasticity of electricity prices during normal periods; Υ gp This indicates the price elasticity characteristics of electricity during off-peak hours relative to normal hours; Υ gg This indicates information about the elasticity of electricity prices during off-peak hours.

[0034] Optionally, the historical load characteristic information includes: instantaneous structure information of historical load and overall structure information of historical load;

[0035] The electricity-consuming sectors include one or more of the following: primary industry, secondary industry, tertiary industry, and residential electricity consumption;

[0036] The first industry includes one or more of the following: agriculture, forestry, fishery and animal husbandry;

[0037] The second sector includes one or more of the following: industry, manufacturing, and construction;

[0038] The tertiary sector includes one or more of the following: commerce, finance, education, and transportation.

[0039] Based on the same inventive concept, the present invention also provides a load response system based on time-of-use pricing, comprising:

[0040] The load forecasting module is used to perform load forecasting for each power-consuming sector based on pre-calculated historical load characteristic information of each power-consuming sector, and to obtain load forecasting information for each power-consuming sector.

[0041] The elasticity extraction module is used to determine the price elasticity characteristics of each electricity consumer in different time-of-use pricing periods based on the load forecast information of each electricity consumer.

[0042] The load response module is used to perform load response for each electricity-consuming sector based on the electricity price elasticity characteristic information and a pre-built load response model, and output the response load data of each electricity-consuming sector during different time-of-use electricity price periods.

[0043] Optionally, the load forecasting module includes:

[0044] The time-series pattern calculation submodule is used to calculate the intraday fluctuation characteristics of each electricity-consuming sector based on the pre-calculated historical load characteristic information of each electricity-consuming sector.

[0045] The load percentage calculation submodule is used to calculate the load percentage information of each electricity-consuming sector based on the intraday fluctuation characteristics of each sector.

[0046] The prediction generation submodule is used to perform load prediction for each electricity-consuming sector based on the load ratio information of each sector, and obtain the load prediction information of each sector.

[0047] The load percentage information includes: average load percentage information and hourly load percentage information.

[0048] Optionally, the load percentage calculation submodule includes:

[0049] The variation amplitude determination submodule is used to obtain the load variation amplitude information of each electricity-consuming sector based on the intraday fluctuation characteristics of each sector.

[0050] The average load calculation submodule is used to calculate the average load percentage information of each power-consuming sector based on the load change amplitude information of each power-consuming sector;

[0051] The time-of-use load calculation submodule is used to calculate the hourly load percentage information of each electricity-consuming sector based on the average load percentage information of each sector.

[0052] Optionally, the expression for the load forecast information of each electricity-consuming sector is as follows:

[0053] L i (D) (h)=L0 (D) (h)·p i (D) (h);

[0054] in, This represents the load forecast information for electricity consumer i at time h in year D; This represents the total load forecast information for all electricity-consuming sectors at time h in year D; This represents the hourly load percentage information for electricity-consuming sector i at time h in year D.

[0055] Optionally, the elastic extraction module includes:

[0056] The elasticity coefficient calculation submodule is used to calculate the self-elasticity coefficient and cross-elasticity coefficient of each power-consuming sector based on the load forecast information of each power-consuming sector.

[0057] The first matrix generation submodule is used to calculate the self-elasticity matrix of each electricity consumer under different time-of-use electricity price periods based on the self-elasticity coefficient of each electricity consumer.

[0058] The second matrix generation submodule is used to calculate the cross elasticity matrix of each electricity consumer under different time-of-use electricity price periods based on the cross elasticity coefficient of each electricity consumer.

[0059] The feature generation submodule is used to use the self-elasticity matrix and the cross-elasticity matrix as the electricity price elasticity feature information of each electricity-consuming sector;

[0060] The time-of-use electricity pricing periods include peak hours, normal hours, and valley hours.

[0061] Optionally, the expression for the self-elasticity matrix of each electricity-consuming sector under different time-of-use pricing periods is as follows:

[0062]

[0063] Among them, Λ ff (i0,j0) represents the self-elasticity matrix of the load in the j0th time period when the electricity price changes in the i0th time period; k f E represents the rate of change in electricity prices during peak hours. ff T represents the self-elasticity coefficient during the peak period; f Indicates peak period; Λ pp (i1,j1) represents the self-elasticity matrix of the load in the j1st time period when the electricity price changes in the i1th time period; T p Indicates the normal segment; Λ gg (i2,j2) represents the self-elasticity matrix of the load in the j2th time period when the electricity price changes in the i2th time period; k g E represents the rate of change in electricity prices during off-peak hours. gg T represents the self-elasticity coefficient during the valley period; g Indicates the valley period.

[0064] Optionally, the expression for the cross-elasticity matrix of each electricity-consuming sector under different time-of-use pricing periods is as follows:

[0065]

[0066] Among them, Λ fp (i3,j3) represents the cross-elasticity matrix of the load in the j3rd time period when the electricity price changes in the i3th time period; T f Indicates peak period; T p Indicates a normal time period; T g Indicates the valley period; k f E represents the rate of change in electricity prices during peak hours. fp This represents the cross-elasticity coefficient between peak and off-peak periods; Λ fg (i4,j4) represents the cross-elasticity matrix of the load in the j4th time period when the electricity price changes in the i4th time period; k g E represents the rate of change in electricity prices during off-peak hours. fg This represents the cross-elasticity coefficient between peak and trough periods; Λ gp (i5,j5) represents the cross-elasticity matrix of the load in the j5th time period when the electricity price changes in the i5th time period; E gp This represents the cross-elasticity coefficient of the valley period to the normal period.

[0067] Optionally, the expression for the load response model is as follows:

[0068]

[0069] Among them, L′ f (i0) represents the response load data for the i0th time period; L′ p (i1) represents the response load data for the i1th time period; L′ g (i2) represents the response load data for the i2th time period; T f Indicates peak period; T p Indicates a normal time period; T g Indicates the valley period; L f (i0) represents the load data before the response in the i0th time period; L p (i1) represents the load data before the response in the i1th time period; L g (i2) represents the load data before the response in the i2th time period; Υ ff This indicates information about the price elasticity characteristics of electricity during peak hours; Υ fp This indicates the price elasticity characteristics of electricity during peak hours compared to normal hours; Υ fg This indicates the price elasticity of electricity during peak hours relative to off-peak hours; Υ pp This indicates the elasticity of electricity prices during normal periods; Υ pp This indicates the price elasticity characteristics of electricity during off-peak hours relative to normal hours; Υ gg This indicates information about the elasticity of electricity prices during off-peak hours.

[0070] Optionally, the historical load characteristic information includes: instantaneous structure information of historical load and overall structure information of historical load;

[0071] The electricity-consuming sectors include one or more of the following: primary industry, secondary industry, tertiary industry, and residential electricity consumption;

[0072] The first industry includes one or more of the following: agriculture, forestry, fishery and animal husbandry;

[0073] The second sector includes one or more of the following: industry, manufacturing, and construction;

[0074] The tertiary sector includes one or more of the following: commerce, finance, education, and transportation.

