A method and system for jointly predicting power load and electricity price considering weather factors

Abstract

The present invention relates to the field of electric load technology, and provides a method and system for jointly predicting electric load and electricity price taking weather factors into consideration, in order to solve the problem of lack of accuracy in dynamically changing scenarios, difficulty in effectively coordinating the decline in line carrying capacity with the allocation of peak-shaving resources, and affecting the rationality of the electricity price adjustment benchmark. The present invention includes: obtaining ice growth data, including the change in ice thickness on the conductor surface, ambient temperature and wind speed parameters; establishing a correlation between ice stress distribution and conductor deformation based on the change in ice thickness; predicting the transition time period of the critical state of ice melting, and calculating the ice melting power demand in different time periods; generating peak-shaving cost parameters in combination with the capacity limit of the peak-shaving units of the power grid; and generating correlation prediction results of electric load changes and electricity price fluctuations in combination with the conductor deformation. The present invention realizes the coordinated prediction of electric load changes and electricity price fluctuations during icing, and improves the safety and economy of power grid dispatching under extreme weather conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of electric load, and in particular to a method and system for jointly predicting electric load and electricity price taking weather factors into consideration. Background Art

[0002] In power system operations, line icing is a significant natural factor affecting the safety and stability of power transmission. Particularly in winter or in cold, high-altitude regions, ice accumulates on conductor surfaces due to factors such as low temperatures, humidity, and wind speeds. This can lead to serious accidents such as line breakage and tower collapse. To mitigate these risks, grid operations and maintenance departments must proactively activate ice-melting devices during icing to perform preventative de-icing operations. However, the de-icing process consumes significant amounts of electricity resources, directly impacting grid load distribution and placing higher demands on the operation and scheduling of peak-shaving units. Furthermore, in the context of power marketization, the additional peak-shaving demand caused by de-icing operations can also impact electricity price fluctuations.

[0003] Current mainstream solutions propose forecasting models based on the fusion of multi-source meteorological data and historical load data. These models employ deep neural network structures to model load trends during icing periods and simulate price responses in conjunction with day-ahead market pricing mechanisms. These existing solutions have several significant limitations. For example, they rely on the statistical relationship between macro-meteorological indicators and historical data, failing to fully explore the impact of micro-physical properties (such as ice deformation and stress distribution) during icing on ice melt timing and power demand, resulting in inaccurate forecasts in dynamic scenarios. Furthermore, they fail to fully consider the coupling relationship between ice melt power and grid transmission capacity, making it difficult to effectively coordinate reduced line capacity with the allocation of peak-shaving resources, impacting the rationality of the electricity price adjustment benchmark. Summary of the Invention

[0004] The present invention provides a method and system for jointly predicting power load and electricity price taking weather factors into consideration, so as to solve the problems in the prior art such as the lack of accuracy of prediction results in dynamically changing scenarios; the difficulty in effectively coordinating the decline in line carrying capacity with the allocation of peak-shaving resources, and the impact on the rationality of the electricity price adjustment benchmark.

[0005] In a first aspect, the present invention provides a method for jointly predicting power load and electricity price taking into account weather factors, comprising:

[0006] Acquiring ice growth data, wherein the ice growth data includes a change in ice thickness on the conductor surface, ambient temperature, and wind speed parameters;

[0007] Based on the change in ice thickness, analyzing the acoustic emission signal characteristics when the ice breaks, and establishing a correlation between ice stress distribution and conductor deformation based on the acoustic emission signal characteristics to predict the transition time period when the ice reaches a critical state of melting;

[0008] According to the transition time period, calculating the ice melting power demand in different time periods and generating peak-shaving cost parameters in combination with the capacity constraints of the peak-shaving units of the power grid, wherein the ice melting power demand includes the minimum starting power and the maintenance power range of the ice melting device;

[0009] Based on the conductor deformation amount and the peak-shaving cost parameter, a correlation prediction result of the power load change and the electricity price fluctuation during the icing period is generated.

[0010] Optionally, based on the change in ice thickness, analyzing acoustic emission signal characteristics when the ice breaks, and establishing a correlation between ice stress distribution and conductor deformation based on the acoustic emission signal characteristics to predict a transition time period when the ice reaches a critical melting state, including:

[0011] When the change in ice thickness reaches a preset threshold, the target acoustic emission signal on the surface of the ice-covered conductor is collected;

[0012] Extracting acoustic emission signal features from the acoustic emission signal, the acoustic emission signal features including waveform change speed, a first proportional parameter, and a second proportional parameter;

[0013] Establishing a correlation between stress distribution within the ice layer and wire deformation based on the waveform change rate and a first proportional parameter, wherein when the waveform change rate exceeds a first set value, a lateral expansion range of the stress concentration region in the ice layer is determined, and when the first proportional parameter exceeds a second set value, a correlation trend between the wire deformation and the ice layer peeling rate is determined;

[0014] Based on the lateral expansion range and the associated trend, combined with the changing characteristics of the second proportional parameter, a transition time period in which the ice layer reaches a critical melting state is predicted. The starting time of the transition time period is the moment when the crack propagation rate inside the ice layer first enters the linear growth stage, and the ending time is the moment when the line sag exceeds a preset sag threshold.

[0015] Optionally, based on the transition time period, the ice melting power requirements in different time periods are calculated, and combined with the capacity constraints of the peak-shaving units of the power grid, a peak-shaving cost parameter is generated. The ice melting power requirements include the minimum starting power and the maintenance power range of the ice melting device, including:

[0016] Divide the transition period into a startup phase, a continuous ice melting phase, and a termination phase, and use the start time of the transition period as a startup time reference point for the ice melting device;

[0017] Calculating the minimum starting power of the ice melting device during the starting phase according to the correlation trend between the conductor deformation and the ice peeling rate;

[0018] Determining a maintenance power range of the ice melting device during the continuous ice melting stage according to real-time changes in the ambient temperature and wind speed parameters;

[0019] Based on the maximum available capacity and startup delay time of the grid peak-shaving unit, the ice-melting power demand and the output constraints of the grid peak-shaving unit are established. The ice-melting power demand includes the minimum startup power and maintenance power range of the ice-melting device.

[0020] According to the minimum starting power, the maintenance power range, the output constraint condition and the capacity limitation condition of the peak-shaving unit of the power grid, a peak-shaving cost parameter that changes with time is generated.

[0021] Optionally, generating a time-varying peak-shaving cost parameter based on the minimum starting power, the maintenance power range, the output constraint, and the capacity constraint of the grid peak-shaving unit includes:

[0022] Calculating a reference value of the minimum starting power based on the lateral expansion range of the ice stress concentration area, and generating a delay compensation power increment based on the start-up delay time of the peak-shaving unit of the power grid;

[0023] Establishing a matching mechanism between the ice melting power demand and the output constraint, the matching mechanism including taking the sum of the baseline value and the delay compensation power increment as the total power demand during the startup phase, and constraining the fluctuation amplitude of the maintenance power range to be within the capacity constraint of the grid peaking unit;

[0024] A peak-shaving cost parameter that varies with time is generated according to the time distribution characteristics of the total power demand in the startup phase and the fluctuation constraint condition of the maintenance power range.

[0025] Optionally, generating a correlation prediction result of power load change and electricity price fluctuation during icing period based on the conductor deformation amount and the peak regulation cost parameter includes:

[0026] Calculate the power attenuation slope of the line transmission power based on the deviation between the conductor deformation and the preset sag threshold;

[0027] According to the time distribution characteristics of the peak-shaving cost parameters in the continuous ice-melting stage, the time period weight coefficient of the floating benchmark value of the electricity price is generated;

[0028] A bidirectional coupling rule is established, and the power attenuation slope and the time period weight coefficient are processed according to the bidirectional coupling rule to generate a correlation prediction result between the power load change and the electricity price fluctuation during the icing period.

