New energy storage group AGC coordination control method and device
Through neural network model and signal decomposition technology, the AGC coordinated control of the new energy storage group is realized, solving the problem of unstable power output at the charging pile point, and improving the safety and battery life of new energy vehicles.
Patent Information
- Application Number
- CN202510425830.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-07
- Publication Date
- 2025-07-11
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The complexity of power output at the charging pile points of new energy vehicles leads to unstable power output, which easily damages the vehicle battery, and it is difficult for the existing technology to achieve power balance.
The neural network model is used to predict electricity consumption load, and the AGC instructions are decomposed into ramp signal combinations for sampling and analysis, and the power consumption optimization configuration and power balance are achieved through coordinated control strategies.
It improves the safety of charging of new energy vehicles and the service life of batteries, reduces equipment losses and maintenance costs, and improves the accuracy and stability of power output.
Smart Images
Figure CN120300844A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of new energy, and in particular to a method and device for AGC coordinated control of a new energy energy storage group.
Background Art
[0002] In recent years, the development of new energy vehicles has been extremely rapid. The sales of new energy vehicles are booming, and at the same time, the demand for charging piles is also increasing. The complexity of the power output at each charging pile location is different. For example, the distances between the charging pile locations and the new energy energy storage power stations are different, and problems such as energy loss caused by wire resistance, etc., resulting in unstable power output and extremely easy damage to vehicle batteries.
[0003] Therefore, a method and device for AGC coordinated control of a new energy energy storage group are proposed, which can predict the power consumption situation according to the power consumption load, analyze the complexity of AGC, so as to achieve power consumption power balance and improve the charging safety of new energy vehicles.
Summary of the Invention
[0004] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art and provide a method and device for AGC coordinated control of a new energy energy storage group, which can predict the power consumption situation according to the power consumption load, analyze the complexity of AGC, so as to achieve power consumption power balance and improve the charging safety of new energy vehicles.
[0005] To solve the above technical problems, the present invention adopts the following technical solutions:
[0006] A method and device for AGC coordinated control of a new energy energy storage group, comprising the following steps:
[0007] Step 1: Study the coordinated control strategy of the new energy energy storage unit;
[0008] Step 2: Establish a coordinated control model for the new energy energy storage unit to participate;
[0009] Step 3: Analyze the power consumption demand of the new energy energy storage unit and achieve optimal power consumption allocation;
[0010] Step 4: Propose a method for the power plant with the characteristics of the new energy energy storage unit to participate in AGC optimal control to adjust the coordinated control strategy;
[0011] The coordinated control strategy includes the following steps: Step 1: A power consumption load prediction method, using a neural network model. The neural network model consists of an input layer, an output layer, and a hidden layer, obtains the model rules through self-training, and obtains the optimal output value through these rules after a given input; Step 2: Analysis of the complexity of the AGC instruction, using the signal decomposition principle, decomposing the instruction signal into a combination of a series of ramp signals for sampling analysis.
[0012] Preferably, the calculation formula of the neural network model is as follows:
[0013]
[0014] In the formula, n eti is the input of the i-th node in the hidden layer; y i is the output of the i-th node in the hidden layer; n etk is the input of the k-th node in the output layer; O k is the output of the k-th node in the output layer; x j is the input of the j-th node in the input layer; ω ij is the weight value between the i-th node in the hidden layer and the j-th node in the input layer; θ i is the threshold of the i-th node in the hidden layer; θ(x) is the activation function of the hidden layer; ω ki is the weight value between the k-th node in the output layer and the i-th node in the hidden layer; a k is the threshold of the k-th node in the output layer; ψ(x) is the activation function of the output layer.
[0015] Preferably, in step two, the superposition principle can also be used to superimpose the complexity of the decomposed ramp instruction, so as to calculate the complexity of the AGC instruction signal.
[0016] Preferably, for the same new energy energy storage unit, the complex characteristics of the AGC instruction can be simplified at one of its stable load points.
