Micro-grid energy supply wave balancing method and system

Abstract

The invention discloses a micro-grid energy supply wave balancing method and system, and relates to the technical field of power grid heat supply balancing, and the method comprises the steps: deploying a high-precision sensor, and monitoring the energy supply, load demand, load output power, voltage and frequency of a micro-grid in real time; constructing an energy fluctuation depth model through the real-time data and the historical data, and outputting an energy fluctuation trend within a preset time; a self-adaptive energy adjustment controller is arranged, and the output power and working state information of each power generation unit are automatically adjusted based on a prediction result through a power control algorithm; solving an energy balance parameter target by taking an adjustment result of the power control algorithm and a current power grid state as input information through an energy balance control strategy, and feeding back the energy balance parameter target to a self-adaptive energy adjustment controller; and dynamically adjusting load distribution according to a final output result of the self-adaptive energy adjustment controller. The problem that balance adjustment lags due to the fact that a traditional heat supply system cannot respond in real time is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid heating balance, and specifically to a method and system for balancing the energy supply wave of a microgrid. Background Art

[0002] A microgrid is usually composed of distributed energy resources (such as solar energy, wind energy, etc.) and an energy storage system (such as a battery pack), aiming to achieve flexible and efficient utilization of energy.

[0003] In a microgrid, due to the volatility and intermittency of renewable energy (such as solar energy, wind energy), the problem of unstable energy supply has become increasingly prominent. This instability not only causes voltage fluctuations and frequency drifts but also affects the overall reliability and energy efficiency of the power system. Existing energy balance methods usually rely on energy storage systems or backup power supplies for regulation, but these methods have limited response speed and regulation accuracy when dealing with frequent and severe energy fluctuations. Therefore, it is necessary to develop a dynamic energy balance control method to achieve the stabilization of energy supply and ensure the efficient and stable operation of the microgrid.

[0004] For example, the existing Chinese patent with the publication number CN113572197A discloses a comprehensive self-consistent energy microgrid configuration method and energy regulation method based on hydrogen energy storage. The intelligent control system of the microgrid collects the electricity-heat-cooling energy demands of the microgrid load in real time, and collects the real-time hydrogen pressure value in the hydrogen storage tank in the microgrid. It relies on the grid connection and islanding discrimination module to identify the relationship between the microgrid and the power grid; in the state where the microgrid is connected to the power grid or the microgrid operates independently away from the power grid, the regulation of the microgrid energy is characterized by the real-time hydrogen pressure value in the hydrogen storage tank, based on the discrimination result of the real-time hydrogen pressure value and the set hydrogen pressure boundary threshold, and combined with whether the wind and photovoltaic power in the microgrid are outputting power, and the cold and heat supply of the microgrid load are used as constraints, and then the corresponding energy control strategy is started. This invention adjusts the command deviation caused by the randomness of wind and light and load fluctuations in real time based on the wind and light prediction results and the typical daily load curve, and ensures the real-time balance of the system energy and power.

[0005] However, this design relies on the wind and light prediction results to adjust the output of each unit in real time to suppress the command deviation caused by the randomness of wind and light and load fluctuations. However, the accuracy of wind and light prediction may be affected by various factors, such as weather changes, equipment failures, etc., which may lead to a deviation between the prediction result and the actual value, and it is impossible to maximize the energy utilization efficiency under the premise of fast response and high-precision regulation, thus affecting the stability and reliability of the system. Therefore, the present invention provides a method and system for balancing the energy supply wave of a microgrid. Summary of the Invention

[0006] The purpose of the present invention is to provide a microgrid energy supply wave balance method and system to solve the existing problems proposed in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solution: A microgrid energy supply wave balance method, comprising the following steps:

[0008] S1. Deploy high-precision sensors to monitor the energy supply, load demand, load output power, voltage, and frequency of the microgrid in real time; construct an energy fluctuation depth model through real-time data and historical data, and output the energy fluctuation trend within a preset time;

[0009] S2. Set an adaptive energy regulation controller, and automatically adjust the output power and working state information of each power generation unit based on the prediction result through a power control algorithm;

[0010] S3. Through an energy balance control strategy, use the adjustment result of the power control algorithm and the current power grid state as input information, solve the energy balance parameter target, and feedback it to the adaptive energy regulation controller;

[0011] S4. Dynamically adjust the load distribution according to the final output result of the adaptive energy regulation controller.

