A time- and price-sensitive adjustable load elasticity forecasting method, system, electronic device, and readable storage medium.

Abstract

This invention provides a time- and price-sensitive adjustable load elasticity forecasting method, system, electronic device, and readable storage medium, belonging to the field of power system load regulation technology. The method involves collecting load data, cleaning, initializing, and performing error analysis; establishing a price elasticity model and a time-sensitive model, optimizing parameters and training the model using historical data; acquiring day-ahead industry power forecast data; adjusting model parameters in real time based on load forecast results to eliminate uncertainty in the price elasticity model; correcting the price- and time-sensitive models using dynamically adjusted parameters; calculating the demand response gap based on renewable energy output forecasts and load forecasts; updating the model input based on time-of-use electricity prices provided by the electricity market; and finally outputting the adjusted load response power. This invention reduces the impact of demand response uncertainty on the price elasticity model, effectively improving its accuracy.

Description

Technical Field

[0001] This invention belongs to the field of power system load regulation technology, and particularly relates to an adjustable load elasticity prediction method, system, electronic device and readable storage medium based on time and price sensitivity. Background Art

[0002] Currently, to fully leverage the adjustable capacity on the user side and improve the effective utilization rate of the power system, the price elasticity mechanism of adjustable load on the demand side is generally used. By rationally adjusting time-of-use pricing and demand response incentive prices, electricity users' consumption behavior can be effectively guided to address the problem of power supply and demand imbalance. Therefore, it is necessary to establish a price elasticity model for adjustable load based on time-of-use pricing and demand response incentive mechanisms to incentivize electricity users to actively participate in peak shaving and valley filling and the consumption of renewable energy, thereby reducing electricity costs.

[0003] Existing adjustable load price elasticity modeling includes two approaches:

[0004] 1) Analyze the sensitivity of different user groups to electricity price changes using a price elasticity matrix, and design pricing strategies accordingly;

[0005] 2) Taking into account user behavior and psychological factors, such as habits, expectations, and perceived value, simulate a price elasticity model based on user psychology. Price elasticity models are gradually becoming an indispensable part of the electricity market and smart grid.

[0006] Disadvantages of existing technology:

[0007] 1. In the traditional linear price elasticity model, price elasticity changes dynamically with user power. However, at present, the load power curve based on peak-valley electricity price is difficult to extract the true price elasticity information of users, and it does not take into account that price elasticity will be constrained by the upward and downward potential of user demand response.

[0008] 2. Traditional price elasticity models do not take into account the changing trend of load elasticity over time, meaning that it has different sensitivities at different times, which affects the accuracy of prediction. Summary of the Invention

[0009] This invention provides an adjustable load elasticity forecasting method based on time and price sensitivity, which at least solves the problem in the prior art that the traditional price elasticity model does not take into account the changing trend of load elasticity over time, i.e., different sensitivities at different times, which affects the forecasting accuracy.

[0010] The methods include:

[0011] S101: Collect load data within a preset time period;

[0012] S102: Clean the collected load data to form a load dataset;

[0013] S103: Initialize the load data in the load dataset;

[0014] S104: Perform error analysis on load data;

[0015] S105: Establish a price elasticity model and a time sensitivity model based on the load dataset, optimize parameters and train the model using historical data, and simulate the load response under a given time-of-use electricity price and demand response incentives using actual data.

[0016] S106: Obtain current day's industry power forecast data;

[0017] S107: Adjust model parameters in real time based on load forecast results to eliminate uncertainty in the price elasticity model;

[0018] S108: Correct the price sensitivity model and time sensitivity model by dynamically adjusting the parameters;

[0019] S109: Calculate the demand response gap based on the forecast of new energy output and load;

[0020] S110: Update the model input based on the time-of-use electricity price provided by the electricity market;

[0021] S111: The final output is the adjusted load response power, used to support demand-side management or market operation decisions of the power system.

[0022] It should be further noted that load data cleaning in S102 includes outlier removal and missing data imputation.

[0023] It should be further noted that in S103, the initial parameters are selected based on past experience, or initialization is performed using a random or uniform distribution.

[0024] It should be further noted that the error analysis of the load data in step S105 includes: calculating the fitting error within a preset time period, and using the mean square error and root mean square error to evaluate the fitting status of the price elasticity model and the time sensitivity model.

