CN117852928A - Near zero energy consumption building load prediction method, device, equipment and medium - Google Patents
Near zero energy consumption building load prediction method, device, equipment and medium Download PDFInfo
- Publication number
- CN117852928A CN117852928A CN202410263360.4A CN202410263360A CN117852928A CN 117852928 A CN117852928 A CN 117852928A CN 202410263360 A CN202410263360 A CN 202410263360A CN 117852928 A CN117852928 A CN 117852928A
- Authority
- CN
- China
- Prior art keywords
- prediction model
- frequency
- data
- historical
- prediction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 75
- 238000005265 energy consumption Methods 0.000 title claims abstract description 71
- 238000012549 training Methods 0.000 claims description 43
- 238000000354 decomposition reaction Methods 0.000 claims description 42
- 238000004590 computer program Methods 0.000 claims description 18
- 230000015654 memory Effects 0.000 claims description 17
- 238000009826 distribution Methods 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 8
- 238000007637 random forest analysis Methods 0.000 claims description 7
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 3
- 231100000279 safety data Toxicity 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 11
- 230000000694 effects Effects 0.000 description 11
- 238000012545 processing Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000001816 cooling Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of building load prediction, and particularly relates to a near-zero energy consumption building load prediction method, device, equipment and medium. According to the method, real-time meteorological data are respectively input into three prediction models, the three prediction models respectively output a high-frequency IMF component predicted value, a medium-frequency IMF component predicted value and a low-frequency IMF component predicted value, and overlapping reconstruction is carried out on the high-frequency IMF component predicted value, the medium-frequency IMF component predicted value and the low-frequency IMF component predicted value to obtain a near-zero energy consumption building load predicted value. The invention improves the traditional EMD method for decomposing all data, decomposes the load of the near zero energy consumption building day by day, considers the time sequence characteristics of the load, and has higher prediction precision and smaller deviation compared with the traditional prediction method.
Description
Technical Field
The invention belongs to the technical field of building load prediction, and particularly relates to a near-zero energy consumption building load prediction method, device, equipment and medium.
Background
The near-zero energy consumption building adopts a large number of building envelope structures with excellent heat preservation and insulation performance and a passive technology, load fluctuation is mainly related to building purposes, personnel behaviors, local climate conditions and excitation policies, and has great randomness, fluctuation and uncertainty, so that the prediction of the near-zero energy consumption building load is very complex. However, building load is closely related to the optimal design of the comprehensive energy system, and accurate load prediction is a key for realizing efficient energy supply of the comprehensive energy system. In order to ensure the optimal scheduling of the comprehensive energy system, the prediction of the building load with near zero energy consumption is required to be researched. Currently, there are many load prediction methods, such as data driving, neural network method, long-term and short-term memory neural network algorithm, support vector machine, random forest algorithm, etc. To improve the accuracy of load prediction, students have studied a prediction model in which signal processing is combined with a machine learning algorithm.
Empirical mode decomposition (Empirical Mode Decomposition, EMD) can convert non-stationary load data into stationary modal components, which are commonly used for data processing for load prediction, creating an emd+machine-learned load prediction model, a number of studies have demonstrated the effectiveness of this approach. However, in the EMD decomposition, the conventional decomposition method fails to fully embody the time series characteristics of the load data, resulting in deviation of the prediction result of the near zero energy consumption building. In the aspect of model application, few scholars research whether the prediction model provided by the model is suitable for prediction of multiple loads, the near-zero energy consumption building load has the particularity, the accurate prediction of the load is difficult to realize, and whether the traditional prediction method can be suitable for the near-zero energy consumption building is still to be discussed. Therefore, research on near zero energy consumption building multi-element load prediction is still required to be continuously carried out.
Disclosure of Invention
The invention aims to provide a method, a device, equipment and a medium for predicting a near-zero energy consumption building load, which are used for solving the problem that in the prior art, the traditional decomposition method cannot fully embody the time sequence characteristics of load data, so that the prediction result of the near-zero energy consumption building has deviation.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the invention provides a method for predicting building load with near zero energy consumption, which comprises the following steps:
acquiring real-time meteorological data of a near-zero energy consumption building;
acquiring a first prediction model, a second prediction model and a third prediction model which are trained in advance; the first prediction model is obtained by training historical meteorological data and high-frequency IMF components of historical load data corresponding to the historical meteorological data; the second prediction model is obtained by training the historical meteorological data and intermediate frequency IMF components of historical load data corresponding to the historical meteorological data; the third prediction model is obtained by training historical meteorological data and low-frequency IMF components of historical load data corresponding to the historical meteorological data;
inputting the real-time meteorological data into the first prediction model, the second prediction model and the third prediction model respectively, wherein the first prediction model, the second prediction model and the third prediction model output a high-frequency IMF component predicted value, a medium-frequency IMF component predicted value and a low-frequency IMF component predicted value respectively;
and overlapping and reconstructing the high-frequency IMF component predicted value, the medium-frequency IMF component predicted value and the low-frequency IMF component predicted value to obtain the near-zero energy consumption building load predicted value.