[0029] Optionally, a bidirectional coupling rule is established, and the power attenuation slope and the time period weight coefficient are processed according to the bidirectional coupling rule to generate a correlation prediction result between the power load change and the electricity price fluctuation during the icing period, including:

[0030] Establishing a bidirectional coupling rule, when the power attenuation slope exceeds a preset deformation critical value, performing a compensatory incremental operation on the time period weight coefficient according to the bidirectional coupling rule, and terminating the compensatory incremental operation when the rate of change of the conductor deformation amount drops below a preset safety threshold, and generating a corrected value of the time period weight coefficient;

[0031] When the time period weight coefficient exceeds a preset cost critical value, a constraint suppression operation is performed on the power attenuation slope according to the bidirectional coupling rule. When the time distribution characteristics of the peak-shaving cost parameter return to a preset reference fluctuation band, the constraint suppression operation is terminated and a power attenuation slope constraint value is generated.

[0032] According to the time period weight coefficient correction value and the power attenuation slope constraint value, the convergence boundary coordinates of the load decrease interval and the phase offset range of the electricity price increase interval are generated to generate the correlation prediction results of the power load change and electricity price fluctuation during the icing period.

[0033] Optionally, based on the time period weight coefficient correction value and the power attenuation slope constraint value, the convergence boundary coordinates of the load reduction interval and the phase offset range of the electricity price increase interval are generated to generate a correlation prediction result of the power load change and electricity price fluctuation during the icing period, including:

[0034] Calculating a ratio of a load recovery rate corresponding to the power attenuation slope constraint value to a rate of change of the conductor deformation, using the ratio as a boundary contraction ratio, and converting the boundary contraction ratio into convergence boundary coordinates of a load reduction interval;

[0035] According to the ratio of the time period weight coefficient correction value to the base floating coefficient, combined with the start-up delay time of the peak-shaving unit of the power grid, the time delay amount is calculated, and the time delay amount is converted into a phase offset range of the electricity price increase interval;

[0036] The time reference point of the phase offset range is corrected by using the convergence boundary coordinates to generate a correlation prediction result between the power load change and the electricity price fluctuation during the icing period.

[0037] In a second aspect, the present invention provides a combined forecasting system for power load and electricity price taking weather factors into consideration, comprising:

[0038] An acquisition module is used to acquire ice growth data, wherein the ice growth data includes a change in ice thickness on the conductor surface, ambient temperature, and wind speed parameters;

[0039] an analysis module for analyzing acoustic emission signal characteristics when the ice layer breaks based on the change in ice layer thickness, and establishing a correlation between ice layer stress distribution and conductor deformation based on the acoustic emission signal characteristics to predict a transition time period when the ice layer reaches a critical melting state;

[0040] a calculation module, configured to calculate, based on the transition time period, ice melting power requirements in different time periods, and generate peak-shaving cost parameters in combination with capacity constraints of peak-shaving units of the power grid, wherein the ice melting power requirements include a minimum starting power and a maintenance power range of the ice melting device;

[0041] A generation module is used to generate a correlation prediction result between the power load change and the electricity price fluctuation during the icing period based on the conductor deformation amount and the peak-shaving cost parameter.

[0042] In a third aspect, an embodiment of the present invention provides a computing device comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for jointly predicting power load and electricity price taking into account weather factors as described in the first aspect above.

[0043] In a fourth aspect, an embodiment of the present invention provides a computer storage medium storing a computer program. When the computer program is executed by a computer, it implements a method for jointly predicting power load and electricity price considering weather factors as described in the first aspect.

[0044] In the present invention, ice growth data is obtained, and the ice growth data includes the change in ice thickness on the conductor surface, ambient temperature, and wind speed parameters; based on the change in ice thickness, the characteristics of acoustic emission signals when the ice layer breaks are analyzed, and based on the characteristics of the acoustic emission signals, a correlation relationship between ice layer stress distribution and conductor deformation is established to predict the transition time period when the ice layer reaches a critical state of ice melting; based on the transition time period, the ice melting power demand in different time periods is calculated, and combined with the capacity limitation conditions of the peak-shaving units of the power grid, a peak-shaving cost parameter is generated, and the ice melting power demand includes the minimum starting power and maintenance power range of the ice melting device; based on the conductor deformation and the peak-shaving cost parameter, a correlation prediction result of the power load change and electricity price fluctuation during the icing period is generated.

[0045] Beneficial effects of the present invention:

[0046] (1) The technical solution provided by the present invention can dynamically perceive the icing state by real-time monitoring of the change in ice thickness on the conductor surface, ambient temperature and wind speed parameters, providing a data basis for subsequent ice breakage risk prediction and power load adjustment, solving the prediction lag problem caused by data loss in traditional methods; based on the characteristics of acoustic emission signals, the correlation between ice stress distribution and conductor deformation is extracted to achieve accurate prediction of the critical state of the ice layer, breaking through the fuzzy judgment of the traditional empirical model on the evolution law of icing, and improving the accuracy of ice melting time window prediction.

[0047] (2) The present invention calculates the ice-melting power demand (including the minimum starting power and the maintenance power range) by time period, combines the capacity constraint conditions of the peak-shaving units of the power grid, dynamically generates peak-shaving cost parameters, optimizes the economic allocation of ice-melting resources, and solves the cost waste problem caused by the mismatch between power demand and peak-shaving capacity in traditional methods; realizes the coordinated optimization of load adjustment and electricity price response, solves the technical bottleneck of traditional single-dimensional prediction that cannot balance supply and demand and economy, and improves the stability and economy of power grid operation.

[0048] (3) The present invention refines the calculation logic of ice-melting power demand. By dividing the ice-melting stage into the start-up stage, the continuous ice-melting stage and the termination stage, and combining the correlation trend between the conductor deformation and the ice peeling rate, the minimum start-up power and the maintenance power range of the ice-melting device are dynamically adjusted. At the same time, based on the maximum available capacity and start-up delay time of the grid peak-shaving unit, a matching mechanism between the ice-melting power demand and the output constraint condition is constructed, and a delay compensation power increment is introduced to deal with the start-up delay problem, and finally a time-varying peak-shaving cost parameter is generated. By dividing different ice-melting stages and calculating the corresponding power demand, the power allocation is dynamically adapted to the grid peak-shaving capacity, avoiding resource waste or shortage caused by fixed power thresholds. The delay compensation power increment is introduced to compensate for the impact of the start-up delay of the grid peak-shaving unit on the ice-melting efficiency, improve the real-time response capability of the ice-melting process, and solve the prediction deviation problem caused by delay in traditional methods. By constraining the power range fluctuation to be within the capacity of the peak-shaving unit and combining the time distribution characteristics of the total power demand in the start-up stage, a peak-shaving cost parameter that is closer to the actual operation scenario is generated, reducing the grid operation risk and optimizing cost expenditure.

[0049] These and other aspects of the present invention will become more readily apparent from the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 A flow chart of a method for jointly predicting power load and electricity price taking weather factors into consideration provided by the present invention is shown;

[0052] Figure 2 The present invention shows a schematic structural diagram of a power load and electricity price joint prediction system taking weather factors into consideration;

[0053] Figure 3 A schematic structural diagram of a computing device provided by the present invention is shown. DETAILED DESCRIPTION

[0054] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0055] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., and do not represent the order of precedence, nor do they limit "first" and "second" to be different types.