[0017] Preferably, step two can also calculate the complexity of the AGC instruction signal according to the discrete signal.
[0018] Preferably, step 4 specifically includes detecting the real-time power operation. When there is a large power shortage or surplus disturbance in the power grid, the AGC is controlled to perform power balance.
[0019] Preferably, the power balance formula is as follows:
[0020]
[0021] In the formula, P AGC,0 is the total initial power generation of the regional new energy energy storage unit; P NAGC,t is the output value of the non-new energy energy storage unit at time t; P D,t is the equivalent load prediction value at the t-th moment; P TIE,t is the line plan value at the t-th moment; ΔP TIE,t is the line power deviation at the t-th moment; is the total sum of the output increments of the new energy energy storage unit at the t-th moment; is the total output of the system units at time t.
[0022] A new energy storage group AGC coordinated control device, characterized in that the above method is used, including a research module for researching the coordinated control strategy participated by the new energy storage unit;
[0023] A coordinated control module for establishing a coordinated control model participated by the new energy storage unit;
[0024] An analysis module for analyzing the electricity demand participated by the new energy storage unit and realizing optimal electricity allocation;
[0025] A balance module for participating in the AGC optimal control method to adjust the coordinated control strategy;
[0026] The coordinated control module includes: an electricity load prediction module for using a neural network model, which is composed of an input layer, an output layer and a hidden layer, obtaining the model rules through self-training, and obtaining the optimal output value through this rule after a given input;
[0027] An AGC instruction complexity analysis module for decomposing the instruction signal into a combination of a series of ramp signals by using the signal decomposition principle for sampling analysis.
[0028] A new energy storage group AGC coordinated control system includes a processor suitable for implementing each instruction; and a storage device suitable for storing multiple instructions, and the instructions are suitable for being loaded and executed by the processor for the above method.
[0029] Advantages of the invention:
[0030] 1. Using a neural network model, which is composed of an input layer, an output layer and a hidden layer, obtaining the model rules through self-training, and obtaining the optimal output value through this rule after a given input to evaluate the error size of the output value and improve the accuracy of the output value;
[0031] The calculation formula of the neural network model is as follows:
[0032]
[0033] In the formula, n eti is the input of the i-th node in the hidden layer; y i is the output of the i-th node in the hidden layer; n etk is the input of the k-th node in the output layer; O k is the output of the k-th node in the output layer; x j is the input of the j-th node in the input layer; ω ij is the weight value between the i-th node in the hidden layer and the j-th node in the input layer; θ i is the threshold of the i-th node in the hidden layer; θ(x) is the activation function of the hidden layer; ω kiis the weight between the k-th node in the output layer and the i-th node in the hidden layer; a k is the threshold of the k-th node in the output layer; ψ(x) is the activation function of the output layer.
[0034] 2. The system load is random. When the new energy energy storage unit executes the AGC command, it needs to adjust the output in real time to track the change of the grid load. This not only makes the new energy energy storage unit unable to operate at the optimal operating point, but also makes it operate under variable working conditions, which will lead to the complication of the load regulation process of the new energy energy storage unit.
[0035] On the other hand, under the AGC command, the new energy energy storage unit needs to track the randomly fluctuating grid load, which will cause the control valves of the new energy energy storage unit to be in a frequent switching state, increasing the equipment loss and raising the maintenance cost.
[0036] Step 2: Analysis of the complexity of the AGC command. Using the signal decomposition principle, the command signal is decomposed into a combination of a series of ramp signals for sampling analysis. The series decomposition reduces errors and improves accuracy.
[0037] Step 2 can also use the superposition principle to superimpose the complexities of the decomposed ramp commands, so as to calculate the complexity of the AGC command signal.
[0038] The command signal can be approximately decomposed into a combination of a series of ramp signals, that is, r(t) = r1(t) + r2(t) + ··· + r n (t)
[0039] , if the time interval is very small and approaches 0, any tiny ramp signal has the property: m i ≈ |r i (t) - r i-1 (t)|, m i is the amplitude of the i-th ramp signal, r i (t) is the sampled value of the AGC command at the i-th moment, r i-1 (t) is the sampled value of the AGC command at the (i - 1)-th moment.