Further, in the step of obtaining the first prediction model, the second prediction model and the third prediction model which are trained in advance, the first prediction model, the second prediction model and the third prediction model are trained in the following manner:
acquiring historical meteorological data of a near-zero energy consumption building, and screening out characteristic parameters with correlation meeting preset standards from the historical meteorological data;
acquiring historical load data corresponding to historical meteorological data, and performing daily empirical mode decomposition on the historical load data to obtain a high-frequency IMF component, a medium-frequency IMF component and a low-frequency IMF component;
forming a first data set by the characteristic parameters and the high-frequency IMF component, and training a first prediction model by using the first data set;
forming a second data set by the characteristic parameters and the intermediate frequency IMF component, and training a second prediction model by using the second data set;
and forming the characteristic parameters and the low-frequency IMF component into a first safety data set, and training a third prediction model by using the third data set.
Further, obtaining historical load data corresponding to historical meteorological data, and performing daily empirical mode decomposition on the historical load data to obtain a high-frequency IMF component, a medium-frequency IMF component and a low-frequency IMF component, wherein the method comprises the following steps:
step 1), acquiring historical load data of a near zero energy consumption building time by time, and determining the days of the historical load data; intercepting historical load data day by day according to days, wherein the intercepted historical load data day by day is used as input data of the step 2);
step 2), determining the distribution of the maximum value and the minimum value of the input data, and determining an upper envelope line and a lower envelope line according to the distribution of the maximum value and the minimum value;
step 3), determining an average envelope according to the upper envelope and the lower envelope;
step 4), calculating an intermediate signal according to the daily intercepted historical load data and the average envelope curve, and judging whether the intermediate signal meets the IMF condition; if the intermediate signal meets the IMF condition, taking the intermediate signal as an IMF component, and turning to the step 5); if the intermediate signal does not meet the IMF condition, returning the intermediate signal as input data to the step 2) until the intermediate signal meets the IMF condition;
step 5), calculating residual errors according to the historical load data and the IMF components, and judging whether the residual errors meet residual error conditions or not; if the residual error does not meet the residual error condition, returning the residual error as input data to the step 2); if the residual meets the residual condition, completing empirical mode decomposition of the intercepted historical load data;
step 6), determining the acquisition sequence of each IMF component of the intercepted historical load data, and dividing each IMF component into a high-frequency daily IMF component, an intermediate-frequency daily IMF component and a low-frequency daily IMF component according to the sequence;
step 7), acquiring high-frequency daily IMF components, medium-frequency daily IMF components and low-frequency daily IMF components of all days, and respectively splicing the high-frequency daily IMF components, the medium-frequency daily IMF components and the low-frequency daily IMF components to obtain high-frequency IMF components, medium-frequency IMF components and low-frequency IMF components of historical load data.
Further, after the training of the first prediction model, the second prediction model and the third prediction model is completed, the method further includes:
based on a preset accuracy evaluation index, respectively evaluating the prediction accuracy of the first prediction model, the second prediction model and the third prediction model to obtain an evaluation result;
and optimizing the super parameters of the first prediction model, the second prediction model and the third prediction model according to the evaluation result.
Further, optimizing the super parameters of the first, second and third prediction models includes:
and optimizing the super parameters of the first prediction model, the second prediction model and the third prediction model by adopting an exhaustive search method.
Further, in the step of screening out the characteristic parameters with the correlation meeting the preset standard from the historical meteorological data, a pearson correlation coefficient method is adopted to screen out the characteristic parameters with the correlation meeting the preset standard from the historical meteorological data.
Further, the first prediction model, the second prediction model and the third prediction model adopt at least one of the following: a back propagation neural network model, a random forest model, and a support vector machine model.
In a second aspect of the present invention, there is provided a near zero energy consumption building load prediction apparatus comprising:
the data acquisition module is used for acquiring real-time meteorological data of the near-zero energy consumption building;
the model acquisition module is used for acquiring a first prediction model, a second prediction model and a third prediction model which are trained in advance; the first prediction model is obtained by training historical meteorological data and high-frequency IMF components of historical load data corresponding to the historical meteorological data; the second prediction model is obtained by training the historical meteorological data and intermediate frequency IMF components of historical load data corresponding to the historical meteorological data; the third prediction model is obtained by training historical meteorological data and low-frequency IMF components of historical load data corresponding to the historical meteorological data;
the data prediction module is used for inputting the real-time meteorological data into the first prediction model, the second prediction model and the third prediction model respectively, and the first prediction model, the second prediction model and the third prediction model output a high-frequency IMF component predicted value, a medium-frequency IMF component predicted value and a low-frequency IMF component predicted value respectively;
and the data reconstruction module is used for carrying out superposition reconstruction on the high-frequency IMF component predicted value, the medium-frequency IMF component predicted value and the low-frequency IMF component predicted value to obtain a near-zero energy consumption building load predicted value.
In a third aspect of the invention, an electronic device is provided, comprising a processor and a memory, the processor being configured to execute a computer program stored in the memory to implement a near zero energy consumption building load prediction method as described above.
In a fourth aspect of the present invention, there is provided a computer readable storage medium storing at least one instruction which when executed by a processor implements a near zero energy consumption building load prediction method as described above.
Compared with the prior art, the invention has the following beneficial effects:
1) According to the near zero energy consumption building load prediction method, real-time meteorological data are respectively input into a first prediction model, a second prediction model and a third prediction model, and the first prediction model, the second prediction model and the third prediction model respectively output a high-frequency IMF component prediction value, a medium-frequency IMF component prediction value and a low-frequency IMF component prediction value; overlapping and reconstructing the high-frequency IMF component predicted value, the intermediate-frequency IMF component predicted value and the low-frequency IMF component predicted value to obtain a near-zero energy consumption building load predicted value; the first prediction model is obtained by training high-frequency IMF components of historical load data corresponding to the historical meteorological data, the second prediction model is obtained by training medium-frequency IMF components of the historical load data corresponding to the historical meteorological data, and the third prediction model is obtained by training low-frequency IMF components of the historical load data corresponding to the historical meteorological data. The invention improves the traditional EMD method for decomposing all data, decomposes the load of the near zero energy consumption building day by day, considers the time sequence characteristics of the load, and has higher prediction precision and smaller deviation compared with the traditional prediction method. The near zero energy consumption building load prediction device, the electronic equipment and the computer readable storage medium provided by the invention also solve the problems in the background art.