[0012] The further improvement of the present invention lies in that the specific construction process of the energy fluctuation depth model includes:

[0013] S11. Install a current sensor and a voltage sensor at the load point, obtain the load demand at the same time, and set a sampling period t to obtain input data x = {x P , x I , x U}, where x P represents the load demand data set, x I represents the current data set, and x U represents the voltage data set;

[0014] S12. Create a special time node data set, add an additional marker hz to the input samples of x P at the special time node in the input data to obtain a marked load demand data set x P _hz, and add it to the input data to obtain an input sequence inx = {x P , x I , x U , x P _hz};

[0015] S13. Create an energy encoder to map the input sequence to a high-dimensional latent representation y i = f θ (inx), f θ() represents a high-dimensional mapping function, where \(i\in\{1,2,\ldots,T_c\}\), \(T_c\) represents the total number of samplings with the sampling period \(t\) as the step size, and the corresponding time is \(T\); map the feature \(y\) i to the hidden dimension and send the output of the hidden dimension to the energy encoder to obtain Append \(x\) U and \(x\) I to the feature vector to obtain the first-layer input feature \(\lambda\) 1 ; pass \(\lambda\) 1 through the energy encoder to obtain the first load feature output vector \(y_1\);

[0016] S14. Convert the first load feature output vector again to obtain to obtain the energy fluctuation depth model , where \(W\) n represents a mapping matrix, and \(y\) T+n represents the predicted load demand at the \(n\)th step with a step size of \(t\).

[0017] A further improvement of the present invention lies in that the energy encoder includes \(N\) layers of convolutional structures, and the multi-head attention mechanism is applied to capture the dependencies among the load demand, current, and voltage in the input sequence \(inx\), expressed as \(\lambda\) χ \(= MHA(||\lambda\) χ-1 || 2 )+\lambda\) χ-1 , \(MHA()\) represents the multi-head attention block, and the feed-forward neural network is used to perform a non-linear transformation on the result of the attention mechanism, expressed as \(MLP()\) represents the feed-forward neural network, \(\chi\in\{2,3,\ldots,N + 1\}\), and \(\lambda\) χ represents the input feature of the \(\chi\)th layer, represents the output feature of the \(\chi\)th layer.

[0018] A further improvement of the present invention lies in that the adaptive energy regulation controller is simultaneously equipped with a power control algorithm and an energy balance control strategy. First, the power control algorithm quickly responds to energy fluctuations to perform rough regulation of voltage and power, and then the energy balance control strategy performs fine regulation of voltage and power.

[0019] A further improvement of the present invention lies in that the specific steps of the power control algorithm include: setting the goal of minimizing the supply-demand mismatch, represented by the variance of , represents the output power of the actual load demand at the \( \)th time step with a step size of \(t\) after the current \(T\) moment, represents the actual load demand at the \( \)th time step with a step size of \(t\) after the current \(T\) moment, and setting the output power constraint of the load demand Represents the minimum output power of the set load demand, Represents the maximum output power of the set load demand;

[0020] Based on the output power, load demand, voltage and current at the current moment, as well as the predicted load demand Construct an optimization model for the nth future step. Based on the solution of the optimization model, obtain the optimal output power for the time step

[0021] A further improvement of the present invention lies in that the optimization model for the nth future step is expressed as:

[0022]

[0023] where K sup_(1:n-1) represents the power sequence of the power generation unit from the first step to the (n - 1)th step with a step size of t after time T, and α 1 , α 2 , α 3 and α 4 represent weight coefficients, represents the set target output power.

