Method and system for predicting electrical load of electric boiler

Abstract

The invention discloses an electrical load prediction method and system for an electric boiler. The method comprises the steps that the current moment t and the current execution frequency are initialized; reading data at the moment t and the moment t + A in the data file; adjusting a heating control flow or a heat release control flow of the electric boiler based on the read data to obtain the load of the electric boiler at the t moment; adding 1 to the moment t, and returning to the step of reading the data until the last moment is reached; obtaining a time sequence load prediction curve of the electric boiler according to the load at each moment; adding 1 to the execution frequency r, and returning to the step of reading the data until a set execution frequency threshold value is reached; and obtaining an electric load prediction result of the electric boiler based on the plurality of time sequence load prediction curves obtained in the multiple repeated execution processes. According to the scheme, the influence of factors such as the electricity price, the state that the electric boiler participates in the demand side response, the environment temperature and the like on the electric boiler load is considered, so that the time sequence load prediction result can be close to the actual situation.

Description

Technical Field

[0001] This application generally relates to the technical field of power system load forecasting. More specifically, this application relates to a method and system for predicting the electricity consumption load of electric boilers. Background Art

[0002] With the accelerating evolution of the integrated energy system and the new power system, the large-scale application of high-power loads such as electric boilers has become an important means to achieve the clean transformation of energy. However, its high energy consumption characteristics have significantly exacerbated the contradiction between supply and demand in the power system: during the winter heating period, the electric boiler load is superimposed on the people's livelihood heating demand, further amplifying the pressure of ensuring power supply. At the same time, the increase in the proportion of new energy power generation has led to a decline in the system's regulation ability, and the randomness and volatility of the electric boiler load have exacerbated the uncertainty on both the source and load sides. Therefore, accurately predicting the electric boiler load plays a key role in ensuring the balance of power and electricity in the system and optimizing the dispatching strategy.

[0003] Existing load forecasting technologies mainly include data-driven load forecasting technologies and physical model-based load forecasting technologies. The data-driven load forecasting technology infers the future load from history through methods such as time series machine learning methods and similar days. This method does not rely on complex physical models and needs to build a time series model based on a large amount of historical data. The physical model-based load forecasting technology establishes physical models for the electric boiler body, its heating and heat release processes, and solves these models through methods such as discretization and finite element to perform simulations to obtain the load of the electric boiler. It is suitable for scenarios with insufficient data or no data at all, but the physical model of the electric boiler is closely coupled with the scenario, and how to build a high-precision physical model based on the real scenario is a difficult point.

[0004] In view of this, there is an urgent need to provide a scheme for predicting the electricity consumption load of electric boilers to model based on the working process of the electric boiler and the influencing factors of the electric boiler load, so as to obtain a more accurate prediction result of the electricity consumption load. Summary of the Invention

[0005] In order to solve at least one or more of the above-mentioned technical problems, this application proposes a scheme for predicting the electricity consumption load of electric boilers in multiple aspects.

[0006] In a first aspect, the present application provides a method for predicting the electrical load of an electric boiler, including: initializing the current time t to 0 and initializing the current execution count r to 1; reading the data at time t and time t+A in a data file, where the data includes electricity price, the status of the electric boiler participating in demand response, and ambient temperature statistical data; invoking the heating control process or the heat release control process of the electric boiler based on the data read in the data file to obtain the load of the electric boiler at time t; incrementing time t by 1 and returning to the step of reading data in the data file until the last time is reached, where the formula for the last time is: t L = t SP / t ST , t L is the last time, t SP is the set time span, t ST is the set time step; obtaining the time series load prediction curve of the electric boiler according to the loads at each time; incrementing the execution count r by 1 and returning to the step of reading data in the data file until the set execution count threshold is reached; obtaining the prediction result of the electrical load of the electric boiler based on the multiple time series load prediction curves obtained during multiple repeated executions.

[0007] In some embodiments, during the execution of invoking the heating control process or the heat release control process of the electric boiler based on the data read in the data file, the following steps are performed: determining whether the electric boiler participates in demand response at time t or time t+A, and simultaneously determining the interval in which the electricity price at time t is located; in response to the electric boiler not participating in demand response at time t or time t+A and the electricity price at time t being in the low valley interval, invoking the heating control process of the electric boiler to make the temperature of the heat storage medium of the electric boiler reach the upper limit of the set appropriate temperature interval and maintaining this temperature; in response to the electric boiler not participating in demand response at time t or time t+A and the electricity price at time t being in the medium price interval, invoking the heating control process or the heat release control process of the electric boiler to make the temperature of the heat storage medium of the electric boiler reach the midpoint of the set appropriate temperature interval and maintaining this temperature; in response to the electric boiler not participating in demand response at time t or time t+A and the electricity price at time t being in the peak interval, invoking the heat release control process of the electric boiler to make the temperature of the heat storage medium of the electric boiler reach the lower limit of the set appropriate temperature interval; in response to the electric boiler participating in demand response at time t, invoking the heat release control process of the electric boiler to make the temperature of the heat storage medium of the electric boiler reach the lower limit of the set appropriate temperature interval; in response to the electric boiler participating in demand response at time t+A, invoking the heating control process of the electric boiler to make the temperature of the heat storage medium of the electric boiler reach the upper limit of the set appropriate temperature interval and maintaining this temperature.

[0008] In some embodiments, during the execution of the heating control process or the heat release control process of the electric boiler, the control process is discretized in time, and the electric boiler is discretized in space; wherein, during the discretization of the control process in time, a time resolution is set, and discrete time points are established, and the difference between each discrete time point is the time resolution; during the discretization of the electric boiler in space, the electric boiler is divided into multiple electric boiler blocks.