2) According to the near-zero energy consumption building load prediction method, the pearson correlation coefficient method is adopted to analyze the correlations between different characteristic parameters and loads, so that the characteristic parameters for input are determined, the prediction dimension is reduced, and the operation efficiency is improved.
3) According to the near-zero energy consumption building load prediction method, the super-parameters of the model are optimized by adopting an exhaustive search method, and the prediction accuracy is further improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention. In the drawings:
FIG. 1 is a flow chart of a method for predicting building load with near zero energy consumption according to an embodiment of the invention;
FIG. 2 is a schematic diagram of annual cold load and heat load distribution of a near zero energy consumption building in an embodiment of the invention;
FIG. 3 is a graph showing the comparison of the prediction effect indexes before and after weather parameter screening by the pearson correlation coefficient method in the embodiment of the present invention;
FIG. 4 is a schematic diagram showing the decomposition effect of the conventional decomposition method in which the cold load is not decomposed by day;
FIG. 5 is a schematic diagram showing the decomposition effect of the cold load according to day decomposition in the embodiment of the present invention;
FIG. 6 is a schematic view showing the decomposition effect of the conventional decomposition method in which the thermal load is not decomposed by day;
FIG. 7 is a schematic view showing the decomposition effect of the thermal load according to the day decomposition in the embodiment of the present invention;
FIG. 8 is a graph showing the predicted result of the cooling load under different decomposition conditions according to the embodiment of the present invention;
FIG. 9 is a graph showing the distribution of the heat load prediction results under different decomposition conditions according to the embodiment of the present invention;
FIG. 10 is a graph showing the distribution of the predicted result and the actual value of the cooling load and the heat load after exhaustive optimization in the embodiment of the invention;
FIG. 11 is a block diagram of a near zero energy consumption building load prediction apparatus according to an embodiment of the present invention;
fig. 12 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The invention will be described in detail below with reference to the drawings in connection with embodiments. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other.
The following detailed description is exemplary and is intended to provide further details of the invention. Unless defined otherwise, all technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the invention.
Example 1
As shown in fig. 1, a method for predicting building load with near zero energy consumption comprises the following steps:
s1, acquiring real-time meteorological data of a near-zero energy consumption building.
S2, acquiring a first prediction model, a second prediction model and a third prediction model which are trained in advance; the first prediction model is obtained by training historical meteorological data and high-frequency IMF components of historical load data corresponding to the historical meteorological data; the second prediction model is obtained by training the historical meteorological data and intermediate frequency IMF components of historical load data corresponding to the historical meteorological data; the third prediction model is obtained by training historical meteorological data and low-frequency IMF components of historical load data corresponding to the historical meteorological data; the low-frequency IMF component, the medium-frequency IMF component and the high-frequency IMF component are obtained by decomposing and reconstructing historical load data day by day.
S3, inputting the real-time meteorological data into the first prediction model, the second prediction model and the third prediction model respectively, and outputting a high-frequency IMF component predicted value, a medium-frequency IMF component predicted value and a low-frequency IMF component predicted value by the first prediction model, the second prediction model and the third prediction model respectively.
And S4, overlapping and reconstructing the high-frequency IMF component predicted value, the medium-frequency IMF component predicted value and the low-frequency IMF component predicted value to obtain the near-zero energy consumption building load predicted value.
The scheme provides different prediction models, the prediction models are decomposed day by near zero energy consumption building loads, and the time sequence characteristics of the loads are considered.
As a specific embodiment, the present invention further provides a method for predicting a building load with near zero energy consumption, including the following steps:
s10, acquiring real-time meteorological data of a near-zero energy consumption building.
It can be understood that the real-time meteorological data obtained in the step is used for predicting the load of the near-zero energy consumption building, and the types of the meteorological data are consistent with the types of training data of the prediction model.
S20, acquiring a first prediction model, a second prediction model and a third prediction model which are trained in advance; the first prediction model is obtained by training historical meteorological data and high-frequency IMF components of historical load data corresponding to the historical meteorological data; the second prediction model is obtained by training the historical meteorological data and intermediate frequency IMF components of historical load data corresponding to the historical meteorological data; the third prediction model is obtained by training historical meteorological data and low-frequency IMF components of historical load data corresponding to the historical meteorological data; the low-frequency IMF component, the medium-frequency IMF component and the high-frequency IMF component are obtained by decomposing and reconstructing historical load data day by day.
As an alternative embodiment, the first, second and third prediction models employ at least one of: a back propagation neural network model, a random forest model, and a support vector machine model.
It should be noted that, the first prediction model, the second prediction model, and the third prediction model provided in the present solution may be one or more of a back propagation neural network model, a random forest model, and a support vector machine model.
As an example, the first predictive model is a back propagation neural network model, the second predictive model is a random forest model, and the third predictive model is a support vector machine model. The first prediction model, the second prediction model and the third prediction model can also all adopt random forest models.