[0025] It should be further noted that step S105 also includes: establishing a load elasticity model that considers time sensitivity and price sensitivity, as shown below:

[0026]

[0027] In the formula: P Power required to meet load demand; h It is a price sensitivity function;g This is a time sensitivity function; X This is a 24-hour price variable matrix; Y This is a 24-hour time variable matrix;

[0028] Variable X represents time-of-use electricity pricing and demand response subsidies:

[0029]

[0030] In the formula: x i Time period i Time-of-use electricity pricing; z i Time period i Demand response subsidy price; i = 1,2,3, …,24;

[0031] Variable Y is a higher-order feature of time information:

[0032]

[0033] In the formula: t For time information; n This is the highest-order term for capturing time information.

[0034] It should be further explained that the method quantifies users' price sensitivity when participating in market transactions, defining the ratio of the percentage change in demand to the percentage change in price:

[0035]

[0036] In the formula: P For the user's response power, Q It's a change in electricity prices;

[0037] Based on the sensitivity formula Z, a load demand response model with generalization characteristics was established, with the aim of calculating load reduction or transfer in real time:

[0038]

[0039] In the formula: P DR Demand response power; P base Baseline load or load forecast power; P max This represents the upper limit of the theoretical load adjustable capacity.

[0040] It should be further noted that step S108 also includes: introducing a real-time matrix. C To elasticity model P ( Q ,t In this process, the elasticity model is adjusted in real time based on load forecasting results to eliminate the uncertainty of load power fluctuations under the same electricity price.

[0041]

[0042] In the formula: C This is a parameter matrix that is adjusted in real time based on load forecast results;

[0043] The real-time parameter matrix C is shown below.

[0044]

[0045] The purpose of parameter calculation is to eliminate the uncertainty in the price elasticity model, as follows:

[0046]

[0047] In the formula: P 0( t ) represents the predicted load power; Δ P ( t () represents the actual load response power. T For 24 hours;

[0048] After real-time parameter adjustments, the load price elasticity model considering both price and time sensitivity is expressed as follows:

[0049]

[0050] In the formula: P '( Q,t ) is the load elasticity model after real-time parameter adjustment.

[0051] This application also provides an adjustable load resilience forecasting system based on time and price sensitivity, the system comprising:

[0052] An information collection module for collecting load data within a preset time period;

[0053] A data cleaning module used to clean the collected load data and form a load dataset;

[0054] An initialization module used to initialize the load data within the load dataset;

[0055] A data analysis module for performing error analysis on load data;

[0056] This module is used to build price elasticity and time sensitivity models based on load datasets, optimize parameters and train models using historical data, and simulate load response under given time-of-use electricity prices and demand response incentives using actual data.

[0057] A data acquisition module for obtaining current day industry power forecast data;

[0058] A parameter adjustment module used to adjust model parameters in real time based on load forecast results in order to eliminate uncertainty in the price elasticity model;

[0059] A model adjustment module used to correct price sensitivity models and time sensitivity models using dynamically adjusted parameters;

[0060] A load calculation module used to calculate the demand response gap based on the forecast of new energy output and load.

[0061] A model update module used to update model inputs based on time-of-use electricity prices provided by the electricity market;

[0062] Load power output module used for final output of adjusted load response power to support demand-side management or market operation decisions of the power system.

[0063] According to another embodiment of this application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of a time- and price-sensitive adjustable load resilience forecasting method.

[0064] According to yet another embodiment of this application, a readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the time- and price-sensitive adjustable load resilience forecasting method.

[0065] As can be seen from the above technical solutions, the present invention has the following advantages:

[0066] The adjustable load elasticity forecasting method based on time and price sensitivity provided by this invention considers the time and price sensitivity of electricity users' participation in demand response. It can effectively capture adjustable load price elasticity information to improve the demand-side response capability of the power system and reduce the electricity cost of the load. By employing a combination of the sigmoid function and a multinomial model, the impact of demand response uncertainty on the price elasticity model is reduced, effectively improving the accuracy of the price elasticity model.

