Virtual power plant multi-element load aggregation adjustable potential index prediction method

Abstract

The invention discloses a virtual power plant multi-element load aggregation adjustable potential index prediction method, and belongs to the technical field of virtual power plant multi-element load aggregation. According to the method, predicted values of all parameters at the next moment are calculated by measuring the total photovoltaic output of a virtual power plant, the charge state of an electricity storage system, the total charging power of an electric vehicle, the total electric power of an electric smelting furnace for magnesia, the molten pool temperature of the electric smelting furnace for magnesia and the illumination intensity; and accurately predicting the multi-element load aggregation adjustable potential index of the virtual power plant at the next moment. According to the method, the photovoltaic output of the virtual power plant can be adjusted according to the index prediction value, so that the photovoltaic consumption level of the virtual power plant is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of virtual power plant multi-load aggregation, and in particular relates to a method for predicting an adjustable potential index of virtual power plant multi-load aggregation. Background Art

[0002] As a new generation of intelligent control technology that aggregates resources in multiple links of "source-load-storage", virtual power plant technology can break geographical restrictions and realize energy interconnection and sharing in a wide area. Virtual power plants based on multi-load aggregation can realize the participation of virtual power plants in peak load regulation and frequency regulation under the premise of ensuring user energy consumption by aggregating multiple types of loads and accurately regulating and controlling the controllable resources after aggregation. However, the characteristics of multi-loads are complex, and the multi-load aggregation process is easily disturbed by various factors such as the natural environment, resulting in the load aggregation results being unable to meet the power regulation requirements, ultimately reducing the regulation accuracy of virtual power plants and reducing the reliability of virtual power plants. Accurate prediction of the adjustable potential index of multi-load aggregation of virtual power plants can improve the reliability of virtual power plants in participating in peak load regulation and frequency regulation, and improve the operating income of virtual power plants under market conditions.

[0003] Therefore, a new technical solution is urgently needed in the prior art to solve this problem. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method for predicting the adjustable potential index of multiple load aggregation of a virtual power plant, which is used to solve the problem in the prior art that due to the complex characteristics of multiple loads, the multiple load aggregation process is easily disturbed by various factors such as the natural environment, resulting in inaccurate load aggregation results.

[0005] The technical solution adopted by the present invention is to provide a method for predicting the adjustable potential index of multiple load aggregation of a virtual power plant, comprising the following steps:

[0006] Step 1: Establish the time series of the measured values ​​of the adjustable potential index parameters of the virtual power plant multi-load aggregation;

[0007] Step 2: Normalization of measurement data;

[0008] Step 3: Calculate the predicted value of the real-time data of the virtual power plant at the next moment in the future;

[0009] Step 4: Calculate the predicted value of the virtual power plant multi-load aggregation adjustable potential index at the next moment in the future.

[0010] The parameters in step 1 include the total photovoltaic output of the virtual power plant, the charge state of the power storage system, the total charging power of the electric vehicle, the total power consumption of the fused magnesium furnace, the molten pool temperature of the fused magnesium furnace, and the light intensity. 1 ,tm 2,…,tm k ,…tm n , n is a natural number, k is a natural number, and k={1,2,…,n}, the time series of measuring the total photovoltaic output of the virtual power plant, the charge state of the power storage system, the total charging power of electric vehicles, the total power consumption of the electric fused magnesium furnace, the temperature of the molten magnesium furnace, and the light intensity are:

[0011]

[0012] In the formula, For tm k The measured value of the total photovoltaic output of the virtual power plant at the moment, For tm k The measured value of the charge state of the energy storage system at any moment, For tm k The measured value of the total charging power of the electric vehicle at the moment, For tm k The measured value of the total power consumption of the electric magnesium furnace at the moment, For tm k The measured value of the molten pool temperature of the electric magnesium furnace at the moment, For tm k The measured value of light intensity at a given moment.

[0013] The specific method of normalization processing in step 2 is:

[0014] The data obtained from each measurement are normalized according to the following formula to obtain the normalized value of the total photovoltaic output of the virtual power plant. Normalized value of the measured value of the state of charge of the power storage system Normalized value of the measured value of the total charging power of the electric vehicle Normalized value of the total power consumption of the fused magnesium furnace Normalized value of measured value of molten pool temperature in electric magnesium furnace Normalized value of the measured value of light intensity The expression is:

[0015]

[0016] Where P PV,max , P PV,min They are the total photovoltaic output of the virtual power plant at n fixed time intervals tm 1 ,tm 2 ,…,tm k ,…tm n Maximum and minimum values ​​of the measured values ​​at the moment, SOC ES,max , SOC ES,min They are respectively the charge state of the energy storage system at n fixed time intervals tm 1,tm 2 ,…,tm k ,…tm n The maximum and minimum values ​​of the measured values ​​at the moment, P EV,max , P EV,min are the total charging power of electric vehicles at n fixed time intervals tm 1 ,tm 2 ,…,tm k ,…tm n The maximum and minimum values ​​of the measured values ​​at the moment, P MEF,max , P MEF,min The total power consumption of the fused magnesium furnace at n fixed time intervals tm 1 ,tm 2 ,…,tm k ,…tm n The maximum and minimum values ​​of the measured values ​​at the moment, T MEF,max , T MEF,min They are respectively the molten pool temperature of the fused magnesium furnace at n fixed time intervals tm 1 ,tm 2 ,…,tm k ,…tm n The maximum and minimum values ​​of the measured values ​​at the moment, LI max , LI min are the light intensity at n fixed time intervals tm 1 ,tm 2 ,…,tm k ,…tm n The maximum and minimum values ​​measured at that moment.