[0024] A further improvement of the present invention lies in that the specific steps of the energy balance control strategy include:

[0025] S31. Initialize the particle state at γ = 0 and set an initial weight for each particle man represents the total number of particles, and each particle consists of two instructions to increase or decrease the output power;

[0026] S32. Extract the predicted load demand data at the moment and and initialize the fading factor σ;

[0027] S33. Design the particle performance fitness function FF;

[0028] S34. Calculate the correction term Add the new correction term to the predicted energy distribution strategy to obtain the updated particle position;

[0029] S35. Update the particle weights based on the proportion of the particle performance fitness function;

[0030] S36. Collect the cumulative weight distribution of each particle, extract the particles with unchanged weights for three consecutive times, and resample each extracted particle;

[0031] S37. Repeat S33 to S36 until satisfied​ wherein represents the set energy supply - demand balance error threshold, and outputs the output power at this time to S4.

[0032] A further improvement of the present invention lies in that the particle performance fitness function FF is expressed as:

[0033]

[0034] wherein, represents the degree of voltage fluctuation, represents the degree of current fluctuation, both obtained through standard deviation, represents the weight coefficient in the particle performance fitness function. When is less than the set demand threshold, When is greater than or equal to the set demand threshold,

[0035] A further improvement of the present invention lies in that the specific process of resampling each extracted particle includes: initializing an array of cumulative weights, the length of which is the same as the number of particles, and initializing all elements to 0; traversing the particle set, adding the weight of each particle to the corresponding position and subsequent positions in the array of cumulative weights; initializing a new particle set, the size of which is the same as the original particle set; generating a random number uniformly distributed in the interval [0, 1]; starting from the starting position of the array of cumulative weights, gradually adding weights with a compensation j until the cumulative sum is greater than or equal to the random number and then stopping; at this time, the particle corresponding to the stopping position is the selected particle; copying the selected particle into the new particle set; repeating the above process until the new particle set is filled.

[0036] On the other hand, the present invention provides a micro - grid energy supply wave balance system, including:

[0037] A real - time energy fluctuation monitoring module, deploying high - precision sensors to monitor the energy supply, load demand, load output power, voltage and frequency of the micro - grid in real time; constructing an energy fluctuation depth model through real - time data and historical data, and outputting the energy fluctuation trend within a preset time;

[0038] The real - time energy fluctuation monitoring module includes a special time - node data - set creation unit and an energy encoder creation unit. The special time - node data - set creation unit is used to add an additional marker to the input samples at the special time nodes x P in the input data to obtain a marked load - demand data set; the energy encoder creation unit is used to map the input sequence to obtain a first load - feature output vector in high - dimensional and hidden dimensions as the input of the energy fluctuation depth model.

[0039] The dynamic energy balance control module sets an adaptive energy regulation controller, which automatically adjusts the output power and working state information of each power generation unit based on the prediction results through a power control algorithm.

[0040] The energy balance optimization module takes the adjustment result of the power control algorithm and the current power grid state as input information through an energy balance control strategy, solves the energy balance parameter target, and feeds it back to the adaptive energy regulation controller.

[0041] The dynamic load balancing module dynamically adjusts the load distribution according to the final output result of the adaptive energy regulation controller.

[0042] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0043] 1. First, the present invention is equipped with a power control algorithm and an energy balance control strategy through an adaptive energy regulation controller, which can automatically adjust the output power and working state information of each power generation unit according to the prediction results and the current power grid state; the power control algorithm can quickly respond to energy fluctuations and perform rough regulation of voltage and power to ensure the stable operation of the power grid; the energy balance control strategy further performs fine regulation of voltage and power, optimizes energy distribution, and improves energy utilization efficiency.