[0067] This invention effectively solves the problem that in the traditional linear price elasticity model, price elasticity changes dynamically with user power, but at present, the load power curve based on peak-valley electricity price is difficult to extract the user's true price elasticity information, and does not take into account the constraint that price elasticity will be constrained by the upward and downward adjustment potential of user demand response. Attached Figure Description

[0068] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0069] Figure 1 The flowchart shows a time- and price-sensitive adjustable load elasticity forecasting method.

[0070] Figure 2 A schematic diagram of an adjustable load demand response framework based on a price elasticity model;

[0071] Figure 3 A schematic diagram of an adjustable load elasticity model that takes into account time and price sensitivity;

[0072] Figure 4 A schematic diagram of price elasticity models for six typical industries;

[0073] Figure 5 This is a schematic diagram of an electronic device. Detailed Implementation

[0074] Various embodiments of this disclosure will be described more fully below. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.

[0075] In the following, the terms “comprising” or “may include”, which may be used in various embodiments of this disclosure, indicate the presence of the disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. Furthermore, as used in various embodiments of this disclosure, the terms “comprising,” “having,” and their cognates are intended only to indicate a particular feature, number, step, operation, element, component, or combination of the foregoing, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing, or the possibility of adding one or more combinations of the foregoing.

[0076] The adjustable load elasticity forecasting method proposed in this invention, based on time and price sensitivity, uses the Sigmoid function to simulate the load's own upward and downward adjustment capabilities, thereby achieving price sensitivity forecasting. Under the constraints of the Sigmoid model, the load's demand response capability dynamically changes with time-of-use pricing and subsidy prices. For time sensitivity, a multinomial model is used to capture the time-series demand response capability characteristics of the load, particularly the nonlinear dynamic changes in electricity demand over time under the current fixed time-of-use pricing system.

[0077] The Sigmoid function involved in this invention is a widely used activation function in machine learning and deep learning. The time- and price-sensitive adjustable load resilience prediction proposed in this invention uses the Sigmoid function to map any real number to the range of 0 to 1.

[0078] In embodiments of the present invention, the time- and price-sensitive adjustable load resilience forecasting method can be written in one or more programming languages ​​or a combination thereof to perform computer program code for carrying out the operations of the present disclosure. The programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages.

[0079] The following will describe in detail the adjustable load elasticity prediction method based on time and price sensitivity of the present invention with reference to the accompanying drawings. The method takes into account time and price sensitivity, and can effectively capture adjustable load price elasticity information to improve the demand-side response capability of the power system and reduce the electricity cost of the load. It has a positive effect on improving the stability and economy of the power system.

[0080] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0081] Please see Figures 1 to 3 The diagram shows a flowchart of an adjustable load elasticity forecasting method based on time and price sensitivity in a specific embodiment. The method includes:

[0082] S101: Collect load data within a preset time period.

[0083] This embodiment can collect load data within a preset time period from a database, or it can collect load data within a preset time period from the currently operating power system. The preset time period can be one month, or it can be inputting 96 load data points from a typical industry over the past year to ensure that the data covers the entire year and captures seasonal variations and holiday effects. The specific duration and collection method are not limited here.

[0084] S102: Clean the collected load data to form a load dataset.

[0085] The data cleaning in this embodiment involves imputing outliers and missing data. Statistical methods can be used to process or impute missing values, identifying and removing outlier data.

[0086] S103: Initialize the load data in the load dataset.

[0087] It should be noted that the parameter matrix initialization is based on the selection of initial parameters according to theory or past experience, or by using a random or uniform distribution method for initialization.

[0088] S104: Perform error analysis on the load data.

[0089] This embodiment can calculate the fitting error over one year and use mean squared error (MSE), root mean square error (RMSE), or other statistical indicators to evaluate the goodness of fit of the model.

[0090] S105: Establish a price elasticity model and a time sensitivity model based on the load dataset, optimize parameters and train the model using historical data, and simulate the load response under a given time-of-use electricity price and demand response incentives using actual data.

[0091] In one exemplary embodiment, user electricity consumption data and electricity price data can be collected from sources such as smart meters and power system monitoring equipment. The data undergoes cleaning, noise reduction, and normalization processes to ensure accuracy and consistency. Historical load data is analyzed to understand peak-valley characteristics and periodic variations in the load.