[0075] In another aspect, the present invention also provides an electronic device, comprising: at least one processor and a memory; the memory and the processor are connected via a bus;

[0076] The memory is used to store one or more programs;

[0077] When the one or more programs are executed by the at least one processor, a load response method based on time-of-use pricing as described above is implemented.

[0078] In another aspect, the present invention also provides a computer device readable storage medium having an executable program stored thereon, wherein when the executable program is executed, it implements a load response method based on time-of-use pricing as described above.

[0079] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0080] This invention provides a load response method, system, device, and medium based on time-of-use pricing, comprising: performing load forecasting on each electricity consumer based on pre-calculated historical load characteristic information of each electricity consumer to obtain load forecast information for each electricity consumer; determining the electricity price elasticity characteristic information of each electricity consumer in different time-of-use pricing periods based on the load forecast information of each electricity consumer; and performing load response on each electricity consumer using a pre-constructed load response model based on the electricity price elasticity characteristic information, outputting the response load data of each electricity consumer in different time-of-use pricing periods. This invention, based on the electricity price elasticity characteristics of different time-of-use pricing periods, can effectively identify the direct and indirect impacts of electricity price changes in different periods on the load behavior of each electricity consumer, thereby truly reflecting the electricity price response behavior of different electricity consumers. Attached Figure Description

[0081] Figure 1 A flowchart illustrating a load response method based on time-of-use pricing provided by this invention;

[0082] Figure 2 A schematic diagram of the structural composition of a load response system based on time-of-use pricing provided by the present invention;

[0083] Figure 3 This is a schematic diagram of the structure of an electronic device provided by the present invention. Detailed Implementation

[0084] This invention proposes a load response method, system, device, and medium based on time-of-use pricing. The specific embodiments of this invention will be further described in detail below with reference to the accompanying drawings.

[0085] Example 1:

[0086] This invention provides a load response method based on time-of-use pricing, the flowchart of which is shown below. Figure 1 As shown, it includes:

[0087] Step 1: Based on the pre-calculated historical load characteristics of each electricity-consuming sector, perform load forecasting for each electricity-consuming sector to obtain load forecasting information for each electricity-consuming sector;

[0088] Step 2: Based on the load forecast information of each electricity-consuming sector, determine the electricity price elasticity characteristics of each electricity-consuming sector during different time-of-use pricing periods;

[0089] Step 3: Based on the electricity price elasticity characteristic information, use the pre-built load response model to perform load response on each electricity-consuming sector, and output the response load data of each electricity-consuming sector during different time-of-use electricity price periods.

[0090] Generally, load response is not achieved through time-of-use pricing mechanisms, but rather by using uniform price elasticity parameters or empirical coefficients to simplify and adjust the overall load. This ignores the differentiated impact of price changes at different times on user behavior. This method is mostly based on macroeconomic assumptions or average response rates, failing to accurately capture the differences in electricity consumption behavior of specific user groups (such as industry, commerce, and residential) at different times, resulting in a lack of structural precision and behavioral accuracy in load response results. Furthermore, existing load forecasting methods typically employ statistical regression, time series analysis, or machine learning, primarily modeling based on data correlation, lacking a structural understanding of load generation mechanisms and failing to effectively reflect the intraday load variation patterns of different electricity-consuming sectors. In contrast, this invention introduces a structured forecasting method based on historical load characteristics, which can characterize the formation process of typical daily load curves at the sectoral level. Combined with the price elasticity characteristics of different time periods, it achieves more refined, behavior-driven load response modeling, thereby improving the accuracy and adaptability of response forecasting. Specifically:

[0091] In one implementation, the process of performing load forecasting on each electricity consumer based on pre-calculated historical load characteristic information of each electricity consumer in step 1 above, to obtain load forecasting information for each electricity consumer, may include:

[0092] Based on the pre-calculated historical load characteristics of each electricity-consuming sector, the intraday fluctuation characteristics of each electricity-consuming sector are calculated.

[0093] Based on the intraday fluctuation characteristics of each electricity-consuming sector, calculate the load percentage information of each electricity-consuming sector;

[0094] Based on the load percentage information of each electricity-consuming sector, load forecasting is performed on each electricity-consuming sector to obtain load forecasting information for each electricity-consuming sector;

[0095] The load percentage information may include: average load percentage information and hourly load percentage information.

[0096] For example, the historical load characteristic information may include: instantaneous historical load structure information and overall historical load structure information;

[0097] The electricity-consuming sectors may include one or more of the following: primary industry, secondary industry, tertiary industry, and residential electricity consumption;

[0098] The first industry may include one or more of the following: agriculture, forestry, fishery and animal husbandry;

[0099] The second sector may include one or more of the following: industry, manufacturing, and construction;

[0100] The tertiary sector may include one or more of the following: commerce, finance, education, and transportation;

[0101] For example, the calculation process for the historical load characteristic information (including historical instantaneous load structure information and historical overall load structure information) of the above-mentioned electricity-consuming sectors can be as follows:

[0102] To calculate the hourly load share of each electricity-consuming sector, first define the historical instantaneous load structure information of electricity-consuming sector i (i = 1, 2, 3, 4 corresponding to primary industry, secondary industry, tertiary industry, and residential life, respectively) at time h on day d of the baseline year (e.g., using...). (Represented by) the instantaneous load structure of each sector at a certain moment; calculate the average load percentage of power-consuming sector i at time h on day d. (Representing the overall historical load structure information of various electricity-consuming sectors on a given day), used to capture long-term trends:

[0103] For example, the above-mentioned historical load instantaneous structural information The expression can be as follows:

[0104]

[0105] For example, the above historical load structure information (i.e., the average load share of electricity consumer i at time h on day d) The expression for ) can be as follows:

[0106]

[0107] in, This represents the load value of electricity consumer i at time h on day d of the base year; This represents the load value of electricity consumer j at time h on day d of the base year; This represents the total load value at time h on day d of the base year.

[0108] For example, the formula for calculating the intraday volatility characteristics mentioned above can be as follows:

[0109]

[0110] in, It represents the intraday fluctuation characteristics of electricity consumption sector i at time h on day d of the base year (also known as the time series morphology coefficient); This represents the historical instantaneous load structure information of electricity-consuming sector i at time h on day d of the reference year; This represents the average load percentage of electricity-consuming sector i on day d; This represents the overall characteristic information of electricity-consuming sector i on day d of the base year; in this example, calculating the time-series morphology coefficient can quantify the intraday fluctuation characteristics of the sector's load, reflecting the degree of deviation of the load fluctuation of electricity-consuming sector i at time h from the daily average level. When the load percentage is higher than the daily average at that moment, it indicates that the load percentage is lower than the daily average.