[0040] The complex characteristic approximation characteristic is Using the superposition principle for superposition, it can be obtained that n is the number of decomposed ramp commands.
[0041] Of course, a more concise formula is Both k1 and k2 are constants.
[0042] If it is the same new energy energy storage unit, at one stable load point, the complex characteristic of the AGC command can be simplified to
[0043] In step two, the complexity of the AGC command signal can also be calculated based on the discrete signal, and is represented by the line integral as F r(t) = ∫ L ds = L(r(t)), where L(r(t)) is the length of the continuous setpoint signal.
[0044] 3. Step 4 specifically includes performing real-time detection on the power operation power. When there is a large power shortage or surplus disturbance in the power grid, the AGC is controlled to perform power balance. The power output balance is beneficial to battery maintenance and extends the service life of the vehicle battery. This is the last safeguard mechanism that plays a safeguarding role.
[0045] The power balance formula is as follows:
[0046]
[0047] In the formula, P AGC,0 is the total initial power generation of the regional new energy energy storage unit; P NAGC,t is the output value of the non-new energy energy storage unit at time t; P D,t is the equivalent load prediction value at the t-th moment; P TIE,t is the line plan value at the t-th moment; ΔP TIE,t is the line power deviation at the t-th moment; is the total sum of the output increments of the new energy energy storage unit at the t-th moment; is the total output of the system units at time t.
[0048] These features and advantages of the present invention will be disclosed in detail in the following specific embodiments and drawings.
BRIEF DESCRIPTION OF THE DRAWINGS
[0049] The present invention will be further described below with reference to the drawings:
[0050] Figure 1 is a schematic flowchart of Embodiment 1 of the present invention.
DETAILED DESCRIPTION OF THE EMBODIMENTS
[0051] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the scope of protection of the present application.
[0052] The concepts involved in the present application will be described below with reference to the drawings first. It should be noted here that the following descriptions of each concept are only for making the content of the present application easier to understand, and do not represent a limitation on the scope of protection of the present application.
[0053] Example 1:
[0054] A new energy energy storage unit AGC coordinated control method and device, as Figure 1 shown, includes the following steps:
[0055] Step 1: Study the coordinated control strategy of the new energy energy storage unit;
[0056] Step 2: Establish a coordinated control model for the new energy energy storage unit to participate;
[0057] Step 3: Analyze the participation of the new energy energy storage unit in electricity demand and achieve optimal allocation of electricity use;
[0058] The coordinated control strategy includes the following steps: Step 1: The electricity load forecasting method, using a neural network model, which is composed of an input layer, an output layer, and a hidden layer. The model rules are obtained through self-training, and the best output value is obtained through this rule after a given input, so as to evaluate the error size of the output value and improve the accuracy of the output value;
[0059] The calculation formula of the neural network model is as follows:
[0060]
[0061] In the formula, n eti is the input of the i-th node in the hidden layer; y i is the output of the i-th node in the hidden layer; n etk is the input of the k-th node in the output layer; O k is the output of the k-th node in the output layer; x j is the input of the j-th node in the input layer; ω ij is the weight value between the i-th node in the hidden layer and the j-th node in the input layer; θ i is the threshold of the i-th node in the hidden layer; θ(x) is the activation function of the hidden layer; ω ki is the weight value between the k-th node in the output layer and the i-th node in the hidden layer; a k is the threshold of the k-th node in the output layer; ψ(x) is the activation function of the output layer.
[0062] The system load has randomness. When the new energy energy storage unit executes the AGC instruction, it needs to adjust the output in real time to track the change of the grid load. This makes the new energy energy storage unit not only unable to operate at the best operating point, but also in a variable operating condition, which will lead to the complication of the load regulation process of the new energy energy storage unit.
