Flexible interconnected power distribution network scheduling method and system based on Gaussian mixture model

Abstract

The invention discloses a flexible interconnected power distribution network scheduling method and system based on a Gaussian mixture model, and the method comprises the steps: building a source load power probability model of a flexible interconnected power distribution network, and determining an injection power random variable through an injection power prediction value and a sampling value of an injection power prediction error; taking the minimum operation loss cost of the flexible interconnected power distribution network as a target function, establishing a constraint condition of the target function, and determining an inverse function of a cumulative distribution function of an injection power random variable based on a source load power probability model; transforming the probability constraint condition that the node voltage does not exceed the limit and the probability constraint condition that the branch power does not exceed the limit by using the inverse function and the node injection power adjustment amount, performing relaxation processing on the power balance constraint condition of the AC / DC system, and forming a flexible interconnected power distribution network dispatching optimization model with the target function; and carrying out iterative solution on the flexible interconnection power distribution network scheduling optimization model to obtain an optimal value of the injection power adjustment amount of each node, taking the optimal value as a power value exchanged by the flexible interconnection device, and meeting the scheduling requirement of the medium-voltage flexible interconnection system.

Description

Technical Field

[0001] The present invention belongs to the technical field of power grid dispatching, and relates to an optimization dispatching technology for a flexible interconnected distribution system, and specifically to an optimization dispatching method and system for a flexible interconnected distribution network that takes into account the probability distribution characteristics of source and load power. Background Art

[0002] Flexible interconnection technology of medium-voltage distribution network based on flexible interconnection device improves system flexibility. The continuous increase of renewable energy and new power loads has put forward higher requirements for the flexibility of distribution system, especially when the source and load power have strong uncertainty, how to maximize the flexibility potential of medium-voltage flexible interconnection system in the dispatching process. In addition, for medium-voltage interconnected flexible distribution network, the number of source and load access is large, and the spatiotemporal distribution of power is complex. Considering the probability distribution, it becomes more difficult to solve the optimization model. Therefore, it is necessary to propose a dispatch optimization method that considers the multi-dimensional randomness of source and load.

[0003] In the prior art, in the optimization dispatching scheme that takes into account the voltage risk perception of AC / DC distribution networks, the day-ahead decision dispatching takes economy as the goal, and the intraday risk dispatching takes into account the ultra-short-term fluctuation characteristics of distributed photovoltaics and loads. Based on the ultra-short-term prediction probability information, the random response surface method combined with the Nataf transform is used to calculate the probabilistic flow, and a voltage risk perception system is established based on the probabilistic flow results; however, this method cannot realize the source-load probability modeling of multi-dimensional random variables. The low-voltage load reduction optimization strategy for AC / DC hybrid systems with static voltage stability indicators as constraints calculates the system flow based on the alternating iteration method, and establishes a static voltage stability index suitable for AC / DC transmission; based on the improved genetic algorithm, the optimal load shedding configuration strategy is solved with the minimum low-voltage load shedding loss cost as the objective function; this method only analyzes the optimal load shedding strategy, and does not consider the impact of the access of large-scale distributed photovoltaics and electric vehicles and other equipment. The distributed multi-PV coordinated control strategy based on discrete consistency algorithm obtains the average value of the power deviation and operation mode of the PV controller through the discrete consistency algorithm, updates the operation mode instruction and power reference instruction, and uses the complementary power between PV to balance the power deviation, so that the PV can adaptively work in the maximum power tracking mode or fixed power mode; this method effectively smoothes the power fluctuation of PV in different application scenarios, but is not suitable for AC / DC distribution network optimization considering uncertainty. Among the existing optimization scheduling methods that take into account the randomness of source and load power, the Monte Carlo method or the analytical method based on probability distribution is mainly used to overcome the influence of uncertainty. However, for the medium-voltage flexible interconnected distribution system, the number of random sources and loads is large, the dimension is high, and there is a significant correlation between the various power variables. The probabilistic modeling method based on the Monte Carlo method takes too long to model such high-dimensional massive data and cannot meet the scheduling requirements. The robust optimization method based on variable interval can only obtain the optimal solution in the worst scenario, facing the problem of excessive conservatism. Although the traditional chance constraint method can calculate the optimal solution under a certain confidence level, the model solution also has the problem of long time, especially in the case of complex source-load scenarios in the medium-voltage interconnected distribution system. In addition, for the flexible interconnected system, since it is necessary to optimize the exchange power of the flexible interconnected equipment, the correlation of random variables between the interconnected systems cannot be ignored. Summary of the invention

[0004] In order to solve the deficiencies in the prior art, the present invention provides a flexible interconnected distribution network scheduling method and system based on a Gaussian mixture model. The Gaussian mixture model is used to implement probability modeling that takes into account the correlation of random variables in the flexible interconnected system, and the probability distribution and correlation of a large number of high-dimensional random variables can be quickly and analytically characterized. Based on the cumulative distribution function of the Gaussian mixture model, the chance constraints are split and transformed, and the cumulative distribution function curve is fitted using a fourth-order polynomial, and the root of the fourth-order polynomial is calculated to obtain the quantile of the cumulative distribution function, thereby converting the difficult-to-handle chance constraints into linear constraints, accelerating the solution of the optimization model, and enabling it to meet the scheduling needs of the medium-voltage flexible interconnected system.

[0005] The present invention adopts the following technical solution.

[0006] The present invention proposes a flexible interconnected distribution network scheduling method based on a Gaussian mixture model, comprising:

[0007] The load power and the output power of distributed generation in the flexible interconnected distribution network are obtained as random variables, and based on the Gaussian mixture model, the superposition of multiple Gaussian distributions of random variables is used as the source-load power probability model of the flexible interconnected distribution network;

[0008] The injection power prediction error is determined by using the actual value of the injection power and the injection power prediction value of each node in the flexible interconnected distribution network; the actual value of the injection power and its sampling time constitute the injection power time series value; based on the source-load power probability model, the joint probability density function of the injection power prediction error and the injection power time series value is determined; using the conditional probability invariance characteristic of the Gaussian mixture model, based on the joint probability density function of the injection power prediction error and the injection power time series value, the conditional probability density function of the injection power prediction error is determined; based on the conditional probability density function of the injection power prediction error, the sampling value of the injection power prediction error is obtained, and the injection power random variable is determined by using the injection power prediction value and the sampling value of the injection power prediction error;

[0009] The objective function is to minimize the operating loss cost of the flexible interconnected distribution network, and the operating loss cost includes the AC system loss cost, the DC system loss cost, and the converter loss cost; the constraint conditions of the objective function are established, including: the probability constraint conditions of the node voltage not exceeding the limit and the probability constraint conditions of the branch power not exceeding the limit established by the chance constraint programming method, the AC / DC system power balance constraint conditions, and the converter operation constraint conditions; the inverse function of the cumulative distribution function of the injected power random variable is determined based on the source-load power probability model, and the probability constraint conditions of the node voltage not exceeding the limit and the probability constraint conditions of the branch power not exceeding the limit are transformed by the inverse function and the node injected power adjustment amount, and the AC / DC system power balance constraint conditions are relaxed based on the Distflow power flow model; the transformed probability constraint conditions of the node voltage not exceeding the limit and the probability constraint conditions of the branch power not exceeding the limit, the processed AC / DC system power balance constraint conditions, and the converter operation constraint conditions are used together with the objective function to form a flexible interconnected distribution network dispatching optimization model; the flexible interconnected distribution network dispatching optimization model is iteratively solved to obtain the optimal value of the injected power adjustment amount of each node as the power value exchanged by the flexible interconnected device.