[0111] This implementation incorporates historical instantaneous structural information and overall structural information, and further calculates the intraday fluctuation characteristics of electricity-consuming sectors. This enables the forecast to not only adapt to cross-sectoral structures but also refine the electricity consumption dynamics down to the hourly level. In particular, the calculation distinguishes the relative deviation of intraday load, reflecting the load fluctuation trend within a typical day through a time-series morphology coefficient. This indicator effectively restores the shape characteristics of the actual load curve, rather than relying solely on static averages or historical normalized curves. Based on the hourly load percentage information obtained from these processing steps, high-resolution load forecast results are further constructed for each electricity-consuming sector, improving the accuracy and interpretability of load time-series simulation. This is especially suitable for scenarios highly sensitive to fine-grained load inputs, such as electricity price response. In the above load forecasting process, not only are long-term structural trends at the sectoral level preserved but also micro-time-series characteristics of intraday response capabilities are introduced. Therefore, it can more realistically reflect the electricity consumption habits of a certain type of user during a specific period, providing highly matched basic data support for subsequent electricity price mechanism response modeling. Although methods such as historical load ratio analysis and time-series curve morphology extraction are common in the field of data analysis, when used to build load forecasting models, a high-precision structural reconstruction method is established based on the dual deconstruction of load structure characteristics and time-series morphology characteristics. This method establishes a high-precision structural reconstruction method at the departmental level, hourly scale, and within the reference day. By accurately calculating the proportional offset between the instantaneous structural ratio and the overall ratio, i.e., the time-series morphology coefficient, not only is a "shape template" of the load curve formed, but it is also further combined with the maximum load information of the forecast year for proportional reconstruction. This approach achieves a structured reconstruction of the typical daily load of future years, and is a modeling approach that fits the real fluctuation pattern of departmental electricity consumption from the data foundation to the behavioral logic. Furthermore, to further improve the adaptability of load forecasting to actual operating day types, a dynamic classification modeling mechanism based on the differences in load patterns between weekdays and non-weekdays can be introduced. For example, weekday labels can be introduced during the historical load analysis phase to calculate the departmental load structure characteristics and time-series morphology coefficients for weekdays and holidays or weekends, thereby enabling branch modeling and fusion output according to operating day type during the forecasting phase. This extended technical feature can effectively avoid forecasting bias caused by assuming consistent electricity consumption patterns throughout the day, especially in scenarios where commercial and office loads account for a high proportion.

[0112] In the above implementation, the process of calculating the load ratio information of each electricity-consuming sector based on its intraday fluctuation characteristics may specifically include:

[0113] Based on the intraday fluctuation characteristics of each electricity-consuming sector, the load change amplitude information of each electricity-consuming sector is obtained (for example, the load change amplitude information of electricity-consuming sector i can be obtained using θ). i express);

[0114] Based on the load change information of each electricity-consuming sector, calculate the average load share information of each electricity-consuming sector (for example, the average load share information of electricity-consuming sector i on day D of the predicted year can be obtained by using...). express);

[0115] Based on the average load share information of each electricity-consuming sector, the hourly load share information of each electricity-consuming sector is calculated (for example, the hourly load share information of electricity-consuming sector i on the predicted date D can be obtained by using...). express).

[0116] For example, the above information on the average load share of electricity-consuming sector i on forecast date D. The expression can be as follows:

[0117]

[0118] in, This represents the average load share of electricity-consuming sector i at time h on day d of the baseline year; in this example, the increase in the share of each sector compared to the baseline year is calculated by combining the electricity consumption share of each sector in the planning scheme year (i.e., the aforementioned θ). i If this is used as the percentage increase in the average load of sector i on day D (which is the same day as the base year but not the base year, with D representing the day in the forecast year) compared to the base year, then the average load share of sector i on day D in the forecast year can be predicted.

[0119] For example, the above information on the hourly load percentage of electricity-consuming sector i on forecast day D of year D. The expression can be as follows:

[0120]

[0121] in, This represents the intraday fluctuation characteristics of electricity-consuming sector i at time h on day d of the base year (it can also be called the time series morphology coefficient). This indicates the average load percentage of electricity-consuming sector j on day D of the predicted year; This represents the intraday fluctuation characteristics of electricity consumption sector j at time h on day D of the predicted year; in this example, the hourly load share for the predicted year is calculated by combining the predicted share with historical pattern characteristics. The main approach combines intraday fluctuation characteristics with historical intraday fluctuation characteristics; the denominator is mainly to eliminate the cumulative deviation that may be caused by independently predicting the proportion of each sector, and to ensure that the sum of the load proportions of each sector on an hourly basis is 1.

[0122] For example, the expressions for the load forecast information of each electricity-consuming sector mentioned above can be as follows:

[0123] L i(D) (h)=L0 (D) (h)·p i (D) (h);

[0124] L0 (D) (h)=L max (D) ·k0 (d) (h);

[0125] in, This indicates the load forecast information for electricity user sector i at time h on day D of the forecast year; This indicates the total load forecast information for all electricity-consuming sectors at time h on day D of the predicted year; This indicates the hourly load percentage of electricity-consuming sector i at time h on day D of the predicted year; This represents the maximum predicted load value on day D of the predicted year; This represents the initial electricity price at time h on day d of the base year; in this example, the total load curve (i.e., the total load forecast information for all electricity-consuming sectors at time h on day D of the forecast year) is predicted by combining the per-unit values ​​of the historical load curve and the maximum annual load under the planning scheme. Combining the hourly load percentage by sector, predict the load curve of electricity-consuming sector i (i.e., the load forecast information of electricity-consuming sector i at time h on day D of the forecast year). In this implementation, by introducing a joint modeling method that combines the departmental electricity consumption variation coefficient with historical intraday fluctuation characteristics, dynamic restoration of the hourly load share for the predicted year is achieved; by setting θ i Using load change as an indicator of a sector's load variation compared to a base year, and adjusting the sector's average load share accordingly, then combining intraday fluctuation characteristics to progressively calculate hourly load shares, this mechanism effectively reflects the impact of inter-sectoral electricity share shifts caused by industrial structure evolution or changes in electricity consumption patterns on the temporal structure of load. Unlike the traditional approach of separating structural adjustments from temporal characteristics, this implementation, through a logically continuous share restoration path, balances the dual constraints of structural changes and temporal stability during load forecasting, thereby improving the accuracy of forecast results in reflecting future power system operating scenarios. Especially in the construction of total load forecasts, by using the per-unit load curve of the base date and combining it with the maximum load level of the planning year for normalized back-calculation, the problem of lacking hourly load measurement data for the target year is effectively solved. This achieves the transformation from static electricity change forecasting to dynamic load curve restoration, making the final output load curves for each sector usable, calculable, and embeddable.