[0092] This embodiment establishes a price elasticity model by defining a price elasticity coefficient, which represents the degree of impact of electricity price changes on load demand. Using statistical methods or machine learning algorithms, based on historical data and the electricity price-demand elasticity coefficient matrix, the load adjustment amount under different electricity prices is calculated. Based on the calculation results, a price elasticity model is established to describe the dynamic relationship between electricity prices and load demand.

[0093] This embodiment, in establishing a time sensitivity model, can analyze users' sensitivity to time (such as different time periods) and understand the differences in users' electricity consumption behavior at different times. Based on historical data and user behavior analysis, a time sensitivity model is established to describe the impact of time factors on load demand.

[0094] This embodiment also utilizes historical data to optimize the parameters of the price elasticity model and the time sensitivity model. Through multi-objective optimization methods or intelligent optimization algorithms, the model parameters and weights are adjusted to achieve objectives such as cost minimization and energy utilization maximization. This enables the model to accurately predict load response under given electricity prices and demand response incentives.

[0095] Optionally, given time-of-use pricing and demand response incentives, the established price elasticity and time sensitivity models can be used to simulate user load response. The simulation results are then used to analyze the impact of different pricing strategies and incentives on the load curve and evaluate their effectiveness.

[0096] To ensure the accuracy and reliability of the model, it can be validated and evaluated using real-world data. Based on the validation results, the model can be adjusted and optimized as necessary.

[0097] S106: Obtain current day industry power forecast data.

[0098] S107: Adjust model parameters in real time based on load forecast results to eliminate uncertainty in the price elasticity model.

[0099] S108: Correct the price sensitivity model and time sensitivity model by dynamically adjusting the parameters.

[0100] S109: Calculate the demand response gap based on the forecast of new energy output and load.

[0101] This embodiment calculates the demand response gap based on the forecast of new energy output and load, and adjusts the compensation strategy to ensure the applicability and practicality of the model output.

[0102] S110: Update the model input based on the time-of-use electricity price provided by the electricity market.

[0103] S111: The final output is the adjusted load response power, used to support demand-side management or market operation decisions of the power system.

[0104] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0105] In one embodiment of the present invention, based on step S105, a possible embodiment will be given below, and its specific implementation will be described in a non-limiting manner.

[0106] The training and application process of the adjustable load price elasticity model in this embodiment involves the following steps:

[0107] The load elasticity model considering time sensitivity and price sensitivity is established as follows:

[0108]

[0109] In the formula: P Power required to meet load demand; h It is a price sensitivity function; g This is a time sensitivity function; X This is a 24-hour price variable matrix; Y It is a 24-hour time variable matrix.

[0110] Variable X represents time-of-use electricity pricing and demand response subsidies:

[0111]

[0112] In the formula: x i Time period i Time-of-use electricity pricing; z i Time period i Demand response subsidy price; i = 1,2,3, …,24.

[0113] Variable Y is a higher-order feature of time information:

[0114]

[0115] In the formula: t For time information; n This is the highest-order term for capturing time information.

[0116] Based on the load resilience model involved in this embodiment, the execution process for improving load demand response capability by adjusting time-of-use pricing and incentive prices is as follows: Figure 2 As shown, firstly, historical power data from load aggregators, large commercial loads, and large industrial loads are input and used to train a load price elasticity model; then, the power grid company calculates the demand response power demand based on the next day's photovoltaic, wind power, and load forecast data; finally, the electricity price and incentive adjustment scheme are calculated using the price elasticity model to guide users' electricity consumption behavior the following day.

[0117] During the training phase, the model's inputs are historical time-of-use electricity prices, demand response subsidy prices, and load power curves; the output is a price elasticity model. During the real-time calculation phase, the inputs are the next day's time-of-use electricity prices and subsidy prices; the output is the load's demand response power, such as... Figure 3 As shown.

[0118] Based on the above embodiments, in order to further improve the reliability of the time- and price-sensitive adjustable load resilience forecasting provided by the above embodiments, and as an implementable approach, in one embodiment, the price sensitivity model can be configured based on the fact that user-side load regulation is a key strategy in power system management.

[0119] According to embodiments of this application, during peak demand periods, optimizing the time-of-use pricing mechanism incentivizes consumers to reduce electricity consumption during peak demand periods, thereby helping the power grid maintain a real-time supply-demand balance.