[0056] 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 those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0057] This is due to the urgent need for coordination between ice-melting operations and grid dispatching in power systems under extreme weather conditions, especially during line icing. The existing deep learning prediction method based on the fusion of macro-meteorological indicators and historical load data can reflect the load change trend and electricity price response mechanism to a certain extent. However, since it only relies on statistical relationship modeling, it fails to deeply combine the physical characteristics of the icing development process, such as ice layer deformation, stress distribution and other key factors, resulting in a lack of dynamic adaptability in the prediction of ice-melting timing and power demand. At the same time, there are also deficiencies in considering the coupling relationship between ice-melting power and grid transmission capacity, making it difficult to accurately assess the impact of line carrying capacity reduction on peak-shaving resource allocation and electricity price adjustment. Therefore, the present invention realizes the coordinated prediction of power load and electricity price fluctuations during icing by integrating a joint prediction method of micro-physical processes and grid operation constraints, thereby improving the operational safety and economy of the grid under extreme weather conditions. Figure 1 The present invention provides a flowchart of a method for jointly predicting power load and electricity price considering weather factors, such as Figure 1 As shown, the method includes:

[0058] Step 101: Acquire ice growth data, where the ice growth data includes ice thickness variation on the conductor surface, ambient temperature, and wind speed parameters.

[0059] In this step, ice growth data refers to a monitoring data set that reflects the dynamic process of icing on the transmission line, including the change in ice thickness on the conductor surface, ambient temperature, and wind speed parameters.

[0060] In an embodiment of the present invention, ice thickness monitoring sensors installed on transmission lines collect the change in ice thickness on the conductor surface in real time, while ambient temperature and wind speed parameters are obtained through a meteorological station. Multi-source data fusion technology is used to fuse and calibrate the conductor surface temperature measured by a contact temperature probe with the temperature distribution data collected by an infrared thermal imager to form ice growth data, which includes ice thickness increments updated every minute, ambient temperature and humidity gradients, and three-dimensional wind speed vectors.

[0061] Step 102: Based on the change in ice thickness, analyzing acoustic emission signal characteristics when the ice breaks, and establishing a correlation between ice stress distribution and conductor deformation based on the acoustic emission signal characteristics, so as to predict a transition period when the ice reaches a critical melting state;

[0062] In this step, the acoustic emission signal characteristics refer to the quantitative parameters of the acoustic wave signal generated when the ice layer breaks, including the waveform change speed, the first proportional parameter, and the second proportional parameter. The ice layer stress distribution refers to the spatial distribution state of the mechanical stress inside the ice cover, which is obtained by inverting the spectrum characteristics of the acoustic emission signal. The conductor deformation refers to the physical quantity of the mechanical deformation of the conductor caused by ice cover, including the sag change and the bending curvature. The critical ice melting state refers to the physical state where the ice-covered line reaches the point where the ice melting device must be activated. The transition period refers to the time interval from the start moment to the end moment of the critical ice melting state, including the startup phase, the continuous ice melting phase, and the termination phase.

[0063] In an embodiment of the present invention, when the change in ice thickness exceeds a preset threshold, a piezoelectric acoustic emission sensor arranged on the surface of the conductor is triggered to collect a target acoustic emission signal; a wavelet packet decomposition algorithm is used to extract the waveform change rate, a first proportional parameter, and a second proportional parameter from the acoustic wave signal; a correlation between the internal stress distribution of the ice layer and the conductor deformation is established based on a support vector machine regression model, and combined with the change characteristics of the second proportional parameter, the transition time period from stress accumulation to the critical melting state of the ice layer is predicted.

[0064] Step 103: Calculating the ice melting power requirements for different time periods based on the transition period, and generating peak-shaving cost parameters in combination with the capacity constraints of the peak-shaving units of the power grid. The ice melting power requirements include the minimum starting power and the maintenance power range of the ice melting device.

[0065] In this step, the ice melting power requirement is determined to eliminate the electrical energy consumption required to remove ice, including the minimum starting power and maintenance power range of the ice melting device.

[0066] In an embodiment of the present invention, the transition time period is divided into a startup phase, a continuous ice-melting phase, and a termination phase according to the starting time. In the startup phase, the minimum startup power of the ice-melting device is calculated by the energy conservation equation based on the correlation trend between the conductor deformation and the ice peeling rate. In the continuous ice-melting phase, the thermodynamic dynamic equation is used to solve the maintenance power range based on the real-time changes in the ambient temperature and wind speed parameters. In combination with the maximum available capacity and startup delay time of the grid peak-shaving unit, the ice-melting power demand and the output constraint conditions of the grid peak-shaving unit are constructed to generate a time-varying peak-shaving cost parameter, which includes the cumulative cost coefficient of the delay time in the startup phase and the cost coefficient of the standby capacity occupancy ratio in the continuous phase.

[0067] Step 104: generating a correlation prediction result between power load changes and electricity price fluctuations during an icing period based on the conductor deformation and the peak-shaving cost parameter;

[0068] In this step, the associated prediction result refers to the quantitative output of the joint fluctuation law of load and electricity price.

[0069] In an embodiment of the present invention, based on the deviation between the conductor deformation amount and a preset safety threshold, a material mechanics deformation-power loss conversion model is used to calculate the power attenuation slope of the line transmission power; at the same time, according to the time distribution characteristics of the peak-shaving cost parameters, a time period weight coefficient of the electricity price floating benchmark value is generated through the cost transmission function; a bidirectional coupling control mechanism is established, and the power attenuation slope and the time period weight coefficient are processed according to the rule to generate a correlation prediction result between the power load change and the electricity price fluctuation during the icing period.

[0070] The embodiment of the present invention realizes accurate prediction of the critical state of the ice layer by real-time monitoring of the change in ice thickness on the conductor surface, ambient temperature and wind speed parameters, and analyzing the correlation between ice stress distribution and conductor deformation in combination with acoustic emission signal characteristics. This breaks through the fuzzy judgment of the traditional empirical model on the evolution law of ice cover, solves the problem of prediction lag caused by data missing, and optimizes the economic allocation of ice melting resources and improves the stability and economy of power grid operation by dynamically generating peak-shaving cost parameters and load-electricity price correlation prediction results.

[0071] The present invention provides a specific embodiment, step 102, analyzing the acoustic emission signal characteristics when the ice layer breaks based on the change in ice layer thickness, and establishing a correlation between the ice layer stress distribution and the conductor deformation based on the acoustic emission signal characteristics to predict the transition time period when the ice layer reaches a critical state of melting. The specific steps include:

[0072] Step 201: When the change in ice thickness reaches a preset threshold, a target acoustic emission signal from the surface of the ice-covered conductor is collected;

[0073] In this step, the preset threshold refers to the critical ice thickness threshold that triggers acoustic emission monitoring. It is calculated based on the conductor diameter and ice density. The ice-covered conductor surface specifically refers to the outer surface monitoring area of ​​the ice-covered section of the transmission line, where a waterproof piezoelectric sensor array is installed. The target acoustic emission signal is the characteristic acoustic wave signal generated by ice breaking, with a frequency range of 20-100kHz and a signal-to-noise ratio greater than 35dB.

[0074] In an embodiment of the present invention, when the change in ice thickness reaches a preset threshold (e.g., ≥3.5 mm / h), a broadband piezoelectric sensor array arranged on the surface of the ice-covered conductor is triggered to collect target acoustic emission signals at a sampling frequency of 200 kHz. The signal preprocessing module eliminates environmental noise interference, retains the characteristic ice fracture band in the frequency range of 20-100 kHz, and forms a three-dimensional signal matrix of time-amplitude-frequency.

[0075] Step 202: extracting acoustic emission signal features from the acoustic emission signal, where the acoustic emission signal features include a waveform change rate, a first proportional parameter, and a second proportional parameter;

[0076] In this step, the waveform change rate reflects the stress release rate (unit: V / μs). The first proportional parameter represents the degree of energy dissipation (unitless percentage). The second proportional parameter indicates the energy concentration (dimensionless ratio).