[0063] On the other hand, under the AGC instruction, the new energy energy storage unit needs to track the randomly fluctuating grid load, which will cause the control valves of the new energy energy storage unit to be in a frequent switching state, increasing the equipment loss and also raising the maintenance cost.
[0064] Step 2: AGC instruction complexity analysis. Using the signal decomposition principle, the instruction signal is decomposed into a combination of a series of ramp signals for sampling analysis. This series decomposition reduces errors and improves accuracy.
[0065] Step 2 can also apply the superposition principle to superimpose the complexities of the decomposed ramp instructions, thereby calculating the complexity of the AGC instruction signal.
[0066] The instruction signal can be approximately decomposed into a combination of a series of ramp signals, i.e., r(t) = r1(t) + r2(t) + ··· + r n (t)
[0067] , if the time interval is very small and approaches 0, any tiny ramp signal has the property: m i ≈ |r i (t) - r i-1 (t)|, where m i is the amplitude of the i-th ramp signal, r i (t) is the sampled value of the AGC instruction at the i-th moment, and r i-1 (t) is the sampled value of the AGC instruction at the (i - 1)-th moment.
[0068] The complex characteristic approximation characteristic is Using the superposition principle for superposition, we can obtain where n is the number of decomposed ramp instructions.
[0069] Of course, a more concise formula is where k1 and k2 are both constants.
[0070] If it is the same new energy energy storage unit, at one of its stable load points, the complex characteristic of the AGC instruction can be simplified to
[0071] Step 2 can also calculate the complexity of the AGC instruction signal according to discrete signals, which is represented by the curve integral as F r(t) = ∫ L ds = L(r(t)), where L(r(t)) is the length of the continuous setpoint signal.
[0072] Step 4: Propose a method for power plants participating in AGC optimal control of new energy energy storage unit characteristics to adjust the coordinated control strategy;
[0073] Step 4 specifically includes, performing real-time detection on the power operation power. When there is a large power shortage or surplus disturbance in the power grid, then control the AGC for power balance. Power output balance is beneficial to battery maintenance and extends the service life of vehicle batteries. This is the last safeguard mechanism that plays a safeguarding role.
[0074] The power balance formula is as follows:
[0075]
[0076] In the formula, P AGC,0 is the total initial power generation of the regional new energy energy storage unit; P NAGC,t is the output value of the non-new energy energy storage unit at time t; P D,t is the predicted value of the equivalent load at the t-th moment; P TIE,t is the line plan value at the t-th moment; ΔP TIE,t is the line power deviation at the t-th moment; is the total sum of the output increments of the new energy energy storage unit at the t-th moment; is the total output of the system units at time t.
[0077] A new energy energy storage group AGC coordinated control device, characterized in that it uses the above method, including a research module for researching the coordinated control strategy of the new energy energy storage unit;
[0078] A coordinated control module for establishing a coordinated control model for the new energy energy storage unit;
[0079] An analysis module for analyzing the participation of the new energy energy storage unit in the electricity demand and realizing the optimal allocation of electricity consumption;
[0080] A balance module for participating in the AGC optimization control method to adjust the coordinated control strategy;
[0081] The coordinated control module includes: an electricity load prediction module for using a neural network model, which is composed of an input layer, an output layer and a hidden layer, obtaining the model rules through self-training, and obtaining the optimal output value through these rules after a given input;
[0082] An AGC instruction complexity analysis module for decomposing the instruction signal into a combination of a series of ramp signals using the signal decomposition principle for sampling analysis.
[0083] A new energy energy storage group AGC coordinated control system, including a processor suitable for implementing each instruction; and a storage device suitable for storing multiple instructions, and the instructions are suitable for being loaded and executed by the processor to perform the above method.
[0084] The order of the invention embodiments is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0085] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments.
[0086] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of the present invention, and should all be included in the protection scope of the present invention.
Claims
1. A method and device for coordinated control of an AGC for a new energy energy storage group, characterized in that, It includes the following steps: Step 1: Research the coordinated control strategy for new energy energy storage units; Step 2: Establish a coordinated control model for new energy energy storage units; Step 3: Analyze the participation of new energy energy storage units in electricity demand and achieve optimal electricity allocation; Step 4: Propose an AGC optimization control method for power plants with the characteristics of new energy energy storage units to adjust the coordinated control strategy; The said coordinated control strategy includes the following steps: Step 1: An electricity load forecasting method, using a neural network model. The neural network model consists of an input layer, an output layer, and a hidden layer. It obtains the model rules through self-training and calculates the optimal output value through these rules after a given input; Step 2: Analysis of the complexity of AGC commands. Using the signal decomposition principle, the command signal is decomposed into a combination of a series of ramp signals for sampling analysis.
2. The AGC coordinated control method and device for a new energy energy storage group according to claim 1, characterized in that, The calculation formula of the said neural network model is as follows: where n eti is the input of the i-th node in the hidden layer; y i is the output of the i-th node in the hidden layer; n etk is the input of the k-th node in the output layer; O k is the output of the k-th node in the output layer; x j is the input of the j-th node in the input layer; ω ij is the weight between the i-th node in the hidden layer and the j-th node in the input layer; θ i is the threshold of the i-th node in the hidden layer; θ(x) is the activation function of the hidden layer; ω ki is the weight between the k-th node in the output layer and the i-th node in the hidden layer; a k is the threshold of the k-th node in the output layer; ψ(x) is the activation function of the output layer.
3. A new energy storage group AGC coordinated control method and device according to claim 1, characterized in that, Step 2 can also use the superposition principle to superimpose the complexity of the decomposed ramp commands, thereby calculating the complexity of the AGC command signal.
4. A new energy energy storage group AGC coordinated control method and device according to claim 2, characterized in that, For the same new energy energy storage unit, at one stable load point, the complex characteristics of the AGC command can be simplified.
5. A new energy storage group AGC coordinated control method and device according to claim 1, characterized in that Step 2 can also calculate the complexity of the AGC command signal according to discrete signals.
6. The AGC coordinated control method and device for a new energy energy storage group according to claim 1, characterized in that, The said Step 4 specifically includes: Real-time detection of the power operation power. When there is a large power shortage or surplus disturbance in the power grid, then control the AGC to perform power balance.
7. A new energy energy storage group AGC coordinated control method and device according to claim 6, characterized in that, The power balance formula is as follows: Where, P AGC,0 is the initial total power generation of the regional new energy energy storage unit; P NAGC,t is the output value of the non-new energy energy storage unit at time t; P D,t is the equivalent load prediction value at the t-th moment; P TIE,t is the line plan value at the t-th moment; ΔP TIE,t is the line power deviation at the t-th moment; is the total sum of the output increments of the new energy energy storage unit at the t-th moment; is the total output of the system units at time t.
8. A new energy energy storage group AGC coordinated control device, characterized in that, Using the method described in any one of claims 1 to 7, it includes a research module for researching the coordinated control strategy for new energy energy storage units; A coordinated control module for establishing a coordinated control model for new energy energy storage units; An analysis module for analyzing the participation of new energy energy storage units in electricity demand and achieving optimal electricity allocation; A balance module for participating in the AGC optimization control method to adjust the coordinated control strategy; The said coordinated control module includes: An electricity load forecasting module for using a neural network model. The neural network model consists of an input layer, an output layer, and a hidden layer. It obtains the model rules through self-training and calculates the optimal output value through these rules after a given input; An AGC command complexity analysis module for using the signal decomposition principle to decompose the command signal into a combination of a series of ramp signals for sampling analysis.
9. A new energy energy storage group AGC coordinated control system, characterized in that, It includes a processor suitable for implementing each instruction; and a storage device suitable for storing multiple instructions. The said instructions are suitable for being loaded and executed by the processor for the method described in any one of claims 1 to 7.