[0120] This embodiment takes heating load as an example. The minimum winter heating temperature for residential buildings is 18°C. The heat saved by users voluntarily adjusting their room temperature from the original setting to 18°C ​​based on their electricity price sensitivity at any given moment is the maximum load reduction amount for users participating in demand response at that moment. This strategy effectively utilizes users' price sensitivity, that is, the degree to which users react to changes in electricity prices. By adjusting electricity prices, it guides users' electricity consumption behavior, thereby optimizing the allocation of generation-side resources and the overall operating efficiency of the power grid.

[0121] The price sensitivity discussed in this embodiment refers to how users adjust their electricity consumption when electricity prices change. Different types of loads show significantly different sensitivities to price. This embodiment applies the Weber-Fechner law to quantify users' price sensitivity when participating in market transactions, defined as the ratio of the percentage change in demand to the percentage change in price.

[0122]

[0123] In the formula: P For the user's response power, Q It's a change in electricity prices.

[0124] If the absolute value of price sensitivity is greater than 1, demand is considered price-sensitive, meaning that a small change in price will lead to a large change in quantity demanded. If the absolute value of price sensitivity is less than 1, demand is considered price-insensitive, meaning that price changes have a small impact on quantity demanded. In the power system, the main factors affecting price sensitivity are time-of-use pricing and demand response subsidies, while it is also constrained by the adjustability of users themselves.

[0125] Specifically, different types of users, such as heating load, steel load, cement load, and data center load, have different electricity consumption habits and price sensitivities. Not all users will allocate 100% of their available load reduction capacity to demand response; instead, they will adjust their response ratio based on electricity price benefits. Therefore, based on the sensitivity formula Z, a load demand response model with generalization characteristics was established to calculate the load reduction or transfer amount in real time.

[0126]

[0127] In the formula: P DR Demand response power; P base Baseline load or load forecast power; P max This represents the upper limit of the theoretical load adjustable capacity.

[0128] Many factors influence load response characteristics, primarily load type, electricity pricing policy, product price, rated power, electricity demand, and users' perception of the pricing mechanism. Under different load types and pricing policies, the electricity-price elasticity matrix structure for users will vary significantly. However, considering the limitations of load's ability to adjust upwards and downwards, and that it will not increase indefinitely with prices, the traditional price elasticity formula in the above equation is improved, assuming that the user's response ratio... Z It is time-of-use electricity pricing Q A,i and subsidized prices Q B,i The Sigmoid function, i.e.:

[0129]

[0130] In the formula: A , B The user's response characteristic coefficient; the user's upscaling capability constraint is... K + C The user's ability to lower their threshold is constrained. C ; Q A,i Time-of-use pricing; Q B,i Subsidized prices in response to demand; g ( Q ) is the formula for price elasticity.

[0131] This embodiment uses the Sigmoid function, which can well express the non-linear response of users to price changes. Its value is between 0 and 1, and can simulate the saturation effect of users on price changes.

[0132] As an embodiment of this application, time sensitivity is one of the important aspects characterizing price elasticity, especially in the electricity market and time-of-use pricing mechanisms. Time factors influence users' electricity consumption behavior because electricity demand and price sensitivity can differ significantly across different time periods (e.g., daytime and nighttime, weekdays and weekends). The form of the time sensitivity model depends on the specific characteristics of the electricity load and historical data. Considering that time-of-use pricing mechanisms are already well-established and that there are multiple peak and off-peak periods within a single day, a multinomial fitting is used to better capture the characteristics of time sensitivity.

[0133] The polynomial function simulation of time sensitivity in this embodiment is a mathematically complex but highly flexible method that can accurately capture the nonlinear dynamic changes in electricity demand throughout the day. Higher-order functions have enough parameters to fit curves of various shapes, making them well-suited for simulating complex power-time dependencies, as detailed below:

[0134]

[0135] In the formula: b These are the coefficients of the time-sensitivity model.

[0136] In this embodiment, under the time-of-use pricing mechanism, only four prices exist: off-peak price, flat-peak price, peak price, and peak-spot price. Therefore, only a fifth-order polynomial is needed for fitting. However, under the same price, the power fluctuations of most loads are large, posing a significant challenge to the accuracy of the load resilience model. Therefore, to improve the accuracy of the load resilience model, a real-time matrix is ​​introduced. C To elasticity model P ( Q , t The main purpose of this is to adjust the resilience model in real time based on load forecasting results in order to eliminate the uncertainty of load power fluctuations under the same electricity price.