As an alternative embodiment, the first, second and third prediction models may be trained as follows:
s201, acquiring historical meteorological data of a near-zero energy consumption building, and screening out characteristic parameters with correlation meeting preset standards from the historical meteorological data.
It should be noted that the building load with near zero energy consumption is affected by various meteorological parameters, including temperature, radiation, humidity, wind speed, etc., however, too many meteorological parameters as input features of prediction will result in very complex prediction process, increased calculation difficulty and poor accuracy of the final prediction result. In order to solve the problem, the scheme analyzes the correlation between the meteorological parameters and the building load, removes the meteorological parameters with lower correlation with the building load, reduces the prediction dimension, and improves the prediction accuracy. The calculation result of the pearson correlation coefficient is in a section (-1, 1), the absolute value is closer to 1, the linear correlation is higher, and the weather parameter with higher correlation is selected as a characteristic parameter of near zero energy consumption building load prediction according to the calculation result.
As an optional embodiment, in step S201, a pearson correlation coefficient method may be used to screen out feature parameters whose correlation meets a preset standard from the historical meteorological data.
Specifically, the pearson correlation coefficient method is adopted to screen out characteristic parameters with correlation meeting preset standards from the historical meteorological data, and the method comprises the following steps:
step 11: converting historical load data and historical meteorological data of the near-zero energy consumption building into an m× (n+1) matrix;
where m is the number of historical load data, and n is the number of influencing factors (i.e. meteorological parameters). In the m× (n+1) matrix, each row represents the weather parameter and load data recorded at each time, the first n columns represent the weather parameter, such as temperature, humidity, radiation, etc., and the n+1 th columns represent the load data.
Step 12: calculating a correlation coefficient;
it can be understood that the pearson correlation coefficient is used to measure the linear correlation strength between the variables, the calculation result is an important basis for the load prediction input feature, and when the absolute value of the correlation coefficient is smaller than 0.3, the correlation between the two is considered to be weaker.
Therefore, in the scheme, whether the absolute value is smaller than 0.3 is taken as a preset standard, the characteristic parameters with low correlation are deleted, and the prediction dimension is reduced.
For example, the pearson correlation coefficient [ ]R) The calculation formula is as follows:
in the method, in the process of the invention,a single-column matrix formed by characteristic parameters; />Is the average value of the characteristic parameters; />A single column matrix for the payload data, +.>N is the total number of characteristic parameters, which is the average value of the load data.
Based on the calculation formula of the pearson correlation coefficient, a pearson correlation coefficient matrix R= [ R1, R2, …, rn,1] is calculated, wherein R is a 1× (n+1) matrix, R1, R2, … and rn respectively represent the correlation coefficients of the characteristic parameters and are between (-1, 1), and the correlation degree of each meteorological parameter and the building load is represented; the last column value is the autocorrelation coefficient of the building load, which is constant at 1.
S202, acquiring historical load data corresponding to historical meteorological data, and performing daily empirical mode decomposition on the historical load data to obtain a high-frequency IMF component, an intermediate-frequency IMF component and a low-frequency IMF component.
The step S202 specifically includes:
step 1), acquiring historical load data of a near zero energy consumption building time by time, and determining the days of the historical load data; and intercepting the historical load data day by day according to the days, wherein the intercepted historical load data day by day is used as the input data of the step 2).
As an example, the data length of the history load data is L, and since the history load data is time-by-time, the number of days of the history load data can be determined using L/24.
Step 2), determining the maximum value and minimum value distribution of the input data, and determining an upper envelope line and a lower envelope line according to the maximum value and the minimum value distribution.
Step 3), determining an average envelope according to the upper envelope and the lower envelope.
As an example, the average envelope is determined as follows:
wherein,m(t) Is the average envelope curve;e max (t) As the upper envelope of the envelope curve,e min (t) Is the lower envelope.
Step 4), calculating an intermediate signal according to the daily intercepted historical load data and the average envelope curve, and judging whether the intermediate signal meets the IMF condition; if the intermediate signal meets the IMF condition, taking the intermediate signal as an IMF component, and turning to the step 5); if the intermediate signal does not meet the IMF condition, the intermediate signal is returned to step 2) as input data until the intermediate signal meets the IMF condition.
As an example, the intermediate signal is calculated according to the following equation:
wherein,is an intermediate signal; />Is historical load data; />Is the average envelope.
Step 5), calculating residual errors according to the historical load data and the IMF components, and judging whether the residual errors meet residual error conditions or not; if the residual error does not meet the residual error condition, returning the residual error as input data to the step 2); and if the residual error meets the residual error condition, finishing empirical mode decomposition of the intercepted historical load data.
As an example, the residual is calculated as follows:
wherein,is residual; />Is an intermediate signal; />Is historical load data.
Thus, as can be seen from the EMD decomposition process, the historical load data is finally decomposedx(t) Can be expressed as:
wherein,kis the number of IMF components.
Step 6), determining the acquisition sequence of each IMF component of the intercepted historical load data, and dividing each IMF component into a high-frequency daily IMF component, an intermediate-frequency daily IMF component and a low-frequency daily IMF component according to the sequence.
Step 7), acquiring high-frequency daily IMF components, medium-frequency daily IMF components and low-frequency daily IMF components of all days, and respectively splicing the high-frequency daily IMF components, the medium-frequency daily IMF components and the low-frequency daily IMF components to obtain high-frequency IMF components, medium-frequency IMF components and low-frequency IMF components of historical load data.
In this scheme, the historical load data for one day is set to include three IMF components.
