Power system balance risk quantitative evaluation method and device

Abstract

The invention relates to the technical field of new energy power generation, and particularly provides a power system balance risk quantitative evaluation method and device, and the method comprises the steps: generating a new energy output scene through employing a pre-trained conditional generative adversarial network; constructing a power balance optimization model for the new energy output scene, and solving the power balance optimization model to obtain the insufficient power supply under the new energy output scene; and performing power system balance risk assessment based on the insufficient power supply under each new energy output scene. According to the technical scheme provided by the invention, insufficient power supply and consumption risks of the power system can be scientifically evaluated, technical support is provided for solving the problem of power supply safety after high-proportion new energy access in the future, and the method has a wide application prospect.

Description

Technical Field

[0001] The present invention relates to the technical field of renewable energy power generation, and in particular to a method and device for quantitatively assessing power system balance risk. Background Art

[0002] New energy is accelerating its development. With the further increase in the proportion of new energy installed capacity and power generation, higher requirements are put forward for system safety, power supply and clean energy consumption. The operation of the power grid may face the dilemma of "difficulty in absorbing large-scale new energy" and "difficulty in ensuring power supply for small-scale power generation". In terms of power and electricity balance, according to current plans, the supply and demand relationship of the power system will become tighter in the future, and weather events such as heat waves, cold waves, rainstorms, and sandstorms will become more frequent and stronger. The low output of new energy and the peak load in extreme weather will increase the difficulty of balance. At the same time, the diversification of power balance scenarios has profoundly changed the complexity of power balance risks. On the one hand, it is because the power balance risk is difficult to accurately assess. On the other hand, it is because the redundant configuration of resources and large-scale power abandonment measures taken by risk defense often bring conflicts between safety margin and economic benefits. Therefore, it is of great significance to build a reasonable quantitative assessment and early warning method for balance risks to ensure the safety, stability and economic operation of the power system.

[0003] In the prior art, the paper "Risk Analysis of Insufficient Flexibility of Regulation Resources in High-Proportion New Energy Power System" aims at the problem of insufficient flexibility of regulation resources in high-proportion new energy power system, constructs an index system for risk analysis of insufficient flexibility of regulation resources from the two aspects of ramp speed and regulation depth, and proposes a risk analysis method for insufficient flexibility. Based on the theory of adaptive kernel density estimation, a new energy and load data-driven model is established, and the adaptive kernel density estimation bandwidth is solved by the sequential optimization principle. Considering the small sample situation where the source and load power is outside the confidence interval, a training sample data enhancement method based on the cloud model is proposed to improve the accuracy of kernel density estimation risk analysis. According to the established kernel density estimation model, the risk interval of the source and load probability distribution is determined and the risk index value is calculated. However, this technical solution does not consider the restrictions of the inter-regional grid, and it is difficult to consider the impact of the transmission capacity restrictions between channels on the balance risk of the power system. At the same time, when generating scenarios, the correlation of the output of multiple fields / groups of new energy is not considered. It is believed that each new energy area is independent of each other, and the spatial correlation between the output of new energy in multiple regions is ignored. The constructed scenario is difficult to effectively describe the spatiotemporal correlation of the output of new energy, which will lead to the insufficient precision of the risk assessment results based on the scenario. Summary of the invention

[0004] In order to overcome the above-mentioned defects, the present invention proposes a method and device for quantitatively evaluating the balance risk of a power system.

[0005] In a first aspect, a method for quantitatively assessing the balance risk of a power system is provided, the method comprising:

[0006] Generate new energy output scenarios using pre-trained conditional generative adversarial networks;

[0007] Constructing a power balance optimization model for the renewable energy output scenario, and solving the power balance optimization model to obtain the insufficient power supply under the renewable energy output scenario;

[0008] The power system balance risk assessment is carried out based on the power supply shortage in each renewable energy output scenario.

[0009] Preferably, the input of the discriminator during the training process of the pre-trained conditional generative adversarial network includes: a three-dimensional tensor of a data matrix consisting of actual power data of new energy and a data matrix consisting of conditional information, or a three-dimensional tensor of a data matrix consisting of new energy output scenario data generated by the generator and a data matrix consisting of conditional information. The input of the generator includes: a three-dimensional tensor of a data matrix consisting of noise and a data matrix consisting of conditional information, wherein the conditional information is new energy power prediction data, the noise is the prediction error of the new energy power prediction data, and the dimension of the data matrix is ​​m×t, m is the number of areas to be analyzed, and t is the time period.

[0010] Furthermore, the dimension numbers of the two data matrices are aligned and concatenated to obtain the three-dimensional tensor.