[0137]

[0138] In the formula: C This is a parameter matrix that is adjusted in real time based on load forecast results.

[0139] The real-time parameter matrix C is shown below. The parameters of this matrix take different values ​​at different times.

[0140]

[0141] The purpose of parameter calculation is to eliminate the uncertainty in the price elasticity model, as follows:

[0142]

[0143] In the formula:P 0( t ) represents the predicted load power; Δ P ( t () represents the actual load response power. T It is 24 hours.

[0144] After real-time parameter adjustments, the load price elasticity model considering both price and time sensitivity is expressed as follows:

[0145]

[0146] In the formula: P '( Q,t ) is the load elasticity model after real-time parameter adjustment.

[0147] The adjustable load elasticity forecasting method based on time and price sensitivity provided by this invention considers the time and price sensitivity of electricity users' participation in demand response. It can effectively capture adjustable load price elasticity information to improve the demand-side response capability of the power system and reduce the electricity cost of the load. By employing a combination of the sigmoid function and a multinomial model, the impact of demand response uncertainty on the price elasticity model is reduced, effectively improving the accuracy of the price elasticity model.

[0148] The following are embodiments of the time- and price-sensitive adjustable load elasticity forecasting system provided in this disclosure. This system and the time- and price-sensitive adjustable load elasticity forecasting methods described in the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the time- and price-sensitive adjustable load elasticity forecasting system, please refer to the embodiments of the time- and price-sensitive adjustable load elasticity forecasting methods described above.

[0149] The system includes:

[0150] An information collection module for collecting load data within a preset time period;

[0151] A data cleaning module used to clean the collected load data and form a load dataset;

[0152] An initialization module used to initialize the load data within the load dataset;

[0153] A data analysis module for performing error analysis on load data;

[0154] This module is used to build price elasticity and time sensitivity models based on load datasets, optimize parameters and train models using historical data, and simulate load response under given time-of-use electricity prices and demand response incentives using actual data.

[0155] A data acquisition module for obtaining current day industry power forecast data;

[0156] A parameter adjustment module used to adjust model parameters in real time based on load forecast results in order to eliminate uncertainty in the price elasticity model;

[0157] A model adjustment module used to correct price sensitivity models and time sensitivity models using dynamically adjusted parameters;

[0158] A load calculation module used to calculate the demand response gap based on the forecast of new energy output and load.

[0159] A model update module used to update model inputs based on time-of-use electricity prices provided by the electricity market;

[0160] Load power output module used for final output of adjusted load response power to support demand-side management or market operation decisions of the power system.

[0161] The system of this invention can combine price elasticity modeling results from multiple types of electricity loads. For example... Figure 4 As shown, the system establishes elasticity models for six typical industries under the influence of price elasticity and time sensitivity. Among them, cement load, heating load, air conditioning load, and electric vehicle load have high time sensitivity, while heating load, steel load, and cement load have strong price elasticity.

[0162] Based on the price elasticity model, the time-of-use electricity price elasticity of six typical industries is analyzed. Regarding the capacity for renewable energy absorption, the electricity price from 12:00 to 14:00 is adjusted from 0.44 yuan to 0.22 yuan, with the heating load increasing by up to 100%, while the air conditioning load increases by as little as 6.0%.

[0163] In response to peak shaving capacity, the period from 7 PM to 9 PM will be adjusted to peak electricity price, with the cement load reduced by up to 37.8% and the air conditioning load reduced by as little as 4.8%.

[0164] Table 1. Impact of Electricity Price Adjustments on Load Demand Response Capability

[0165]

[0166] Next, the demand response incentive elasticity of six typical industries is analyzed. For renewable energy absorption capacity, a subsidy of 0.5 yuan / kWh is provided between 12:00 and 14:00, with the heating load response rate reaching a maximum of 100%, while data centers have a minimum of only 3.9%. For peak shaving and valley filling capacity, a demand response subsidy of 2 yuan / kWh is set, with peak shaving capacity reaching 50% in all cases, while data centers have the highest valley filling capacity at 59.3%.