It should be noted that, compared with a general building, the load of the near zero energy consumption building has its own characteristics such as a small total load amount, a small fluctuation with temperature change, and the like. The EMD decomposition has excellent performance in the aspect of processing nonlinear and non-stationary signals, can perform signal decomposition according to the characteristics of the data without a preset basis function, has smaller correlation among all components obtained after the EMD decomposition, and has different time sequence characteristics. The innovation point of the method is that a method for decomposing the building load according to the day is provided, the decomposition process is refined, the time scale characteristics of the building load in the unit of the day are fully embodied, and the reliability of load prediction is improved.
S203, forming the characteristic parameters and the high-frequency IMF components into a first data set, and training a first prediction model by using the first data set; forming a second data set by the characteristic parameters and the intermediate frequency IMF component, and training a second prediction model by using the second data set; and forming the characteristic parameters and the low-frequency IMF component into a first safety data set, and training a third prediction model by using the third data set.
Specifically, after the first data set, the second data set and the third data set are obtained, in the process of training a model, the three data sets are respectively divided into a training set and a testing set, the training set is used for training the model, a black box decision mechanism between input characteristics and building loads is established, and the testing set is used for verifying the accuracy of the decision mechanism.
In a preferred embodiment, after the training of the first prediction model, the second prediction model and the third prediction model is completed, the method further comprises: based on a preset accuracy evaluation index, respectively evaluating the prediction accuracy of the first prediction model, the second prediction model and the third prediction model to obtain an evaluation result; and optimizing the super parameters of the first prediction model, the second prediction model and the third prediction model according to the evaluation result.
As an example, the accuracy evaluation index may include: determining coefficientsR 2 Root mean square errorRMSEAverage absolute errorMAEPercentage of mean absolute errorMAPEEtc.
Wherein the coefficient is determinedR 2 Reflects the goodness of fit of the predicted value and the true value, and the closer to 1, the prediction is explainedThe more accurate the result. Average absolute error percentageMAPEThe closer to 0, the better the prediction effect is explained. Root mean square errorRMSEAbsolute error from averageMAEThe smaller the value, the higher the prediction result accuracy.
As an example:
root mean square errorRMSEExpressed as:
determining coefficientsR 2 Expressed as:
average absolute errorMAEExpressed as:
average absolute error percentageMAPEExpressed as:
in the method, in the process of the invention,for predictive value +.>To be a true value of the value,ndata number>Is the average of the true values.
As an alternative embodiment, the first prediction model, the second prediction model and the third prediction model are optimized by adopting an exhaustive search method and other modes.
S30, inputting the real-time meteorological data into the first prediction model, the second prediction model and the third prediction model respectively, and outputting a high-frequency IMF component predicted value, a medium-frequency IMF component predicted value and a low-frequency IMF component predicted value by the first prediction model, the second prediction model and the third prediction model respectively.
And S40, overlapping and reconstructing the high-frequency IMF component predicted value, the medium-frequency IMF component predicted value and the low-frequency IMF component predicted value to obtain the near-zero energy consumption building load predicted value.
As an example, the effect of the present solution applied to some near zero energy consumption building load prediction case is shown in fig. 2 to 10.
FIG. 2 shows the annual cold and heat load distribution of a near zero energy consumption building, which has a certain load distribution in transitional seasons in addition to summer and winter;
FIG. 3 shows prediction effect indexes before and after weather parameter screening by the Pearson correlation coefficient method, and shows that the RMSE of the cold load and the hot load prediction results after screening is reduced, which indicates that the prediction precision is improved;
FIG. 4 illustrates decomposition components of a cooling load under a conventional decomposition method; FIG. 5 shows the decomposition components of the cold load under the decomposition per day method;
FIG. 6 illustrates decomposition components of a thermal load under a conventional decomposition method; FIG. 7 illustrates the decomposition components of the thermal load under the decomposition per day method;
FIG. 8 is a graph showing the distribution of the predicted result and the true value of the cold load under the conditions of decomposition by the day and the traditional decomposition without the day, and the fitting effect of the predicted result and the true value distribution under the conditions of decomposition by the day can be found to be better;
FIG. 9 is a graph showing the distribution of the predicted result and the true value of the thermal load under the conditions of decomposition by the day and the traditional decomposition without the day, and the fitting effect of the predicted result and the true value distribution under the conditions of decomposition by the day can be found to be better;
fig. 10 shows the distribution of the predicted results and the true values of the cold load and the hot load after the initial parameters are optimized by the exhaustive search method, so that the fitting effect of the predicted results and the true value curves after the optimization by the exhaustive search method is further improved, which illustrates that the precision of the predicted results is effectively improved by the exhaustive search method.
Example 2
As shown in fig. 11, based on the same inventive concept as the above embodiment, the present invention also provides a near zero energy consumption building load prediction apparatus, comprising:
the data acquisition module is used for acquiring real-time meteorological data of the near-zero energy consumption building;
the model acquisition module is used for acquiring a first prediction model, a second prediction model and a third prediction model which are trained in advance; the first prediction model is obtained by training historical meteorological data and high-frequency IMF components of historical load data corresponding to the historical meteorological data; the second prediction model is obtained by training the historical meteorological data and intermediate frequency IMF components of historical load data corresponding to the historical meteorological data; the third prediction model is obtained by training historical meteorological data and low-frequency IMF components of historical load data corresponding to the historical meteorological data;
the data prediction module is used for inputting the real-time meteorological data into the first prediction model, the second prediction model and the third prediction model respectively, and the first prediction model, the second prediction model and the third prediction model output a high-frequency IMF component predicted value, a medium-frequency IMF component predicted value and a low-frequency IMF component predicted value respectively;
and the data reconstruction module is used for carrying out superposition reconstruction on the high-frequency IMF component predicted value, the medium-frequency IMF component predicted value and the low-frequency IMF component predicted value to obtain a near-zero energy consumption building load predicted value.