[0077] In an embodiment of the present invention, a wavelet packet energy spectrum analysis method is used to process a target acoustic emission signal, specifically including: calculating the waveform change rate by calculating the voltage change in the 10%-90% amplitude range of the signal rising edge and dividing it by the time differential (unit: V / μs); extracting the maximum amplitude attenuation in the main frequency band (80±5kHz) and dividing it by the initial amplitude peak (maximum amplitude attenuation / initial amplitude peak×100%) to calculate a first proportional parameter; and taking the maximum amplitude absolute value during the signal duration and dividing it by the moving average amplitude (maximum amplitude absolute value / moving average amplitude) to calculate a second proportional parameter.

[0078] Step 203: Establishing a correlation between stress distribution inside the ice layer and wire deformation based on the waveform change rate and a first proportional parameter, wherein when the waveform change rate exceeds a first set value, determining a lateral expansion range of the stress concentration region in the ice layer, and when the first proportional parameter exceeds a second set value, determining a correlation trend between the wire deformation and the ice peeling rate;

[0079] In this step, the first set value is the stress concentration criterion (150V / μs), calibrated through material fatigue testing. The ice stress concentration area refers to the local region within the ice cover where the maximum tensile stress is ≥15MPa. The lateral extension range refers to the width of the ice stress concentration area (in meters), inferred from acoustic diffraction characteristics. The second set value is the ice detachment criterion (50%), determined based on the ice-conductor adhesion model. The ice detachment rate refers to the area of ​​ice detached from the conductor per unit time (mm² / s). The correlation trend shows a positive correlation between conductor deformation and ice detachment rate (slope k3 = 0.28mm·s / mm²).

[0080] In the embodiment of the present invention, when the waveform change speed exceeds a first set value (e.g., 150V / μs), the lateral expansion range of the ice stress concentration area is calculated using an exponential function relationship. Specifically, the lateral expansion range is equal to the constant k1 multiplied by the waveform change speed of the natural exponential function (i.e., lateral expansion range = k1×e 波形变化速度 , where k1 is the conductor diameter correction coefficient (unit: meter); the peeling rate is associated with the deformation: when the first proportional parameter exceeds 50% (the second set value), the ice peeling rate is determined by a linear proportional relationship, specifically: ice peeling rate = k2 × first proportional parameter, and the correlation trend between the conductor deformation and the ice peeling rate is established, specifically: conductor deformation = k3 × ice peeling rate.

[0081] Step 204: Based on the lateral expansion range and the correlation trend, combined with the variation characteristics of the second proportional parameter, predict a transition period in which the ice layer reaches a critical melting state. The transition period starts at the moment when the crack growth rate inside the ice layer first enters a linear growth phase, and ends at the moment when the line sag exceeds a preset sag threshold.

[0082] In this step, the variation characteristic refers to the exponential decay of the second proportional parameter. The crack growth rate refers to the speed of the crack tip moving within the ice layer (in mm / s). The linear growth phase refers to the period of acceleration from 5 mm / s to 20 mm / s, during which the growth rate remains constant. The height difference between the lowest point of the line sag guideline and the suspension point (in meters) is used. The preset sag threshold is the maximum allowable sag value of the guideline, which is the standard value multiplied by 120%.

[0083] In an embodiment of the present invention, based on the lateral expansion range and the associated trend, combined with the change characteristics of the second proportional parameter (such as an exponential decay coefficient ≥ 0.8): starting time: when the crack growth rate is ≥ 5 mm / s for the first time (i.e., entering the linear growth stage), marked as t1; ending time: when the laser rangefinder detects that the line sag is greater than the safety threshold (standard sag × 120%), marked as t2; output the transition time period [t1, t2].

[0084] The embodiments of the present invention solve the problem of low accuracy in identifying the critical state of the ice layer in traditional technologies. By quantifying the correlation between the crack propagation rate and the sag threshold, accurate determination of the start and end times of the transition time period is achieved, providing a reliable basis for the formulation of subsequent ice melting strategies.

[0085] The present invention provides a specific embodiment, step 103, calculating the ice melting power requirements for different time periods based on the transition time period, and generating peak-shaving cost parameters in combination with the capacity constraints of the peak-shaving units of the power grid. The ice melting power requirements include the minimum starting power and the maintenance power range of the ice melting device. The specific steps include:

[0086] Step 301: Divide the transition period into a startup phase, a continuous ice-melting phase, and a termination phase, and use the start time of the transition period as a startup time reference point for the ice-melting device;

[0087] In this step, the startup phase refers to the first 15 minutes of ice-melting operation, characterized by accelerated crack propagation and power ramp-up. The continuous ice-melting phase is the steady-state ice-melting period from the end of the startup phase to 5 minutes before termination, during which power fluctuations are regulated by environmental parameters. The termination phase is the 5 minutes before the end of ice-melting, during which residual ice is detached. The startup time reference point is the start time t1 of the transition period, which serves as the absolute timestamp for the synchronized startup of all units.

[0088] In an embodiment of the present invention, the transition period, such as 2:25 PM to 3:40 PM, is divided into the following: a startup phase (the first 15 minutes): from the start time t1 to t1+15 minutes; a continuous ice-melting phase (the middle 55 minutes): from t1+15 minutes to t2-5 minutes; and a termination phase (the last 5 minutes): from t2-5 minutes to t2. The start time t1 is used as the unified startup time reference point for the ice-melting device, and the clock signals of all units are aligned using a time synchronizer.

[0089] Step 302: Calculating the minimum starting power of the ice melting device during the starting phase based on the correlation trend between the conductor deformation and the ice peeling rate;

[0090] In this step, the ice peeling rate refers to the area of ​​ice detached from the conductor per unit time (mm ² / s), the first proportional parameter is calculated. The minimum starting power value refers to the energy threshold that causes the initial crack propagation range of the ice layer to reach the lateral extension range of the stress concentration area. The correlation trend guides the proportional relationship between the linear variable and the ice peeling rate (formula: wire deformation = k × ice peeling rate, k = 0.28mm·s / mm ² )

[0091] In the embodiment of the present invention, based on the correlation trend between the conductor deformation and the ice peeling rate, the minimum starting power is calculated by the energy conversion model: the ice peeling area per unit time is calculated according to the ice peeling rate: ice peeling area = π × conductor diameter × ice peeling rate; according to the thermodynamic formula: minimum starting power = ice density × phase change latent heat × ice peeling area; for example, the density is 917kg / m ³ ×334kJ / kg×0.15m ² / s≈4.6MW.

[0092] Step 303: determining a maintenance power range of the ice melting device in the continuous ice melting stage according to the real-time changes in the ambient temperature and wind speed parameters;

[0093] In the embodiment of the present invention, the ambient temperature and wind speed parameters are obtained in real time, and the power range is maintained by updating the heat balance equation. Specifically, the upper limit of the power range is maintained: anti-regeneration power = conductor surface area × convection heat transfer coefficient × (freezing point temperature - ambient temperature), where convection heat transfer coefficient = 6.2 × wind speed 0.78 For example, the conductor surface area is 2.5m ² , wind speed 12m / s, i.e. upper limit = anti-regeneration power = 2.5×35.1×[0-(-8)]≈702W); lower limit of the power range: critical control power = (ice density × crack growth rate ²× kinetic energy coefficient per unit area) ÷ thermal efficiency conversion rate, where the crack kinetic energy is calculated from the linear growth stage rate; for example: density 917kg / m ³ , crack rate 5mm / s, kinetic energy coefficient 0.12, thermal efficiency 0.85, that is, lower limit value = critical control power = [917×(0.005)²×0.12] / 0.85≈0.16kW.