[0044] 2. According to the output result of the adaptive energy regulation controller, the system can dynamically adjust the load distribution to ensure that each load receives reasonable energy supply; this dynamic adjustment can be optimized in real time according to the actual demand and the power grid state, improving the flexibility and response speed of the microgrid.

[0045] 3. The entire microgrid energy supply wave balance method realizes intelligence and automation, reducing manual intervention and decision-making costs; the system can automatically learn, predict, and optimize the energy distribution strategy, improving the efficiency and accuracy of energy management.

[0046] 4. Through real-time monitoring, prediction, and adaptive regulation, the system can ensure the supply-demand balance and stable operation of the microgrid; this balance and stability contribute to improving energy utilization efficiency, reducing energy waste, and enhancing the reliability and resilience of the microgrid. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is the flowchart of the microgrid energy supply wave balance method of the present invention;

[0048] Figure 2 It is the flowchart of the power control algorithm in the microgrid energy supply wave balance method of the present invention;

[0049] Figure 3 It is the framework diagram of the microgrid energy supply wave balance system of the present invention. Detailed implementation mode

[0050] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. Without conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0051] The term "and / or" is merely a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " generally represents an "or" relationship between the associated objects before and after.

[0052] Embodiment 1

[0053] Figure 1 The flowchart of the microgrid energy supply wave balance method disclosed in this embodiment is shown as follows, and the steps are as follows:

[0054] S1. Deploy high-precision sensors to monitor the load demand, load output power, voltage, and frequency of the microgrid in real time; construct an energy fluctuation depth model through real-time data and historical data, and output the energy fluctuation trend within a preset time;

[0055] The specific construction process of the energy fluctuation depth model includes:

[0056] S11. Install current sensors and voltage sensors at the load points, obtain the load demand simultaneously, and set the sampling period t to obtain the input data x = {x P , x I , x U}, where x P represents the load demand data set, x I represents the current data set, and x U represents the voltage data set;

[0057] S12. Create a special time node data set, add an additional marker hz to the input samples of x P at the special time node in the input data to obtain the marked load demand data set x P _hz, and add it to the input data to obtain the input sequence inx = {x P , x I , x U , x P _hz};

[0058] If it is known that an important event (such as a load peak) will occur at time point t, in this embodiment, a marker hz can be inserted at this position. During model processing, the marker hz will be linearly projected to hz', and then together with other linearly projected data, it will be input into the Transformer. In the multi-head attention mechanism of the Transformer, the marker hz will help the model better focus on the associated context information, thereby improving the prediction accuracy.

[0059] The special time node dataset is determined by the staff based on experience or experimental data.

[0060] Doing so allows the model to better capture the information at key time points when processing complex time series data and make full use of this information during prediction.

[0061] S13. Create an energy encoder to map the input sequence to a high-dimensional latent representation y i = f θ (inx), f θ () represents a high-dimensional mapping function, i ∈ {1, 2,..., Tc}, Tc represents the total number of sampling times with the sampling period t as the step size, and the corresponding time is T; map the feature y i to the hidden dimension W Trans , and deliver the output of the hidden dimension to the energy encoder to obtain Attach x U and x I to the feature vector to obtain the first-layer input feature λ 1 ; pass λ 1 through the energy encoder to obtain the first load feature output vector y1;

[0062] The energy encoder includes N layers of convolutional structures, and applies the multi-head attention mechanism to capture the dependencies among the load demand, current, and voltage in the input sequence inx, expressed as λ χ = MHA(||λ χ-1 || 2 ) + λ χ-1 , MHA() represents the multi-head attention block, and uses a feed-forward neural network to perform a non-linear transformation on the result of the attention mechanism, expressed as MLP() represents the feed-forward neural network, χ ∈ {2, 3,..., N + 1}, λ χ represents the input feature of the χ-th layer, represents the output feature of the χ-th layer.