Example 3
As shown in fig. 12, the present invention further provides an electronic device 100 for implementing the method for predicting a near zero energy consumption building load according to the above embodiment; the electronic device 100 comprises a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.
The memory 101 may be used to store a computer program 103 and the processor 102 implements a near zero energy consumption building load prediction method step of embodiment 1 by running or executing the computer program stored in the memory 101 and invoking data stored in the memory 101.
The memory 101 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data) created according to the use of the electronic device 100, and the like. In addition, the memory 101 may include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card), at least one disk storage device, a Flash memory device, or other non-volatile solid state storage device.
The at least one processor 102 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The processor 102 may be a microprocessor or the processor 102 may be any conventional processor or the like, the processor 102 being a control center of the electronic device 100, the various interfaces and lines being utilized to connect various portions of the overall electronic device 100.
The memory 101 in the electronic device 100 stores a plurality of instructions to implement a near zero energy consumption building load prediction method, the processor 102 being executable to implement:
acquiring real-time meteorological data of a near-zero energy consumption building;
acquiring a first prediction model, a second prediction model and a third prediction model which are trained in advance; the first prediction model is obtained by training historical meteorological data and high-frequency IMF components of historical load data corresponding to the historical meteorological data; the second prediction model is obtained by training the historical meteorological data and intermediate frequency IMF components of historical load data corresponding to the historical meteorological data; the third prediction model is obtained by training historical meteorological data and low-frequency IMF components of historical load data corresponding to the historical meteorological data;
inputting the real-time meteorological data into the first prediction model, the second prediction model and the third prediction model respectively, wherein the first prediction model, the second prediction model and the third prediction model output a high-frequency IMF component predicted value, a medium-frequency IMF component predicted value and a low-frequency IMF component predicted value respectively;
and overlapping and reconstructing the high-frequency IMF component predicted value, the medium-frequency IMF component predicted value and the low-frequency IMF component predicted value to obtain the near-zero energy consumption building load predicted value.
Example 4
The modules/units integrated with the electronic device 100 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as a stand alone product. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the steps of each method embodiment described above may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, and a Read-Only Memory (ROM).
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (10)
1. The method for predicting the building load with near zero energy consumption is characterized by comprising the following steps:
acquiring real-time meteorological data of a near-zero energy consumption building;
acquiring a first prediction model, a second prediction model and a third prediction model which are trained in advance; the first prediction model is obtained by training historical meteorological data and high-frequency IMF components of historical load data corresponding to the historical meteorological data; the second prediction model is obtained by training the historical meteorological data and intermediate frequency IMF components of historical load data corresponding to the historical meteorological data; the third prediction model is obtained by training historical meteorological data and low-frequency IMF components of historical load data corresponding to the historical meteorological data;
inputting the real-time meteorological data into the first prediction model, the second prediction model and the third prediction model respectively, wherein the first prediction model, the second prediction model and the third prediction model output a high-frequency IMF component predicted value, a medium-frequency IMF component predicted value and a low-frequency IMF component predicted value respectively;
and overlapping and reconstructing the high-frequency IMF component predicted value, the medium-frequency IMF component predicted value and the low-frequency IMF component predicted value to obtain the near-zero energy consumption building load predicted value.
2. The near zero energy consumption building load prediction method according to claim 1, wherein in the step of obtaining a first prediction model, a second prediction model and a third prediction model trained in advance, the first prediction model, the second prediction model and the third prediction model are trained as follows:
acquiring historical meteorological data of a near-zero energy consumption building, and screening out characteristic parameters with correlation meeting preset standards from the historical meteorological data;
acquiring historical load data corresponding to historical meteorological data, and performing daily empirical mode decomposition on the historical load data to obtain a high-frequency IMF component, a medium-frequency IMF component and a low-frequency IMF component;
forming a first data set by the characteristic parameters and the high-frequency IMF component, and training a first prediction model by using the first data set;
forming a second data set by the characteristic parameters and the intermediate frequency IMF component, and training a second prediction model by using the second data set;
and forming the characteristic parameters and the low-frequency IMF component into a first safety data set, and training a third prediction model by using the third data set.