[0009] In some embodiments, during the execution of the heating control process of the electric boiler, the following steps are performed: initialize the parameters of the electric boiler, initialize the discrete time point s to 0, and initialize the ordinal number i of the electric boiler block to 1; heat each electric boiler block with the unit heating duration of the time resolution, and at the same time, each electric boiler block transfers heat to the adjacent electric boiler block whose temperature is lower than its temperature; traverse all electric boiler blocks to determine whether the temperature of each electric boiler block reaches the required temperature; in response to the temperature of each electric boiler block reaching the required temperature, record the current discrete time point to obtain the total heating duration; in response to the temperature of some electric boiler blocks not reaching the required temperature, return to the step of heating the electric boiler blocks until the temperature of each electric boiler block reaches the required temperature; wherein, during the heating of each electric boiler block, different heating powers are respectively used. After heating the i-th electric boiler block for the unit heating duration, the expression of its temperature rise is: ΔT Gi is the temperature rise caused by heating for the i-th electric boiler block, P bi (t) is the heating power of the i-th electric boiler block at time t, Δt is the time resolution, η is the heating efficiency, C bi is the specific heat capacity of the heat storage medium of the i-th electric boiler block, m bi is the mass of the heat storage medium of the i-th electric boiler block.

[0010] In some embodiments, during the execution of the heat release control process of the electric boiler, the following steps are performed: Initialize the parameters of the electric boiler, initialize the discrete time point s to 0, and initialize the ordinal number i of the electric boiler block to 1; Each electric boiler block releases heat to the environment at a heat release duration per unit of time resolution. At the same time, each electric boiler block transfers heat to the adjacent electric boiler blocks whose temperatures are lower than its temperature; Traverse all electric boiler blocks to determine whether the temperature of each electric boiler block reaches the required temperature; In response to the temperature of each electric boiler block reaching the required temperature, record the current discrete time point to obtain the total heat release duration; In response to the temperature of some electric boiler blocks not reaching the required temperature, return to the step where each electric boiler block releases heat to the environment until the temperature of each electric boiler block reaches the required temperature; Wherein, during the process of each electric boiler block releasing heat to the environment at a heat release duration per unit of time resolution, after the i-th electric boiler block releases heat to the environment for a unit heat release duration, the expression for the temperature drop is: ΔT Gi is the temperature drop caused by heat release to the i-th electric boiler block, Q loss is the heat released by the i-th electric boiler block to the environment, C bi is the specific heat capacity of the heat storage medium of the i-th electric boiler block, m bi is the mass of the heat storage medium of the i-th electric boiler block, Q loss =K i ·(T i -T a )·Δt, K i is the heat dissipation coefficient of the electric boiler block i, T i is the temperature of the i-th electric boiler block, T a is the actual ambient temperature, and Δt is the time resolution.

[0011] In some embodiments, during the process of each electric boiler block transferring heat to the adjacent electric boiler blocks whose temperatures are lower than its temperature, the expression for the temperature change amount brought to the i-th electric boiler block due to heat transfer between electric boiler blocks is: Wherein, ΔT bi is the temperature change amount brought to the i-th electric boiler block due to heat transfer between electric boiler blocks, Q b is the heat conducted between electric boiler blocks, C bi is the specific heat capacity of the heat storage medium of the i-th electric boiler block, m bi is the mass of the heat storage medium of the i-th electric boiler block; Q b =C H ·ΔT b ·Δt, C H is the heat transfer coefficient between electric boiler blocks, ΔT b is the temperature difference between two adjacent electric boiler blocks, and Δt is the time resolution.

[0012] In some embodiments, the actual ambient temperature is obtained from the ambient temperature statistical data, where the ambient temperature statistical data includes the mean value of the ambient temperature, the standard deviation of the ambient temperature, the lower limit value of the ambient temperature, and the upper limit value of the ambient temperature within a set time period.

[0013] In some embodiments, in the process of obtaining the actual ambient temperature from the ambient temperature statistical data, the following steps are performed: constructing a probability density function of the actual ambient temperature based on the ambient temperature statistical data, where the probability density function of the actual ambient temperature is expressed as:

[0014] T μ is the mean value of the ambient temperature, T std is the standard deviation of the ambient temperature, T lower is the lower limit value of the ambient temperature, T upper is the upper limit value of the ambient temperature, T a is the actual ambient temperature, φ(·) is the probability density function of a general Gaussian distribution, and Φ(·) is the cumulative distribution function of a general Gaussian distribution; sampling operations are performed according to the constructed probability density function of the actual ambient temperature to obtain the actual ambient temperature.

[0015] In some embodiments, obtaining the electric boiler power load prediction result based on multiple time-series load prediction curves obtained during multiple repeated executions includes the following steps: aligning the multiple time-series load prediction curves at the same moments so that there are multiple load values corresponding to each moment; sorting the multiple load values corresponding to each moment in ascending order, and calculating the quartiles corresponding to each moment based on the sorting result, where the quartiles include the lower quartile, the median, and the upper quartile; connecting the lower quartiles, the medians, and the upper quartiles corresponding to each moment respectively to form an electric boiler power load prediction band.

[0016] In a second aspect, the present application provides a set of electric boiler power load prediction systems that perform electric boiler power load prediction using the electric boiler power load prediction method described in any embodiment of the first aspect. The system includes: an initialization module for initializing the current moment t to 0 and initializing the current execution count r to 1; a data reading module for reading the data at moment t and moment t + A in a data file, where the data includes electricity price, the status of the electric boiler participating in demand-side response, and ambient temperature statistical data; an electric boiler control process calling module for calling the heating control process or the heat release control process of the electric boiler based on the data read in the data file to obtain the load of the electric boiler at moment t; a moment loop module for incrementing moment t by 1 and returning to the step of reading data in the data file until the last moment is reached, where the formula for the last moment is: t L = tSP / t ST ,t L is the last moment, t SP is the set time span, t ST is the set time step; The time-series load prediction curve acquisition module is used to obtain the time-series load prediction curve of the electric boiler according to the load at each moment; The execution times loop module is used to increase the execution times r by 1 and return to the step of reading data from the data file until the set execution times threshold is reached; The electricity load prediction result acquisition module is used to obtain the electricity load prediction result of the electric boiler based on multiple time-series load prediction curves obtained during multiple repeated executions.