[0010] Preferably, the source-load power probability model of the flexible interconnected distribution network satisfies the following relationship:

[0011]

[0012] In the formula, f X (x) is the marginal probability density of the random variable X, M is the number of Gaussian components in the Gaussian mixture model; x is the sample of the random variable; ω m is the weight of the mth Gaussian component; N m () is the mth one-dimensional normal distribution; are the mean and covariance of the mth Gaussian component of sample x, respectively.

[0013] Preferably, the injected powers of W nodes in the flexible interconnected distribution network are random, and a first random vector X1 is used to represent the actual values ​​of the injected powers of the W nodes, satisfying X1=[X 11 X 12 …X 1i …X 1W ] T , where X 1i is the actual value of the injected power of the ith node, and the second random vector X2 is used to represent the predicted value of the injected power of W nodes, satisfying X2 = [X 21 X 22 … X 2i … X 2W ] T , X 2iis the injection power prediction value of the ith node, then the third random vector representing the injection power prediction error of the W nodes satisfies the following relationship:

[0014] X e =X1-X2 (3)

[0015] Satisfy X e =[X e1 X e2 …X ei …X eW ] T , X ei is the injection power prediction error of the i-th node.

[0016] Preferably, the sampling times of the actual values ​​of the injected powers of the W nodes constitute a time series vector, satisfying T=[T1 T2…T i …T W ] T , T i is the sampling time of the actual value of the injected power of the i-th node;

[0017] Construct a matrix Y that satisfies Y = [X1 T] T , Y i is the injection power timing value of the ith node, including the actual value of the injection power of the ith node and its sampling time;

[0018] Based on the Gaussian mixture model, the joint probability density function of the injection power prediction error of the i-th node and the injection power time series value of the i-th node satisfies the following relationship:

[0019]

[0020] In the formula, is the joint probability density function of the injection power prediction error of the i-th node and the injection power time series value of the i-th node, y i Y i A sample of x ei For X ei A sample of are the mean and covariance of the mth Gaussian component of the ith node, is the weight of the mth Gaussian component of the ith node, is the m-th one-dimensional normal distribution of the ith node, is the covariance of the injection power prediction error of the ith node to the mth Gaussian component of the injection power prediction error, is the covariance of the mth Gaussian component of the injection power prediction error of the ith node with respect to the injection power time series value, is the covariance of the injected power timing value of the ith node with respect to the mth Gaussian component of the injected power timing value, is the mean value of the mth Gaussian component of the injection power prediction error of the ith node, is the mean value of the mth Gaussian component of the injection power timing value of the ith node, and W is the number of nodes.

[0021] Preferably, the conditional probability density function of the injection power prediction error satisfies the following relationship:

[0022]

[0023] In the formula, is the joint probability density function of the injection power prediction error of the i-th node and the injection power time series value of the i-th node, is the weight of the mth Gaussian component of the injection power prediction error of the ith node under the condition of the given injection power actual value time series distribution, is the m-th one-dimensional normal distribution of the ith node, is the mean value of the mth Gaussian component of the conditional probability distribution of the injection power prediction error of the ith node under the condition of the given injection power actual value time series distribution, is the covariance of the mth Gaussian component of the conditional probability distribution of the injection power prediction error of the ith node under the condition of a given injection power actual value time series distribution.

[0024] Preferably, the objective function is to minimize the operating loss cost of the flexible interconnected distribution network, and the operating loss cost includes the AC system loss cost, the DC system loss cost, and the converter loss cost; the objective function satisfies the following relationship:

[0025] C loss =C loss，AC +C loss，DC +C loss，VSC (6)

[0026]

[0027] In the formula, C loss is the operating loss cost of the flexible interconnected distribution network, C loss，AC is the AC system loss cost; C loss，DC is the DC system loss cost, C loss，VSC is the converter loss cost; N AC is the number of nodes in the AC system; N DC is the number of nodes in the DC system network; Ω(i) is the set of neighboring nodes of node i; r ij，AC is the resistance of the AC branch ij; r ij，DC is the resistance of the DC branch ij; Iij，AC is the square value of the current flowing through the AC branch ij; I ij，DC is the square value of the current flowing through the DC branch ij.

[0028] Preferably, the constraints of the objective function are established, including: probability constraints of node voltage not exceeding the limit and branch power not exceeding the limit established by chance constraint programming method, AC / DC system power balance constraints and converter operation constraints.

[0029] Preferably, the probability constraint condition that the node voltage does not exceed the limit satisfies the following relationship:

[0030] P{U i,min ≤U i (ξ)≤U i,max}≥β U

[0031] Where U i (ξ) is the voltage of node i in the distribution network operation state ξ; U i,min and U i,max is the lower and upper limits of the voltage at node i; P{U i,min ≤U i (ξ)≤U i,max} is the probability that the voltage of node i does not exceed the limit under the distribution network operation state ξ; β U is the confidence level that the node voltage does not exceed the limit;

[0032] The probability constraint condition for the branch power not to exceed the limit satisfies the following relationship:

[0033] P{P k (ξ)≤P k,max}≥β P

[0034] Where P k (ξ) is the active power of branch k in the distribution network operating state ξ; P k,max is the upper limit of active power of branch k; P{P k (ξ)≤P k,max} is the probability that the active power of branch k does not exceed the limit under the distribution network operation state ξ; β P is the confidence level that the branch power does not exceed the limit.

[0035] Preferably, the AC / DC system power balance constraint condition satisfies the following relationship:

[0036]

[0037] Where P AC,i and Q AC,iare the active power and reactive power injected into the AC system node i respectively; G AC,ij , B ij ,θ ij are the conductance, susceptance and voltage phase difference between nodes i and j in the AC system respectively; U AC,i and U AC,j are the voltage amplitudes of nodes i and j in the AC system respectively; P DC,i is the active power injected into the DC system node i; U DC,i and U DC,j are the voltages of nodes i and j in the DC system respectively; G DC,ij is the conductance between nodes i and j in the DC system, N AC is the number of nodes in the AC system; N DC is the number of nodes in the DC system network.

[0038] Preferably, the operating constraints of the converter satisfy the following relationship:

[0039]

[0040] Where P VSC and Q VSC are the active power and reactive power flowing through the converter respectively; S VSC is the capacity of the converter.

[0041] Preferably, the inverse function of the cumulative distribution function of the injected power random variable is determined based on the source load power probability model, and the probability constraint condition that the node voltage does not exceed the limit and the probability constraint condition that the branch power does not exceed the limit are transformed by the inverse function and the node injected power adjustment amount, including:

[0042] Based on the injected power random variable, the probability constraint condition of the node voltage not exceeding the limit and the probability constraint condition of the branch power not exceeding the limit are transformed by the following relationship:

[0043]

[0044] Where P r () is the probability of a specific event occurring, ΔV i,max is the upper limit of the voltage deviation at node i, ΔP i,max is the upper limit of branch power deviation, A1 is the conversion coefficient matrix of node injection power adjustment and node voltage deviation, B1 is the conversion coefficient matrix of node injection power adjustment and branch power deviation, A2 is the conversion coefficient matrix of node injection power random variable and node voltage deviation, B2 is the conversion coefficient matrix of node injection power random variable and branch power deviation, ΔP adj,t is the injection power adjustment amount of the node at time t, ΔP ran,tis the random variable of the injected power at the node at time t, α set For a given confidence level;

[0045] Based on the source-load power probability model, the cumulative distribution function of the node injection power random variable is determined; based on the cumulative distribution function, the probability constraint conditions of the converted node voltage not exceeding the limit and the probability constraint conditions of the branch power not exceeding the limit are transformed for the first time, and the following relationship is obtained:

[0046]

[0047] In the formula, is the cumulative distribution function of the random variable of the injected power at the node at time t;

[0048] Based on the inverse function of the cumulative distribution function, the probability constraint condition of the node voltage not exceeding the limit and the probability constraint condition of the branch power not exceeding the limit are transformed for the second time, and the following relationship is obtained:

[0049]

[0050] In the formula, It is the inverse of the cumulative distribution function.

[0051] The present invention also proposes a flexible interconnected distribution network dispatching system based on a Gaussian mixture model, comprising:

[0052] The load power modeling module is used to obtain the load power and the output power of the distributed power source in the flexible interconnected distribution network as random variables. Based on the Gaussian mixture model, the superposition of multiple Gaussian distributions of random variables is used as the source-load power probability model of the flexible interconnected distribution network.

[0053] The power prediction error modeling module is used to determine the injection power prediction error by using the actual value of the injection power and the injection power prediction value of each node in the flexible interconnected distribution network; the actual value of the injection power and its sampling time constitute the injection power time series value; based on the source-load power probability model, the joint probability density function of the injection power prediction error and the injection power time series value is determined; using the conditional probability invariance characteristic of the Gaussian mixture model, based on the joint probability density function of the injection power prediction error and the injection power time series value, the conditional probability density function of the injection power prediction error is determined;

[0054] The flexible interconnected distribution network dispatching optimization module is used to take the minimization of the operating loss cost of the flexible interconnected distribution network as the objective function, and the operating loss cost includes the AC system loss cost, the DC system loss cost, and the converter loss cost; establish the constraint conditions of the objective function, including: the probability constraint conditions of the node voltage not exceeding the limit and the probability constraint conditions of the branch power not exceeding the limit established by the chance constraint programming method, the AC and DC system power balance constraint conditions, and the converter operation constraint conditions; construct a flexible interconnected distribution network dispatching optimization model with the objective function and its constraint conditions; iteratively solve the flexible interconnected distribution network dispatching optimization model to obtain the optimal value of the injected power adjustment amount of each node as the power value exchanged by the flexible interconnected device.

[0055] A terminal comprises a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the steps of the method.

[0056] A computer-readable storage medium stores a computer program, which implements the steps of the method when executed by a processor.

[0057] The beneficial effects of the present invention are that, compared with the prior art, at least the present invention includes: firstly, considering the access of uncertain resources on the source and load side, such as photovoltaics and electric vehicles, to the flexible interconnected distribution network, and characterizing the probability distribution characteristics of the source and load power through the Gaussian mixture model. On this basis, an optimization scheduling model of the AC and medium voltage flexible interconnected distribution system is established based on opportunity constraint optimization, and the maximum comprehensive benefit of AC and DC distribution station operation is set as the goal. The constraints include power balance constraints, equipment operation constraints, and probability constraints of node voltage and branch power. The properties that can be expressed analytically by the cumulative distribution function of the Gaussian mixture model are used, and the quantile function is used to convert the opportunity constraints containing probability values ​​into deterministic constraints, and then the power flow equation constraints are relaxed into second-order cone constraints, thereby converting the probability optimization scheduling model considering uncertainty into a deterministic second-order cone optimization model, and realizing rapid solution of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 is a typical medium voltage power distribution network wiring diagram in an embodiment of the present invention;

[0059] Figure 2 It is a wiring diagram of an AC / DC hybrid power distribution network including SOP and VSC in an embodiment of the present invention;

[0060] Figure 3 It is a flow chart of a flexible interconnected distribution network dispatching method based on Gaussian mixture model proposed by the present invention;

[0061] Figure 4 is a wiring diagram of a modified IEEE33 node system in an embodiment of the present invention;

[0062] Figure 5is a distributed power source and load power curve diagram in an embodiment of the present invention;

[0063] Figure 6 It is the active and reactive output curve diagram of two SOPs in the embodiment of the present invention;

[0064] Figure 7 This is a voltage distribution diagram of the outgoing line 1 of the substation before optimization in an embodiment of the present invention;

[0065] Figure 8 This is a voltage distribution diagram of outgoing line 1 of a substation after optimization in an embodiment of the present invention. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The embodiments described in this application are only embodiments of a part of the present invention, rather than all embodiments. Based on the spirit of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work belong to the protection scope of the present invention.

[0067] Figure 1 The figure shows a typical medium voltage distribution network wiring diagram. Line 1 and Line 2 are connected to the 10kV AC busbar respectively. The distribution networks connected to Line 1 and Line 2 are connected to the photovoltaic power station PV and the wind farm WT respectively. Among them, Line 1 is equipped with 5 normally open contact switches, such as Figure 1 The dotted line between node 8 and node 21, the dotted line between node 12 and node 22, the dotted line between node 25 and node 29, the dotted line between node 9 and node 15, and the dotted line between node 18 and node 33 on the middle line 1 all represent tie switches.

[0068] right Figure 1 The medium voltage distribution network wiring shown in the figure is modified to obtain Figure 2 The AC / DC hybrid distribution network wiring shown in FIG. 1 is a diagram in which the tie switch between node 25 and node 29 on line 1 is replaced with an intelligent soft switch SOP1, and the tie switch between node 12 and node 22 is replaced with an intelligent soft switch SOP2. A voltage source converter VSC1 is configured at the head end of line 2, and a voltage source converter VSC2 is configured between line 1 and line 2 to transform the entire AC line of line 2 into a DC line, such as Figure 2As shown by the midpoint line. Through the above transformation, an AC / DC hybrid distribution network containing SOP and VSC is formed. Taking into account that the cost of flexible equipment such as converters and intelligent soft switches is still relatively expensive, converting lines with more DC sources and loads such as distributed photovoltaic power generation and electric vehicles into DC lines, and replacing some interconnecting switches in the AC distribution network with intelligent soft switches, is a feasible solution that takes into account both investment costs and the operation effect of the distribution network. It is conducive to the absorption of distributed clean energy and improves the asset utilization rate of the distribution network. In this AC / DC hybrid distribution network, the distribution network flow control and operation optimization can be achieved by coordinating interconnecting switches and SOP. The exchange power of the flexible interconnection device is the decision variable of the method proposed in the present invention, which represents the active power exchanged between the interconnected systems through SOP and the reactive power emitted or absorbed by SOP in the interconnected systems on both sides during the scheduling process. Compared with the random fluctuating power in the system, the above decision variables belong to adjustable power, so they are uniformly defined as ΔP adj,t , which is used to represent the exchange power of the flexible interconnection device in the system, i.e., the decision variable.

[0069] Taking a flexible interconnected distribution network including SOP and VSC as an object, the present invention provides a flexible interconnected distribution network scheduling method based on a Gaussian mixture model, such as Figure 3 As shown, including:

[0070] Step 1: Obtain the load power and the output power of the distributed power source in the flexible interconnected distribution network as random variables, and based on the Gaussian mixture model, use the superposition of multiple Gaussian distributions of the random variables as the source-load power probability model of the flexible interconnected distribution network.

[0071] Specifically, the load power of a node in the flexible interconnected distribution network and the output power of the distributed generation are taken as random variables X. Based on the Gaussian mixture model (GMM), the probability distribution of the random variable X is characterized by the superposition form of several Gaussian distributions. The established source-load power probability model satisfies the following relationship:

[0072]

[0073] In the formula, f X (x) is the marginal probability density of the random variable X, M is the number of Gaussian components in the Gaussian mixture model; x is the sample of the random variable; ω m is the weight of the mth Gaussian component; N m () is the mth one-dimensional normal distribution; are the mean and covariance of the mth Gaussian component of sample x, respectively.

[0074] Take the random variable X and its conjugate matrix Constructing random variables Since GMM has marginal probability invariance and conditional probability invariance, the random variable If it obeys GMM, then its marginal probability distribution and conditional probability distribution also obey GMM, satisfying the following relationship:

[0075]

[0076] In the formula, For the random variable X in the event The conditional probability of occurrence, For events Sample, ω′ m For the random variable X in the event The weight of the mth Gaussian component of the conditional probability is, is the conditional probability of the mth one-dimensional normal distribution.

[0077] Step 2, using the actual value of injected power and the predicted value of injected power of each node in the flexible interconnected distribution network, determine the injected power prediction error; the actual value of injected power and its sampling time constitute the injected power time series value, and based on the source-load power probability model, determine the joint probability density function of the injected power prediction error and the injected power time series value; using the conditional probability invariance characteristic of the Gaussian mixture model, based on the joint probability density function of the injected power prediction error and the injected power time series value, determine the conditional probability density function of the injected power prediction error; based on the conditional probability density function of the injected power prediction error, obtain the sampling value of the injected power prediction error, and determine the injected power random variable using the injected power prediction value and the sampling value of the injected power prediction error;

[0078] Specifically, step 2 includes:

[0079] Step 2.1, using the actual value of injected power and the predicted value of injected power of each node in the flexible interconnected distribution network, determine the injected power prediction error;

[0080] Specifically, the injected power of W nodes in the flexible interconnected distribution network is random, and the first random vector X1 is used to represent the actual value of the injected power of W nodes, satisfying X1=[X 11 X 12 …X 1i …X 1W ] T , where X 1i is the actual value of the injected power of the ith node, and the second random vector X2 is used to represent the predicted value of the injected power of W nodes, satisfying X2 = [X 21 X 22 … X 2i … X 2W ] T , X 2iis the injection power prediction value of the ith node, then the third random vector representing the injection power prediction error of the W nodes satisfies the following relationship:

[0081] X e =X1-X2 (3)

[0082] Satisfy X e =[X e1 X e2 …X ei …X eW ] T , X ei is the injection power prediction error of the i-th node.

[0083] Step 2.2, the actual value of the injected power and its sampling time constitute the injected power time series value, and based on the source-load power probability model, the joint probability density function of the injected power prediction error and the injected power time series value is determined;

[0084] The sampling time of the actual value of the injected power of W nodes constitutes a time series vector, satisfying T = [T1 T2…T i …T W ] T , T i is the sampling time of the actual value of the injected power of the i-th node.

[0085] Construct a matrix Y that satisfies Y = [X1 T] T , Y i is the injection power timing value of the ith node, including the actual value of the injection power of the ith node and its sampling time, y i Y i A sample of x ei For X ei Therefore, based on the Gaussian mixture model, the joint probability density function of the injection power prediction error of the i-th node, the injection power prediction error of the i-th node and the injection power time series value satisfies the following relationship:

[0086]

[0087] In the formula, is the joint probability density function of the injection power prediction error of the i-th node and the injection power time series value of the i-th node, are the mean and covariance of the mth Gaussian component of the ith node, is the weight of the mth Gaussian component of the ith node, is the m-th one-dimensional normal distribution of the ith node, is the covariance of the injection power prediction error of the ith node to the mth Gaussian component of the injection power prediction error, is the covariance of the mth Gaussian component of the injection power prediction error of the ith node with respect to the injection power time series value, is the covariance of the injected power timing value of the ith node with respect to the mth Gaussian component of the injected power timing value, is the mean value of the mth Gaussian component of the injection power prediction error of the ith node, is the mean value of the mth Gaussian component of the injection power timing value of the ith node, and W is the number of nodes.

[0088] Furthermore, based on the joint probability density function of the injection power prediction error and the injection power time series value, the sampling expectation maximization algorithm is used to fit the historical data of the injection power time series value to solve the parameters in formula (4): and Thus, the relationship between the injection power prediction error and the injection power timing value is determined.

[0089] Step 2.3, utilizing the conditional probability invariance characteristic of the Gaussian mixture model, based on the joint probability density function of the injection power prediction error and the injection power time series value, determine the conditional probability density function of the injection power prediction error;

[0090] Under the condition of a given time series distribution of the actual value of the injected power, it can be seen from the conditional probability invariance of GMM that the conditional probability of the prediction error still obeys GMM, that is, under the condition of a given time series distribution of the actual value of the injected power, the conditional probability density function of the injected power prediction error of the i-th node satisfies the following relationship:

[0091]

[0092] In the formula, is the joint probability density function of the injection power prediction error of the i-th node and the injection power time series value of the i-th node, is the weight of the mth Gaussian component of the injection power prediction error of the ith node under the condition of the given injection power actual value time series distribution, is the m-th one-dimensional normal distribution of the ith node, is the mean value of the mth Gaussian component of the conditional probability distribution of the injection power prediction error of the ith node under the condition of the given injection power actual value time series distribution, is the covariance of the mth Gaussian component of the conditional probability distribution of the injection power prediction error of the ith node under the condition of a given injection power actual value time series distribution.

[0093] Step 2.4, based on the conditional probability density function of the injection power prediction error, obtaining a sample value of the injection power prediction error, and determining the injection power random variable using the injection power prediction value and the sample value of the injection power prediction error;

[0094] The present invention characterizes the correlation between various power variables of random source and load as the probability distribution characteristics of source and load power. The injected power random variable determined accordingly conforms to the probability distribution characteristics of source and load power. Moreover, when faced with high-dimensional massive data, the injected power random variable that characterizes the correlation between various power variables can be efficiently obtained. Therefore, it has good application prospects in medium-voltage interconnected distribution systems with complex source and load scenarios.

[0095] Step 3, taking the minimization of the operating loss cost of the flexible interconnected distribution network as the objective function, the operating loss cost includes the AC system loss cost, the DC system loss cost, and the converter loss cost; establishing the constraint conditions of the objective function, including: the probability constraint conditions of the node voltage not exceeding the limit and the probability constraint conditions of the branch power not exceeding the limit established by the chance constraint programming method, the AC and DC system power balance constraint conditions, and the converter operation constraint conditions; determining the inverse function of the cumulative distribution function of the injected power random variable based on the source-load power probability model, and using the inverse function and the node injected power adjustment amount to determine the probability of the node voltage not exceeding the limit The rate constraint condition and the probability constraint condition of branch power not exceeding the limit are transformed, and the power balance constraint condition of the AC / DC system is relaxed based on the Distflow power flow model; the transformed probability constraint condition of node voltage not exceeding the limit and the probability constraint condition of branch power not exceeding the limit, the processed power balance constraint condition of the AC / DC system and the converter operation constraint condition are used with the objective function to form a flexible interconnected distribution network scheduling optimization model; the flexible interconnected distribution network scheduling optimization model is iteratively solved to obtain the optimal value of the injected power adjustment amount of each node as the power value exchanged by the flexible interconnected device.

[0096] Specifically, step 3 includes:

[0097] Step 3.1, taking the minimization of the operating loss cost of the flexible interconnected distribution network as the objective function, the operating loss cost includes the AC system loss cost, the DC system loss cost, and the converter loss cost.

[0098] The objective function satisfies the following relationship:

[0099] C loss =C loss，AC +C loss，DC +C loss，VSC (6)

[0100]

[0101] In the formula, C loss is the operating loss cost of the flexible interconnected distribution network, C loss，AC is the AC system loss cost; C loss，DC is the DC system loss cost, C loss，VSC is the converter loss cost; NAC is the number of nodes in the AC system; N DC is the number of nodes in the DC system network; Ω(i) is the set of neighboring nodes of node i; r ij，AC is the resistance of the AC branch ij; r ij，DC is the resistance of the DC branch ij; I ij，AC is the square value of the current flowing through the AC branch ij; I ij，DC is the square value of the current flowing through the DC branch ij.

[0102] In the embodiment, for the low voltage converter, since the power flowing through is small, the converter loss cost C loss，VSC The calculation is based on 2% of the power flowing through it.

[0103] Step 3.2, establishing the constraint conditions of the objective function, including: the probability constraint conditions of node voltage not exceeding the limit and branch power not exceeding the limit established by the chance constraint programming method, the AC / DC system power balance constraint conditions and the converter operation constraint conditions;

[0104] In the chance-constrained programming model, the probability constraints of the objective function satisfy the following relationship:

[0105]

[0106] Where N max represents the total number of states of the system; f(X,ξ i ) indicates that in state ξ i is the function of the physical quantity X; α is the confidence level; F represents f(X,ξ i ) is the maximum value achieved when the probability level is at least α.

[0107] 1) The probability constraint condition that the node voltage does not exceed the limit satisfies the following relationship:

[0108] P{U i,min ≤U i (ξ)≤U i,max}≥β U (9)

[0109] Where U i (ξ) is the voltage of node i in the distribution network operation state ξ; U i,min and U i,max is the lower and upper limits of the voltage at node i; P{U i,min ≤U i (ξ)≤U i,max} is the probability that the voltage of node i does not exceed the limit under the distribution network operation state ξ; β U is the confidence level that the node voltage does not exceed the limit.

[0110] 2) The probability constraint condition that the branch power does not exceed the limit satisfies the following relationship:

[0111] P{P k (ξ)≤P k,max}≥β P (10)

[0112] Where P k (ξ) is the active power of branch k in the distribution network operating state ξ; P k,max is the upper limit of active power of branch k; P{P k (ξ)≤P k,max} is the probability that the active power of branch k does not exceed the limit under the distribution network operation state ξ; β P is the confidence level that the branch power does not exceed the limit.

[0113] 3) The AC / DC system power balance constraint condition satisfies the following relationship:

[0114]

[0115] Where P AC,i and Q AC,i are the active power and reactive power injected into the AC system node i respectively; G AC,ij , B ij ,θ ij are the conductance, susceptance and voltage phase difference between nodes i and j in the AC system respectively; U AC,i and U AC,j are the voltage amplitudes of nodes i and j in the AC system respectively; P DC,i is the active power injected into the DC system node i; U DC,i and U DC,j are the voltages of nodes i and j in the DC system respectively; G DC,ij is the conductance between nodes i and j in the DC system, N AC is the number of nodes in the AC system; N DC is the number of nodes in the DC system network.

[0116] 4) The operating constraints of the converter satisfy the following relationship:

[0117]

[0118] Where P VSC and Q VSC are the active power and reactive power flowing through the converter respectively; S VSC is the capacity of the converter.

[0119] Step 3.3, based on the source-load power probability model, determine the inverse function of the cumulative distribution function of the injected power random variable, and use the inverse function and the node injected power adjustment amount to transform the probability constraints of the node voltage not exceeding the limit and the probability constraints of the branch power not exceeding the limit. Based on the Distflow power flow model, relax the power balance constraints of the AC and DC systems; the transformed probability constraints of the node voltage not exceeding the limit and the probability constraints of the branch power not exceeding the limit, the processed power balance constraints of the AC and DC systems, and the converter operation constraints, together with the objective function, constitute a flexible interconnected distribution network scheduling optimization model.

[0120] The probability constraints of node voltage not exceeding the limit, branch power not exceeding the limit, AC / DC system power balance constraints, and converter operation constraints established by the chance constraint programming method, together with the objective function and the flexible interconnected distribution network dispatch optimization model, are a chance constraint model. The difficulty in solving the chance constraint model is that the constraints of node voltage not exceeding the limit and branch power not exceeding the limit are probability constraints, and the traditional model solving method cannot handle such probability constraints. Therefore, it is necessary to transform equations (9) and (10).

[0121] Specifically, step 3.3 includes:

[0122] Step 3.3.1, based on the injected power random variable, transform the probability constraint condition of the node voltage not exceeding the limit and the probability constraint condition of the branch power not exceeding the limit by the following relationship:

[0123]

[0124] Where P r () is the probability of a specific event occurring, ΔV i,max is the upper limit of the voltage deviation at node i, ΔP i,max is the upper limit of branch power deviation, A1 is the conversion coefficient matrix of node injection power adjustment and node voltage deviation, B1 is the conversion coefficient matrix of node injection power adjustment and branch power deviation, A2 is the conversion coefficient matrix of node injection power random variable and node voltage deviation, B2 is the conversion coefficient matrix of node injection power random variable and branch power deviation, ΔP adj,t is the injection power adjustment amount of the node at time t, ΔP ran,t is the random variable of the injected power at the node at time t, α set for a given confidence level.

[0125] Step 3.3.2, based on the source load power probability model, determine the cumulative distribution function of the node injection power random variable; based on the cumulative distribution function, perform the first transformation on the transformed probability constraint condition that the node voltage does not exceed the limit and the probability constraint condition that the branch power does not exceed the limit, and obtain the following relationship:

[0126]

[0127] In the formula, is the cumulative distribution function of the random variable of the injected power at the node at time t;

[0128] Step 3.3.3, based on the inverse function of the cumulative distribution function, the probability constraint condition of the node voltage not exceeding the limit and the probability constraint condition of the branch power not exceeding the limit are transformed for the second time to obtain the following relationship:

[0129]

[0130] In the formula, It is the inverse of the cumulative distribution function.

[0131] In the embodiment, for the node injection power random variable, the mean is μ m The variance is σ m The cumulative distribution function of the Gaussian distribution satisfies the fourth-order polynomial shown below:

[0132]

[0133] In the formula, h0 = -0.0005, h1 = 0.424, h2 = -0.06211, h3 = -0.02918, h4 = 0.00709, v is the voltage variable, x is the given voltage limit, is the comparison variable of the given voltage limit relative to the mean of the random variable,

[0134] Therefore, the inverse function The function value of can be obtained by solving the above fourth-order polynomial.

[0135] The key to solving the above-mentioned chance-constrained optimization problem lies in the processing of equation (14). After the function value of , equation (14) is converted into a linear constraint on the decision variables as shown in equation (15), where the decision variables include: the injection power adjustment amount of the node.

[0136] Step 3.3.4, based on the Distflow power flow model, relax the power balance constraints of the AC and DC systems.

[0137] In step 3.3.5, the flexible interconnected distribution network dispatching optimization model is constructed with the transformed probability constraints of the node voltage not exceeding the limit and the branch power not exceeding the limit, the processed AC / DC system power balance constraints and the converter operation constraints, together with the objective function.

[0138] The flexible interconnected distribution network dispatch optimization model constructed by using the transformed and processed constraints and the objective function is a second-order cone optimization model. In addition, the decision variables of the second-order cone optimization model include: the active power and reactive power exchanged by the flexible interconnected device, which is ΔP in formula (15) adj,t and the corresponding ΔQ adj,t (Since the formula expression is exactly the same, it is not given in the paper). The state variables of the second-order cone optimization model include: node voltage distribution and branch power distribution.

[0139] Step 3.4, solving the flexible interconnected distribution network dispatch optimization model to obtain the optimal value of the injection power adjustment amount of each node as the power value exchanged by the flexible interconnected device;

[0140] The flexible interconnected distribution network dispatching plan includes the power values ​​exchanged by the flexible interconnected devices.

[0141] The present invention is modified based on the IEEE33 node example, and its topology diagram is as follows Figure 4 As shown. Among them, substation outgoing line 1 has a high proportion of clean energy units connected, and substation outgoing line 2 has fewer clean energy units connected, but there are two groups of SOPs for power transfer within the line and power mutual assistance between lines. Both outgoing lines are equipped with energy storage. The parameters of each device are shown in Tables 1 to 3.

[0142] Table 1 Power supply side equipment parameters

[0143]

[0144]

[0145] Table 2 Energy storage equipment parameters

[0146] serial number line Device Name node Capacity / kWh Maximum charge and discharge power / kW 9 Outlet 1 ESS1 30 900 300 10 Outgoing 2 ESS2 13 600 150

[0147] Table 3 Flexible interconnection equipment parameters

[0148]

[0149] Use Figure 5 The distributed generation and load power curves shown in the figure optimize the active and reactive power and energy storage charging and discharging power of the intelligent soft switch according to the proposed day-ahead optimization scheduling model.

[0150] The following three optimization schemes are selected for comparison:

[0151] Solution 1: No optimization;

[0152] Solution 2: Use the second-order cone linear programming method for optimization;

[0153] Solution 3: Use the method proposed in this paper for optimization;

[0154] The system operation status under the three schemes is shown in Table 4. When the distribution network is not optimized, the total network loss is 4764.5 kWh per day. As can be seen from Table 4, Scheme 2 has the best loss reduction effect, but due to the large scale of the optimization model, the solution time is long. Scheme 3 uses the method proposed in the present invention to achieve an optimization effect similar to that of Scheme 2, while shortening the solution time.

[0155] Table 4 Comparison of results of three schemes

[0156] plan System loss / kWh Loss reduction ratio / % System operating cost / yuan Solution time / s Solution 1 4764.5 - 7360.1 - Solution 2 3839.7 19.4％ 8372.2 568.3 Solution 3 3921.6 17.6％ 8391.9 14.2

[0157] In scheme 3, the active and reactive output of the two SOPs is as follows: Figure 6 As shown. Substation outlet 1 has a lighter load and more distributed power sources, while substation outlet 2 has a heavier load. Therefore, SOP2 injects active power into the 33 nodes of substation outlet 2. At noon, the photovoltaic output is high, and the power transmitted by SOP2 also increases. One side of SOP1 is connected to 25 nodes of industrial loads, whose load power changes little over time, and the other side is connected to 29 nodes of residential loads, whose load power changes greatly over time. When the residential load is small in the morning and evening, SOP1 injects active power into the industrial load, and at noon, SOP1 injects active power into the residential load. In summary, SOP transfers active power and emits reactive power, so that the power of each line in the network is balanced, thereby reducing network losses.

[0158] In addition, due to the high mismatch between the source and load of substation outgoing line 1, the system will have serious voltage over-limit problems when it is not optimized, such as Figure 7 After optimization, SOP transfers power within and between lines, broadens the way to absorb distributed power, and can generate reactive power to adjust voltage. Substation outgoing line 1 no longer has the problem of outgoing line voltage exceeding the limit, as shown in the figure. Figure 8 shown.

[0159] The present invention also proposes a flexible interconnected distribution network dispatching system based on a Gaussian mixture model, comprising:

[0160] The load power modeling module is used to obtain the load power and the output power of the distributed power source in the flexible interconnected distribution network as random variables. Based on the Gaussian mixture model, the superposition of multiple Gaussian distributions of random variables is used as the source-load power probability model of the flexible interconnected distribution network.

[0161] The power prediction error modeling module is used to determine the injection power prediction error by using the actual value of the injection power and the injection power prediction value of each node in the flexible interconnected distribution network; the actual value of the injection power and its sampling time constitute the injection power time series value; based on the source-load power probability model, the joint probability density function of the injection power prediction error and the injection power time series value is determined; using the conditional probability invariance characteristic of the Gaussian mixture model, based on the joint probability density function of the injection power prediction error and the injection power time series value, the conditional probability density function of the injection power prediction error is determined;

[0162] The flexible interconnected distribution network dispatching optimization module is used to take the minimization of the operating loss cost of the flexible interconnected distribution network as the objective function, and the operating loss cost includes the AC system loss cost, the DC system loss cost, and the converter loss cost; establish the constraint conditions of the objective function, including: the probability constraint conditions of the node voltage not exceeding the limit and the probability constraint conditions of the branch power not exceeding the limit established by the chance constraint programming method, the AC and DC system power balance constraint conditions, and the converter operation constraint conditions; construct a flexible interconnected distribution network dispatching optimization model with the objective function and its constraint conditions; iteratively solve the flexible interconnected distribution network dispatching optimization model to obtain the optimal value of the injected power adjustment amount of each node as the power value exchanged by the flexible interconnected device.

[0163] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0164] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0165] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0166] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0167] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A flexible interconnected distribution network scheduling method based on Gaussian mixture model, characterized in that: include: The load power and the output power of distributed power sources in the flexible interconnected distribution network are obtained as random variables, and based on the Gaussian mixture model, the superposition of multiple Gaussian distributions of random variables is used as the source-load power probability model of the flexible interconnected distribution network; The injection power prediction error is determined by using the actual value of injection power and the injection power prediction value of each node in the flexible interconnected distribution network; the actual value of injection power and its sampling time constitute the injection power time series value; based on the source-load power probability model, the joint probability density function of the injection power prediction error and the injection power time series value is determined; Utilizing the invariant conditional probability characteristic of the Gaussian mixture model, based on the joint probability density function of the injection power prediction error and the injection power time series value, the conditional probability density function of the injection power prediction error is determined; based on the conditional probability density function of the injection power prediction error, a sampling value of the injection power prediction error is obtained, and the injection power random variable is determined using the injection power prediction value and the sampling value of the injection power prediction error; The objective function is to minimize the operating loss cost of the flexible interconnected distribution network. The operating loss cost includes the AC system loss cost, the DC system loss cost, and the converter loss cost. Establish the constraint conditions of the objective function, including: the probability constraint conditions of node voltage not exceeding the limit and branch power not exceeding the limit established by the chance constraint programming method, the power balance constraint conditions of the AC / DC system and the converter operation constraint conditions; determine the inverse function of the cumulative distribution function of the injected power random variable based on the source-load power probability model, transform the probability constraint conditions of node voltage not exceeding the limit and branch power not exceeding the limit by the inverse function and the node injected power adjustment amount, and relax the power balance constraint conditions of the AC / DC system based on the Distflow power flow model; form a flexible interconnected distribution network dispatching optimization model with the transformed probability constraint conditions of node voltage not exceeding the limit and branch power not exceeding the limit, the processed power balance constraint conditions of the AC / DC system and the converter operation constraint conditions and the objective function; The flexible interconnected distribution network dispatch optimization model is iteratively solved to obtain the optimal value of the injected power adjustment amount of each node as the power value exchanged by the flexible interconnected device.

2. The flexible interconnected distribution network dispatching method based on Gaussian mixture model according to claim 1 is characterized in that: The source-load power probability model of the flexible interconnected distribution network satisfies the following relationship: In the formula, f X (x) is the marginal probability density of the random variable X, M is the number of Gaussian components in the Gaussian mixture model; x is the sample of the random variable; ω m is the weight of the mth Gaussian component; N m () is the mth one-dimensional normal distribution; are the mean and covariance of the mth Gaussian component of sample x, respectively.

3. The flexible interconnected distribution network dispatching method based on Gaussian mixture model according to claim 1 is characterized in that: The injected power of W nodes in the flexible interconnected distribution network is random. The first random vector X1 is used to represent the actual value of the injected power of W nodes, satisfying X1 = [X 11 X 12 … X 1i … X 1W ] T , where X 1i is the actual value of the injected power of the ith node, and the second random vector X2 is used to represent the predicted value of the injected power of W nodes, satisfying X2 = [X 21 X 22 …X 2i …X 2W ] T , X 2i is the injection power prediction value of the ith node, then the third random vector representing the injection power prediction error of the W nodes satisfies the following relationship: Satisfy X e =[X e1 X e2 …X ei …X eW ] T , X ei is the injection power prediction error of the i-th node.

4. The flexible interconnected distribution network dispatching method based on Gaussian mixture model according to claim 3 is characterized in that: The sampling time of the actual value of the injected power of W nodes constitutes a time series vector, satisfying T = [T1 T2…T i …T W ] T , T i is the sampling time of the actual value of the injected power of the i-th node; Construct a matrix Y that satisfies Y = [X1 T] T , Y i is the injection power timing value of the ith node, including the actual value of the injection power of the ith node and its sampling time; Based on the Gaussian mixture model, the joint probability density function of the injection power prediction error of the i-th node and the injection power time series value of the i-th node satisfies the following relationship: In the formula, is the joint probability density function of the injection power prediction error of the i-th node and the injection power time series value of the i-th node, y i Y i A sample of x ei For X ei A sample of are the mean and covariance of the mth Gaussian component of the ith node, is the weight of the mth Gaussian component of the ith node, is the m-th one-dimensional normal distribution of the ith node, is the covariance of the injection power prediction error of the ith node to the mth Gaussian component of the injection power prediction error, is the covariance of the mth Gaussian component of the injection power prediction error of the ith node with respect to the injection power time series value, is the covariance of the injected power timing value of the ith node with respect to the mth Gaussian component of the injected power timing value, is the mean value of the mth Gaussian component of the injection power prediction error of the ith node, is the mean value of the mth Gaussian component of the injection power timing value of the ith node, and W is the number of nodes.

5. The flexible interconnected distribution network dispatching method based on Gaussian mixture model according to claim 4 is characterized in that: The conditional probability density function of the injection power prediction error satisfies the following relationship: In the formula, is the joint probability density function of the injection power prediction error of the i-th node and the injection power time series value of the i-th node, is the weight of the mth Gaussian component of the injection power prediction error of the ith node under the condition of the given injection power actual value time series distribution, is the m-th one-dimensional normal distribution of the ith node, is the mean value of the mth Gaussian component of the conditional probability distribution of the injection power prediction error of the ith node under the condition of the given injection power actual value time series distribution, is the covariance of the mth Gaussian component of the conditional probability distribution of the injection power prediction error of the ith node under the condition of a given time series distribution of the actual value of the injection power.

6. The flexible interconnected distribution network dispatching method based on Gaussian mixture model according to claim 1 is characterized in that: The objective function is to minimize the operating loss cost of the flexible interconnected distribution network. The operating loss cost includes the AC system loss cost, the DC system loss cost, and the converter loss cost. The objective function satisfies the following relationship: C loss =C loss,AC +C loss,DC +C loss,VSC (6) In the formula, C loss is the operating loss cost of the flexible interconnected distribution network, C loss，AC is the AC system loss cost; C loss，DC is the DC system loss cost, C loss，VSC is the converter loss cost; N AC is the number of nodes in the AC system; N DC is the number of nodes in the DC system network; Ω(i) is the set of neighboring nodes of node i; r ij，AC is the resistance of the AC branch ij; r ij，DC is the resistance of the DC branch ij; I ij，AC is the square value of the current flowing through the AC branch ij; I ij，DC is the square value of the current flowing through the DC branch ij.

7. The flexible interconnected distribution network dispatching method based on Gaussian mixture model according to claim 6 is characterized in that: Establish the constraint conditions of the objective function, including: the probability constraint conditions of node voltage not exceeding the limit and branch power not exceeding the limit established by chance constraint programming method, AC / DC system power balance constraint conditions and converter operation constraint conditions.

8. The flexible interconnected distribution network dispatching method based on Gaussian mixture model according to claim 7 is characterized in that: The probability constraint condition that the node voltage does not exceed the limit satisfies the following relationship: P{U i,min ≤U i (ξ)≤U i,max }≥β U Where U i (ξ) is the voltage of node i in the distribution network operation state ξ; U i,min and U i,max are the lower and upper limits of the voltage at node i; P{U i,min ≤U i (ξ)≤U i,max } is the probability that the voltage of node i does not exceed the limit under the distribution network operation state ξ; β U is the confidence level that the node voltage does not exceed the limit; The probability constraint condition for the branch power not to exceed the limit satisfies the following relationship: P{P k (ξ)≤P k,max }≥β P Where P k (ξ) is the active power of branch k in the distribution network operating state ξ; P k,max is the upper limit of active power of branch k; P{P k (ξ)≤P k,max } is the probability that the active power of branch k does not exceed the limit under the distribution network operation state ξ; β P is the confidence level that the branch power does not exceed the limit.

9. The flexible interconnected distribution network dispatching method based on Gaussian mixture model according to claim 7 is characterized in that: The power balance constraints of the AC and DC systems satisfy the following relationship: Where P AC,i and Q AC,i are the active power and reactive power injected into the AC system node i respectively; G AC,ij , B ij ,θ ij are the conductance, susceptance and voltage phase difference between nodes i and j in the AC system respectively; U AC,i and U AC,j are the voltage amplitudes of nodes i and j in the AC system respectively; P DC,i is the active power injected into the DC system node i; U DC,i and U DC,j are the voltages of nodes i and j in the DC system respectively; G DC,ij is the conductance between nodes i and j in the DC system, N AC is the number of nodes in the AC system; N DC is the number of nodes in the DC system network.

10. The flexible interconnected distribution network dispatching method based on Gaussian mixture model according to claim 7, characterized in that: The operating constraints of the converter satisfy the following relationship: Where P VSC and Q VSC are the active power and reactive power flowing through the converter respectively; S VSC is the capacity of the converter.

11. The flexible interconnected distribution network dispatching method based on Gaussian mixture model according to claim 8, characterized in that: Based on the source-load power probability model, the inverse function of the cumulative distribution function of the injected power random variable is determined, and the probability constraint conditions of the node voltage not exceeding the limit and the branch power not exceeding the limit are transformed by the inverse function and the node injected power adjustment amount, including: Based on the injected power random variable, the probability constraint condition of the node voltage not exceeding the limit and the probability constraint condition of the branch power not exceeding the limit are transformed by the following relationship: Where P r () is the probability of a specific event occurring, ΔV i,max is the upper limit of the voltage deviation at node i, ΔP i,max is the upper limit of branch power deviation, A1 is the conversion coefficient matrix of node injection power adjustment and node voltage deviation, B1 is the conversion coefficient matrix of node injection power adjustment and branch power deviation, A2 is the conversion coefficient matrix of node injection power random variable and node voltage deviation, B2 is the conversion coefficient matrix of node injection power random variable and branch power deviation, ΔP adj,t is the injection power adjustment amount of the node at time t, ΔP ran,t is the random variable of the injected power of the node at time t, α set For a given confidence level; Based on the source-load power probability model, the cumulative distribution function of the node injection power random variable is determined; based on the cumulative distribution function, the probability constraint conditions of the converted node voltage not exceeding the limit and the probability constraint conditions of the branch power not exceeding the limit are transformed for the first time, and the following relationship is obtained: In the formula, is the cumulative distribution function of the random variable of the injected power at the node at time t; Based on the inverse function of the cumulative distribution function, the probability constraint condition of the node voltage not exceeding the limit and the probability constraint condition of the branch power not exceeding the limit are transformed for the second time, and the following relationship is obtained: In the formula, is the inverse of the cumulative distribution function.

12. A flexible interconnected distribution network dispatching system based on Gaussian mixture model, characterized in that: include: The load power modeling module is used to obtain the load power and the output power of the distributed power source in the flexible interconnected distribution network as random variables. Based on the Gaussian mixture model, the superposition of multiple Gaussian distributions of random variables is used as the source-load power probability model of the flexible interconnected distribution network. The power prediction error modeling module is used to determine the injection power prediction error by using the actual value of the injection power and the injection power prediction value of each node in the flexible interconnected distribution network; the actual value of the injection power and its sampling time constitute the injection power time series value; based on the source-load power probability model, determine the joint probability density function of the injection power prediction error and the injection power time series value; By utilizing the invariant conditional probability characteristic of the Gaussian mixture model, the conditional probability density function of the injection power prediction error is determined based on the joint probability density function of the injection power prediction error and the injection power time series value; The flexible interconnected distribution network dispatching optimization module is used to minimize the operating loss cost of the flexible interconnected distribution network as the objective function. The operating loss cost includes the AC system loss cost, the DC system loss cost, and the converter loss cost; Establish constraint conditions of the objective function, including: probability constraint conditions of node voltage not exceeding the limit and branch power not exceeding the limit established by chance constraint programming method, AC / DC system power balance constraint conditions and converter operation constraint conditions; construct a flexible interconnected distribution network dispatching optimization model with the objective function and its constraint conditions; iteratively solve the flexible interconnected distribution network dispatching optimization model to obtain the optimal value of the injected power adjustment amount of each node as the power value exchanged by the flexible interconnected device.

13. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1 to 11.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 11 are implemented.

Images