[0017] In step 3, the next moment tm is calculated n+1 Normalized value of the total photovoltaic output forecast of the virtual power plant Normalized value of charge state prediction of power storage system Normalized value of total charging power prediction for electric vehicles Normalized value of total power consumption prediction of fused magnesium furnace Normalized value of molten pool temperature prediction in fused magnesium furnace Normalized value of light intensity prediction The expression is:

[0018]

[0019] In step 4, the next moment tm is calculated n+1 Virtual power plant multi-load aggregation adjustable potential index The expression is:

[0020]

[0021] The calculated adjustable potential index of multiple load aggregation of virtual power plant at the next moment in the future This indicates that the virtual power plant has strong multi-load regulation capability and can appropriately increase photovoltaic output; the calculated multi-load aggregation adjustable potential index of the virtual power plant at the next moment in the future is This indicates that the virtual power plant has a moderate multi-load regulation capability and can maintain photovoltaic output. The calculated multi-load aggregation adjustable potential index of the virtual power plant at the next moment in the future is This means that the virtual power plant’s ability to regulate multiple loads is weak, which can reduce photovoltaic output.

[0022] Through the above design scheme, the present invention can bring the following beneficial effects:

[0023] By measuring the total photovoltaic output of the virtual power plant, the state of charge of the power storage system, the total charging power of electric vehicles, the total power consumption of the fused magnesium furnace, the temperature of the molten magnesium furnace, and the light intensity, the predicted values ​​of each parameter at the next moment are calculated, and then the virtual power plant multi-load aggregation adjustable potential index at the next moment is accurately predicted. According to the size of the index prediction value, the photovoltaic output of the virtual power plant is adjusted to improve the photovoltaic consumption level of the virtual power plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 The present invention is a flow chart of a method for predicting the adjustable potential index of multiple load aggregation of a virtual power plant. DETAILED DESCRIPTION

[0025] The present invention is further described below with reference to the accompanying drawings and specific embodiments:

[0026] Step 1: Establish a time series of measured values ​​of the virtual power plant multi-load aggregate adjustable potential index parameter

[0027] The virtual power plant multi-load aggregation adjustable potential index prediction data is used as a case to further explain and analyze the time tm of n fixed time intervals. 1 ,tm 2 ,…,tm k ,…tm n The total photovoltaic output of the virtual power plant, the state of charge of the power storage system, the total charging power of electric vehicles, the total power consumption of the fused magnesium furnace, the temperature of the molten magnesium furnace, and the light intensity are measured. The fixed time interval is 15 minutes, and the number of measurements is 4 times, that is, n = 4, then at tm 1 ,tm 2 ,tm 3 ,tm 4 The measured values ​​of the required data at these four fixed time intervals are as follows:

[0028]

[0029] Step 2: Normalization of measurement data

[0030] According to the measured data, tm 1 ,tm 2 ,tm 3 ,tm 4 During these four fixed time intervals, the maximum value of the total photovoltaic output of the virtual power plant is P PV,max , minimum value P PV,min , the maximum value of the state of charge SOC of the power storage system ES,max , minimum SOC ES,min , the maximum value of the total charging power of electric vehicles P EV,max , minimum value P EV,min , the maximum value of the total power consumption of the electric magnesium furnace P MEF,max , minimum value P MEF,min , the maximum temperature of the molten pool of the electric magnesium furnace is T MEF,max , minimum value T MEF,min , the maximum light intensity LI max , minimum value LI min The above measured values ​​are normalized and the data processing results are as follows:

[0031]

[0032] Step 3: Calculate the next moment in the future tm 5 Normalized value of the total photovoltaic output forecast of the virtual power plant Normalized value of charge state prediction of power storage system Normalized value of total charging power prediction for electric vehicles Normalized value of total power consumption prediction of fused magnesium furnace Normalized value of molten pool temperature prediction in fused magnesium furnace Normalized value of light intensity prediction

[0033]

[0034] Step 4: Calculate the next moment in the future tm 5 Virtual power plant multi-load aggregation adjustable potential index

[0035]

[0036] The calculated adjustable potential index of multiple load aggregation of virtual power plant at the next moment in the future This indicates that the virtual power plant has strong multi-load regulation capability and can appropriately increase photovoltaic output; the calculated multi-load aggregation adjustable potential index of the virtual power plant at the next moment in the future is This indicates that the virtual power plant has a moderate multi-load regulation capability and can maintain photovoltaic output. The calculated multi-load aggregation adjustable potential index of the virtual power plant at the next moment in the future is This means that the virtual power plant’s ability to regulate multiple loads is weak and photovoltaic output needs to be reduced.