[0017] Through the electric boiler electricity load prediction scheme provided above, in the embodiments of the present application, by calling the heating control process or the heat release control process of the electric boiler based on the electricity price at time t, the state of the electric boiler participating in the demand-side response, and the ambient temperature statistical data, the load of the electric boiler at time t is obtained, considering the influence of factors such as electricity price, the state of the electric boiler participating in the demand-side response, and ambient temperature on the load of the electric boiler, so that the time-series load prediction result can be close to the actual situation. At the same time, increase time t by 1 and return to the step of reading data from the data file until the last moment is reached, which can simulate the operating characteristics of the electric boiler in a continuous time series and is applicable to short-term scheduling and long-term energy efficiency optimization. In addition, by obtaining the time-series load prediction curve of the electric boiler according to the load at each moment, the operating characteristics of the electric boiler at different time periods can be accurately reflected. By obtaining the electricity load prediction result of the electric boiler based on multiple time-series load prediction curves obtained through multiple repetitions, the random error of single prediction can be effectively eliminated.

[0018] Further, in some embodiments, determining whether to call the heating control process or the heat release control process of the electric boiler according to whether the electric boiler participates in the demand-side response at time t or time t+A and the interval where the electricity price at time t is located can simulate the influence of time-of-use electricity price and the state of the electric boiler participating in the demand-side response on the heating and heat release behaviors of the electric boiler, thereby improving the time-series accuracy and dynamic adaptability of load prediction and enhancing the multi-factor coupling ability in the load prediction process.

[0019] Furthermore, in some embodiments, during the execution of the heating control process or the heat release control process of the electric boiler, discretize the control process in time and discretize the electric boiler in space, which can model the inconsistencies in the heating control process and the heat release control process of the electric boiler, make the heating control process and the heat release control process of the electric boiler closer to the actual situation, and thus improve the prediction accuracy of the electricity load of the electric boiler. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present application will become readily understandable. In the drawings, several embodiments of the present application are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts, where:

[0021] Figure 1 Shows an exemplary flowchart of the electric boiler power load prediction method according to an embodiment of the present application;

[0022] Figure 2 Shows an exemplary flowchart of the control process for calling an electric boiler based on the read data according to an embodiment of the present application;

[0023] Figure 3 Shows an exemplary flowchart of the heating control process for executing an electric boiler according to an embodiment of the present application;

[0024] Figure 4 Shows an exemplary flowchart of the heat release control process for executing an electric boiler according to an embodiment of the present application;

[0025] Figure 5 Shows an exemplary flowchart of obtaining the electric boiler power load prediction result according to an embodiment of the present application;

[0026] Figure 6 Shows an exemplary structural block diagram of the electric boiler power load prediction system according to an embodiment of the present application. Detailed Embodiments

[0027] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present application.

[0028] It should be understood that the terms "including" and "comprising" used in the specification and claims of the present application indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0029] It should also be understood that the terms used in the specification of this application are merely for the purpose of describing specific embodiments and are not intended to limit this application. As used in the specification and claims of this application, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms. It should be further understood that the term " / or" used in the specification and claims of this application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0030] Figure 1 FIG. shows an exemplary flowchart of the electric boiler power load prediction method 100 according to an embodiment of this application.

[0031] As Figure 1 shown, in step S110, the current time t is initialized to 0, and the current execution count r is initialized to 1.

[0032] In an embodiment of this application, by setting the time span and time step of the electric boiler load prediction, the time span of the electric boiler load prediction is divided into multiple moments, and the time interval between adjacent moments is the set time step.

[0033] In an embodiment of this application, the time span of the electric boiler load prediction is set to 24 hours, and the time step is set to 1 minute. At this time, the time span of the electric boiler load prediction is divided into 1440 moments.

[0034] In another embodiment of this application, the time span of the electric boiler load prediction is set to 4 hours, and the time step is set to 1 minute. At this time, the time span of the electric boiler load prediction is divided into 60 moments.

[0035] In other embodiments of this application, the specific values of the time span and time step of the electric boiler load prediction can also be set according to actual needs, and this application does not limit this here.

[0036] By dividing the time span of the electric boiler load prediction into multiple moments, the load demand at different moments can be accurately predicted, so as to perform resource scheduling and optimal allocation more effectively.

[0037] After step S110 is executed, in step S120, the data at time t and time t+A are read from the data file, and the data includes electricity price, the status of the electric boiler participating in demand response, and environmental temperature statistical data.

[0038] In an embodiment of this application, the data file is a data file obtained by statistically analyzing the electricity price, the status of the electric boiler participating in demand response, and environmental temperature statistical data within the time span of the electric boiler load prediction.

[0039] In an embodiment of the present application, A is the set continuation time.

[0040] In some embodiments of the present application, the value of A is 30 minutes.

[0041] In other embodiments of the present application, the value of A can be set according to actual needs and historical experience, and the present application does not limit this here.

[0042] In an embodiment of the present application, it can be determined whether the electricity price is in the low valley interval, medium price interval, and peak interval according to the interval where the electricity price value is located.

[0043] In an embodiment of the present application, the numerical ranges corresponding to the low valley interval, medium price interval, and peak interval can be set according to the local electricity price interval and actual needs, and the present application does not limit this here.

[0044] In an embodiment of the present application, the states of the electric boiler participating in the demand-side response include the electric boiler participating in the demand-side response and the electric boiler not participating in the demand-side response. Specifically, when the power grid dispatching issues a demand-side response of "load shedding", the electric boiler participates in the demand-side response. When the power grid dispatching does not issue a demand-side response of "load shedding", the electric boiler does not participate in the demand-side response.

[0045] In an embodiment of the present application, the environmental temperature statistical data includes the mean value of the environmental temperature, the standard deviation of the environmental temperature, the lower limit value of the environmental temperature, and the upper limit value of the environmental temperature within the set time.

[0046] In some embodiments of the present application, the aforementioned set time is 30 minutes.

[0047] In other embodiments of the present application, the aforementioned set time can be set according to actual needs and historical experience, and the present application does not limit this here.

[0048] After step S120 is executed, in step S130, based on the data read from the data file, the heating control process or the heat release control process of the electric boiler is called to obtain the load of the electric boiler at time t.

[0049] In an embodiment of the present application, the specific process of calling the heating control process or the heat release control process of the electric boiler based on the data read from the data file can be referred to Figure 2 .

[0050] Figure 2 The exemplary flowchart shows the control process of the electric boiler called based on the read data in the embodiment of the present application.

[0051] As Figure 2As shown, in step S210, it is determined whether the electric boiler participates in the demand response at time t or at time t + A. In response to the electric boiler not participating in the demand response at time t or at time t + A, in step S220, it is determined whether the electricity price at time t is in the low valley interval. In response to the electricity price at time t being in the low valley interval, in step S230, the heating control process of the electric boiler is called to make the temperature of the heat storage medium of the electric boiler reach the upper limit of the set appropriate temperature interval and maintain this temperature. In response to the electricity price at time t not being in the low valley interval, in step S240, it is determined whether the electricity price at time t is in the medium price interval. In response to the electricity price at time t being in the medium price interval, in step S250, the heating control process or the heat release control process of the electric boiler is called to make the temperature of the heat storage medium of the electric boiler reach the midpoint of the set appropriate temperature interval and maintain this temperature. In response to the electricity price at time t not being in the medium price interval, that is, the electricity price at time t is in the peak interval, in step S260, the heat release control process of the electric boiler is called to make the temperature of the heat storage medium of the electric boiler reach the lower limit of the set appropriate temperature interval.

[0052] In response to the electric boiler participating in the demand response at time t or at time t + A, in step S270, it is determined whether the electric boiler participates in the demand response at time t. In response to the electric boiler participating in the demand response at time t, in step S280, the heat release control process of the electric boiler is called to make the temperature of the heat storage medium of the electric boiler reach the lower limit of the set appropriate temperature interval. In response to the electric boiler not participating in the demand response at time t, that is, the electric boiler participates in the demand response at time t + A, in step S290, the heating control process of the electric boiler is called to make the temperature of the heat storage medium of the electric boiler reach the upper limit of the set appropriate temperature interval and maintain this temperature.

[0053] By calling the heating control process or the heat release control process of the electric boiler based on determining whether the electric boiler participates in the demand response at time t or at time t + A and determining the interval in which the electricity price at time t is located, the influence of the interval in which the electricity price is located and the state of the electric boiler participating in the demand response on the heating and heat release behaviors of the electric boiler is simulated, and the principle of "heating at low valley electricity price, releasing heat at peak electricity price, and flexibly operating at flat electricity price" is realized, thereby improving the timing accuracy and dynamic adaptability of load forecasting and enhancing the multi-factor coupling ability in the load forecasting process.

[0054] In the process of invoking the heating control process of the electric boiler or the heat release control process of the electric boiler above, by enabling the electric boiler to adopt the operating mode within the set appropriate temperature range, that is, maintaining the temperature of the heat storage medium within the set appropriate temperature range. This operating mode provides flexibility to the electric load of the electric boiler. Due to the existence of thermal inertia and heat storage capacity, the electric boiler does not need to be in the heating state all the time, but only needs to be heated intermittently to meet the requirements of the appropriate temperature range, and can be in the heat release (standby) state at other times. The heating time is also flexibly adjustable within a certain range, thereby providing flexibility to the electric load.

[0055] In some embodiments of the present application, the aforementioned appropriate temperature range is set to [60°C, 80°C].

[0056] In other embodiments of the present application, the aforementioned appropriate temperature range can also be set according to actual needs and historical experience, and the present application does not limit this here.

[0057] In the embodiments of the present application, in the process of executing the heating control process of the electric boiler or the heat release control process of the electric boiler, the control process is discretized in time, and the electric boiler is discretized in space.

[0058] Specifically, in the process of discretizing the control process in time, a time resolution is set, and discrete time points are established. The difference between each discrete time point is the time resolution.

[0059] In some embodiments of the present application, the time resolution is set to 10 s. In other embodiments of the present application, the time resolution can also be set according to actual needs and historical experience, and the present application does not limit this here.

[0060] Specifically, in the process of discretizing the electric boiler in space, the electric boiler is divided into multiple electric boiler blocks. Each electric boiler block has consistency inside, while there is inconsistency between the electric boiler blocks.

[0061] Specifically, in the heating control process of the electric boiler, when the electric boiler is divided into multiple electric boiler blocks, the heating power is the same everywhere inside each electric boiler block, and for different electric boiler blocks, their heating powers are different, thereby simulating the inconsistency in the heating process of the electric boiler. In the heat release control process of the electric boiler, when the electric boiler is divided into multiple electric boiler blocks, the areas with a relatively small change range of the heat dissipation coefficient can be classified into the same electric boiler block, so that the heat release inside each electric boiler block has consistency, that is, the heat dissipation coefficient is the same.

[0062] In the embodiments of the present application, for the specific process of executing the heating control process of the electric boiler, reference can be made to Figure 3 .

[0063] Figure 3 An exemplary flowchart showing the heating control process of the electric boiler implemented in this application is presented.

[0064] As Figure 3 shown, in step S310, the parameters of the electric boiler are initialized, the discrete time point s is initialized to 0, and the ordinal number i of the electric boiler block is initialized to 1. In step S320, each electric boiler block is heated with a heating duration per unit of time resolution. Meanwhile, each electric boiler block transfers heat to adjacent electric boiler blocks whose temperatures are lower than its own. In step S330, all electric boiler blocks are traversed to determine whether the temperature of each electric boiler block reaches the required temperature. In response to the temperature of each electric boiler block reaching the required temperature, in step S340, the current discrete time point is recorded to obtain the total heating duration. In response to there being an electric boiler block whose temperature has not reached the required temperature, the process returns to the step of heating the electric boiler block, that is, returns to step S320, until the temperature of each electric boiler block reaches the required temperature.

[0065] Specifically, during the heating process of each electric boiler block, different heating powers are respectively adopted. After heating the i-th electric boiler block for a unit heating duration, the expression for the temperature rise amount is: ΔT Gi is the temperature rise amount brought to the i-th electric boiler block by heating, P bi (t) is the heating power of the i-th electric boiler block at time t, Δt is the time resolution, η is the heating efficiency, C bi is the specific heat capacity of the heat storage medium of the i-th electric boiler block, m bi is the mass of the heat storage medium of the i-th electric boiler block.

[0066] In the embodiments of this application, for the specific process of implementing the heat release control process of the electric boiler, reference can be made to Figure 4 .

[0067] Figure 4 An exemplary flowchart showing the heat release control process of the electric boiler implemented in this application is presented.

[0068] As Figure 4As shown, in step S410, the parameters of the electric boiler are initialized, the discrete time point s is initialized to 0, and the ordinal number i of the electric boiler block is initialized to 1. In step S420, each electric boiler block releases heat to the environment in units of heat release duration with a time resolution. At the same time, each electric boiler block transfers heat to the adjacent electric boiler blocks whose temperatures are lower than its temperature. In step S430, all electric boiler blocks are traversed to determine whether the temperature of each electric boiler block reaches the required temperature. In response to the temperature of each electric boiler block reaching the required temperature, in step S440, the current discrete time point is recorded to obtain the total heat release duration. In response to the temperature of some electric boiler blocks not reaching the required temperature, return to the step where each electric boiler block releases heat to the environment, that is, return to step S420, until the temperature of each electric boiler block reaches the required temperature.

[0069] Specifically, during the process where each electric boiler block releases heat to the environment in units of heat release duration with a time resolution, after the i-th electric boiler block releases heat to the environment for a unit heat release duration, the expression for the temperature drop is: ΔT Gi is the temperature drop caused by heat release to the i-th electric boiler block, Q loss is the heat released by the i-th electric boiler block to the environment, C bi is the specific heat capacity of the heat storage medium of the i-th electric boiler block, m bi is the mass of the heat storage medium of the i-th electric boiler block, Q loss =K i ·(T i -T a )·Δt, K i is the heat dissipation coefficient of the electric boiler block i, T i is the temperature of the i-th electric boiler block, T a is the actual ambient temperature, and Δt is the time resolution.

[0070] In the embodiments of the present application, the aforementioned actual ambient temperature is obtained through the aforementioned ambient temperature statistical data. During the process of obtaining the actual ambient temperature through the ambient temperature statistical data, first, a probability density function of the actual ambient temperature is constructed based on the ambient temperature statistical data, where the probability density function of the actual ambient temperature is expressed as: T μ is the mean value of the ambient temperature, T std is the standard deviation of the ambient temperature, T lower is the lower limit value of the ambient temperature, T upper is the upper limit value of the ambient temperature, T a is the actual ambient temperature, φ(·) is the probability density function of the general Gaussian distribution, and Φ(·) is the cumulative distribution function of the general Gaussian distribution. Then, sampling operations are performed according to the constructed probability density function of the actual ambient temperature to obtain the actual ambient temperature.

[0071] In an embodiment of the present application, in the process of sampling according to the probability density function of the built actual ambient temperature to obtain the actual ambient temperature, various existing technologies can be adopted, and the present application does not limit this here. For example, first, a random number Z of a standard normal distribution is generated using a common random number generator. Second, the inverse function - 1

[0072] ψ(·) of the probability density function is calculated to convert the random number Z of the standard normal distribution into the ambient temperature. Third, it is checked whether the generated ambient temperature is between T lower and T upper . In response to the ambient temperature not being between T lower and T upper , return to the step of generating a random number. In response to the ambient temperature being between T lower and T upper , the generated ambient temperature is used as the actual ambient temperature.

[0073] In an embodiment of the present application, in the process of heat transfer from each of the foregoing electric boiler blocks to an adjacent electric boiler block with a temperature lower than its own temperature, the expression for the temperature change amount brought to the i-th electric boiler block due to heat transfer between the electric boiler blocks is: where ΔT bi is the temperature change amount brought to the i-th electric boiler block due to heat transfer between the electric boiler blocks, Q b is the heat conducted between the electric boiler blocks, C bi is the specific heat capacity of the heat storage medium of the i-th electric boiler block, m bi is the mass of the heat storage medium of the i-th electric boiler block, Q b =C H ·ΔT b ·Δt, C H is the heat transfer coefficient between the electric boiler blocks, ΔT b is the temperature difference between two adjacent electric boiler blocks, and Δt is the time resolution.

[0074] In an embodiment of the present application, in the process of executing the heating control process of the electric boiler, by statistically analyzing the temperatures before and after the electric boiler is heated, the heat absorbed by the electric boiler can be obtained based on the temperatures before and after the electric boiler is heated, the mass of the heat storage medium of the electric boiler, and the specific heat capacity of the heat storage medium of the electric boiler. Specifically, the calculation formula for the heat absorbed by the electric boiler is: Q 吸收 =C×m×ΔT, where Q 吸收 is the heat absorbed by the electric boiler, C is the specific heat capacity of the heat storage medium of the electric boiler, n H is the total number of electric boiler blocks corresponding to the electric boiler, C biis the specific heat capacity of the heat storage medium of the i-th electric boiler block, and m is the specific heat capacity of the heat storage medium of the electric boiler. m bi is the mass of the heat storage medium of the i-th electric boiler block.

[0075] In the embodiments of the present application, in the process of executing the heat release control of the electric boiler, by statistically analyzing the temperature before and after the heat release of the electric boiler, the heat released by the electric boiler can be obtained based on the temperature before and after the heat release of the electric boiler, the mass of the heat storage medium of the electric boiler, and the specific heat capacity of the heat storage medium of the electric boiler. Specifically, the calculation formula for the heat released by the electric boiler is the same as the calculation formula for the heat absorbed by the electric boiler, and details are not elaborated herein.

[0076] After step S130 is executed, in step S140, it is determined whether the last moment is reached.

[0077] After step S140 is executed, in response to the fact that the last moment is not reached, the time t is incremented by 1, and the process returns to the step of reading data from the data file. That is, it returns to step S120.

[0078] Specifically, the calculation formula for the last moment is: t L = t SP / t ST t L is the last moment, t SP is the set time span, and t ST is the set time step.

[0079] By incrementing the time t by 1 when the last moment is not reached and returning to the step of reading data from the data file until the last moment is reached, the operating characteristics of the electric boiler under continuous time series can be simulated, which is applicable to short-term scheduling and long-term energy efficiency optimization.

[0080] After step S140 is executed, in response to the fact that the last moment is reached, in step S150, the time series load prediction curve of the electric boiler is obtained according to the load at each moment.

[0081] After step S150 is executed, in step S160, it is determined whether the set execution times threshold is reached.

[0082] After step S160 is executed, in response to the fact that the set execution times threshold is not reached, the execution times r is incremented by 1, and the process returns to the step of reading data from the data file. That is, it returns to step S120.

[0083] By obtaining the electric boiler power load prediction result based on multiple time series load prediction curves obtained through multiple repetitions, the random error of single prediction can be effectively eliminated.

[0084] After step S160 is executed, in response to reaching the set execution times threshold, in step S170, based on multiple time series load prediction curves obtained during multiple repeated executions, an electric boiler power consumption load prediction result is obtained.

[0085] In an embodiment of the present application, the specific steps involved in step S170 can be referred to Figure 5 .

[0086] Figure 5 An exemplary flowchart showing the acquisition of the electric boiler power consumption load prediction result in an embodiment of the present application is shown.

[0087] As Figure 5 shown, in step S510, multiple time series load prediction curves are aligned at the same moment, so that multiple load values corresponding to each moment. In step S520, the multiple load values corresponding to each moment are sorted in ascending order, and quartiles corresponding to each moment are calculated based on the sorting result, where the quartiles include the lower quartile, the median, and the upper quartile. In step S530, the lower quartiles, medians, and upper quartiles corresponding to each moment are connected respectively to form an electric boiler power consumption load prediction band.

[0088] Specifically, the lower quartile is the 25% quantile among multiple load values, representing a conservative load estimate. The median is the 50% quantile among multiple load values, representing the most likely load level. The upper quartile is the 75% quantile among multiple load values, reflecting the high load potential risk.

[0089] By forming the electric boiler power consumption load prediction band, the load fluctuation range and the confidence interval can be visually displayed (for example, the lower quartile - upper quartile covers a 50% probability scenario). Thus, a probabilistic prediction result is provided, which can assist in evaluating the reliability of the load prediction and reduce the risk of equipment overload or energy waste caused by load mutations.

[0090] In summary, through the electric boiler power load prediction solution provided above, in the embodiment of the present application, the heating control process or the heat release control process of the electric boiler is called based on the electricity price at time t, the status of the electric boiler participating in the demand response, and the ambient temperature statistical data, and the load of the electric boiler at time t is obtained. The influence of factors such as electricity price, the status of the electric boiler participating in the demand response, and ambient temperature on the electric boiler load is considered, so that the time-series load prediction result can be close to the actual situation. At the same time, increment time t by 1 and return to the step of reading data from the data file until the last moment is reached, which can simulate the operating characteristics of the electric boiler in a continuous time series and is applicable to short-term scheduling and long-term energy efficiency optimization. In addition, by obtaining the time-series load prediction curve of the electric boiler according to the load at each moment, the operating characteristics of the electric boiler at different time periods can be accurately reflected. By obtaining the electric boiler power load prediction result based on multiple time-series load prediction curves obtained through multiple repetitions, the random error of a single prediction can be effectively eliminated.

[0091] Further, in some embodiments, determining whether to call the heating control process or the heat release control process of the electric boiler according to whether the electric boiler participates in the demand response at time t or time t+A and the interval in which the electricity price at time t is located can simulate the influence of time-of-use electricity price and the status of the electric boiler participating in the demand response on the heating and heat release behaviors of the electric boiler, thereby improving the time-series accuracy and dynamic adaptability of load prediction and enhancing the multi-factor coupling ability in the load prediction process.

[0092] Furthermore, in some embodiments, during the execution of the heating control process or the heat release control process of the electric boiler, the control process is discretized in time and the electric boiler is discretized in space, which can model the inconsistencies in the heating control process and the heat release control process of the electric boiler, making the heating control process and the heat release control process of the electric boiler closer to the actual situation, thereby improving the prediction accuracy of the electric boiler power load.

[0093] The embodiment of the present application also provides an electric boiler power load prediction system, which can use the aforementioned electric boiler power load prediction method 100 to predict the electric boiler power load, or can use other methods to predict the electric boiler power load, and the present application does not limit this here.

[0094] Figure 6 The exemplary structural block diagram of the electric boiler power load prediction system 600 according to the embodiment of the present application is shown.

[0095] As Figure 6As shown, the system 600 includes an initialization module 610, a data reading module 620, an electric boiler control process calling module 630, a time loop module 640, a time-series load prediction curve obtaining module 650, an execution times loop module 660, and an electricity load prediction result obtaining module 670. In an embodiment of the present application, the initialization module 610, the data reading module 620, the electric boiler control process calling module 630, the time loop module 640, the time-series load prediction curve obtaining module 650, the execution times loop module 660, and the electricity load prediction result obtaining module 670 may be separate units or integrated in the same integrated circuit, and the present application does not limit this here.