3. The near zero energy consumption building load prediction method according to claim 2, wherein obtaining historical load data corresponding to historical meteorological data, and performing daily empirical mode decomposition on the historical load data to obtain a high-frequency IMF component, a medium-frequency IMF component and a low-frequency IMF component, comprises:
step 1), acquiring historical load data of a near zero energy consumption building time by time, and determining the days of the historical load data; intercepting historical load data day by day according to days, wherein the intercepted historical load data day by day is used as input data of the step 2);
step 2), determining the distribution of the maximum value and the minimum value of the input data, and determining an upper envelope line and a lower envelope line according to the distribution of the maximum value and the minimum value;
step 3), determining an average envelope according to the upper envelope and the lower envelope;
step 4), calculating an intermediate signal according to the daily intercepted historical load data and the average envelope curve, and judging whether the intermediate signal meets the IMF condition; if the intermediate signal meets the IMF condition, taking the intermediate signal as an IMF component, and turning to the step 5); if the intermediate signal does not meet the IMF condition, returning the intermediate signal as input data to the step 2) until the intermediate signal meets the IMF condition;
step 5), calculating residual errors according to the historical load data and the IMF components, and judging whether the residual errors meet residual error conditions or not; if the residual error does not meet the residual error condition, returning the residual error as input data to the step 2); if the residual meets the residual condition, completing empirical mode decomposition of the intercepted historical load data;
step 6), determining the acquisition sequence of each IMF component of the intercepted historical load data, and dividing each IMF component into a high-frequency daily IMF component, an intermediate-frequency daily IMF component and a low-frequency daily IMF component according to the sequence;
step 7), acquiring high-frequency daily IMF components, medium-frequency daily IMF components and low-frequency daily IMF components of all days, and respectively splicing the high-frequency daily IMF components, the medium-frequency daily IMF components and the low-frequency daily IMF components to obtain high-frequency IMF components, medium-frequency IMF components and low-frequency IMF components of historical load data.
4. The near zero energy building load prediction method of claim 2, wherein after the first, second and third prediction models are trained, further comprising:
based on a preset accuracy evaluation index, respectively evaluating the prediction accuracy of the first prediction model, the second prediction model and the third prediction model to obtain an evaluation result;
and optimizing the super parameters of the first prediction model, the second prediction model and the third prediction model according to the evaluation result.
5. The near zero energy building load prediction method of claim 4, wherein the super-parametric optimization of the first, second, and third prediction models comprises:
and optimizing the super parameters of the first prediction model, the second prediction model and the third prediction model by adopting an exhaustive search method.
6. The near zero energy consumption building load prediction method according to claim 2, wherein in the step of screening out characteristic parameters with correlation satisfying a preset standard from the historical meteorological data, a pearson correlation coefficient method is adopted to screen out characteristic parameters with correlation satisfying the preset standard from the historical meteorological data.
7. The near zero energy building load prediction method of claim 1, wherein the first, second and third prediction models employ at least one of: a back propagation neural network model, a random forest model, and a support vector machine model.
8. A near zero energy consumption building load prediction device, comprising:
the data acquisition module is used for acquiring real-time meteorological data of the near-zero energy consumption building;
the model acquisition module is used for acquiring a first prediction model, a second prediction model and a third prediction model which are trained in advance; the first prediction model is obtained by training historical meteorological data and high-frequency IMF components of historical load data corresponding to the historical meteorological data; the second prediction model is obtained by training the historical meteorological data and intermediate frequency IMF components of historical load data corresponding to the historical meteorological data; the third prediction model is obtained by training historical meteorological data and low-frequency IMF components of historical load data corresponding to the historical meteorological data;
the data prediction module is used for inputting the real-time meteorological data into the first prediction model, the second prediction model and the third prediction model respectively, and the first prediction model, the second prediction model and the third prediction model output a high-frequency IMF component predicted value, a medium-frequency IMF component predicted value and a low-frequency IMF component predicted value respectively;
and the data reconstruction module is used for carrying out superposition reconstruction on the high-frequency IMF component predicted value, the medium-frequency IMF component predicted value and the low-frequency IMF component predicted value to obtain a near-zero energy consumption building load predicted value.
9. An electronic device comprising a processor and a memory, the processor configured to execute a computer program stored in the memory to implement the near zero energy consumption building load prediction method of any one of claims 1 to 7.
10. A computer readable storage medium storing at least one instruction that when executed by a processor implements the near zero energy consumption building load prediction method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410263360.4A CN117852928B (en) | 2024-03-08 | Near zero energy consumption building load prediction method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410263360.4A CN117852928B (en) | 2024-03-08 | Near zero energy consumption building load prediction method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117852928A true CN117852928A (en) | 2024-04-09 |