[0037] The implementation methods of the present invention are not limited to the above-mentioned embodiments, and any other changes, modifications, substitutions, combinations, and simplifications made without departing from the spirit and principle of the present invention should be equivalent replacement methods and are included in the protection scope of the present invention.

Claims

1. A method for predicting the adjustable potential index of multi-load aggregation of a virtual power plant, characterized by: The following steps are involved: Step 1: Establish the time series of the measured values ​​of the virtual power plant multi-load aggregation adjustable potential index parameters; Step 2: Normalization of measurement data; Step 3: Calculate the predicted value of the real-time data of the virtual power plant at the next moment in the future; Step 4: Calculate the predicted value of the virtual power plant multi-load aggregation adjustable potential index at the next moment in the future.

2. The method for predicting the adjustable potential index of multiple load aggregation of a virtual power plant according to claim 1 is characterized by: The parameters in step 1 include the total photovoltaic output of the virtual power plant, the charge state of the power storage system, the total charging power of the electric vehicle, the total power consumption of the fused magnesium furnace, the molten pool temperature of the fused magnesium furnace, and the light intensity. k ,…tm n , n is a natural number, k is a natural number, and k={1,2,…,n}, the time series of measuring the total photovoltaic output of the virtual power plant, the charge state of the power storage system, the total charging power of electric vehicles, the total power consumption of the electric fused magnesium furnace, the temperature of the molten magnesium furnace, and the light intensity are: In the formula, For tm k The measured value of the total photovoltaic output of the virtual power plant at the moment, For tm k The measured value of the charge state of the energy storage system at any moment, For tm k The measured value of the total charging power of the electric vehicle at the moment, For tm k The measured value of the total power consumption of the electric magnesium furnace at the moment, For tm k The measured value of the molten pool temperature of the electric magnesium furnace at the moment, For tm k The measured value of light intensity at a given moment.

3. The method for predicting the adjustable potential index of multiple load aggregation of a virtual power plant according to claim 1 is characterized by: The specific method of normalization processing in step 2 is: The data obtained from each measurement are normalized according to the following formula to obtain the normalized value of the total photovoltaic output of the virtual power plant. Normalized value of the measured value of the state of charge of the power storage system Normalized value of the measured value of the total charging power of the electric vehicle Normalized value of the total power consumption of the fused magnesium furnace Normalized value of measured value of molten pool temperature in electric magnesium furnace Normalized value of the measured value of light intensity , the expression is: Where P PV,max , P PV,min are the total photovoltaic output of the virtual power plant at n fixed time intervals tm1, tm2, …, tm k ,…tm n Maximum and minimum values ​​of the measured values ​​at the moment, SOC ES,max , SOC ES,min are the charge states of the energy storage system at n fixed time intervals tm1, tm2, ..., tm k ,…tm n The maximum and minimum values ​​of the measured values ​​at the moment, P EV,max , P EV,min are the total charging power of electric vehicles at n fixed time intervals tm1, tm2, …, tm k ,…tm n The maximum and minimum values ​​of the measured values ​​at the moment, P MEF,max , P MEF,min are the total power consumption of the fused magnesium furnace at n fixed time intervals tm1, tm2, ..., tm k ,…tm n The maximum and minimum values ​​of the measured values ​​at the moment, T MEF,max , T MEF,min The molten pool temperature of the electric magnesium furnace is respectively at n fixed time intervals tm1, tm2, ..., tm k ,…tm n The maximum and minimum values ​​of the measured values ​​at the moment, LI max , LI min are the light intensity at n fixed time intervals tm1, tm2, ..., tm k ,…tm n The maximum and minimum values ​​measured at that moment.

4. The method for predicting the adjustable potential index of multiple load aggregation of a virtual power plant according to claim 1 is characterized by: In step 3, the next moment tm is calculated n+1 Normalized value of the total photovoltaic output forecast of the virtual power plant Normalized value of charge state prediction of power storage system Normalized value of total charging power prediction for electric vehicles Normalized value of total power consumption prediction of fused magnesium furnace Normalized value of molten pool temperature prediction in fused magnesium furnace Normalized value of light intensity prediction The expression is:

5. The method for predicting the adjustable potential index of multiple load aggregation of a virtual power plant according to claim 1 is characterized by: In step 4, the next moment tm is calculated n+1 Virtual power plant multi-load aggregation adjustable potential index The expression is: The calculated adjustable potential index of multiple load aggregation of virtual power plant at the next moment in the future This indicates that the virtual power plant has strong multi-load regulation capability and can appropriately increase photovoltaic output; the calculated multi-load aggregation adjustable potential index of the virtual power plant at the next moment in the future is This indicates that the virtual power plant has a moderate ability to adjust multiple loads and can maintain photovoltaic output. The calculated adjustable potential index of multiple load aggregation of the virtual power plant at the next moment in the future is This means that the virtual power plant’s ability to regulate multiple loads is weak, which can reduce photovoltaic output.

Images