[0096] Specifically, the initialization module 610 is used to initialize the current time t to 0 and initialize the current execution times r to 1.

[0097] Specifically, the data reading module 620 is used to read the data at time t and time t + A in the data file, and the data includes electricity price, the status of the electric boiler participating in demand-side response, and ambient temperature statistical data.

[0098] Specifically, the electric boiler control process calling module 630 is used to call the heating control process or the heat release control process of the electric boiler based on the data read in the data file to obtain the load of the electric boiler at time t.

[0099] Specifically, the time loop module 640 is used to increment the time t by 1 and return to the step of reading data in the data file until the last time is reached, where the formula for the last time is: t L = t SP / t ST t L is the last time, t SP is the set time span, and t ST is the set time step.

[0100] Specifically, the time-series load prediction curve obtaining module 650 is used to obtain the time-series load prediction curve of the electric boiler according to the load at each time.

[0101] Specifically, the execution times loop module 660 is used to increment the execution times r by 1 and return to the step of reading data in the data file until the set execution times threshold is reached.

[0102] Specifically, the electricity load prediction result obtaining module 670 is used to obtain the electricity load prediction result of the electric boiler based on multiple time-series load prediction curves obtained during multiple repeated executions.

[0103] When the system 600 performs the electric boiler power load prediction using the aforementioned electric boiler power load prediction method 100, the initialization module 610 is used to execute the aforementioned step S110, the data reading module 620 is used to execute the aforementioned step S120, the electric boiler control process calling module 630 is used to execute the aforementioned step S130, the time loop module 640 is used to execute the aforementioned step S140, the time series load prediction curve obtaining module 650 is used to execute the aforementioned step S150, the execution times loop module 660 is used to execute the aforementioned step S160, and the power load prediction result obtaining module 670 is used to execute the aforementioned step S170. The specific execution process can be referred to the foregoing text and will not be elaborated here.

[0104] Although multiple embodiments of the present application have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many variations, changes, and alternative ways may occur to those skilled in the art without departing from the spirit and scope of the present application. It should be understood that various alternatives to the embodiments of the present application described herein may be employed in practicing the present application. The appended claims are intended to define the scope of the present application and thus cover equivalents or alternatives within the scope of these claims.

Claims

1. A method for predicting the electrical load of an electric boiler, characterized in that, Including: Initialize the current time t to 0 and initialize the current execution count r to 1; Read the data at time t and time t+A in the data file, where the data includes electricity price, the status of the electric boiler participating in demand response, and ambient temperature statistical data; Based on the data read in the data file, call the heating control process or the heat release control process of the electric boiler to obtain the load of the electric boiler at time t; Increment the time t by 1 and return to the step of reading data from the data file until the last time is reached, where the calculation formula for the last time is: t L = t SP / t ST , t L is the last time, t SP is the set time span, and t ST is the set time step; Obtain the time-series load prediction curve of the electric boiler according to the loads at each moment; Increment the execution count r by 1 and return to the step of reading data in the data file until the set execution count threshold is reached; Obtain the electric boiler electricity load prediction result based on multiple time-series load prediction curves obtained during multiple repeated executions.

2. The electric boiler power load prediction method according to claim 1, characterized in that, During the execution of calling the heating control process or the heat release control process of the electric boiler based on the data read in the data file, perform the following steps: Judge whether the electric boiler participates in demand response at time t or time t+A, and simultaneously judge the interval where the electricity price at time t is located; In response to the electric boiler not participating in demand response at time t or time t+A, and the electricity price at time t being in the low valley interval, call the heating control process of the electric boiler to make the temperature of the heat storage medium of the electric boiler reach the upper limit of the set appropriate temperature interval and maintain this temperature; In response to the electric boiler not participating in demand response at time t or time t+A, and the electricity price at time t being in the medium price interval, call the heating control process or the heat release control process of the electric boiler to make the temperature of the heat storage medium of the electric boiler reach the midpoint of the set appropriate temperature interval and maintain this temperature; In response to the electric boiler not participating in demand response at time t or time t+A, and the electricity price at time t being in the peak interval, call the heat release control process of the electric boiler to make the temperature of the heat storage medium of the electric boiler reach the lower limit of the set appropriate temperature interval; In response to the electric boiler participating in demand response at time t, call the heat release control process of the electric boiler to make the temperature of the heat storage medium of the electric boiler reach the lower limit of the set appropriate temperature interval; In response to the electric boiler participating in demand response at time t+A, call the heating control process of the electric boiler to make the temperature of the heat storage medium of the electric boiler reach the upper limit of the set appropriate temperature interval and maintain this temperature.

3. The electric boiler power load prediction method according to claim 1 or 2, characterized in that During the execution of the heating control process or the heat release control process of the electric boiler, discretize the control process in time and discretize the electric boiler in space; Among them, during the process of discretizing the control process in time, set the time resolution and establish discrete time points, and the difference between each discrete time point is the time resolution; During the process of discretizing the electric boiler in space, divide the electric boiler into multiple electric boiler blocks.