[0126] The above implementation method enables load forecasting for each electricity-consuming sector based on historical load characteristics and obtains corresponding hourly load data. To further simulate the impact of electricity price changes on user load behavior, it is possible to incorporate electricity price elasticity characteristics reflecting user response behavior into the forecasted load level, thereby enabling load response modeling for each electricity-consuming sector under different time-of-use pricing periods. Specifically:

[0127] In one implementation, step 2 above, which involves determining the electricity price elasticity characteristics of each electricity consumer based on their load forecast information during different time-of-use pricing periods, may include:

[0128] Based on the load forecast information of each electricity-consuming sector, calculate the self-elasticity coefficient and cross-elasticity coefficient of each electricity-consuming sector;

[0129] Based on the self-elasticity coefficient of each electricity-consuming sector, calculate the self-elasticity matrix of each electricity-consuming sector under different time-of-use electricity price periods;

[0130] Based on the cross elasticity coefficients of each electricity-consuming sector, calculate the cross elasticity matrix of each electricity-consuming sector under different time-of-use pricing periods;

[0131] The self-elasticity matrix and the cross-elasticity matrix are used as the electricity price elasticity characteristic information of each electricity-consuming sector;

[0132] The time-of-use electricity pricing periods may include peak periods, normal periods, and valley periods.

[0133] For example, the expressions for the self-elasticity matrix of each electricity-consuming sector under different time-of-use pricing periods can be as follows:

[0134]

[0135] Among them, Λ ff (i0,j0) represents the self-elasticity matrix of the load in the j0th time period when the electricity price changes in the i0th time period; k f E represents the rate of change in electricity prices during peak hours. ff T represents the self-elasticity coefficient during the peak period; f Indicates peak period; Λ pp (i1,j1) represents the self-elasticity matrix of the load in the j1st time period when the electricity price changes in the i1th time period; T p Indicates the normal segment; Λ gg (i2,j2) represents the self-elasticity matrix of the load in the j2th time period when the electricity price changes in the i2th time period; k g E represents the rate of change in electricity prices during off-peak hours. gg T represents the self-elasticity coefficient during the valley period; gThis represents the valley period; in this example, the elasticity coefficient (e.g., the elasticity coefficient of the random period t can be represented by E) is used. tt (This indicates the impact of electricity price fluctuations on its own load during a given period, reflecting the effect of electricity savings. The calculation formula can be expressed as:)

[0136]

[0137] Where, ΔL t L represents the load change during time period t; t ΔP represents the load level during time period t; t P represents the change in electricity price during time period t; t Indicates the electricity price level during period t; Λ tt k represents the load variation rate during time period t; t This represents the rate of change in electricity prices over time period t, typically expressed as the elasticity coefficient E. tt A negative value indicates that the increase in electricity prices will suppress electricity demand during this period. In this example, parameter settings can refer to publicly available information on time-of-use pricing policies. The self-elasticity coefficient can mainly be obtained through literature reviews, user surveys, etc., and usually does not change electricity prices during normal periods, hence Λ pp =0. Considering that electricity prices typically rise during peak hours and fall during off-peak hours, therefore k f >0, k g <0, and because E ff E gg <0, therefore Λ ff <0, Λ gg >0.

[0138] For example, the expression for the cross-elasticity matrix of each electricity-consuming sector under different time-of-use pricing periods can be as follows:

[0139]

[0140] Among them, Λ fp (i3,j3) represents the cross-elasticity matrix of the load in the j3rd time period when the electricity price changes in the i3th time period; T f Indicates peak period; T p Indicates a normal time period; T g Indicates the valley period; k f E represents the rate of change in electricity prices during peak hours. fp This represents the cross-elasticity coefficient between peak and off-peak periods; Λ fg (i4,j4) represents the cross-elasticity matrix of the load in the j4th time period when the electricity price changes in the i4th time period; k g E represents the rate of change in electricity prices during off-peak hours. fg This represents the cross-elasticity coefficient between peak and trough periods; Λ gp(i5,j5) represents the cross-elasticity matrix of the load in the j5th time period when the electricity price changes in the i5th time period; E gp This represents the cross-elasticity coefficient between the valley period and the normal period; in this example, the cross-elasticity coefficient (e.g., the cross-elasticity coefficient between any two time periods can be represented by E) xy (represented by) the impact of electricity price changes during time period x on load during time period y, reflecting the load shift effect during time periods. The calculation formula can be expressed as follows:

[0141]

[0142] Where, ΔL y L represents the load change during the y-period period; y Indicates the load level during period y; ΔP x P represents the change in electricity price during period x; x This represents the electricity price level during period x; generally, cross-price elasticity is divided into three categories, mainly obtained through literature surveys, user visits, and other channels. Among them, the peak-to-flat cross-price elasticity coefficient E fp This indicates the impact of peak-hour electricity price fluctuations on normal-hour load, typically E. fp A value greater than 0 indicates that the increase in peak-hour electricity prices will incentivize users to shift their load to off-peak hours, achieving "peak shaving and valley filling"; the peak-to-valley cross-elasticity coefficient E fg This indicates the impact of peak-hour electricity price fluctuations on off-peak-hour load, typically E. fg >0; Valley-to-flat cross elasticity coefficient E gp This indicates the impact of off-peak electricity price fluctuations on load during normal periods, typically E. gp >0;

[0143] In this example, assume the cross-elasticity matrix Λ of the second industry peak period versus the normal period. fp =0.015, meaning that for every 1% increase in peak-hour electricity price, the load during normal hours increases by 0.015%. Since k is usually... f E fp >0, therefore Λ fp >0; Peak-to-valley cross-elasticity matrix Λ fg In the middle, (k f -k g This reflects the peak-valley electricity price difference. The off-peak electricity price is lower (k). g If k < 0, the peak-valley price difference widens, further incentivizing load shifting. Since k is typically... f >0, k g <0、E fg >0, therefore Λ fg >0; the cross-elasticity matrix Λ between the valley period and the normal period gp The negative sign indicates a price reduction during off-peak hours (k). g <0) will cause the load to shift from normal periods to off-peak periods. Because k is usually...g <0、E gp >0, therefore Λ gp >0.

[0144] In this implementation, based on the time-of-use pricing elasticity theory, a systematic model of the load response behavior of various electricity-consuming sectors under different time periods (peak, flat, and valley) is achieved by constructing sector-level self-elasticity and cross-elasticity matrices under time-of-use pricing. The elasticity coefficient, as a key parameter for measuring the dynamic relationship between price changes and load changes, reflects the energy-saving and load-suppressing effect of price increases on the current time period's load, while the cross-elasticity coefficient describes the cross-time period load transfer trend caused by price changes. Combining previous sector load forecasts, this implementation further couples the elasticity characteristic parameters of each sector under different time periods with the price adjustment magnitude coefficient to construct self-elasticity and cross-elasticity matrices, thereby achieving quantitative calculation of the load response direction and intensity. This matrix-based response modeling method can completely preserve the response path relationships between multiple sectors and time periods, breaking through the simplistic assumption of linear scaling of the total load with fixed coefficients in traditional models, and avoiding structural flattening and response error accumulation problems. In practical applications, the response matrix can not only automatically adapt parameter signs and numerical directions according to electricity pricing strategies (such as peak-hour price increases and off-peak-hour price decreases), but also possesses good strategy adaptability and structural adjustment capabilities. It can support response calculation tasks for various scenarios, including time-of-use pricing policy simulation, system reserve capacity assessment, and demand-side resource optimization scheduling, providing a model foundation for achieving flexible load management and coordinated system operation. While resilience analysis is a classic method in economics and energy management, traditional approaches typically focus on estimating the correlation between electricity price changes and overall load changes, making it difficult to refine behavioral difference modeling down to the time-period level, and even more difficult to handle the quantitative decomposition of load migration paths between sectors. This implementation goes beyond simply adjusting the load curve using elasticity coefficients. Instead, it designs an elastic matrix construction method highly consistent with the actual electricity price structure and user response paths. Its key technical features lie in three interconnected aspects: setting policy intensity variables based on time-of-use pricing; modeling homogeneous response effects using self-elasticity coefficients; and constructing migration paths using cross-elasticity coefficients. This generates structurally controllable load change data while maintaining the constraint of total system load conservation. Therefore, it can dynamically construct response curves based on predicted annual load data, without relying on experience-based adjustments or static templates. Furthermore, this elastic matrix construction method supports parallel simulation of multiple pricing strategies, allowing for separate modeling of multiple migration paths, including peak-to-flat, peak-to-valley, and valley-to-peak scenarios. This not only enhances the logical integrity of behavioral simulation but also possesses the structural characteristic of directly integrating the response model into the system operation optimization platform.

[0145] The self-elasticity and cross-elasticity characteristics of each electricity-consuming sector can be obtained through the above implementation methods. Therefore, based on these self-elasticity and cross-elasticity characteristics, a load response model based on the time-of-use pricing mechanism can be considered. Specifically:

[0146] In one implementation, the expression for the load response model in step 3 above can be as follows:

[0147]

[0148] Among them, L′ f (i0) represents the response load data for the i0th time period; L′ p (i1) represents the response load data for the i1th time period; L′ g (i2) represents the response load data for the i2th time period; T f Indicates peak period; T p Indicates a normal time period; T g Indicates the valley period; L f (i0) represents the load data before the response in the i0th time period; L p (i1) represents the load data before the response in the i1th time period; L g (i2) represents the load data before the response in the i2th time period; Υ ff This indicates information about the price elasticity characteristics of electricity during peak hours; Υ fp This indicates the price elasticity characteristics of electricity during peak hours compared to normal hours; Υ fg This indicates the price elasticity of electricity during peak hours relative to off-peak hours; Υ pp This indicates the elasticity of electricity prices during normal periods; Υ gp This indicates the price elasticity characteristics of electricity during off-peak hours relative to normal hours; Υ gg This expression represents the electricity price elasticity characteristics during off-peak hours. In this expression, the self-elasticity of peak hours and the cross-elasticity with normal and off-peak hours both lead to a decrease in peak load. Since the self-elasticity of normal hours is 0, the cross-elasticity with peak hours leads to an increase in normal load, and the cross-elasticity with off-peak hours leads to a decrease in normal load. The self-elasticity of off-peak hours and the cross-elasticity with peak and normal hours lead to an increase in off-peak load. Preferably, the above-mentioned response load data may include: hourly response load curves, total load response results for the time period, response behavior structure data (e.g., numerical representations of peak load reduction, migration to normal hours, and migration to off-peak hours), and departmental response intensity indicators (e.g., analyzing which department is more sensitive to electricity price policies). If the expression of the above load response model is written in matrix form, it can be described as:

[0149] L′(i')=L(i')+Λ×L(i');

[0150] Where L′(i′) represents the matrix representation of the load response data for time period i′; L(i′) represents the matrix representation of the load data before the response for time period i′; and Λ represents the matrix representation of the elasticity characteristic information.

[0151] Specifically, the matrix representation Λ of the aforementioned elasticity characteristic information and the matrix representation L(i′) of the response preload data are as follows:

[0152]

[0153] Among them, Λ ff The matrix representing the self-elasticity of peak periods relative to peak periods; Λ pp Represents the self-elasticity matrix of the normal segment relative to the normal segment; Λ gg The self-elasticity matrix representing the valley period to the valley period; Λ fp The cross-elasticity matrix representing the peak period versus the normal period; Λ fg This represents the cross-elasticity matrix between peak and trough periods; Λ gp L represents the cross-elasticity matrix of the valley period to the normal period; f Represents the load matrix before peak-hour response; L p L represents the load matrix before the normal response period; g This represents the load matrix before the response during the valley period. It's important to note that to characterize the multi-period coupling effect, if the load granularity is on the hourly level, Λ is a 24*24 dimensional elastic matrix. For any element within the matrix, its value can be determined by considering its corresponding time period type.

[0154] In this implementation, the load response model not only characterizes the impact of electricity price changes on the load of each time period at the scalar level, but also integrates cross-time period coupling effects at the matrix level, enabling it to describe the load redistribution mechanism caused by price adjustments across different time periods. Specifically, the self-elasticity matrix controls the load saving trend, while the cross-elasticity matrix constructs the load migration path. These two elements work synergistically in a unified expression, ensuring that the load after response still possesses structural rationality and temporal consistency under the constraint of total load conservation. Through matrix construction, the model can be extended to hourly response accuracy, with the elasticity matrix dimension reaching 24×24, achieving fine-grained modeling of interactions between different time periods within a day, and meeting the needs of modeling complex electricity consumption behavior in typical daily scenarios. Compared to traditional response models that only define empirical allocation logic for peak shaving or valley filling, this implementation supports the dynamic generation of time-series load adjustment results based on load forecasting results, according to price signal strength and behavioral elasticity coefficients. The output data has a structure and format that can be directly used for scheduling optimization or strategy simulation, significantly improving the practicality, flexibility, and integration capability of response modeling. In this implementation, load adjustment is expressed as a linear combination of "pre-response load × elasticity action term," which supports elasticity matrix replacement and combination operations under different electricity price strategies. This gives the model the engineering advantage of unchanged data structure and reusable response logic when facing policy scenario changes. This approach, which integrates electricity price signal mapping, behavioral elasticity mechanisms, and load migration paths into a unified matrix system, establishes a response modeling method that is formally closed, model-unified, and easy to perform systematic calculations and integration, and has practical engineering significance and applicability.

[0155] In summary, this invention addresses the problem that existing load response methods often exhibit significant deviations and fail to accurately reflect different types of electricity consumption behavior. It proposes a load response method based on time-of-use pricing. This method constructs structural characteristic information for each electricity-consuming sector based on historical load data. By extracting intraday fluctuation characteristics, average load share, and hourly load share information, and combining this with the maximum load level for the planned year, it forecasts the hourly load for each sector. Furthermore, based on the load characteristics of each sector during peak, flat, and valley time-of-use pricing periods, it constructs a sector-level electricity price elasticity parameter system, including self-elasticity and cross-elasticity coefficients, to simulate energy-saving and load migration effects, respectively. Based on this, an elasticity matrix is ​​calculated to characterize the load interaction relationships between different time periods. Finally, by constructing a response model with sector load forecasting and the elasticity matrix as core inputs, it automatically generates hourly response load data for each electricity-consuming sector under different pricing strategies. The output results include load changes in each time period, comparisons of curves before and after the response, and the load transfer structure between different time periods. Therefore, by establishing a complete link from historical load structure mining, future load forecasting, behavioral resilience modeling to response result output, this invention enables the load response process to have strong behavioral simulation capabilities, structural adaptability, and time series prediction capabilities, which can significantly improve the accuracy and practicality of electricity price response and provide a reliable load response input basis for power system operation optimization, electricity price mechanism evaluation, and demand-side management strategy formulation.