[0094] Step 304: Based on the maximum available capacity and startup delay time of the grid peak-shaving unit, construct an ice-melting power requirement and output constraints of the grid peak-shaving unit, wherein the ice-melting power requirement includes a minimum startup power and a maintenance power range of the ice-melting device;

[0095] In this step, the maximum available capacity refers to the maximum instantaneous output (in MW) that the peak-shaving unit can provide, determined by the unit's nameplate parameters. The startup delay time refers to the time (in minutes) required for the peak-shaving unit to reach rated output after receiving a command, with an average measured value of 8 minutes. Output constraints refer to the boundary conditions that limit the power demand for ice melting, including response lag constraints during the startup phase and fluctuation bandwidth constraints during the continuous ice melting phase.

[0096] In an embodiment of the present invention, output constraints are established based on the physical limitations of the grid peak-shaving units, including the maximum available capacity and the start-up delay time. Specifically, in the startup phase, the ice-melting power demand is ≤ the maximum available capacity of the grid peak-shaving unit × the response factor, where the response factor = min(1, operating time / start-up delay time); in the sustained phase, the fluctuation amplitude of the power range is maintained ≤ the response bandwidth value of the standby capacity of the grid peak-shaving unit, where the standby capacity response bandwidth value = standby capacity / 60s.

[0097] Step 305: Generate a time-varying peak-shaving cost parameter based on the minimum starting power, the maintenance power range, the output constraint, and the capacity constraint of the peak-shaving unit of the power grid;

[0098] In an embodiment of the present invention, a minimum starting power reference value is calculated based on the lateral expansion range of the ice stress concentration area, and a delay compensation power increment is generated in combination with the startup delay time of the grid peak-shaving unit. A matching mechanism is established between the ice-melting power demand and the output constraint conditions. Based on the time distribution characteristics of the total power demand in the startup phase and the fluctuation constraint conditions for maintaining the power range in the matching mechanism, a peak-shaving cost parameter that varies with time is generated.

[0099] The embodiments of the present invention solve the problem of resource waste or shortage caused by traditional fixed power thresholds. By modeling power demand by time period, dynamic adaptation of ice melting power and grid peak regulation capacity is achieved, thereby reducing grid operation risks and improving ice melting efficiency.

[0100] The present invention provides a specific embodiment, step 305, generating a time-varying peak-shaving cost parameter based on the minimum starting power, the maintenance power range, the output constraint, and the capacity constraint of the grid peak-shaving unit, specifically comprising the following steps:

[0101] Step 311: Calculate the minimum starting power reference value based on the lateral expansion range of the ice stress concentration area, and generate a delay compensation power increment in combination with the start-up delay time of the peak-shaving unit of the power grid;

[0102] In this step, the baseline value refers to the theoretical minimum starting power (in MW) calculated based on the lateral extension of the ice stress concentration area, reflecting the base energy required to cover the stress area. The delay compensation power increment refers to the additional power (in MW) added to offset the unit's response lag, used to compensate for the ice melt energy shortfall during the delay period.

[0103] In an embodiment of the present invention, based on the lateral expansion range of the ice layer stress concentration area, the energy density formula is used to calculate the reference value of the minimum starting power. The reference value = stress area area × ice melting energy consumption per unit area, where the stress area = π × conductor radius × lateral expansion range, and the unit energy consumption is 4.5 kJ / cm². In combination with the start-up delay time of the grid peak-shaving unit, a lag compensation algorithm is used to calculate the delay compensation power increment. The delay compensation power increment = reference value × (start-up delay time / standard response time), where the standard response time is set to 10 minutes.

[0104] Step 312: Establishing a matching mechanism between the ice melting power demand and the output constraint, wherein the matching mechanism includes taking the sum of the baseline value and the delay compensation power increment as the total power demand during the startup phase, and constraining the fluctuation amplitude of the maintenance power range to be within the capacity constraint of the grid peaking unit;

[0105] In this step, the matching mechanism refers to the dynamic adaptation rules for the ice-melting power demand and the unit's capabilities. This includes power synthesis during the startup phase (baseline value + delay compensation power increment) and fluctuation constraints during the continuous ice-melting phase (real-time power fluctuation ≤ unit regulation bandwidth). The total power demand during the startup phase refers to the total power actually required during the startup phase (in MW), consisting of the minimum startup power baseline value + delay compensation power increment. Fluctuation amplitude constraints are the boundary conditions that limit the range of real-time power fluctuations.

[0106] In an embodiment of the present invention, a two-dimensional matching mechanism is established, including: power synthesis in the startup phase: the baseline value is added to the delay compensation power increment to obtain the total power demand in the startup phase; fluctuation constraint in the sustained phase: real-time monitoring of the fluctuation amplitude of the power range is maintained, and the bandwidth limiter constraint condition is set by the following: |real-time power-mean|≤reserve capacity response bandwidth×regulation margin, with the regulation margin set to 0.7, to ensure that the fluctuation amplitude is always within the capacity constraint condition of the grid peak-shaving unit (reserve capacity ≥ 20MW).

[0107] Step 313: Generate a time-varying peak-shaving cost parameter based on the time distribution characteristics of the total power demand during the startup phase and the fluctuation constraint of the power maintenance range;

[0108] In this step, the time distribution characteristic refers to the change pattern of the power demand over time during the startup phase, which is expressed as a linear climbing curve from 0 to the total required power.

[0109] In an embodiment of the present invention, based on the time distribution characteristics of the total power demand in the startup phase, such as the linear increase in power demand in the first 5 minutes, a time cost accumulation model is adopted: startup phase cost = basic cost × (1 + time accumulation coefficient), where the time accumulation coefficient = operating time / startup delay time; at the same time, according to the fluctuation constraint condition of maintaining the power range (fluctuation amplitude ≤ 1.5MW), through the backup resource occupation model: continuous phase cost = unit backup cost × (actual fluctuation amplitude / maximum allowable fluctuation amplitude), combined with the startup phase cost and the continuous phase cost, a peak-shaving cost parameter that changes with time is output, such as the cost increases by 0.02 yuan / kWh per minute in the startup phase.

[0110] The embodiments of the present invention solve the problem of mismatch between power demand and peak-shaving capability caused by delayed response in traditional methods, improve the real-time response capability of the ice melting process, and ensure that the generation of peak-shaving cost parameters is more in line with actual operating scenarios.

[0111] The present invention provides a specific embodiment, step 104, generating a correlation prediction result between power load changes and electricity price fluctuations during an icing period based on the conductor deformation and the peak-shaving cost parameter, specifically comprising the following steps:

[0112] Step 401: Calculating the power attenuation slope of the line transmission power based on the degree of deviation between the conductor deformation and a preset sag threshold;

[0113] In this step, the sag threshold guideline specifies the maximum allowable sag (standard sag value x 120%), measured in meters, based on the conductor model and span. The deviation guideline specifies the percentage by which the measured sag exceeds the preset sag threshold. The line transmission power guideline specifies the maximum transmittable active power (in MW), with a baseline value provided by the grid dispatching system. The power decay slope, which is the percentage decrease in transmission power per unit time (% / min), reflects the rate of power loss due to deformation.

[0114] In an embodiment of the present invention, the deformation of the conductor is processed using a deformation-power conversion model: the degree of deviation of the conductor deformation from a preset safety threshold is calculated: deviation = (measured sag value - preset sag threshold) / preset sag threshold × 100%; the power attenuation slope is derived based on a material mechanics formula: power attenuation slope = reference power loss rate × (1 + deviation × deformation sensitivity coefficient). For example, when the deviation is 15%, the power attenuation slope = 2.5% / min × (1 + 0.15 × 0.8) = 2.8% / min.