| CN117852928B CN117852928B (en) | 2024-06-04 |
Family
ID=
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112488415A (en) * | 2020-12-14 | 2021-03-12 | 国网江苏省电力有限公司经济技术研究院 | Power load prediction method based on empirical mode decomposition and long-and-short-term memory network |
| US20210296897A1 (en) * | 2019-11-27 | 2021-09-23 | Robert F. Cruickshank, III | System method and apparatus for providing a load shape signal for power networks |
| CN113486433A (en) * | 2020-12-31 | 2021-10-08 | 上海东方低碳科技产业股份有限公司 | Method for calculating energy consumption shortage number of net zero energy consumption building and filling system |
| WO2021213192A1 (en) * | 2020-04-22 | 2021-10-28 | 国网江苏省电力有限公司苏州供电分公司 | Load prediction method and load prediction system employing general distribution |
| CN114036850A (en) * | 2021-11-16 | 2022-02-11 | 南昌工程学院 | Runoff prediction method based on VECGM |
| CN114037142A (en) * | 2021-11-04 | 2022-02-11 | 建科环能科技有限公司 | Near-zero energy consumption community cold and hot load prediction method |
| CN115169232A (en) * | 2022-07-11 | 2022-10-11 | 山东科技大学 | Daily peak load prediction method, computer equipment and readable storage medium |
| CN116663744A (en) * | 2023-06-20 | 2023-08-29 | 宁夏中昊银晨能源技术服务有限公司 | Energy consumption prediction method and system for near-zero energy consumption building |
| CN116865248A (en) * | 2023-06-29 | 2023-10-10 | 许继电气股份有限公司 | Ultra-short-term wind power prediction method and electronic equipment |
| CN117543544A (en) * | 2023-10-31 | 2024-02-09 | 国网浙江省电力有限公司杭州供电公司 | Load prediction method, device, equipment and storage medium |
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210296897A1 (en) * | 2019-11-27 | 2021-09-23 | Robert F. Cruickshank, III | System method and apparatus for providing a load shape signal for power networks |
| WO2021213192A1 (en) * | 2020-04-22 | 2021-10-28 | 国网江苏省电力有限公司苏州供电分公司 | Load prediction method and load prediction system employing general distribution |
| CN112488415A (en) * | 2020-12-14 | 2021-03-12 | 国网江苏省电力有限公司经济技术研究院 | Power load prediction method based on empirical mode decomposition and long-and-short-term memory network |
| CN113486433A (en) * | 2020-12-31 | 2021-10-08 | 上海东方低碳科技产业股份有限公司 | Method for calculating energy consumption shortage number of net zero energy consumption building and filling system |
| CN114037142A (en) * | 2021-11-04 | 2022-02-11 | 建科环能科技有限公司 | Near-zero energy consumption community cold and hot load prediction method |
| CN114036850A (en) * | 2021-11-16 | 2022-02-11 | 南昌工程学院 | Runoff prediction method based on VECGM |
| CN115169232A (en) * | 2022-07-11 | 2022-10-11 | 山东科技大学 | Daily peak load prediction method, computer equipment and readable storage medium |
| CN116663744A (en) * | 2023-06-20 | 2023-08-29 | 宁夏中昊银晨能源技术服务有限公司 | Energy consumption prediction method and system for near-zero energy consumption building |
| CN116865248A (en) * | 2023-06-29 | 2023-10-10 | 许继电气股份有限公司 | Ultra-short-term wind power prediction method and electronic equipment |
| CN117543544A (en) * | 2023-10-31 | 2024-02-09 | 国网浙江省电力有限公司杭州供电公司 | Load prediction method, device, equipment and storage medium |
Non-Patent Citations (4)
| Title |
|---|
| 于群等: "基于EEMD和BP神经网络的短期光伏功率预测模型", 《电网与清洁能源》, vol. 32, no. 07, 25 July 2016 (2016-07-25), pages 136 - 141 * |
| 刘达等: "基于EEMD和随机森林的月度负荷预测", 《智慧电力》, vol. 46, no. 06, 31 December 2018 (2018-12-31), pages 12 - 18 * |
| 周晖等: "基于多时段气象数据判断相似日的日负荷曲线预测研究", 《继电器》, vol. 33, no. 23, 1 December 2005 (2005-12-01), pages 41 - 45 * |
| 祝志慧等: "基于EMD和SVM的短期负荷预测", 《高电压技术》, vol. 33, no. 05, 31 May 2007 (2007-05-31), pages 118 - 122 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Farias et al. | An approximate dynamic programming approach to solving dynamic oligopoly models | |
| DE112021004908T5 (en) | COMPUTER-BASED SYSTEMS, COMPUTATION COMPONENTS AND COMPUTATION OBJECTS SET UP TO IMPLEMENT DYNAMIC OUTLIVER DISTORTION REDUCTION IN MACHINE LEARNING MODELS | |
| CN111680841B (en) | Short-term load prediction method, system and terminal equipment based on principal component analysis | |
| US20200356865A1 (en) | System and method for decision-making using a weighted comparison | |
| Imsland et al. | Robust triple mode MPC | |
| Borrajo et al. | A complex case-based advisor | |
| Darvishan et al. | Unit commitment-based load uncertainties based on improved particle swarm optimisation | |
| Urraca et al. | Improving hotel room demand forecasting with a hybrid GA-SVR methodology based on skewed data transformation, feature selection and parsimony tuning | |
| Sun et al. | Condition-based maintenance for the offshore wind turbine based on long short-term memory network | |
| De Livera | Automatic forecasting with a modified exponential smoothing state space framework | |
| Zhang et al. | Prediction method of line loss rate in low‐voltage distribution network based on multi‐dimensional information matrix and dimensional attention mechanism‐long‐and short‐term time‐series network | |
| CN117852928B (en) | Near zero energy consumption building load prediction method, device, equipment and medium | |
| US20160189026A1 (en) | Running Time Prediction Algorithm for WAND Queries | |
| CN117852928A (en) | Near zero energy consumption building load prediction method, device, equipment and medium | |
| CN116933037A (en) | Photovoltaic output prediction method based on multi-model fusion and related device | |
| Su et al. | Multi-state reliability assessment for hydraulic lifting system based on the theory of dynamic Bayesian networks | |
| Sun et al. | Predicting cooling loads for the next 24 hours based on general regression neural network: methods and results | |
| CN115619449A (en) | Deep learning model-based fertilizer price prediction method, device and storage medium | |
| CN114638405A (en) | Energy demand prediction method and device and computer equipment | |
| CN114970357A (en) | Energy-saving effect evaluation method, system, device and storage medium | |
| CN113705929A (en) | Spring festival holiday load prediction method based on load characteristic curve and typical characteristic value fusion | |
| Li et al. | Deep intelligence-driven efficient forecasting for the agriculture economy of computational social systems | |
| CN112561186A (en) | Short-term power load prediction method | |
| CN113449904A (en) | Multi-energy load prediction method, device and equipment | |
| Aalto et al. | Achieving a smooth flow of fuel deliveries by truck to an urban biomass power plant in Helsinki, Finland–an agent-based simulation approach |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |