A power grid dispatching method and system based on photovoltaic power generation power prediction

Abstract

The application discloses a power grid dispatching method and system based on photovoltaic power generation power prediction, comprising: establishing a power grid double-layer control model containing a main power grid, photovoltaic power generation modules, standby diesel generators and energy storage systems; defining constraint conditions of the power grid double-layer control model; using a photovoltaic power generation power prediction model to perform power prediction on each photovoltaic power generation module; constructing a target function of an upper controller with the aim of improving photovoltaic power generation utilization rate and reducing power fluctuation; determining an optimal power flow curve through the upper controller optimization under the constraint conditions; constructing a lower control target function according to the photovoltaic power generation power prediction value, and determining an optimal power grid dispatching scheme through the lower controller. The application improves the photovoltaic power generation utilization rate, reduces the power fluctuation, reduces the dispatching cost, improves the overall efficiency and stability of the system, avoids falling into a local optimal solution, maintains the overall efficiency of the system in a long time scale, and maximizes the utilization of clean energy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a power grid dispatching method and system based on photovoltaic power prediction. BACKGROUND

[0002] With the continuous development of photovoltaic, wind power and hydroelectric clean energy, more and more clean energy is connected to the power grid system. In order to reduce the fluctuation of clean energy caused by weather, a corresponding energy storage system and a standby diesel generator are often provided for the clean energy system. The energy storage system can store electric energy when photovoltaic power generation is excessive and release electric energy when photovoltaic power generation is insufficient, thereby smoothing the power output and stabilizing the power grid operation. The standby diesel generator can provide reliable emergency power supply to ensure the continuous power supply of critical loads in the case of main power grid power failure or insufficient photovoltaic power generation. The photovoltaic power generation module provides clean energy, the energy storage system stores excess electric energy, and the diesel generator serves as a backup, thereby realizing efficient utilization of renewable energy.

[0003] Currently, model predictive control (MPC) control technology is often used for power grid dispatching. MPC can predict the system behavior at multiple future time points and optimize the control strategy within the entire prediction period to ensure the optimal performance of the system at future time points.

[0004] However, the current MPC control technology is prone to local optimal solution, although a local optimal dispatching scheme can be obtained at each time step, it cannot guarantee to remain in the global optimal state, especially there will be deviations in long time scale, and in long time operation, the system may gradually deviate from the global optimal path, and the accumulated small deviations will lead to the decline of the overall efficiency and benefit of the system, the clean energy cannot be maximized, and the stability of the power grid is affected. SUMMARY

[0005] In view of the above problems, the present application is proposed.

[0006] Therefore, the technical problem solved by the present application is that the existing cloud service platform computing method has the problems of high power consumption loss, load rate reward and punishment, high cost, and how to allocate task requests to each host to realize load balancing optimization.

[0007] To solve the above technical problems, the present application provides the following technical scheme: a power grid dispatching method based on photovoltaic power prediction, comprising:

[0008] establishing a power grid double-layer control model comprising a main power grid, a photovoltaic power generation module, a standby diesel generator and an energy storage system;

[0009] defining the constraint conditions of the power grid double-layer control model;

[0010] The photovoltaic power prediction model is used to predict the power of each photovoltaic power generation module.

[0011] A target function of the upper controller is constructed to improve the utilization rate of photovoltaic power generation and reduce power fluctuation.

[0012] The optimal power flow curve is determined by the upper controller under the constraint condition.

[0013] According to the photovoltaic power prediction value, a lower control target function is constructed, and the optimal power grid scheduling scheme is determined by the lower controller.

[0014] As a preferred scheme of the power grid scheduling method based on photovoltaic power prediction, the power grid double-layer control model includes an upper controller for determining the optimal power flow curve and a lower controller for determining the optimal power grid scheduling scheme.

[0015] As a preferred scheme of the power grid scheduling method based on photovoltaic power prediction, the power grid double-layer control model includes an upper controller for determining the optimal power flow curve and a lower controller for determining the optimal power grid scheduling scheme.

[0016] The weather prediction unit includes a first convolutional layer, a first gating unit and a first attention layer connected in series, and the power prediction unit includes a second convolutional layer, a second gating unit and a second attention layer connected in series.

[0017] The first attention layer and the second attention layer are connected with a fully connected network, and the fully connected layer is connected with a prediction layer.

[0018] The historical weather data and the historical photovoltaic power generation data are obtained. The weather features in the historical weather data are extracted by the first convolutional layer in the weather prediction unit, and the power features in the historical photovoltaic power generation data are extracted by the second convolutional layer in the power prediction unit.

[0019] The weather hidden features in the weather features are extracted by the first gating unit in the weather prediction unit, and the power hidden features in the power features are extracted by the second gating unit in the power prediction unit.

[0020] The first attention layer in the weather prediction unit adds attention weights to the weather hidden features at each time, and the second attention layer in the power prediction unit adds attention weights to the power hidden features at each time.

[0021] The weather hidden features and the power hidden features with the added attention weights are spliced by the fully connected network, and the spliced fusion features are used for power prediction by the prediction layer to obtain the preliminary predicted power.

[0022] The final predicted power is determined by correcting the preliminary predicted power based on time periodicity and neighbor similarity, and the final predicted power is determined by correcting the preliminary predicted power based on correlation predicted power.

[0023] As a preferred scheme of the power grid scheduling method based on photovoltaic power prediction, the power prediction of each photovoltaic power generation module by using the photovoltaic power prediction model comprises that the photovoltaic power prediction model further comprises that, in order to improve the utilization rate of photovoltaic power generation and reduce power fluctuation, a target function of an upper controller is constructed, and the target function comprises calculating correlation coefficients between each adjacent day in the years before the prediction day.

[0024]

[0025] S ij =f(w ij ,w 00 )

[0026] V ij =g(w ij )

[0027] Wherein, C i j represents the correlation coefficient between the prediction day and the jth adjacent day in the i years, T i j represents the time correlation coefficient of the jth adjacent day in the i years, k1 represents the year correlation coefficient, k2 represents the date correlation coefficient, S i j represents the weather correlation coefficient of the jth adjacent day in the i years, w i j represents the weather type of the jth adjacent day in the i years, w 00 represents the weather type prediction value of the prediction day, and the weather type prediction value of the prediction day is calculated according to the weather hidden feature after adding attention weight, V i j represents the randomness coefficient of the jth adjacent day in the i years, V 00 represents the randomness coefficient of the prediction day.

[0028] The correlation predicted power is calculated according to the correlation coefficient between the prediction day and each adjacent day in the years before the prediction day.

[0029]

[0030] Wherein, P c represents the correlation predicted power of the prediction day, P ij represents the power generation power of the jth adjacent day in the i years, n represents the total number of years, and m represents the total number of adjacent days.

[0031] The specific way of correcting the preliminary predicted power according to the correlation predicted power is: The specific way of correcting the preliminary predicted power according to the correlation predicted power is:

[0032]

[0033] P t P P ct P

[0034] As a preferred scheme of the power grid scheduling method based on photovoltaic power prediction, the target function of the upper controller is constructed to improve the utilization rate of photovoltaic power generation and reduce power fluctuation, and the upper control target function is specifically:

[0035]

[0036] J H J P P

[0037] The power flow is specifically:

[0038] P PCC P + P -

[0039] P P CC + P - P

[0040] The smaller the power flow indicated by the power flow term, the higher the degree of self-sufficiency of the microgrid, and the greater the utilization rate of photovoltaic power generation.

[0041] As a preferred scheme of the power grid scheduling method based on photovoltaic power prediction, the optimal power flow curve is determined by the upper controller optimization under the constraint condition, and the optimal power flow curve is determined by the upper controller under the constraint of the constraint condition, using the particle swarm optimization algorithm, and taking the upper control target function as the target.

[0042] Initialize the population, and the population contains a plurality of particles, each particle representing a feasible power flow curve

[0043] Line, the fitness of each particle is calculated, the individual optimal position and the global optimal position are determined, and the formula is expressed as:

[0044]

[0045] wherein, denotes the velocity of the i-th particle at the t+1-th iteration, denotes the velocity of the i-th particle at the t-th iteration, ω denotes an inertia weight factor, c1 denotes an individual learning factor, c2 denotes a global learning factor, and r1 and r2 both denote random numbers between 0 and 1, denotes the individual optimal position of the i-th particle at the t-th iteration, denotes the global optimal position of the i-th particle at the t-th iteration, denotes the position of the i-th particle at the t-th iteration, denotes the position of the i-th particle at the t+1-th iteration;

[0046] It is determined whether the maximum number of iterations is reached. If yes, the power flow curve represented by the particle with the highest fitness value is output as the optimal power flow curve. Otherwise, the iteration is returned to continue.

[0047] The replacement probability is specifically:

[0048]

[0049] wherein, P denotes the replacement probability, e denotes a natural constant, δ() denotes a fitness function, and C t denotes the temperature at the t-th iteration;

[0050] The temperature is updated as:

[0051] T i+1 = εT i

[0052] wherein, ε denotes a cooling coefficient, T i +1 denotes the temperature at the i+1-th iteration, T i denotes the temperature at the i-th iteration;

[0053] When the temperature is higher, a poorer solution is more likely to be accepted, thereby increasing the chance of jumping out of a local optimum. As the number of iterations increases, the temperature gradually decreases, so that the algorithm performs more global search in the early stage and gradually concentrates on local search in the later stage, thereby improving the optimization effect;

[0054] The cooling coefficient is specifically:

[0055]

[0056] Wherein, A1 represents the first half cycle of the cooling oscillation factor, B1 represents the first half cycle of the cooling floating 25 factor, A2 represents the second half cycle of the cooling oscillation factor, B2 represents the second half cycle of the cooling floating factor.

[0057] As a preferred scheme of the power grid scheduling method based on photovoltaic power prediction of the application, wherein: according to the photovoltaic power prediction value, the lower control target function is constructed, and the optimal power grid scheduling scheme is determined through the lower controller, including that the lower control target function is specifically:

[0058]

[0059] Wherein, J L represents the lower control target function, min represents the minimum value, represents the power flow at t time, represents the reference power flow, T represents the total observation time, C t represents the scheduling cost at t time, μ1 represents the weight coefficient of the power flow deviation term, and μ2 represents the weight coefficient of the scheduling cost term;

[0060] By flexibly adjusting the weight coefficient, different operation requirements and strategies are adapted to ensure that the lower control can realize the overall optimization target of the upper control, and the comprehensive performance of the system is improved;

[0061] The scheduling cost is specifically:

[0062]

[0063] Wherein, C t represents the scheduling cost at t time, represents the main grid price at t time, represents the main grid purchase power at t time, N G represents the number of standby diesel generators, represents the unit power generation cost of the nth standby diesel generator, represents the power generation power of the nth standby diesel generator at t time, N E SS represents the number of energy storage systems, represents the unit energy storage cost of the nth energy storage system, represents the storage power of the nth energy storage system at t time, N P V represents the number of photovoltaic power modules, represents the unit power generation cost of the nth photovoltaic power module, P n t P V represents the power generation power prediction value of the nth photovoltaic power module at t time.

[0064] A power grid scheduling system based on photovoltaic power prediction, wherein:

[0065] a main power grid providing basic power supply and transmission functions;

[0066] a photovoltaic power generation module for power generation using photovoltaic technology;

[0067] a backup diesel generator for providing emergency power supply when the main power grid or photovoltaic power generation is insufficient;

[0068] a storage system for storing power when there is excess power and releasing power when there is insufficient power, thereby smoothing power output;

[0069] an upper controller for determining an optimal power flow curve, optimizing photovoltaic power generation utilization, and reducing power fluctuations;

[0070] a lower controller for optimizing power grid scheduling schemes according to photovoltaic power generation power prediction values and the optimal power flow curve, reducing deviations between actual power flow and reference power flow, and reducing scheduling costs;

[0071] a processor for executing power grid scheduling algorithms and control strategies;

[0072] a memory for storing relevant computer-readable instructions and data for executing scheduling methods.

[0073] A computer device comprises a memory and a processor; the memory stores a computer program, and the processor executes the computer program to implement the steps of the method of any one of the embodiments.

[0074] A computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the method of any one of the embodiments.

[0075] The power grid scheduling method based on photovoltaic power generation power prediction provided by the present application improves photovoltaic power generation utilization, reduces power fluctuations, reduces scheduling costs, improves overall system efficiency and stability, avoids local optimal solutions, maintains overall system efficiency on a long time scale, maximizes the use of clean energy, promotes the development of renewable energy, and ultimately realizes efficient, economic, and sustainable operation of the power grid. BRIEF DESCRIPTION OF DRAWINGS

[0076] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0077] Figure 1 A flow chart of a power grid scheduling method based on photovoltaic power prediction is provided for the first embodiment of the present application.

[0078] Figure 2 A structural schematic diagram of a power grid scheduling method based on photovoltaic power prediction is provided for the first embodiment of the present application. DETAILED DESCRIPTION

[0079] In order to make the above objectives, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the scope of protection of the present application.

[0080] Embodiment 1, refer to Figure 1 For an embodiment of the present application, a power grid scheduling method based on photovoltaic power prediction is provided, comprising:

[0081] S1: Establish a power grid double-layer control model comprising a main power grid, a photovoltaic power generation module, a backup diesel generator and an energy storage system.

[0082] The power grid double-layer control model comprises an upper controller for determining an optimal power flow curve and a lower controller for determining an optimal power grid scheduling scheme.

[0083] It should be noted that the energy storage system can store electrical energy when photovoltaic power generation is in excess and release electrical energy when photovoltaic power generation is insufficient, thereby smoothing the power output and stabilizing the operation of the power grid. In the event of a power outage of the main power grid or insufficient photovoltaic power generation, the backup diesel generator can be quickly started to provide a reliable emergency power supply and ensure continuous power supply for critical loads. The photovoltaic power generation module provides clean energy, the energy storage system stores excess electrical energy, and the diesel generator serves as a backup, with the three complementing each other to achieve efficient utilization of renewable energy.

[0084] S2: Define the constraint conditions of the power grid double-layer control model.

[0085] In one possible implementation, the constraint conditions specifically comprise:

[0086] Power balance constraint:

[0087]

[0088] wherein, Pb represents the purchase amount of the main power grid at time t, N G Nd represents the number of backup diesel generators, N represents the power generated by the nth standby diesel generator at time t, P V represents the number of photovoltaic power generation modules, N represents the power generation of the nth photovoltaic power generation module at time t, E SS represents the number of energy storage systems, P n t DCh,ESS represents the discharge power of the nth energy storage system at time t, P n t Ch,ESS represents the nth energy storage, R represents the load, I t represents the current at time t, represents the load power at time t. It should be noted that the power balance constraint ensures that at each time step t, the total power generation and purchased electricity of the grid can meet the total load demand. This considers the power purchased from the main grid, the power generated by backup diesel generators, the power generated by photovoltaics, the charge and discharge power of the energy storage system, and the power flow and load current losses.

[0089] Standby diesel generator power constraints:

[0090] P G ≤P G,Nom

[0091] Among them, P G Indicates the power generation of the standby diesel generator, P G,Nom Indicates backup diesel generator

[0092] The nominal power of the machine.

[0093] It should be noted that the backup diesel generator power constraint can ensure that the power generated by the backup diesel generator does not exceed its nominal power, prevent the generator from overloading, protect the equipment and extend its life. Energy storage system charging power constraint:

[0094] bs + ≤β·bs max

[0095] Among them, bs + Indicates the charging power of the energy storage system, bs max Represents the maximum charging power of the energy storage system, and β represents the charging and discharging efficiency. It should be noted that the energy storage system charging power constraint can limit the energy storage system's charging power to no more than a portion of its maximum charging power, ensuring that the charging process is within the range allowed by the equipment. Energy storage system discharge power constraint:

[0096] bs - ≤(1-β)·bs max

[0097] Among them, bs - Indicates the discharge power of the energy storage system, bsmax represents the maximum charging power of the energy storage system, and β represents the charging and discharging efficiency. It should be noted that the energy storage system discharging power constraint can limit the discharging power of the energy storage system not to exceed a part of its maximum charging power, ensuring that the charging process is within the allowable range of the device. The energy storage system storage capacity constraint:

[0098]

[0099] wherein C ESS represents the storage capacity of the energy storage system, represents the maximum storage capacity of the energy storage system, represents the minimum storage capacity of the energy storage system. It should be noted that the energy storage system storage capacity constraint can ensure that the storage capacity of the energy storage system is between the maximum and minimum storage capacities, preventing overcharging or over-discharging of the energy storage system, thereby protecting the battery life and performance. The charging and discharging capacity balance constraint:

[0100] C Ch =C DCh

[0101] wherein, represents the charging capacity, represents the discharging capacity. It should be noted that the charging and discharging capacity balance constraint can ensure that the charging capacity is equal to the discharging capacity, maintaining the energy balance of the energy storage system.

[0102] |E G +E PV -E Load -E Loss |=E ESS

[0103] wherein E G represents the standby diesel generator energy, E P V represents the photovoltaic power module energy, E L oad

[0104] The energy balance constraint represents the load consumption energy, represents the energy loss of abandoned electricity, E E SS represents the energy storage system energy. It should be noted that the energy balance constraint can ensure the energy balance between the standby diesel generator energy, the photovoltaic power module energy, the load consumption energy, the energy loss of abandoned electricity, and the energy storage system energy, ensuring the energy conservation of the system. The energy storage system storage power constraint:

[0105] P ESS =βP Ch +(1-β)P DCh

[0106] wherein P ESS represents the storage power of the energy storage system, P C h represents the charging power, P D Ch represents the discharging power, and β represents the charging and discharging efficiency. It should be noted that the energy storage system storage power constraint can ensure that the energy conversion process of the energy storage system is in line with the actual situation.

[0107] The maximum and minimum storage power constraints of the energy storage system are:

[0108]

[0109] wherein, SSmax represents the maximum storage power of the energy storage system, SSmin represents the minimum storage power of the energy storage system.

[0110] It should be noted that the maximum and minimum storage power constraints of the energy storage system can ensure that the storage power of the energy storage system is between the maximum and minimum storage power, preventing the energy storage system from being overcharged or discharged.

[0111] The energy storage system energy update constraint is:

[0112]

[0113] wherein, E t +1 ESS SS(t+1) represents the storage energy of the energy storage system at time t+1, SS(t) represents the storage energy of the energy storage system at time t, SS(u) represents the storage power of the energy storage system at time u, and du represents the differential of u.

[0114] It should be noted that the energy storage system energy update constraint can determine the change of energy of the energy storage system within time by integrating the storage power of the energy storage system, ensuring the accuracy of the energy change process.

[0115] The energy balance constraint of the energy storage system within the time interval is:

[0116]

[0117] wherein, SS1 represents the storage energy of the energy storage system within the first time interval, SSk represents the storage energy of the energy storage system within the kth time interval.

[0118] It should be noted that the energy balance constraint of the energy storage system within the time interval can ensure the consistency and balance of the energy of the energy storage system within different time intervals, ensuring the stable operation of the system within different time periods.

[0119] The node power flow constraint is:

[0120]

[0121] wherein, Pupstream represents the active power in the upstream direction of the node, - Pdownstream represents the active power in the downstream direction of the node, N om represents the nominal voltage, max Iom represents the maximum sustained current of the node.

[0122] S3: predicting the power of each photovoltaic power generation module by using the photovoltaic power generation power prediction model.

[0123] It should be noted that the node power flow constraint can ensure that the sum of the upstream and downstream active powers of the node does not exceed the nominal power, thereby protecting the power grid equipment and ensuring its safe operation.

[0124] Optionally, the photovoltaic power generation power prediction model comprises a weather prediction unit and a power prediction unit. The weather prediction unit comprises a first convolutional layer, a first gating unit and a first attention layer connected in series, and the power prediction unit comprises a second convolutional layer, a second gating unit and a second attention layer connected in series. The first attention layer and the second attention layer are connected with a fully connected network, and the fully connected network is connected with a prediction layer.

[0125] Optionally, historical weather data and historical photovoltaic power generation data are obtained. The weather features in the historical weather data are extracted by the first convolutional layer in the weather prediction unit, and the power features in the historical photovoltaic power generation data are extracted by the second convolutional layer in the power prediction unit. The weather hidden features in the weather features are extracted by the first gating unit in the weather prediction unit, and the power hidden features in the power features are extracted by the second gating unit in the power prediction unit. The first attention layer in the weather prediction unit adds attention weights to the weather hidden features at each time, and the second attention layer in the power prediction unit adds attention weights to the power hidden features at each time. The weather hidden features and the power hidden features after adding the attention weights are spliced by the fully connected network. According to the spliced fusion features, the prediction layer is used for power prediction to obtain the preliminary predicted power. The preliminary predicted power is corrected based on the time periodicity and the neighbor similarity to determine the final predicted power. The preliminary predicted power is corrected according to the correlation predicted power to determine the final predicted power.

[0126] In a possible implementation, the convolution features in the historical weather data and the power features in the historical photovoltaic power generation data are extracted by convolution kernels respectively:

[0127]

[0128] wherein, represents the output of the current convolutional layer, an output of a previous convolutional layer, a convolution kernel weight of a current convolutional layer, b′ i a bias term of a current convolutional layer, M j an input feature map selected, and σ() represents an activation function. The extracted convolutional features are subjected to a pooling process:

[0129]

[0130] wherein down represents a down-sampling function, an output of a current pooling layer, an output of a previous pooling layer. The features subjected to the pooling process are summarized to obtain weather features and power features, respectively.

[0131] In a possible implementation, a weather hidden feature in the weather features is extracted by a first gating unit in the weather prediction unit, and a power hidden feature in the power features is extracted by a second gating unit in the power prediction unit, and specifically includes:

[0132] z t = σ(W uz x t +W hz hw t-1 +b z )

[0133] r t = σ(W ur x t +W hr hw t-1 +b r )

[0134] c t = σ(W uc x t +W hc (r t ⊙hw t-1 )+b c )

[0135] jw t = (1-z t )⊙hw t-1 +z t ⊙c t

[0136] wherein z t represents an output vector of an update gate at t, σ() represents an activation function, w u z represents a weight matrix between an input layer and the update gate, x t represents weather features or power features at t, W hz represents the self-connection weight matrix of the update gate between t time and t-1 time, hw t-1 h represents the hidden state vector of t-1 time, b z r represents the bias term of the update gate, t c represents the output vector of the reset gate at t time, W represents the weight matrix between the input layer and the reset gate, b represents the self-connection weight matrix of the reset gate between t time and t-1 time, b r c represents the bias term of the reset gate, t h represents the output vector of the candidate layer at t time, W uc W represents the weight matrix between the input layer and the candidate layer, W h c represents the self-connection weight matrix of the candidate layer between t time and t-1 time, b c r represents the bias term of the candidate layer, represents the element-wise product operation, hw t h represents the hidden state vector at t time. The activation function such as ReLU, tanh, sigmoid, etc. can be selected according to the specific requirements of the problem.

[0137] In a possible implementation, the first attention layer is used to add attention weights to the weather hidden features at each time, and the second attention layer in the power prediction unit is used to add attention weights to the power hidden features at each time, which specifically includes:

[0138] e t = σ(W h hw t +b h )

[0139]

[0140] hw′ t = α t hw t

[0141] wherein e t represents the attention score at t time, σ() represents the activation function, W represents the attention weight matrix, hw t h represents the hidden state vector at t time, b h r represents the bias term of the attention layer, α t represents the attention weight at t time, exp() represents the exponential function with the natural constant as the base, T represents the total time length of the data, hw′ tThe weather hidden feature or the power hidden feature to which the attention weight is added. In a possible implementation, the weather hidden feature and the power hidden feature to which the attention weight is added are spliced by a fully connected network:

[0142] H t t t

[0143] wherein H t represents the fused feature after splicing, hw t represents the weather hidden feature to which the attention weight is added, and hp t represents the power hidden feature to which the attention weight is added. In a possible implementation, according to the fused feature after splicing, a preliminary predicted power is obtained by a prediction layer:

[0144]

[0145] wherein represents the preliminary predicted power at time t, σ() represents an activation function, W H represents a prediction weight matrix, H t represents the fused feature after splicing, and b H represents a prediction layer bias term. In a possible implementation, a correlation coefficient between each adjacent day in the years before the prediction day is calculated:

[0146] wherein C i j represents the correlation coefficient between the prediction day and the jth adjacent day in the i years before, T i j represents the correlation number:

[0147]

[0148] V ij = g(w ij )

[0149] the time correlation coefficient of the jth adjacent day in the i years before, k1 represents the year correlation coefficient, k2 represents the date correlation coefficient, S i represents the weather correlation coefficient of the jth adjacent day in the i years before, f() represents a weather correlation function, w i j represents the weather type of the jth adjacent day in the i years before, and w 00 represents the weather type prediction value of the prediction day. The weather type prediction value of the prediction day is calculated according to the weather hidden feature to which the attention weight is added, V i j represents the randomness coefficient of the jth adjacent day in the i years before, and V 00 ​​​represents the correlation prediction power of the prediction day, g() is a random function. The correlation prediction power is calculated according to the correlation coefficient between the prediction day and each adjacent day in previous years.

[0150]

[0151] wherein, P c represents the correlation prediction power of the prediction day, P i j represents the power generation of the jth adjacent day in the ith previous year, n represents the total number of years, and m represents the total number of adjacent days. In a possible implementation, the specific manner in which the preliminary prediction power is corrected according to the correlation prediction power is as follows:

[0152]

[0153] wherein, P t represents the final prediction power at time t, P t represents the preliminary prediction power at time t, P ct represents the correlation prediction power at time t in the prediction day, and λ represents a correction coefficient.

[0154] S4: Constructing a target function of the upper-layer controller, aiming to improve the utilization rate of photovoltaic power generation and reduce power fluctuation.

[0155] In a possible implementation, the upper-layer control target function is specifically as follows:

[0156]

[0157] wherein, J H represents the upper-layer control target function, min represents taking the minimum value, represents the power flow at time t, represents the average power flow, T represents the total observation time length, λ1 represents the weight coefficient of the power flow term, and λ2 represents the weight coefficient of the power flow fluctuation term. In the present application, the weight coefficient λ1 of the power flow term and the weight coefficient λ2 of the power flow fluctuation term can be set according to actual conditions, and the present application is not limited in this regard. It should be noted that the smaller the power flow indicated by the power flow term, the higher the degree of self-sufficiency of the micro-grid, and the greater the utilization rate of photovoltaic power generation. In the present application, by constructing the upper-layer control target function, a balance between optimizing the power flow of the power grid and reducing fluctuation can be found, the utilization rate of photovoltaic power generation can be improved, the operation cost can be reduced, and the reliability and stability of the system can be improved. These benefits, taken together, help to achieve efficient, economic, and sustainable operation of the power grid.

[0158] Optionally, the power flow is specifically as follows:

[0159] P PCC = P+ -P -

[0160] wherein P P CC represents the power flow, P + represents the active power in the upstream direction of the node, P - represents the active power in the downstream direction of the node.

[0161] S5: determining the optimal power flow curve by the upper layer controller optimization under the constraints.

[0162] By the upper layer controller, the optimal power flow curve is determined under the constraints of the constraints using the particle swarm optimization algorithm with the upper layer control objective function as the target.

[0163] wherein the particle swarm optimization algorithm (PSO) is a swarm intelligence-based optimization algorithm inspired by the foraging behavior of bird flocks, which finds the optimal solution of a problem through information sharing and collaboration between individuals.

[0164] Specifically, the reciprocal of the upper layer control objective function is used as the fitness function of the particle swarm optimization algorithm.

[0165] Initialize the population, which contains multiple particles, each representing a feasible power flow curve.

[0166] Calculate the fitness of each particle.

[0167] Determine the individual optimal position and the global optimal position.

[0168]

[0169] wherein, represents the velocity of the ith particle at the t+1th iteration, represents the velocity of the ith particle at the tth iteration, ω represents the inertia weight factor, c1 represents the individual learning factor, c2 represents the global learning factor, and r1 and r2 both represent random numbers between 0 and 1, represents the individual optimal position of the ith particle at the tth iteration, represents the global optimal position of the ith particle at the tth iteration, represents the position of the ith particle at the tth iteration, represents the position of the ith particle at the t+1th iteration.

[0170] By calculating the velocity and position of the particles, combining the guidance of the individual optimal position and the global optimal position, the global search and the local search can be effectively balanced, and the optimal solution can be quickly approached. The fitness of each particle is recalculated. In the case that the fitness of the current particle is better than the individual optimal solution of the particle itself, the individual optimal solution of the particle itself is updated. In the case that the fitness of the current particle is worse than the individual optimal solution of the particle itself, the individual optimal solution of the particle itself is updated with a certain replacement probability. In the case that the fitness of the current particle is better than the global optimal solution, the global optimal solution is updated.

[0171] It should be noted that in the case that the fitness of the current particle is better than the individual optimal solution of the particle itself, the individual optimal solution is directly updated. Such an adaptive updating mechanism can ensure that the particle swarm timely follows the better solution found in the search process, and improves the convergence speed of the algorithm. In the case that the fitness of the current particle is worse than the individual optimal solution of the particle itself, the individual optimal solution is updated with a certain replacement probability. Such a mechanism introduces a certain randomness, prevents the individual optimal solution from falling into a local optimum, and thus enhances the global exploration ability.

[0172] It is judged whether the maximum number of iterations is reached. If yes, the power flow curve represented by the particle with the highest fitness value is output as the optimal power flow curve. Otherwise, the iteration is returned to continue.

[0173] The replacement probability is specifically:

[0174]

[0175] Wherein, P represents the replacement probability, e represents the natural constant, δ() represents the fitness function, C t represents the temperature at the t-th iteration. Wherein, the temperature is updated according to the following formula:

[0176] T i+1 = εT i

[0177] Wherein, ε represents the cooling coefficient, T i +1 represents the temperature at the i+l-th iteration, T i represents the temperature at the i-th iteration.

[0178] It should be noted that when the temperature is higher, it is easier to accept a worse solution, thereby increasing the chance of jumping out of the local optimum. With the increase of the number of iterations, the temperature gradually decreases, so that the algorithm performs more global search in the early stage, and gradually concentrates on local search in the later stage, thereby improving the optimization effect.

[0179] The cooling coefficient is specifically:

[0180]

[0181] Wherein, A1 represents the temperature oscillation factor of the first half cycle, B1 represents the temperature floating factor of the first half cycle, A2 represents the temperature oscillation factor of the second half cycle, and B2 represents the temperature floating factor of the second half cycle.

[0182] It should be noted that by dividing the temperature reduction process into two cycles, the temperature change in different stages can be finely controlled to adapt to different optimization requirements and search strategies. In each cycle, the temperature change not only considers exponential decay, but also combines sinusoidal oscillation and floating factor, making the temperature change more smooth and flexible. At the same time, the sinusoidal oscillation introduces a certain temperature fluctuation, avoiding premature convergence, increasing the diversity of solution space, and reducing the risk of falling into local optimal value.

[0183] In the present application, by using particle swarm optimization algorithm in upper layer control, the advantages of strong global search ability, fast convergence speed, simple implementation and adaptation to dynamic environment can be fully utilized, effectively improving the efficiency and quality of power grid dispatching optimization. This method can ensure that in the complex power grid operation environment, the optimal power flow scheme that meets various constraint conditions is found, and the overall performance and stability of the system are improved.

[0184] S6: According to the photovoltaic power prediction value, the lower layer control objective function is constructed, and the optimal power grid dispatching scheme is determined by the lower layer controller.

[0185] According to the power prediction value of each photovoltaic power generation module, the optimal power flow curve is taken as the reference power flow, the deviation between the actual power flow and the reference power flow is reduced, and the scheduling cost is reduced as the target, and the lower layer control objective function of the lower layer controller is constructed.

[0186] In one possible implementation, the lower layer control objective function is specifically:

[0187]

[0188] Wherein, J L represents the lower layer control objective function, min represents the minimum value, represents the power flow at time t, represents the reference power flow, T represents the total observation time, C t represents the scheduling cost at time t, μ1 represents the weight coefficient of the power flow deviation term, and μ2 represents the weight coefficient of the scheduling cost term.

[0189] Wherein, the person skilled in the art can set the weight coefficient μ1 of the power flow deviation term and the weight coefficient μ2 of the scheduling cost term according to the actual situation, and the present application is not limited.

[0190] In the present application, by constructing the lower layer control objective function, a balance between minimizing power flow deviation and scheduling cost can be found, improving the operation efficiency, stability and economy of the system. At the same time, by adjusting the weight coefficient flexibly, different operation requirements and strategies can be adapted to ensure that the lower layer control can achieve the overall optimization goal of the upper layer control and improve the comprehensive performance of the system.

[0191] Optionally, the scheduling cost is specifically:

[0192]

[0193] Wherein, C t represents the scheduling cost at time t, represents the main grid electricity price at time t, represents the main grid purchase electricity quantity at time t, N G represents the number of standby diesel generators, represents the unit power generation cost of the nth standby diesel generator, represents the power generation power of the nth standby diesel generator at time t, N ESS represents the number of energy storage systems, represents the unit energy storage cost of the nth energy storage system, represents the storage power of the nth energy storage system at time t, N PV represents the number of photovoltaic power generation modules, represents the unit power generation cost of the nth photovoltaic power generation module, represents the power generation power prediction value of the nth photovoltaic power generation module at time t.

[0194] In the present application, the actual cost of different power resources in the power grid can be considered comprehensively, the scheduling decision is optimized, and the economic benefit and operation efficiency of the system are improved. At the same time, the cost parameters can be adjusted flexibly to adapt to different market environments and operation conditions, enhance the robustness and stability of the system, promote the preferential use of renewable energy, and realize the efficient, economic and sustainable operation of the power grid.

[0195] The power generation power prediction values of each photovoltaic power generation module obtained by substituting the photovoltaic power generation power prediction model are determined by the lower layer controller under the constraint of the constraint condition, and the optimal power grid scheduling scheme is determined by taking the lower layer control objective function as the goal.

[0196] It should be noted that the power generation power prediction values of each photovoltaic power generation module obtained by substituting the photovoltaic power generation power prediction model can reduce the uncertainty brought by photovoltaic power generation, maintain the stability of power flow of the power grid combined with the regulation ability of the energy storage system, enhance the reliability of the system, and make the scheduling scheme more accurately reflect the actual situation.

[0197] In a possible implementation, the predicted power generation values of each photovoltaic power generation module predicted by substituting into the photovoltaic power generation power prediction model are used to determine the optimal power grid scheduling scheme by using the particle swarm optimization algorithm under the constraints of the constraints and by taking the lower layer control target function as the goal.

[0198] It should be noted that how to use the particle swarm optimization algorithm to determine the optimal power grid scheduling scheme can refer to the related technical solutions of using the particle swarm optimization algorithm to determine the optimal power flow curve, and details are not described herein again.

[0199] The application further provides a power grid scheduling system 20 based on photovoltaic power generation power prediction, applied to the power grid scheduling method based on photovoltaic power generation power prediction.

[0200] The processor 201.

[0201] The memory 202, the memory 202 stores computer readable instructions, and the computer readable instructions are executed by the processor 201 to realize the power grid scheduling method based on photovoltaic power generation power prediction.

[0202] The power grid scheduling system 20 based on photovoltaic power generation power prediction provided by the application can execute the power grid scheduling method based on photovoltaic power generation power prediction, and achieve the same or similar technical effects, and details are not described herein again.

[0203] In another aspect, the application further provides a power grid scheduling system based on photovoltaic power generation power prediction, which comprises:

[0204] The main power grid provides basic power supply and transmission functions.

[0205] The photovoltaic power generation module generates power by using photovoltaic technology.

[0206] The standby diesel generator provides emergency power supply when the main power grid or photovoltaic power generation is insufficient.

[0207] The energy storage system stores electrical energy when there is excess power and releases electrical energy when there is insufficient power, thereby smoothing the power output.

[0208] The upper layer controller is responsible for determining the optimal power flow curve, optimizing the photovoltaic power generation utilization rate and reducing the power fluctuation.

[0209] The lower layer controller optimizes the power grid scheduling scheme according to the photovoltaic power generation power prediction value and the optimal power flow curve, reduces the deviation between the actual power flow and the reference power flow, and reduces the scheduling cost.

[0210] The processor executes the power grid scheduling algorithm and the control strategy.

[0211] A memory stores related computer readable instructions and data for performing the scheduling method.

[0212] If the above functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts of the prior art that make contributions or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0213] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered a list of executable instructions for implementing logic functions, and can be specifically embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processor, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions, or in conjunction with these instructions. For the purpose of this specification, the "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport programs for use by an instruction execution system, apparatus, or device, or in conjunction with these instructions.

[0214] More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection having one or more wires (electrical devices), a portable computer diskette (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium can even be paper or other suitable medium on which the program can be printed, because the program can be electronically obtained, for example, by optical scanning of the paper or other medium, followed by editing, interpreting, or otherwise processing, if necessary, in other suitable ways, to be electronically obtained, and then stored in the computer memory.

[0215] It should be understood that various aspects of the application can be implemented in hardware, software, firmware or a combination of them. In the above embodiments, various steps or methods can be implemented in software or firmware that is stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any of the following technologies, known in the art, or their combinations, can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0216] Example 2

[0217] The test environment includes a power grid containing a main power grid, photovoltaic power generation modules, backup diesel generators and energy storage systems. The test scenario is set in an industrial park, which has 5 photovoltaic power generation modules, each with a rated power of 50kW; equipped with 2 backup diesel generators, each with a rated power of 100kW; and 1 energy storage system with a capacity of 200kWh.

[0218] A double-layer control model of the power grid is constructed. The upper-layer control model mainly includes the main power grid, photovoltaic power generation modules, backup diesel generators and energy storage systems, which are responsible for determining the optimal power flow curve. The lower-layer control model further refines the upper-layer control model to determine the optimal power grid scheduling scheme.

[0219] The constraint conditions of the double-layer control model of the power grid are defined, including power balance constraints, backup diesel generator power constraints, energy storage system charging and discharging power constraints, etc. These constraints ensure the stable operation of the power grid under various operating conditions. For example, the power balance constraint ensures that the total power generation of the power grid is equal to the total load demand at each time step, the backup diesel generator power constraint ensures that the generator power does not exceed its rated power, and the energy storage system charging and discharging power constraint limits the charging and discharging power of the energy storage system within the allowable range of the device. A photovoltaic power prediction model is constructed. This model uses historical weather data and photovoltaic power data to extract features through convolutional neural networks, and combines time series analysis methods to predict photovoltaic power within the next 24 hours. The input of the prediction model includes parameters such as temperature, humidity and solar radiation, and the output is the power prediction value of each photovoltaic power generation module.

[0220] After obtaining the photovoltaic power prediction value, the objective function of the upper-layer controller is constructed to improve the utilization rate of photovoltaic power generation and reduce power fluctuations. This objective function optimizes the operation of the power grid by minimizing power flow fluctuations and maximizing photovoltaic power utilization.

[0221] The upper controller optimizes the best power flow curve under the constraint condition. A particle swarm optimization algorithm is used for solving, and the particle swarm is initialized, each particle representing a feasible power flow curve. Through iterative calculation, the power flow curve represented by the particle with the highest fitness is finally determined.

[0222] According to the photovoltaic power prediction value, the lower control target function is constructed. The target function optimizes the scheduling scheme of the power grid by minimizing the deviation between the actual power flow and the reference power flow, and the scheduling cost. Finally, the lower controller determines the best power grid scheduling scheme under the constraint condition, and the same particle swarm optimization algorithm is used for solving, ensuring that the scheduling scheme meets the constraint conditions and realizes the efficient and stable operation of the system. The experimental data are shown in Table 1.

[0223] Table 1 Experimental data table

[0224]

[0225] From the data in the table, it can be seen that the present application effectively improves the utilization rate of photovoltaic power generation by constructing a double-layer control model and using a photovoltaic power generation power prediction model. Specifically, the photovoltaic power generation power is close to the rated power of 50kW, the photovoltaic power generation power fluctuation range of each test object is between 45-50kW, and the fluctuation amplitude is small. In addition, the power of the standby diesel generator is basically stable at 90-97kW, and the charge and discharge power of the energy storage system is between 20-30kW, which meets the set constraint conditions.

[0226] In terms of scheduling cost, through optimization of the scheduling scheme, the scheduling cost of each test object is less than 0.36 yuan / kWh, and the lowest is 0.31 yuan / kWh, which shows the significant advantage of the present application in reducing the scheduling cost. In terms of power fluctuation, the power fluctuation of all test objects is controlled within 5%, which shows high system stability, and the score is more than 9.3 points, with the highest reaching 9.8 points.

[0227] Compared with the prior art, the present application has obvious innovation and advantage in photovoltaic power prediction and power grid scheduling optimization. The prior art often cannot simultaneously consider the optimization of power fluctuation and scheduling cost, while the present application realizes the double optimization of power fluctuation and scheduling cost through the double-layer control model and the particle swarm optimization algorithm. In addition, the use of the photovoltaic power generation power prediction model makes the scheduling scheme more accurate, further improving the stability and economy of the system.

[0228] It should be noted that the above examples are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced, without departing from the spirit and scope of the technical solutions of the present application, which should be covered in the scope of the claims of the present application.

Claims

1. A grid dispatching method based on photovoltaic power generation power prediction, characterized in that: include: Establish a two-layer control model for the power grid including the main power grid, photovoltaic power generation modules, backup diesel generators and energy storage systems; Define the constraints of the two-tier control model for the power grid; Use the photovoltaic power prediction model to predict the power of each photovoltaic power generation module; With the goal of improving photovoltaic power generation utilization and reducing power fluctuations, the objective function of the upper-level controller is constructed; Under the constraints, the optimal power flow curve is determined by optimizing the upper controller; According to the predicted value of photovoltaic power generation, the lower-level control objective function is constructed, and the optimal grid dispatching plan is determined through the lower-level controller; The grid two-layer control model includes an upper layer controller for determining an optimal power flow curve and a lower layer controller for determining an optimal grid dispatching solution; Using a photovoltaic power generation power prediction model, power prediction is performed on each photovoltaic power generation module, and the photovoltaic power generation power prediction model includes a weather prediction unit and a power prediction unit; The weather prediction unit includes a first convolutional layer, a first gating unit, and a first attention layer connected in series, and the power prediction unit includes a second convolutional layer, a second gating unit, and a second attention layer connected in series; The first and second attention layers are both connected to the fully connected network, and the fully connected layer is connected to the prediction layer; Obtain historical weather data and historical photovoltaic power generation data, extract weather features from the historical weather data through the first convolutional layer in the weather prediction unit, and extract power features from the historical photovoltaic power generation data through the second convolutional layer in the power prediction unit; Extracting weather hidden features from weather features through a first gating unit in a weather prediction unit, and extracting power hidden features from power features through a second gating unit in a power prediction unit; The first attention layer in the weather prediction unit adds attention weights to the weather hidden features at each moment, and the second attention layer in the power prediction unit adds attention weights to the power hidden features at each moment; The weather hidden features and power hidden features after adding attention weights are spliced ​​together through a fully connected network. Based on the spliced ​​fusion features, power prediction is performed through the prediction layer to obtain the preliminary predicted power. Based on the time periodicity and the nearest neighbor similarity, the preliminary predicted power is revised to determine the final predicted power. According to the correlation predicted power, the preliminary predicted power is revised to determine the final predicted power.

2. The grid dispatching method based on photovoltaic power generation prediction according to claim 1, characterized in that: The photovoltaic power generation prediction model is used to predict the power of each photovoltaic power generation module. The photovoltaic power generation prediction model also includes, with the goal of improving photovoltaic power generation utilization and reducing power fluctuations, constructing the objective function of the upper-level controller, including calculating the correlation coefficient between each adjacent day in the year before the prediction day: S ij =f(w ij ,w 00 ) V ij =g(w ij ) Among them, C i j represents the correlation coefficient between the forecast day and the jth adjacent day in the previous i years, T i j represents the time correlation coefficient of the jth adjacent day in the previous i years, k1 represents the year correlation coefficient, k2 represents the date correlation coefficient, S i j represents the weather correlation coefficient of the jth adjacent day in the previous i year, w i j represents the weather type of the jth consecutive day in the previous i year, w 00 Represents the weather type prediction value of the forecast day. The weather type prediction value of the forecast day is calculated based on the weather hidden features after adding the attention weight. V i j represents the randomness coefficient of the jth consecutive day in the previous i years, V 00 represents the random coefficient of the forecast day; The correlation prediction power is calculated based on the correlation coefficient between the forecast day and each adjacent day in the previous year: Among them, P c Represents the correlation prediction power of the prediction day, P ij represents the power generation on the jth consecutive day in the previous i years, n represents the total number of years, and m represents the total number of consecutive days; The specific method of correcting the preliminary predicted power according to the correlation predicted power is as follows: Among them, P t represents the final predicted power at time t, represents the preliminary predicted power at time t, P ct represents the correlation prediction power at time t in the forecast day, and λ represents the correction coefficient.

3. The grid dispatching method based on photovoltaic power generation prediction according to claim 2, characterized in that: With the goal of improving photovoltaic power generation utilization and reducing power fluctuations, the objective function of the upper-level controller is constructed. The upper-level control objective function is specifically: Among them, J H Represents the upper control objective function, min represents the minimum value, represents the power flow at time t, represents the average power flow, T represents the total observation time, λ1 represents the weight coefficient of the power flow term, and λ2 represents the weight coefficient of the power flow fluctuation term. Those skilled in the art can set the values ​​of the weight coefficient λ1 of the power flow term and the weight coefficient λ2 of the power flow fluctuation term according to actual conditions; The power flow is specifically: P PCC =P + -P - Among them, P P CC represents power flow, P + Indicates the active power in the upstream direction of the node, P - Indicates the active power in the downstream direction of the node; The smaller the power flow indicated by the power flow item, the higher the degree of self-sufficiency within the microgrid, and the greater the utilization rate of photovoltaic power generation.

4. The grid dispatching method based on photovoltaic power generation prediction according to claim 3, characterized in that: Under the constraint conditions, optimizing and determining the optimal power flow curve through the upper-level controller includes, through the upper-level controller, under the constraint conditions, taking the upper-level control objective function as a target, using a particle swarm optimization algorithm to determine the optimal power flow curve; Initialize the population, which contains multiple particles. Each particle represents a feasible power flow curve. Calculate the fitness of each particle and determine the individual optimal position and the global optimal position. The formula is expressed as: in, represents the velocity of the i-th particle at the t+l-th iteration, represents the velocity of the i-th particle at the t-th iteration, ω represents the inertia weight factor, c1 represents the individual learning factor, c2 represents the global learning factor, r1 and r2 both represent random numbers between 0 and l, represents the individual optimal position of the i-th particle at the t-th iteration, represents the global optimal position of the i-th particle at the t-th iteration, represents the position of the i-th particle at the t-th iteration, represents the position of the i-th particle at the t+l-th iteration; Determine whether the maximum number of iterations has been reached. If so, output the power flow curve represented by the particle with the highest fitness value as the optimal power flow curve. Otherwise, return to continue iteration. The replacement probability is specifically: Among them, P represents the replacement probability, e represents the natural constant, δ() represents the fitness function, C t represents the temperature at the tth iteration; Update the temperature: T i+1 =εT i Where ε represents the temperature drop coefficient, T i +1 represents the temperature at the i+1th iteration, T i represents the temperature at the i-th iteration; When the temperature is high, it is easier to accept poor solutions, thereby increasing the chance of escaping the local optimum. As the number of iterations increases, the temperature gradually decreases, causing the algorithm to conduct more global searches in the early stages and gradually focus on local searches in the later stages, improving the optimization effect. The specific temperature reduction coefficient is: Among them, A1 represents the cooling oscillation factor of the first half cycle, B1 represents the cooling floating factor of the first half cycle, A2 represents the cooling oscillation factor of the second half cycle, and B2 represents the cooling floating factor of the second half cycle.

5. The grid dispatching method based on photovoltaic power generation prediction according to claim 4, characterized in that: According to the predicted value of photovoltaic power generation, the lower-level control objective function is constructed, and the optimal grid dispatching scheme is determined by the lower-level controller. The specific lower-level control objective function is: Among them, J L Represents the lower-level control objective function, min represents the minimum value, represents the power flow at time t, represents the reference power flow, T represents the total observation time, C t represents the dispatch cost at time t, μ1 represents the weight coefficient of the power flow deviation term, and μ2 represents the weight coefficient of the dispatch cost term; By flexibly adjusting the weight coefficients to adapt to different operating requirements and strategies, it ensures that the lower-level control can achieve the overall optimization goals of the upper-level control and improve the overall performance of the system; The scheduling cost is specifically: Among them, C t represents the scheduling cost at time t, represents the main grid electricity price at time t, N represents the amount of electricity purchased by the main power grid at time t. G Indicates the number of standby diesel generators, represents the unit power generation cost of the nth standby diesel generator, N represents the power generated by the nth standby diesel generator at time t, E SS represents the number of energy storage systems, represents the unit energy storage cost of the nth energy storage system, represents the storage power of the nth energy storage system at time t, N P V represents the number of photovoltaic power generation modules, represents the unit power generation cost of the nth photovoltaic power generation module, P n t P V represents the predicted power generation value of the nth photovoltaic power generation module at time t.

6. A power grid dispatching system based on photovoltaic power generation prediction using the method according to any one of claims 1 to 5, characterized in that: The main power grid provides basic power supply and transmission functions; Photovoltaic power generation modules, which use photovoltaic technology to generate electricity; A backup diesel generator provides emergency power supply when the main power grid or photovoltaic power generation is insufficient; Energy storage systems store electricity when there is excess power and release it when there is a power shortage, thus smoothing power output; The upper controller is responsible for determining the optimal power flow curve, optimizing photovoltaic power generation utilization and reducing power fluctuations; The lower-level controller optimizes the grid dispatching plan based on the predicted photovoltaic power generation value and the optimal power flow curve, reduces the deviation between the actual power flow and the reference power flow, and reduces the dispatching cost; Processor, which executes grid dispatch algorithms and control strategies; The memory stores relevant computer-readable instructions and data for executing the scheduling method.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the power grid scheduling method based on photovoltaic power generation power prediction according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the power grid dispatching method based on photovoltaic power generation prediction according to any one of claims 1 to 5 are implemented.

Images