[0115] Step 402: Generate a time period weight coefficient for the electricity price floating benchmark value based on the time distribution characteristics of the peak-shaving cost parameter during the continuous ice-melting phase;

[0116] In this step, the temporal distribution characteristics refer to the changing patterns of peak-shaving cost parameters during the continuous thawing phase, including fluctuation cycles, extreme points, and gradients. The electricity price fluctuation benchmark refers to the median price (yuan / kWh) of day-ahead transactions in the power market, which serves as the basis for fluctuation calculations. The time period weight coefficient is a normalized parameter (0–1) that quantifies the cost fluctuation range for each time period and is calculated by normalizing the cost range.

[0117] In an embodiment of the present invention, the time distribution characteristics of the peak-shaving cost parameters in the continuous ice-melting stage are extracted, specifically including: 1. constructing a time-cost distribution curve and extracting the fluctuation period and amplitude characteristics; 2. calculating the time period weight coefficient by normalizing the fluctuation period and amplitude characteristics, and the time period weight coefficient = (real-time cost - minimum cost) / (maximum cost - minimum cost). For example, when the cost range is [0.18, 0.25] yuan / kWh, 0.22 yuan corresponds to a weight coefficient of 0.57.

[0118] Step 403: establishing a bidirectional coupling rule, processing the power attenuation slope and the time period weight coefficient according to the bidirectional coupling rule, and generating a correlation prediction result between the power load change and the electricity price fluctuation during the icing period;

[0119] In this step, the bidirectional coupling rule refers to the interaction mechanism between load and electricity price. Specifically: on the physical side: if the power attenuation slope exceeds the limit, the electricity price compensation weight will be increased; on the economic side: if the time period weight coefficient of the electricity price floating benchmark value exceeds the limit, the power attenuation speed will be suppressed.

[0120] In an embodiment of the present invention, a bidirectional coupling rule is established. For example, when the power attenuation slope is greater than a preset deformation critical value, the compensation increase of the time period weight coefficient is triggered: the time period weight coefficient correction value = the time period weight coefficient × (1 + the slope excess value × 0.2); when the time period weight coefficient is greater than the preset cost critical value, the power attenuation slope growth is limited: the power attenuation slope constraint value = the benchmark power attenuation slope / (the time period weight coefficient excess value × 1.5); based on the time period weight coefficient correction value and the power attenuation slope constraint value, a joint probability model is used to generate a correlation prediction result between the power load change and the electricity price fluctuation during the icing period.

[0121] The embodiments of the present invention solve the problem that traditional single-dimensional prediction cannot balance power load and electricity price fluctuations. Through bidirectional coupling rules, the coordinated optimization of load adjustment and electricity price response is achieved, thereby improving the economy and stability of the power grid supply and demand balance.

[0122] The present invention provides a specific embodiment, step 403, establishing a bidirectional coupling rule, processing the power attenuation slope and the time period weight coefficient according to the bidirectional coupling rule, and generating a correlation prediction result between power load changes and electricity price fluctuations during icing, specifically comprising the following steps:

[0123] Step 411: Establish a bidirectional coupling rule. When the power attenuation slope exceeds a preset deformation threshold, perform a compensatory incremental operation on the time period weight coefficient according to the bidirectional coupling rule. When the rate of change of the conductor deformation drops below a preset safety threshold, terminate the compensatory incremental operation and generate a corrected value of the time period weight coefficient.

[0124] In this step, the preset deformation threshold serves as the safety threshold for power attenuation, based on the material fatigue limit. The compensatory incremental operation involves increasing the electricity price weight when the slope exceeds the limit. The preset safety threshold serves as the upper limit for the deformation rate, derived from the sag change monitoring standard. The time period weight coefficient correction value refers to the normalized cost weight (0-1.2) after the compensation operation.

[0125] In an embodiment of the present invention, when the power attenuation slope exceeds a preset deformation threshold (e.g., 4% / min), the compensation mechanism in the bidirectional coupling rule is triggered: compensation calculation: time period weight coefficient correction value = time period weight coefficient × (1 + (power attenuation slope - deformation threshold) × compensation factor) (the compensation factor is 0.2); termination condition: real-time monitoring of the rate of change of the conductor deformation (e.g., sag change / time). If the rate is ≤ a preset safety threshold, the compensation operation is terminated immediately. For example, when the power attenuation slope is 5.2%, the generated time period weight coefficient correction value = original value × 1.24).

[0126] Step 412: When the time period weight coefficient exceeds a preset cost threshold, a constraint suppression operation is performed on the power attenuation slope according to the bidirectional coupling rule. When the time distribution characteristics of the peak shaving cost parameter return to a preset reference fluctuation band, the constraint suppression operation is terminated and a power attenuation slope constraint value is generated.

[0127] In this step, the preset cost threshold refers to the price weight risk threshold, exceeding which triggers the slope constraint. Constraint suppression refers to the calculation of limiting slope growth when the weight exceeds the limit. The preset baseline fluctuation band refers to the reasonable range of peak-shaving costs. The power reduction slope constraint value refers to the power loss rate (% / min) after the suppression operation.

[0128] In this embodiment of the present invention, when the time period weight coefficient exceeds the preset cost threshold, a constraint mechanism is activated: Constraint calculation: Power decay slope constraint value = Power decay slope / (1 + (time period weight coefficient - cost threshold) × suppression coefficient), where the suppression coefficient is 1.5. Termination condition: Compare the time distribution curve of the peak-shaving cost parameter with a preset benchmark fluctuation band (with cost values ​​between [0.18, 0.25] yuan / kWh and a stable fluctuation period). If the distribution curve returns to this fluctuation band, the constraint is lifted, and the power decay slope constraint value is generated. For example, when the time period weight coefficient is 0.85, the power decay slope constraint value = power decay slope / 1.075.

[0129] Step 413: Generate the convergence boundary coordinates of the load reduction interval and the phase offset range of the electricity price increase interval based on the time period weight coefficient correction value and the power attenuation slope constraint value, so as to generate a correlation prediction result between the power load change and the electricity price fluctuation during the icing period;

[0130] In this step, the convergence boundary coordinates refer to the load fluctuation range [P min ,P max ], by P min =P max ×(1-boundary contraction ratio); the phase offset range refers to the lag time interval [t1, t2] of the electricity price increase, and its length = time delay.

[0131] In an embodiment of the present invention, the ratio of the load recovery rate corresponding to the power attenuation slope constraint value to the rate of change of the conductor deformation is calculated and converted into the convergence boundary coordinates of the load reduction interval; based on the ratio of the time period weight coefficient correction value to the reference floating coefficient, combined with the start-up delay time of the grid peak-shaving unit, the time delay is calculated and converted into the phase offset range of the electricity price increase interval; based on the convergence boundary coordinates and the phase offset range, a correlation prediction result of the power load change and electricity price fluctuation during the icing period is generated.

[0132] The embodiments of the present invention solve the problem that traditional static rules cannot adapt to complex icing scenarios. By adaptively adjusting the correlation between load recovery rate and electricity price fluctuations, the spatiotemporal matching accuracy and control flexibility of the prediction results are improved.

[0133] The present invention provides a specific embodiment, step 413, generating the convergence boundary coordinates of the load reduction interval and the phase offset range of the electricity price increase interval based on the time period weight coefficient correction value and the power attenuation slope constraint value, so as to generate a correlation prediction result between the power load change and the electricity price fluctuation during the icing period, specifically including the following steps:

[0134] Step 421: Calculate the ratio of the load recovery rate corresponding to the power attenuation slope constraint value to the rate of change of the conductor deformation, use the ratio as the boundary contraction ratio, and convert the boundary contraction ratio into the convergence boundary coordinates of the load reduction interval;

[0135] In this step, the load recovery rate (MW / min) indicates the rate at which the transmitted power recovers after linear deformation is alleviated. This rate is calculated by fitting the historical deformation-power recovery curve. The boundary contraction ratio (dimensionless) represents the degree of contraction within the load reduction interval, reflecting the power recovery capability per unit deformation improvement.