[0063] Since the amount of data required for energy fluctuations increases with the increase in the number of users, there are high requirements for the scalability of the model. The encoder part can process the entire sequence in parallel, rather than processing step by step like a Recurrent Neural Network (RNN), thus greatly improving the computational efficiency and scalability.

[0064] It is trained through the backpropagation algorithm, which calculates the gradient of the loss function with respect to each weight and uses these gradients for weight updates to minimize the difference between the prediction and the actual output, thereby optimizing the model performance.

[0065] S14. Convert the first load feature output vector again to obtain In order to predict the probability distribution of potential features occurring at future times, in this embodiment, the following formula is used to maintain the correlation between potential features at future times and and obtain the energy fluctuation depth model where W n represents a mapping matrix, and y T+n represents the predicted load demand at the nth step with a step size of t.

[0066] S2. Set an adaptive energy regulation controller, and based on the prediction result, automatically adjust the output power and working state information of each power generation unit through a power control algorithm; for making decisions in a short time; the adaptive energy regulation controller is equipped with both a power control algorithm and an energy balance control strategy. First, the power control algorithm quickly responds to energy fluctuations for rough voltage and power regulation, and then the energy balance control strategy is used for fine voltage and power regulation.

[0067] The specific steps of the power control algorithm include: setting the goal of minimizing the supply-demand mismatch, represented by the variance of , represents the output power of the actual load demand at the th time step with a step size of t after the current T moment, represents the actual load demand at the th time step with a step size of t after the current T moment, and set the output power constraint of the load demand represents the minimum value of the output power of the set load demand, represents the maximum value of the output power of the set load demand;

[0068] Based on the output power of the load demand, the load demand, the voltage and the current at the current moment, as well as the predicted load demand Construct an optimization model for the nth step in the future. Based on the solution of the optimization model, obtain the optimal output power at the current time step. The optimal output power.

[0069] The optimization model for the nth step in the future is expressed as:

[0070]

[0071] Where K sup_(1:n-1) represents the power sequence of the power generation unit from the first step to the (n - 1)th step with a step size of t after time T, and α 1 , α 2 , α 3 and α 4 represent weight coefficients, represents the set target output power.

[0072] S3. Through the energy balance control strategy, take the adjustment result of the power control algorithm and the current grid state as input information, solve the energy balance parameter target, and feedback it to the adaptive energy regulation controller;

[0073] S4. Dynamically adjust the load distribution according to the final output result of the adaptive energy regulation controller.

[0074] Embodiment 2

[0075] Figure 2 Shows the flowchart of the power control algorithm in the microgrid energy supply wave balance method disclosed in this embodiment. Take the adjustment result of the power control algorithm and the current grid state as input information, solve the energy balance parameter target, and feedback it to the adaptive energy regulation controller; the steps are as follows:

[0076] S31. Initialize the particle state at γ = 0 and set an initial weight for each particle man represents the total number of particles, and each particle consists of two instructions: increasing or decreasing the output power;

[0077] Conventionally, the particle filter algorithm has poor tracking ability when facing mutation states and cannot efficiently solve the problems to be solved in this embodiment, that is:

[0078] Once the power control algorithm generates an adjustment result, this result needs to be executed quickly. This usually involves sending control instructions to each power generation unit to adjust its output power and working state. These control instructions may include increasing or decreasing the output power, starting or stopping certain power generation units, etc. During the execution process, it is necessary to ensure the accuracy and timeliness of the instructions to avoid unnecessary impacts or fluctuations on the power grid.

[0079] After executing the adjustment result, the system needs to continuously monitor the state changes of the power grid, including the stability of energy supply, the satisfaction of load demand, and the stability of voltage and frequency. If any problems or deviations are found, the system needs to immediately provide feedback and make adjustments. This real-time monitoring and feedback mechanism is the key to ensuring the continuous and effective operation of the power control algorithm.