[0156] Example 2:

[0157] Based on the same inventive concept, this invention also provides a load response system based on time-of-use pricing, the structural composition of which is shown in the schematic diagram below. Figure 2 As shown, it includes:

[0158] The load forecasting module is used to perform load forecasting for each power-consuming sector based on pre-calculated historical load characteristic information of each power-consuming sector, and to obtain load forecasting information for each power-consuming sector.

[0159] The elasticity extraction module is used to determine the price elasticity characteristics of each electricity consumer in different time-of-use pricing periods based on the load forecast information of each electricity consumer.

[0160] The load response module is used to perform load response for each electricity-consuming sector based on the electricity price elasticity characteristic information and a pre-built load response model, and output the response load data of each electricity-consuming sector during different time-of-use electricity price periods.

[0161] In one implementation, the load forecasting module described above may include:

[0162] The time-series pattern calculation submodule is used to calculate the intraday fluctuation characteristics of each electricity-consuming sector based on the pre-calculated historical load characteristic information of each electricity-consuming sector.

[0163] The load percentage calculation submodule is used to calculate the load percentage information of each electricity-consuming sector based on the intraday fluctuation characteristics of each sector.

[0164] The prediction generation submodule is used to perform load prediction for each electricity-consuming sector based on the load ratio information of each sector, and obtain the load prediction information of each sector.

[0165] The load percentage information includes: average load percentage information and hourly load percentage information.

[0166] In this implementation, the load percentage calculation submodule mentioned above may include:

[0167] The variation amplitude determination submodule is used to obtain the load variation amplitude information of each electricity-consuming sector based on the intraday fluctuation characteristics of each sector.

[0168] The average load calculation submodule is used to calculate the average load percentage information of each power-consuming sector based on the load change amplitude information of each power-consuming sector;

[0169] The time-of-use load calculation submodule is used to calculate the hourly load percentage information of each electricity-consuming sector based on the average load percentage information of each sector.

[0170] For example, the expressions for the load forecast information of each electricity-consuming sector mentioned above can be as follows:

[0171] L i (D) (h)=L0 (D) (h)·p i (D) (h);

[0172] in, This represents the load forecast information for electricity consumer i at time h in year D; This represents the total load forecast information for all electricity-consuming sectors at time h in year D; This indicates the hourly load percentage information of electricity-consuming sector i at time h in year D;

[0173] For example, the historical load characteristic information mentioned above may include: instantaneous structure information of historical load and overall structure information of historical load;

[0174] The electricity-consuming sectors may include one or more of the following: primary industry, secondary industry, tertiary industry, and residential electricity consumption;

[0175] The first industry may include one or more of the following: agriculture, forestry, fishery and animal husbandry;

[0176] The second sector may include one or more of the following: industry, manufacturing, and construction;

[0177] The tertiary sector may include one or more of the following: commerce, finance, education, and transportation.

[0178] In one implementation, the aforementioned flexible extraction module may include:

[0179] The elasticity coefficient calculation submodule is used to calculate the self-elasticity coefficient and cross-elasticity coefficient of each power-consuming sector based on the load forecast information of each power-consuming sector.

[0180] The first matrix generation submodule is used to calculate the self-elasticity matrix of each electricity consumer under different time-of-use electricity price periods based on the self-elasticity coefficient of each electricity consumer.

[0181] The second matrix generation submodule is used to calculate the cross elasticity matrix of each electricity consumer under different time-of-use electricity price periods based on the cross elasticity coefficient of each electricity consumer.

[0182] The feature generation submodule is used to use the self-elasticity matrix and the cross-elasticity matrix as the electricity price elasticity feature information of each electricity-consuming sector;

[0183] The time-of-use electricity pricing periods include peak hours, normal hours, and valley hours.

[0184] For example, the expressions for the self-elasticity matrix of each electricity-consuming sector under different time-of-use pricing periods can be as follows:

[0185]

[0186] Among them, Λ ff (i0,j0) represents the self-elasticity matrix of the load in the j0th time period when the electricity price changes in the i0th time period; k f E represents the rate of change in electricity prices during peak hours. ff T represents the self-elasticity coefficient during the peak period; f Indicates peak period; Λ pp (i1,j1) represents the self-elasticity matrix of the load in the j1st time period when the electricity price changes in the i1th time period; T p Indicates the normal segment; Λ gg (i2,j2) represents the self-elasticity matrix of the load in the j2th time period when the electricity price changes in the i2th time period; k g E represents the rate of change in electricity prices during off-peak hours. gg T represents the self-elasticity coefficient during the valley period; g Indicates the valley period.

[0187] For example, the expression for the cross-elasticity matrix of each electricity-consuming sector under different time-of-use pricing periods can be as follows:

[0188]

[0189] Among them, Λ fp (i3,j3) represents the cross-elasticity matrix of the load in the j3rd time period when the electricity price changes in the i3th time period; T f Indicates peak period; T p Indicates a normal time period; T g Indicates the valley period; k f E represents the rate of change in electricity prices during peak hours. fp This represents the cross-elasticity coefficient between peak and off-peak periods; Λ fg (i4,j4) represents the cross-elasticity matrix of the load in the j4th time period when the electricity price changes in the i4th time period; k g E represents the rate of change in electricity prices during off-peak hours. fg This represents the cross-elasticity coefficient between peak and trough periods; Λ gp (i5,j5) represents the cross-elasticity matrix of the load in the j5th time period when the electricity price changes in the i5th time period; E gp This represents the cross-elasticity coefficient of the valley period to the normal period.

[0190] For example, the expression for the above load response model can be as follows:

[0191]

[0192] Among them, L′ f (i0) represents the response load data for the i0th time period; L′ p (i1) represents the response load data for the i1th time period; L′ g (i2) represents the response load data for the i2th time period; T f Indicates peak period; T p Indicates a normal time period; T g Indicates the valley period; L f (i0) represents the load data before the response in the i0th time period; L p (i1) represents the load data before the response in the i1th time period; L g (i2) represents the load data before the response in the i2th time period; Υ ff This indicates information about the price elasticity characteristics of electricity during peak hours; Υ fp This indicates the price elasticity characteristics of electricity during peak hours compared to normal hours; Υ fg This indicates the price elasticity of electricity during peak hours relative to off-peak hours; Υ pp This indicates the elasticity of electricity prices during normal periods; Υ gp This indicates the price elasticity characteristics of electricity during off-peak hours relative to normal hours; Υgg This indicates information about the elasticity of electricity prices during off-peak hours.

[0193] Example 3:

[0194] like Figure 3 As shown, the present invention also provides an electronic device, which may be a computer device, a microcontroller device, a smart mobile device, etc. The electronic device in this embodiment may include a processor, a memory, a transceiver component, etc. The memory, processor, and transceiver component are connected via a bus; the memory can be used to store executable programs, and an exemplary executable program may include instructions; the processor is used to execute the instructions stored in the memory. The memory can also be used to store data, which can be accessed and / or modified when instructions are executed.

[0195] The processor may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, and it is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions in the storage medium to implement the corresponding method flow or corresponding function, so as to implement the steps of a load response method based on time-of-use pricing in the above embodiments.

[0196] Example 4:

[0197] Based on the same inventive concept, this invention also provides a readable storage medium, specifically an electronic device readable storage medium (Memory). This readable storage medium is a memory device within an electronic device used to store programs and data. It is understood that the storage medium here can include both built-in storage media within the electronic device and extended storage media supported by the electronic device. The storage medium provides storage space, which stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more executable programs (including program code). It should be noted that the storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. Loading and executing one or more instructions stored in the storage medium by the processor can implement the steps of a load response method based on time-of-use pricing in the above embodiments.

[0198] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0199] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0200] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0201] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0202] 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 its scope of protection. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that after reading the present invention, they can still make various changes, modifications or equivalent substitutions to the specific implementation methods of the application, but these changes, modifications or equivalent substitutions are all within the scope of protection of the claims pending approval.

Claims

1. A load response method based on time-of-use pricing, characterized in that, include: Based on the pre-calculated historical load characteristics of each electricity-consuming sector, load forecasting is performed on each electricity-consuming sector to obtain load forecasting information for each electricity-consuming sector; Based on the load forecast information of each electricity-consuming sector, determine the electricity price elasticity characteristics of each electricity-consuming sector during different time-of-use pricing periods; Based on the electricity price elasticity characteristic information, the pre-built load response model is used to perform load response on each electricity-consuming sector, and the response load data of each electricity-consuming sector during different time-of-use electricity price periods are output.

2. The method as described in claim 1, characterized in that, The method of load forecasting for each electricity consumer based on pre-calculated historical load characteristics information of each electricity consumer, and obtaining load forecast information for each electricity consumer, includes: Based on the pre-calculated historical load characteristics of each electricity-consuming sector, the intraday fluctuation characteristics of each electricity-consuming sector are calculated. Based on the intraday fluctuation characteristics of each electricity-consuming sector, calculate the load percentage information of each electricity-consuming sector; Based on the load percentage information of each electricity-consuming sector, load forecasting is performed on each electricity-consuming sector to obtain load forecasting information for each electricity-consuming sector; The load percentage information includes: average load percentage information and hourly load percentage information.

3. The method as described in claim 2, characterized in that, The step of calculating the load percentage information of each electricity-consuming sector based on its intraday fluctuation characteristics includes: Based on the intraday fluctuation characteristics of each electricity-consuming sector, the load change amplitude information of each electricity-consuming sector is obtained; Based on the load change information of each electricity-consuming sector, calculate the average load percentage information of each electricity-consuming sector; Based on the average load percentage information of each electricity-consuming sector, the hourly load percentage information of each electricity-consuming sector is calculated.

4. The method as described in claim 2, characterized in that, The expressions for the load forecast information of each electricity-consuming sector are as follows: L i (D) (h)=L0 (D) (h)·p i (D) (h); in, This represents the load forecast information for electricity consumer i at time h in year D; This represents the total load forecast information for all electricity-consuming sectors at time h in year D; This represents the hourly load percentage information for electricity-consuming sector i at time h in year D.

5. The method as described in claim 1, characterized in that, The step of determining the electricity price elasticity characteristics of each electricity consumer in different time-of-use pricing periods based on the load forecast information of each electricity consumer includes: Based on the load forecast information of each electricity-consuming sector, calculate the self-elasticity coefficient and cross-elasticity coefficient of each electricity-consuming sector; Based on the self-elasticity coefficient of each electricity-consuming sector, calculate the self-elasticity matrix of each electricity-consuming sector under different time-of-use electricity price periods; Based on the cross elasticity coefficients of each electricity-consuming sector, calculate the cross elasticity matrix of each electricity-consuming sector under different time-of-use pricing periods; The self-elasticity matrix and the cross-elasticity matrix are used as the electricity price elasticity characteristic information of each electricity-consuming sector; The time-of-use electricity pricing periods include peak hours, normal hours, and valley hours.

6. The method as described in claim 5, characterized in that, The expressions for the self-elasticity matrix of each electricity-consuming sector under different time-of-use pricing periods are as follows: Among them, Λ ff (i0,j0) represents the self-elasticity matrix of the load in the j0th time period when the electricity price changes in the i0th time period; k f E represents the rate of change in electricity prices during peak hours. ff T represents the self-elasticity coefficient during the peak period; f Indicates peak period; Λ pp (i1,j1) represents the self-elasticity matrix of the load in the j1st time period when the electricity price changes in the i1th time period; T p Indicates the normal segment; Λ gg (i2,j2) represents the self-elasticity matrix of the load in the j2th time period when the electricity price changes in the i2th time period; k g E represents the rate of change in electricity prices during off-peak hours. gg T represents the self-elasticity coefficient during the valley period; g Indicates the valley period.

7. The method as described in claim 5, characterized in that, The expressions for the cross-elasticity matrix of each electricity-consuming sector under different time-of-use pricing periods are as follows: Among them, Λ fp (i3,j3) represents the cross-elasticity matrix of the load in the j3rd time period when the electricity price changes in the i3th time period; T f Indicates peak period; T p Indicates a normal time period; T g Indicates the valley period; k f E represents the rate of change in electricity prices during peak hours. fp This represents the cross-elasticity coefficient between peak and off-peak periods; Λ fg (i4,j4) represents the cross-elasticity matrix of the load in the j4th time period when the electricity price changes in the i4th time period; k g E represents the rate of change in electricity prices during off-peak hours. fg This represents the cross-elasticity coefficient between peak and trough periods; Λ gp (i5,j5) represents the cross-elasticity matrix of the load in the j5th time period when the electricity price changes in the i5th time period; E gp This represents the cross-elasticity coefficient of the valley period to the normal period.

8. The method as described in claim 1, characterized in that, The expression for the load response model is as follows: Among them, L′ f (i0) represents the response load data for the i0th time period; L′ p (i1) represents the response load data for the i1th time period; L′ g (i2) represents the response load data for the i2th time period; T f Indicates peak period; T p Indicates a normal time period; T g Indicates the valley period; L f (i0) represents the load data before the response in the i0th time period; L p (i1) represents the load data before the response in the i1th time period; L g (i2) represents the load data before the response in the i2th time period; Υ ff This indicates information about the price elasticity of electricity during peak hours; Υ fp This indicates the price elasticity characteristics of electricity during peak hours compared to normal hours; Υ fg This indicates the price elasticity of electricity during peak hours relative to off-peak hours; Υ pp This indicates the elasticity of electricity prices during normal periods; Υ pp This indicates the price elasticity characteristics of electricity during off-peak hours relative to normal hours; Υ gg This indicates the characteristics of electricity price elasticity during off-peak hours.

9. The method as described in claim 1, characterized in that, The historical load characteristic information includes: instantaneous structure information of historical load and overall structure information of historical load; The electricity-consuming sectors include one or more of the following: primary industry, secondary industry, tertiary industry, and residential electricity consumption; The first industry includes one or more of the following: agriculture, forestry, fishery and animal husbandry; The second sector includes one or more of the following: industry, manufacturing, and construction; The tertiary sector includes one or more of the following: commerce, finance, education, and transportation.

10. A load response system based on time-of-use pricing, characterized in that, include: The load forecasting module is used to perform load forecasting for each power-consuming sector based on pre-calculated historical load characteristic information of each power-consuming sector, and to obtain load forecasting information for each power-consuming sector. The elasticity extraction module is used to determine the price elasticity characteristics of each electricity consumer in different time-of-use pricing periods based on the load forecast information of each electricity consumer. The load response module is used to perform load response for each electricity-consuming sector based on the electricity price elasticity characteristic information and a pre-built load response model, and output the response load data of each electricity-consuming sector during different time-of-use electricity price periods.

11. The system as claimed in claim 10, characterized in that, The load forecasting module includes: The time-series pattern calculation submodule is used to calculate the intraday fluctuation characteristics of each electricity-consuming sector based on the pre-calculated historical load characteristic information of each electricity-consuming sector. The load percentage calculation submodule is used to calculate the load percentage information of each electricity-consuming sector based on the intraday fluctuation characteristics of each sector. The prediction generation submodule is used to perform load prediction for each electricity-consuming sector based on the load ratio information of each sector, and obtain the load prediction information of each sector. The load percentage information includes: average load percentage information and hourly load percentage information.

12. The system as claimed in claim 11, characterized in that, The load percentage calculation submodule includes: The variation amplitude determination submodule is used to obtain the load variation amplitude information of each electricity-consuming sector based on the intraday fluctuation characteristics of each sector. The average load calculation submodule is used to calculate the average load percentage information of each power-consuming sector based on the load change amplitude information of each power-consuming sector; The time-of-use load calculation submodule is used to calculate the hourly load percentage information of each electricity-consuming sector based on the average load percentage information of each sector.

13. The system as described in claim 11, characterized in that, The expressions for the load forecast information of each electricity-consuming sector are as follows: L i (D) (h)=L0 (D) (h)·p i (D) (h); in, This represents the load forecast information for electricity consumer i at time h in year D; This represents the total load forecast information for all electricity-consuming sectors at time h in year D; This represents the hourly load percentage information for electricity-consuming sector i at time h in year D.

14. The system as claimed in claim 10, characterized in that, The elastic extraction module includes: The elasticity coefficient calculation submodule is used to calculate the self-elasticity coefficient and cross-elasticity coefficient of each power-consuming sector based on the load forecast information of each power-consuming sector. The first matrix generation submodule is used to calculate the self-elasticity matrix of each electricity consumer under different time-of-use electricity price periods based on the self-elasticity coefficient of each electricity consumer. The second matrix generation submodule is used to calculate the cross elasticity matrix of each electricity consumer under different time-of-use electricity price periods based on the cross elasticity coefficient of each electricity consumer. The feature generation submodule is used to use the self-elasticity matrix and the cross-elasticity matrix as the electricity price elasticity feature information of each electricity-consuming sector; The time-of-use electricity pricing periods include peak hours, normal hours, and valley hours.

15. The system as described in claim 14, characterized in that, The expressions for the self-elasticity matrix of each electricity-consuming sector under different time-of-use pricing periods are as follows: Among them, Λ ff (i0,j0) represents the self-elasticity matrix of the load in the j0th time period when the electricity price changes in the i0th time period; k f E represents the rate of change in electricity prices during peak hours. ff t represents the self-elasticity coefficient during the peak period; f Indicates peak period; Λ pp (i1,j1) represents the self-elasticity matrix of the load in the j1st time period when the electricity price changes in the i1th time period; T p Indicates the normal segment; Λ gg (i2,j2) represents the self-elasticity matrix of the load in the j2th time period when the electricity price changes in the i2th time period; k g E represents the rate of change in electricity prices during off-peak hours. gg T represents the self-elasticity coefficient during the valley period; g Indicates the valley period.

16. The system as described in claim 14, characterized in that, The expressions for the cross-elasticity matrix of each electricity-consuming sector under different time-of-use pricing periods are as follows: Among them, Λ fp (i3,j3) represents the cross-elasticity matrix of the load in the j3rd time period when the electricity price changes in the i3th time period; T f Indicates peak period; T p Indicates a normal time period; T g Indicates the valley period; k f E represents the rate of change in electricity prices during peak hours. fp This represents the cross-elasticity coefficient between peak and off-peak periods; Λ fg (i4,j4) represents the cross-elasticity matrix of the load in the j4th time period when the electricity price changes in the i4th time period; k g E represents the rate of change in electricity prices during off-peak hours. fg This represents the cross-elasticity coefficient between peak and trough periods; Λ gp (i5,j5) represents the cross-elasticity matrix of the load in the j5th time period when the electricity price changes in the i5th time period; E gp This represents the cross-elasticity coefficient of the valley period to the normal period.

17. The system as claimed in claim 10, characterized in that, The expression for the load response model is as follows: Among them, L′ f (i0) represents the response load data for the i0th time period; L′ p (i1) represents the response load data for the i1th time period; L′ g (i2) represents the response load data for the i2th time period; T f Indicates peak period; T p Indicates a normal time period; T g Indicates the valley period; L f (i0) represents the load data before the response in the i0th time period; L p (i1) represents the load data before the response in the i1th time period; L g (i2) represents the load data before the response in the i2th time period; Υ ff This indicates information about the price elasticity of electricity during peak hours; Υ fp This indicates the price elasticity characteristics of electricity during peak hours compared to normal hours; Υ fg This indicates the price elasticity of electricity during peak hours relative to off-peak hours; Υ pp This indicates the elasticity of electricity prices during normal periods; Υ gp This indicates the price elasticity characteristics of electricity during off-peak hours relative to normal hours; Υ gg This indicates the characteristics of electricity price elasticity during off-peak hours.

18. The system as claimed in claim 10, characterized in that, The historical load characteristic information includes: instantaneous structure information of historical load and overall structure information of historical load; The electricity-consuming sectors include one or more of the following: primary industry, secondary industry, tertiary industry, and residential electricity consumption; The first industry includes one or more of the following: agriculture, forestry, fishery and animal husbandry; The second sector includes one or more of the following: industry, manufacturing, and construction; The tertiary sector includes one or more of the following: commerce, finance, education, and transportation.

19. An electronic device, characterized in that, include: At least one processor and memory; The memory and processor are connected via a bus; The memory is used to store one or more programs; When the one or more programs are executed by the at least one processor, a load response method based on time-of-use pricing as described in any one of claims 1 to 9 is implemented.

20. A computing device readable storage medium, characterized in that, It contains an execution program, which, when executed, implements a load response method based on time-of-use pricing as described in any one of claims 1 to 9.

Images