[0136] In the embodiment of the present invention, the load recovery rate corresponding to the power attenuation slope constraint value is obtained by the deformation recovery monitoring system, and the rate of change of the conductor deformation is monitored at the same time; the boundary contraction ratio is calculated, and the boundary contraction ratio = load recovery rate ÷ conductor deformation change rate, and the ratio is input into the boundary transformation model, that is, the convergence boundary coordinate = [P max ×(1-boundary shrinkage ratio×0.01),P max ].

[0137] Step 422: Calculate the time delay based on the ratio of the time period weight coefficient correction value to the base floating coefficient and the start-up delay time of the peak-shaving unit of the power grid, and convert the time delay into a phase offset range of the electricity price increase interval;

[0138] In this step, the base fluctuation coefficient refers to the upper limit of the normal fluctuation of the peak-shaving cost parameter (unit: yuan / kWh), which is 90% of the maximum cost during the continuous ice-melting phase. The time delay refers to the length of time (unit: minutes) that the electricity price response lags behind load changes.

[0139] In this embodiment of the present invention, a time period weight coefficient correction value (e.g., 0.86) and a base floating coefficient are extracted, where the upper limit of normal cost fluctuation is 0.25 yuan / kWh. The ratio of the time period weight coefficient correction value to the base floating coefficient is calculated, where the ratio = the time period weight coefficient correction value ÷ the base floating coefficient, e.g., 0.86 / 0.25 = 3.44. Combined with the start-up delay time of the grid peak-shaving unit (8 minutes), the time delay is calculated as the proportional factor × the start-up delay time, e.g., 3.44 × 8 ≈ 27.5 minutes. The time delay is mapped to a phase offset range of [t, t+27.5 minutes] (t is the start time of load reduction).

[0140] Step 423: using the convergence boundary coordinates to correct the time reference point of the phase offset range, and generating a correlation prediction result between the power load change and the electricity price fluctuation during the icing period;

[0141] In this step, the time reference point refers to the absolute timestamp of the start time of the load reduction interval (such as 14:30:00), which serves as the synchronization reference for the electricity price phase offset.

[0142] In an embodiment of the present invention, the starting time of the convergence boundary coordinate (e.g., 14:30) is used as the time reference point, and the corrected phase offset range is [14:30, 14:57.5]. The load value range boundary (e.g., [78MW, 92MW]) is aligned with the electricity price time offset interval through a spatiotemporal association algorithm to generate a correlation prediction result of power load changes and electricity price fluctuations during the icing period containing dual-axis coordinates, wherein the horizontal axis time is: 14:30-14:57.5, the left vertical axis load is: 78-92MW, and the right vertical axis electricity price is: electricity price floating reference value × time period weight coefficient.

[0143] The embodiments of the present invention solve the problem of misalignment of the time and space reference points of load and electricity price in traditional prediction models. By dynamically correcting the time reference point and the boundary contraction ratio, high-precision correlation prediction of power load and electricity price fluctuations during icing period is achieved, providing more reliable decision support for power grid scheduling.

[0144] Figure 2 The present invention provides a structural diagram of a power load and electricity price joint prediction system considering weather factors, such as Figure 2 As shown, the system includes:

[0145] An acquisition module 21 is configured to acquire ice growth data, wherein the ice growth data includes ice thickness variation on the conductor surface, ambient temperature, and wind speed parameters;

[0146] An analysis module 22 is configured to analyze acoustic emission signal characteristics when the ice breaks based on the change in ice thickness, and establish a correlation between ice stress distribution and conductor deformation based on the acoustic emission signal characteristics to predict a transition period when the ice reaches a critical melting state;

[0147] A calculation module 23 is configured to calculate the ice melting power requirements for different time periods according to the transition period, and generate peak-shaving cost parameters in combination with the capacity constraints of the peak-shaving units of the power grid, wherein the ice melting power requirements include the minimum starting power and the maintenance power range of the ice melting device;

[0148] The generating module 24 is configured to generate a correlation prediction result between the power load change and the electricity price fluctuation during the icing period based on the conductor deformation amount and the peak-shaving cost parameter.

[0149] Figure 2 The power load and electricity price joint forecasting system considering weather factors can be executed Figure 1 The implementation principle and technical effects of the weather-based combined power load and electricity price forecasting method described in the illustrated embodiment are not further elaborated. The specific manner in which each module and unit performs operations in the weather-based combined power load and electricity price forecasting system described in the above embodiment has been described in detail in the relevant embodiments of the method and will not be elaborated on here.

[0150] In one possible design, Figure 2 The embodiment shown is a power load and electricity price joint prediction system considering weather factors that can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0151] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0152] The processing component 32 is used for the above Figure 1 The embodiment provides a method for jointly predicting power load and electricity price taking weather factors into consideration.

[0153] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0154] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0155] Of course, a computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0156] The input / output interface provides an interface between the processing component and the peripheral interface module, which can be an output device, an input device, etc.

[0157] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0158] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0159] The embodiment of the present invention further provides a computer storage medium storing a computer program, which can achieve the above-mentioned Figure 1 The illustrated embodiment provides a method for jointly predicting power load and electricity price taking weather factors into consideration.

[0160] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0161] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0162] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0163] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for jointly predicting power load and electricity price considering weather factors, characterized in that: include: Acquiring ice growth data, wherein the ice growth data includes a change in ice thickness on the conductor surface, ambient temperature, and wind speed parameters; Based on the change in ice thickness, analyzing the acoustic emission signal characteristics when the ice breaks, and establishing a correlation between ice stress distribution and conductor deformation based on the acoustic emission signal characteristics to predict the transition time period when the ice reaches a critical state of melting; According to the transition time period, calculating the ice melting power demand in different time periods and generating peak-shaving cost parameters in combination with the capacity constraints of the peak-shaving units of the power grid, wherein the ice melting power demand includes the minimum starting power and the maintenance power range of the ice melting device; generating, based on the conductor deformation amount and the peak-shaving cost parameter, a correlation prediction result of the power load change and the electricity price fluctuation during the icing period; Based on the change in ice thickness, characteristics of acoustic emission signals when the ice breaks are analyzed. Based on the characteristics of the acoustic emission signals, a correlation between ice stress distribution and conductor deformation is established to predict a transition period when the ice reaches a critical melting state, including: When the change in ice thickness reaches a preset threshold, a target acoustic emission signal is collected from the surface of the ice-covered conductor; acoustic emission signal features are extracted from the acoustic emission signal, wherein the acoustic emission signal features include a waveform change rate, a first proportional parameter, and a second proportional parameter; based on the waveform change rate and the first proportional parameter, a correlation relationship between the stress distribution inside the ice layer and the conductor deformation is established, wherein when the waveform change rate exceeds a first set value, the lateral expansion range of the ice stress concentration area is determined, and when the first proportional parameter exceeds a second set value, the correlation trend between the conductor deformation and the ice peeling rate is determined; based on the lateral expansion range and the correlation trend, combined with the change characteristics of the second proportional parameter, a transition time period when the ice layer reaches a critical state of ice melting is predicted, wherein the starting time of the transition time period is the time when the crack propagation rate inside the ice layer first enters a linear growth stage, and the ending time is the time when the line sag exceeds a preset sag threshold; Based on the conductor deformation amount and the peak-shaving cost parameter, a correlation prediction result of the power load change and the electricity price fluctuation during the icing period is generated, including: Based on the degree of deviation between the conductor deformation and the preset sag threshold, the power attenuation slope of the line transmission power is calculated; based on the time distribution characteristics of the peak-shaving cost parameters in the continuous ice melting stage, the time period weight coefficient of the electricity price floating benchmark value is generated; a bidirectional coupling rule is established, and the power attenuation slope and the time period weight coefficient are processed according to the bidirectional coupling rule to generate a correlation prediction result between the power load change and the electricity price fluctuation during the icing period.

2. The method according to claim 1, characterized in that Based on the transition period, the ice melting power requirements for different periods are calculated, and the peak-shaving cost parameters are generated in combination with the capacity constraints of the peak-shaving units of the power grid. The ice melting power requirements include the minimum starting power and the maintenance power range of the ice melting device, including: Divide the transition period into a startup phase, a continuous ice melting phase, and a termination phase, and use the start time of the transition period as a startup time reference point for the ice melting device; Calculating the minimum starting power of the ice melting device during the starting phase according to the correlation trend between the conductor deformation and the ice peeling rate; Determining a maintenance power range of the ice melting device during the continuous ice melting stage according to real-time changes in the ambient temperature and wind speed parameters; Based on the maximum available capacity and startup delay time of the grid peak-shaving unit, the ice-melting power demand and the output constraints of the grid peak-shaving unit are established. The ice-melting power demand includes the minimum startup power and maintenance power range of the ice-melting device. According to the minimum starting power, the maintenance power range, the output constraint condition and the capacity limitation condition of the peak-shaving unit of the power grid, a peak-shaving cost parameter that changes with time is generated.

3. The method according to claim 2, characterized in that According to the minimum starting power, the maintenance power range, the output constraint condition, and the capacity constraint condition of the grid peak-shaving unit, a time-varying peak-shaving cost parameter is generated, including: Calculating a reference value of the minimum starting power based on the lateral expansion range of the ice stress concentration area, and generating a delay compensation power increment based on the start-up delay time of the peak-shaving unit of the power grid; Establishing a matching mechanism between the ice melting power demand and the output constraint, the matching mechanism including taking the sum of the baseline value and the delay compensation power increment as the total power demand during the startup phase, and constraining the fluctuation amplitude of the maintenance power range to be within the capacity constraint of the grid peaking unit; A peak-shaving cost parameter that varies with time is generated according to the time distribution characteristics of the total power demand in the startup phase and the fluctuation constraint condition of the maintenance power range.

4. The method according to claim 1, wherein A bidirectional coupling rule is established, and the power attenuation slope and the time period weight coefficient are processed according to the bidirectional coupling rule to generate a correlation prediction result between the power load change and the electricity price fluctuation during the icing period, including: Establishing a bidirectional coupling rule, when the power attenuation slope exceeds a preset deformation critical value, performing a compensatory incremental operation on the time period weight coefficient according to the bidirectional coupling rule, and terminating the compensatory incremental operation when the rate of change of the conductor deformation amount drops below a preset safety threshold, and generating a corrected value of the time period weight coefficient; When the time period weight coefficient exceeds a preset cost critical value, a constraint suppression operation is performed on the power attenuation slope according to the bidirectional coupling rule. When the time distribution characteristics of the peak-shaving cost parameter return to a preset reference fluctuation band, the constraint suppression operation is terminated and a power attenuation slope constraint value is generated. According to the time period weight coefficient correction value and the power attenuation slope constraint value, the convergence boundary coordinates of the load decrease interval and the phase offset range of the electricity price increase interval are generated to generate the correlation prediction results of the power load change and electricity price fluctuation during the icing period.

5. The method according to claim 4, characterized in that Based on the time period weight coefficient correction value and the power attenuation slope constraint value, the convergence boundary coordinates of the load reduction interval and the phase offset range of the electricity price increase interval are generated to generate a correlation prediction result between the power load change and the electricity price fluctuation during the icing period, including: Calculating a ratio of a load recovery rate corresponding to the power attenuation slope constraint value to a rate of change of the conductor deformation, using the ratio as a boundary contraction ratio, and converting the boundary contraction ratio into convergence boundary coordinates of a load reduction interval; According to the ratio of the time period weight coefficient correction value to the base floating coefficient, combined with the start-up delay time of the peak-shaving unit of the power grid, the time delay amount is calculated, and the time delay amount is converted into a phase offset range of the electricity price increase interval; The time reference point of the phase offset range is corrected by using the convergence boundary coordinates to generate a correlation prediction result between the power load change and the electricity price fluctuation during the icing period.

6. A power load and electricity price joint prediction system considering weather factors, characterized in that: include: An acquisition module is used to acquire ice growth data, wherein the ice growth data includes a change in ice thickness on the conductor surface, ambient temperature, and wind speed parameters; an analysis module for analyzing acoustic emission signal characteristics when the ice layer breaks based on the change in ice layer thickness, and establishing a correlation between ice layer stress distribution and conductor deformation based on the acoustic emission signal characteristics to predict a transition time period when the ice layer reaches a critical melting state; a calculation module, configured to calculate, based on the transition time period, ice melting power requirements in different time periods, and generate peak-shaving cost parameters in combination with capacity constraints of peak-shaving units of the power grid, wherein the ice melting power requirements include a minimum starting power and a maintenance power range of the ice melting device; A generating module, configured to generate a correlation prediction result between the power load change and the electricity price fluctuation during the icing period based on the conductor deformation amount and the peak regulation cost parameter; Based on the change in ice thickness, characteristics of acoustic emission signals when the ice breaks are analyzed. Based on the characteristics of the acoustic emission signals, a correlation between ice stress distribution and conductor deformation is established to predict a transition period when the ice reaches a critical melting state, including: When the change in ice thickness reaches a preset threshold, a target acoustic emission signal is collected from the surface of the ice-covered conductor; acoustic emission signal features are extracted from the acoustic emission signal, wherein the acoustic emission signal features include a waveform change rate, a first proportional parameter, and a second proportional parameter; based on the waveform change rate and the first proportional parameter, a correlation relationship between the stress distribution inside the ice layer and the conductor deformation is established, wherein when the waveform change rate exceeds a first set value, the lateral expansion range of the ice stress concentration area is determined, and when the first proportional parameter exceeds a second set value, the correlation trend between the conductor deformation and the ice peeling rate is determined; based on the lateral expansion range and the correlation trend, combined with the change characteristics of the second proportional parameter, a transition time period when the ice layer reaches a critical state of ice melting is predicted, wherein the starting time of the transition time period is the time when the crack propagation rate inside the ice layer first enters a linear growth stage, and the ending time is the time when the line sag exceeds a preset sag threshold; Based on the conductor deformation amount and the peak-shaving cost parameter, a correlation prediction result of the power load change and the electricity price fluctuation during the icing period is generated, including: Based on the degree of deviation between the conductor deformation and the preset sag threshold, the power attenuation slope of the line transmission power is calculated; based on the time distribution characteristics of the peak-shaving cost parameters in the continuous ice melting stage, the time period weight coefficient of the electricity price floating benchmark value is generated; a bidirectional coupling rule is established, and the power attenuation slope and the time period weight coefficient are processed according to the bidirectional coupling rule to generate a correlation prediction result between the power load change and the electricity price fluctuation during the icing period.

7. A computing device, characterized in that It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a joint prediction method for power load and electricity price considering weather factors as described in any one of claims 1 to 5.

8. A computer storage medium, characterized in that A computer program is stored, and when the computer program is executed by a computer, the method for jointly predicting power load and electricity price taking into account weather factors as described in any one of claims 1 to 5 is implemented.

Images