4. The electric boiler electric load prediction method according to claim 3, characterized in that, During the execution of the heating control process of the electric boiler, perform the following steps: Initialize the parameters of the electric boiler, initialize the discrete time point s to 0, and initialize the ordinal number i of the electric boiler block to 1; Heat each electric boiler block with the heating duration per unit of time resolution. At the same time, each electric boiler block transfers heat to the adjacent electric boiler blocks whose temperatures are lower than its temperature; Traverse all electric boiler blocks and determine whether the temperature of each electric boiler block reaches the required temperature; In response to the temperature of each electric boiler block reaching the required temperature, record the current discrete time point to obtain the total heating duration; In response to the temperature of any electric boiler block not reaching the required temperature, return to the step of heating the electric boiler block until the temperature of each electric boiler block reaches the required temperature; Among them, during the heating process of each electric boiler block, different heating powers are respectively adopted. After heating the i-th electric boiler block for a unit heating duration, the expression for the temperature rise is as follows: ΔT Gi is the temperature rise caused by heating for the i-th electric boiler block, P bi (t) is the heating power of the i-th electric boiler block at time t, Δt is the time resolution, η is the heating efficiency, C bi is the specific heat capacity of the heat storage medium of the i-th electric boiler block, m bi is the mass of the heat storage medium of the i-th electric boiler block.

5. The electric boiler electric load prediction method according to claim 3, characterized in that, During the execution of the heat release control process of the electric boiler, the following steps are executed: Initialize the parameters of the electric boiler, initialize the discrete time point s to 0, and initialize the ordinal number i of the electric boiler block to 1; Each electric boiler block releases heat to the environment in units of time resolution of the heat release duration. At the same time, each electric boiler block transfers heat to the adjacent electric boiler blocks with a temperature lower than its own; Traverse all electric boiler blocks and determine whether the temperature of each electric boiler block reaches the required temperature; In response to the temperature of each electric boiler block reaching the required temperature, record the current discrete time point to obtain the total heat release duration; In response to the temperature of any electric boiler block not reaching the required temperature, return to the step of each electric boiler block releasing heat to the environment until the temperature of each electric boiler block reaches the required temperature; Among them, during the heat release process of each electric boiler block to the environment with a time resolution as the unit of heat release duration, after the i-th electric boiler block releases heat to the environment for a unit heat release duration, the expression for the temperature drop is as follows: ΔT Gi is the temperature drop caused by heat release to the i-th electric boiler block, Q loss is the heat released by the i-th electric boiler block to the environment, C bi is the specific heat capacity of the heat storage medium of the i-th electric boiler block, m bi is the mass of the heat storage medium of the i-th electric boiler block, Q loss = K i ·(T i - T a )·Δt, K i is the heat dissipation coefficient of the electric boiler block i, T i is the temperature of the i-th electric boiler block, T a is the actual ambient temperature, and Δt is the time resolution.

6. The method for predicting the electrical load of an electric boiler according to claim 4 or 5, characterized in that During the heat transfer process from each electric boiler block to its adjacent electric boiler block with a lower temperature, the expression for the temperature change of the i-th electric boiler block caused by heat transfer between electric boiler blocks is: Among them, ΔT bi is the temperature change of the i-th electric boiler block caused by heat transfer between electric boiler blocks, Q b is the heat conducted between electric boiler blocks, C bi is the specific heat capacity of the heat storage medium of the i-th electric boiler block, m bi is the mass of the heat storage medium of the i-th electric boiler block; Q b = C H ·ΔT b ·Δt, C H is the heat transfer coefficient between the electric boiler blocks, ΔT b is the temperature difference between two adjacent electric boiler blocks, and Δt is the time resolution.

7. The method for predicting the electrical load of an electric boiler according to claim 5, characterized in that The actual ambient temperature is obtained through the ambient temperature statistical data, where the ambient temperature statistical data includes the mean value of the ambient temperature, the standard deviation of the ambient temperature, the lower limit value of the ambient temperature, and the upper limit value of the ambient temperature within a set time; 8. The electric boiler electric load prediction method according to claim 7, characterized in that, During the process of obtaining the actual ambient temperature through the ambient temperature statistical data, the following steps are executed: Construct a probability density function of the actual ambient temperature based on the ambient temperature statistical data, where the probability density function of the actual ambient temperature is expressed as: T μ is the mean value of the ambient temperature, T std is the standard deviation of the ambient temperature, T lower is the lower limit value of the ambient temperature, T upper is the upper limit value of the ambient temperature, T a is the actual ambient temperature, φ(·) is the probability density function of the general Gaussian distribution, and Φ(·) is the cumulative distribution function of the general Gaussian distribution; Perform a sampling operation according to the constructed probability density function of the actual ambient temperature to obtain the actual ambient temperature; 9. The electric boiler electric load prediction method according to claim 1, characterized in that Obtaining the electric boiler power load prediction result based on multiple time series load prediction curves obtained during multiple repeated executions includes the following steps: Align multiple time series load prediction curves at the same moment so that there are multiple load values corresponding to each moment; Sort the multiple load values corresponding to each moment in ascending order, and calculate the quartiles corresponding to each moment based on the sorting result, where the quartiles include the lower quartile, the median, and the upper quartile; Connect the lower quartiles, medians, and upper quartiles corresponding to each moment respectively to form an electric boiler power load prediction band; 10. An electric load prediction system for an electric boiler, characterized in that, Use the electric boiler power load prediction method described in any one of claims 1-9 to predict the electric boiler power load. The system includes: An initialization module for initializing the current moment t to 0 and initializing the current execution count r to 1; A data reading module for reading the data at time t and time t+A in the data file, where the data includes electricity price, the status of the electric boiler participating in the demand response, and ambient temperature statistical data; An electric boiler control process call module for calling the heating control process or the heat release control process of the electric boiler based on the data read in the data file to obtain the load of the electric boiler at time t; The time loop module is used to increment the time t by 1 and return to the step of reading data from the data file until the last time is reached, where the formula for the last time is: t L = t SP / t ST , t L is the last time, t SP is the set time span, t ST is the set time step; A time series load prediction curve acquisition module for obtaining the time series load prediction curve of the electric boiler according to the load at each moment; An execution times loop module, which is used to increment the execution times r by 1 and return to the step of reading data from the data file until the set execution times threshold is reached; An electric load prediction result acquisition module, which is used to obtain the electric boiler electric load prediction result based on multiple time series load prediction curves obtained during multiple repeated executions.

Images