[0167] Table 2 Impact of Incentive Prices on Load Demand Response Capability

[0168]

[0169] Figure 5 This is a schematic diagram of the hardware structure of an electronic device to implement various embodiments of the present invention. The electronic device 500 in this embodiment includes, but is not limited to, components such as: a radio frequency unit 501, a network module 502, an audio output unit 503, an input unit 504, a display unit 506, an interface unit 508, a memory 509, a processor 510, and a power supply 511. Those skilled in the art will understand that the electronic device structure involved in the embodiments of the present invention does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the diagram, or a combination of certain components, or different arrangements of components. In the embodiments of the present invention, the electronic device includes, but is not limited to, mobile phones, tablet computers, laptops, PDAs, in-vehicle terminals, wearable devices, and pedometers.

[0170] It should be understood that, in this embodiment of the invention, the radio frequency unit 501 can be used for receiving and transmitting signals during information transmission or calls. Specifically, it receives downlink data from the base station and processes it with the processor 510; additionally, it transmits uplink data to the base station. Typically, the radio frequency unit 501 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, etc. Furthermore, the radio frequency unit 501 can also communicate with networks and other devices through a wireless communication system.

[0171] The electronic device in this embodiment provides users with wireless broadband Internet access through the network module 502, such as helping users send and receive emails, browse web pages, and access streaming media.

[0172] The audio output unit 503 of this embodiment can convert audio data received by the radio frequency unit 501 or the network module 502 or stored in the memory 509 into audio signals and output them as sound. Furthermore, the audio output unit 503 can also provide audio output related to specific functions performed by the electronic device 500 (e.g., call signal reception sound, message reception sound, etc.). The audio output unit 503 includes a speaker, a buzzer, and a receiver, etc.

[0173] The input unit 504 in this embodiment is used to receive audio or video signals. The input unit 504 may include a graphics processing unit (GPU) and a microphone. The GPU processes image data of still images or videos acquired by an image capture device (such as a camera) in video capture mode or image capture mode. The processed image frames can be displayed on the display unit 506.

[0174] The display unit 506 is used to display information input by the user or information provided to the user. The display unit 506 may include a display panel, which may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0175] Furthermore, the touch panel can be overlaid on the display panel. When the touch panel detects a touch operation on or near it, it transmits the information to the processor 510 to determine the type of touch event. Subsequently, the processor 510 provides corresponding visual output on the display panel according to the type of touch event.

[0176] It is understood that in one embodiment, the touch panel and the display panel are two separate components to realize the input and output functions of the electronic device. However, in some embodiments, the touch panel and the display panel can be integrated to realize the input and output functions of the electronic device. The specifics are not limited here.

[0177] Interface unit 508 serves as an interface for connecting external devices to electronic device 500. For example, external devices may include a wired or wireless headphone port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device with an identification module, an audio input / output (I / O) port, a video I / O port, a headphone port, and so on. Interface unit 508 can be used to receive input from external devices (e.g., data, power, etc.) and transmit the received input to one or more components within electronic device 500, or it can be used to transmit data between electronic device 500 and external devices.

[0178] The memory 509 can be used to store software programs and various data. The memory 509 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, applications required for at least one function (such as sound playback, image playback, etc.), etc.; the data storage area may store data created based on the use of the mobile phone (such as audio data, phonebook, etc.). Furthermore, the memory 509 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0179] The processor 510 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 509, and by calling data stored in the memory 509, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. The processor 510 may include one or more processing units; preferably, the processor 510 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 510.

[0180] The time- and price-sensitive adjustable load resilience forecasting method and system provided by this invention comprises the units and algorithmic steps of various examples described in conjunction with the embodiments disclosed herein. These can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0181] The readable storage medium provided by this invention stores a program product capable of implementing the methods described above in this specification. In some possible embodiments, various aspects of this disclosure can also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.

[0182] A readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0183] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting adjustable load elasticity based on time and price sensitivity, characterized in that, The methods include: S101: Collect load data within a preset time period; S102: Clean the collected load data to form a load dataset; S103: Initialize the load data in the load dataset; S104: Perform error analysis on load data; S105: Establish a price elasticity model and a time sensitivity model based on the load dataset, optimize parameters and train the model using historical data, and simulate the load response under a given time-of-use electricity price and demand response incentives using actual data. S106: Obtain current day's industry power forecast data; S107: Adjust model parameters in real time based on load forecast results to eliminate uncertainty in the price elasticity model; S108: Correct the price elasticity model and time sensitivity model by dynamically adjusting the parameters; S109: Calculate the demand response gap based on the forecast of new energy output and load; S110: Update the model input based on the time-of-use electricity price provided by the electricity market; S111: The final output is the adjusted load response power, used to support demand-side management or market operation decisions of the power system; Step S108 further includes: introducing the real-time parameter matrix C into the elasticity model P(Q,t), where the elasticity model is the sum of the price elasticity model and the time sensitivity model, and adjusting the elasticity model in real time according to the load forecast results to eliminate the uncertainty of load power fluctuations under the same electricity price, where Q is the sum of the time-of-use electricity price and the demand response subsidy price, t represents time, and C is the parameter matrix that is adjusted in real time according to the load forecast results; The real-time parameter matrix C is shown below. The purpose of parameter calculation is to eliminate the uncertainty in the price elasticity model, as follows: In the formula: ΔP(t) represents the predicted load power; ΔP(t) represents the actual load response power, and T represents 24 hours. After real-time parameter adjustments, the load price elasticity model, considering both price and time sensitivity, is expressed as follows: In the formula: This is the load elasticity model after real-time parameter adjustment. X is the 24-hour price variable matrix; Y is the 24-hour time variable matrix; A and B are the user's response characteristic coefficients.

2. The adjustable load elasticity prediction method based on time and price sensitivity according to claim 1, characterized in that, Load data cleaning in S102 includes outlier removal and missing data imputation.

3. The adjustable load elasticity prediction method based on time and price sensitivity according to claim 1, characterized in that, In S103, initial parameters are selected based on past experience, or initialization is performed using a random or uniform distribution.

4. The adjustable load elasticity prediction method based on time and price sensitivity according to claim 1, characterized in that, S105 also includes error analysis methods for load data, including: calculating the fitting error within a preset time period, and using mean square error and root mean square error to evaluate the fitting status of the price elasticity model and the time sensitivity model.

5. The adjustable load elasticity prediction method based on time and price sensitivity according to claim 1, characterized in that, S105 also includes: establishing a load elasticity model that considers time sensitivity and price sensitivity, as shown below: In the formula: P(X,Y) is the load demand response power; h(X) is the price sensitivity function; g(Y) is the time sensitivity function; X is the 24-hour price variable matrix; Y is the 24-hour time variable matrix; Variable X represents time-of-use electricity pricing and demand response subsidies: Where: Let be the time-of-use electricity price for time period i; zi be the demand response subsidy price for time period i; i = 1,2,3, … ,24; Variable Y is a higher-order feature of time information: In the formula: t represents time information; n is the highest-order term for capturing time information.

6. A time- and price-sensitive adjustable load elasticity forecasting system, characterized in that, The system is used to implement the time- and price-sensitive adjustable load elasticity forecasting method as described in any one of claims 1 to 5; The system includes: An information collection module for collecting load data within a preset time period; A data cleaning module used to clean the collected load data and form a load dataset; An initialization module used to initialize the load data within the load dataset; A data analysis module for performing error analysis on load data; This module is used to build price elasticity and time sensitivity models based on load datasets, optimize parameters and train models using historical data, and simulate load response under given time-of-use electricity prices and demand response incentives using actual data. A data acquisition module for obtaining current day industry power forecast data; A parameter adjustment module used to adjust model parameters in real time based on load forecast results in order to eliminate uncertainty in the price elasticity model; A model adjustment module used to correct price elasticity models and time sensitivity models using dynamically adjusted parameters; A load calculation module used to calculate the demand response gap based on the forecast of new energy output and load. A model update module used to update model inputs based on time-of-use electricity prices provided by the electricity market; Load power output module used for final output of adjusted load response power to support demand-side management or market operation decisions of the power system.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the time- and price-sensitive adjustable load resilience forecasting method as described in any one of claims 1 to 5.

8. A readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the time- and price-sensitive adjustable load resilience forecasting method as described in any one of claims 1 to 5.

Images