[0080] Over time and with the changes in the power grid state, the power control algorithm may need to be continuously optimized and adjusted. This includes updating the prediction model based on new data, adjusting algorithm parameters to improve accuracy and efficiency, etc. By continuously optimizing and adjusting, it can be ensured that the power control algorithm can always adapt to the actual needs of the power grid and play its best role.

[0081] Therefore, in this embodiment, by combining strong tracking filtering, a targeted correction term is effectively generated during the update process of the real-time measurement data fusion prediction error. This correction term is used to optimize the particle set in the PF algorithm, enabling the particles to quickly move towards regions with higher likelihood, thereby effectively curbing the phenomenon of particle degradation. The specific steps include:

[0082] S32. Extract the predicted load demand data set at the and Initialize the fading factor σ, which is used to adjust the weights of historical data and real-time observation data during the update process;

[0083] S33. Design the particle performance fitness function FF;

[0084] S34. Calculate the correction term Add the new correction term to the predicted energy allocation strategy to obtain the updated particle positions;

[0085] S35. Update the particle weights based on the proportion of the particle performance fitness function; (The proportion of the fitness of the m-th particle in the total fitness of all particles represents the new particle weight)

[0086] S36. Collect the cumulative weight distribution of each particle, extract the particles with unchanged weights for three consecutive times, and resample each extracted particle;

[0087] S37. Repeat S33 to S36 until where represents the set energy supply and demand balance error threshold, and output the output power at this time to S4.

[0088] The particle performance fitness function FF is expressed as:

[0089]

[0090] where, Indicates the degree of voltage fluctuation, Indicates the degree of current fluctuation, both obtained through the standard deviation, Indicates the weight coefficient in the particle performance fitness function. When is less than the set demand threshold, When is greater than or equal to the set demand threshold, It realizes giving priority to efficiency at low loads and giving priority to stability at high loads.

[0091] The specific process of resampling each extracted particle includes: initializing an array of cumulative weights with the same length as the number of particles and initializing all elements to 0; traversing the particle set and adding the weight of each particle to the corresponding position and subsequent positions in the cumulative weight array. For example, the weight of the m-th particle will be added to the m-th element and all subsequent elements in the cumulative weight array; initializing a new particle set with the same size as the original particle set; generating a random number uniformly distributed in the interval [0,1]; starting from the beginning of the cumulative weight array, gradually adding weights with an offset j until the cumulative sum is greater than or equal to the random number and then stopping; at this time, the particle corresponding to the stopping position is the selected particle; copying the selected particle into the new particle set; repeating the above process until the new particle set is filled.

[0092] The setting of the threshold and weight can be based on the default settings of the present invention or can be set by the operator himself.

[0093] Embodiment 3

[0094] Figure 3 Shows the framework diagram of the microgrid energy supply wave balance system of the present invention. Based on the same inventive concept as Embodiment 1 and Embodiment 2, the present invention provides a microgrid energy supply wave balance system, including:

[0095] A real-time energy fluctuation monitoring module deploys high-precision sensors to monitor the energy supply, load demand, load output power, voltage and frequency of the microgrid in real time; constructs an energy fluctuation depth model through real-time data and historical data and outputs the energy fluctuation trend within a preset time;

[0096] A dynamic energy balance control module sets an adaptive energy regulation controller and automatically adjusts the output power and working state information of each power generation unit based on the prediction result through a power control algorithm;

[0097] The energy balance optimization module, through the energy balance control strategy, takes the adjustment result of the power control algorithm and the current power grid state as input information, solves the energy balance parameter target, and feeds it back to the adaptive energy regulation controller;

[0098] The dynamic load balancing module dynamically adjusts the load distribution according to the final output result of the adaptive energy regulation controller.

[0099] The real-time energy fluctuation monitoring module includes a special time node dataset creation unit and an energy encoder creation unit;

[0100] The special time node dataset creation unit is used to add an additional marker to the input samples at the special time nodes in the input data to obtain a marked load demand dataset; P Add an additional marker to the input samples at the special time nodes in the input data to obtain a marked load demand dataset;

[0101] The energy encoder creation unit is used to map the input sequence to the first load feature output vector obtained in the high-dimensional and hidden dimensions as the input of the energy fluctuation depth model.

[0102] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0103] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, and the combination of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0104] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device realizes the functions in the process Figure 1One or more processes and / or blocks Figure 1 The functions specified in one or more blocks.

[0105] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 One or more processes and / or blocks Figure 1 The steps of the functions specified in one or more blocks.

[0106] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative rather than restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the purpose of the present invention and the scope protected by the claims. All of these are within the protection scope of the present invention.

Claims

1. A microgrid energy supply wave balancing method, characterized in that: The following steps are involved: S1. Deploy high-precision sensors to monitor the energy supply, load demand, load output power, voltage and frequency of the microgrid in real time; build an energy fluctuation depth model through real-time data and historical data, and output the energy fluctuation trend within a preset time; S2. Setting an adaptive energy regulation controller to automatically adjust the output power and working status information of each power generation unit based on the prediction results through a power control algorithm; S3, through the energy balance control strategy, the adjustment result of the power control algorithm and the current grid state are used as input information to solve the energy balance parameter target and feed it back to the adaptive energy regulation controller; S4. Dynamically adjust load distribution according to the final output result of the adaptive energy regulation controller.

2. The microgrid energy supply wave balancing method according to claim 1, characterized in that: The specific construction process of the energy fluctuation depth model includes: S11, install current sensors and voltage sensors at the load point, obtain the load demand at the same time, and set the sampling period t to obtain input data x={x P ,x I ,x U }, where x P represents the load demand dataset, x I represents the current data set, x U represents a voltage data set; S12, create a special time node data set, for x in the input data P Add an additional tag hz to the input sample at the special time node to obtain the tag load requirement dataset x P _hz, add to the input data to get the input sequence inx = {x P ,x I ,x U ,x P _hz}; S13. Create an energy encoder to map the input sequence to a high-dimensional potential representation y i =f θ (inx), f θ () represents a high-dimensional mapping function, i∈{1,2,…,Tc}, Tc represents the total number of sampling times with the sampling period t as the step length, corresponding to time T; the feature y i Mapped to the hidden dimension, and the output of the hidden dimension is fed to the energy encoder to obtain x U and x I Append to the feature vector to obtain the first layer input feature λ1; pass λ1 through the energy encoder to obtain the first load feature output vector y1; S14, convert the first load characteristic output vector again to obtain Get the energy fluctuation depth model Among them, W n Represents a mapping matrix, y T+n represents the predicted load demand at the nth step with a step length of t.

3. The microgrid energy supply wave balancing method according to claim 2, characterized in that: The energy encoder includes an N-layer convolutional structure and applies a multi-head attention mechanism to capture the dependencies between load demand, current and voltage in the input sequence inx, denoted as λ χ =MHA(||λ χ-1 ||2)+λ χ-1 , MHA() represents a multi-head attention block, which uses a feedforward neural network to perform a nonlinear transformation on the result of the attention mechanism, expressed as MLP() represents a feedforward neural network, χ∈{2,3,…,N+1}, λ χ represents the input features of the χth layer, represents the output features of the xth layer.

4. The microgrid energy supply wave balancing method according to claim 3, characterized in that: The adaptive energy regulation controller is equipped with a power control algorithm and an energy balance control strategy. First, the power control algorithm is used to quickly respond to energy fluctuations and perform rough voltage and power regulation, and then the energy balance control strategy is used to perform fine voltage and power regulation.

5. The microgrid energy supply wave balancing method according to claim 4, characterized in that: The specific steps of the power control algorithm include: setting a goal of minimizing the mismatch between supply and demand, The variance of Indicates the first time after the current time T with a step length of t The actual load output power required in each time step is Indicates the first time after the current time T with a step length of t The actual load demand and set the output power constraint of the load demand Indicates the minimum output power required by the set load. Indicates the maximum output power required by the set load; Output power, load demand, and voltage based on the current load demand and current and the predicted load demand Construct an optimization model for the nth step in the future, and obtain the time step based on the solution of the optimization model. The optimal output power.

6. The microgrid energy supply wave balancing method according to claim 5, characterized in that: The optimization model of the future nth step is expressed as: Among them, K sup_(1:n-1) represents the power sequence of the power generation unit from the first step with a step length of t after time T to the n-1th step, α1, α2, α3 and α4 represent weight coefficients, Indicates the set target output power.

7. The microgrid energy supply wave balancing method according to claim 4, characterized in that: The specific steps of the energy balance control strategy include: S31, initialize the particle state at the moment γ = 0, and set the initial weight for each particle man represents the total number of particles, and each particle consists of two instructions to increase or decrease the output power; S32. Extracting predicted Load demand data at all times and And initialize the fading factor σ; S33, design particle performance fitness function FF; S34. Calculate correction items The new correction term is added to the predicted energy allocation strategy to obtain the updated particle position; S35, updating particle weights based on the proportion of particle performance fitness functions; S36, collecting the cumulative weight distribution of each particle, extracting particles whose weights remain unchanged for three consecutive times, and resampling each extracted particle; S37, repeat S33 to S36 until the in It indicates the set energy supply and demand balance error threshold, and outputs the output power at this time to S4.

8. The microgrid energy supply wave balancing method according to claim 7, characterized in that: The particle performance fitness function FF is expressed as: in, Indicates the voltage fluctuation degree, Indicates the degree of current fluctuation, which is obtained through standard deviation. Represents the weight coefficient in the particle performance fitness function. When it is less than the set demand threshold, when When it is greater than or equal to the set demand threshold, 9. The microgrid energy supply wave balancing method according to claim 7, characterized in that: The specific process of resampling each extracted particle includes: initializing a cumulative weight array, whose length is the same as the number of particles, and initializing all elements to 0; traversing the particle set, accumulating the weight of each particle to the corresponding position of the cumulative weight array and its subsequent position; initializing a new particle set, whose size is the same as the original particle set; generating a random number uniformly distributed in the interval [0,1]; starting from the starting position of the cumulative weight array, gradually accumulating the weight with compensation j until the cumulative sum is greater than or equal to the random number; at this time, the particle corresponding to the stopped position is the selected particle; copying the selected particle to the new particle set; repeating the above process until the new particle set is filled.

10. A microgrid energy supply wave balancing system, used to execute the microgrid energy supply wave balancing method according to any one of claims 1 to 9, characterized in that: include: Real-time energy fluctuation monitoring module, deploying high-precision sensors to monitor the energy supply, load demand, load output power, voltage and frequency of the microgrid in real time; Build an energy fluctuation depth model through real-time data and historical data, and output the energy fluctuation trend within a preset time; The real-time energy fluctuation monitoring module includes a special time node data set creation unit and an energy encoder creation unit. The special time node data set creation unit is used to create x in the input data. P Add an additional tag to the input sample at the special time node to obtain a marked load demand data set; The energy encoder creation unit is used to map the input sequence to the high dimension and the hidden dimension to obtain a first load feature output vector as an input of the energy fluctuation deep model; The dynamic energy balance control module is equipped with an adaptive energy regulation controller, which automatically adjusts the output power and working status information of each power generation unit based on the prediction results through the power control algorithm; The energy balance optimization module uses the adjustment result of the power control algorithm and the current grid state as input information through the energy balance control strategy to solve the energy balance parameter target and feed it back to the adaptive energy regulation controller; The dynamic load balancing module dynamically adjusts the load distribution according to the final output result of the adaptive energy regulation controller.

Images