[0011] Preferably, the power balance optimization model includes: an objective function with the goal of maximizing the power generation from renewable energy and its corresponding constraints.

[0012] Furthermore, the objective function is as follows:

[0013]

[0014] In the above formula, T is the optimization period, N is the number of regions, and P w (t,n) is the wind power generation power in area n during period t, P pv (t,n) is the photovoltaic power generation power of region n in period t, λ is the penalty term, e L,Curt (t,n) is the power shortage in area n during period t.

[0015] Furthermore, the constraints include: power balance constraints, thermal power output range constraints, hydropower output range constraints, new energy output constraints, thermal power ramp constraints, inter-regional line transmission capacity constraints, and reserve constraints.

[0016] Furthermore, the power balance constraint is as follows:

[0017]

[0018] The thermal power output range is constrained as follows:

[0019] P G,min (t,n)≤P G (t,n)≤P G,max (t,n)

[0020] The hydropower output range is constrained as follows:

[0021] P H,min (t,n)≤P H (t,n)≤P H,max (t,n)

[0022] The new energy output constraints are as follows:

[0023]

[0024] The thermal power ramping constraints are as follows:

[0025] P G,down ≤P G (t,n)-P G (t-1,n)≤P G,up

[0026] The inter-area line transmission capacity constraints are as follows:

[0027] L i,min ≤L i (t)≤L i,max

[0028] The alternate constraints are as follows:

[0029]

[0030] In the above formula, P G (t,n) is the total output of the n thermal power units in the region at time t, P H (t,n) is the total output of regional n hydropower units at time t, P CX (t,n) is the planned output of pumped storage unit n in region at time t, P CN (t,n) is the planned output of energy storage in area n at time t, L i (t) is the transmission power of the i-th section transmission line at time t, I is the number of sections, P l (t,n) is the energy storage load in area n at time t, P line (t,n) is the transmission interconnection line power of energy storage in area n at time t, P G,min (t,n) is the total minimum technical output of n thermal power units in the region at time t, P G,max (t,n) is the total maximum technical output of n thermal power units in the region at time t, PH,min (t,n) is the total minimum technical output of regional n hydropower units at time t, P H,max (t,n) is the total maximum technical output of the n hydropower units in the region at time t, is the predicted output of wind power at time t, is the predicted output of photovoltaic power generation at time t, P G,down is the downward climbing amount of the thermal power unit, P G,up is the upward climbing amount of the thermal power unit, P G (t-1,n) is the total output of the n thermal power units in the region at time t-1, L i,max , L i,min are the upper and lower limits of the transmission capacity of the ith transmission line, respectively, P re (t,n) is the positive reserve of area n at time t, N re (t,n) is the negative reserve of region n at time t, and N is the number of regions.

[0031] Preferably, the power system balance risk assessment based on the power supply shortage in each renewable energy output scenario includes:

[0032] Determine the power system balance risk warning index based on the power supply shortage in each renewable energy output scenario;

[0033] When the power system balance risk warning indicator exceeds a preset range, a power system balance risk warning is issued.

[0034] Furthermore, the power system balance risk warning indicators are as follows:

[0035]

[0036] In the above formula, R t is the power system balance risk warning indicator, S is the set of new energy output scenarios, Pr(S i ) is the new energy output scenario S i The probability of power shortage risk caused by i ) is the new energy output scenario S i The power supply is insufficient.

[0037] In a second aspect, a device for quantitatively evaluating the balance risk of a power system is provided, the device for quantitatively evaluating the balance risk of a power system comprising:

[0038] A simulation module for generating renewable energy output scenarios using a pre-trained conditional generative adversarial network;

[0039] An analysis module is used to construct a power balance optimization model for the new energy output scenario, and solve the power balance optimization model to obtain the power shortage in the new energy output scenario;

[0040] The assessment module is used to assess the risk of power system balance based on the power shortage in each renewable energy output scenario.

[0041] Preferably, the input of the discriminator during the training process of the pre-trained conditional generative adversarial network includes: a three-dimensional tensor of a data matrix consisting of actual power data of new energy and a data matrix consisting of conditional information, or a three-dimensional tensor of a data matrix consisting of new energy output scenario data generated by the generator and a data matrix consisting of conditional information. The input of the generator includes: a three-dimensional tensor of a data matrix consisting of noise and a data matrix consisting of conditional information, wherein the conditional information is new energy power prediction data, the noise is the prediction error of the new energy power prediction data, and the dimension of the data matrix is ​​m×t, m is the number of areas to be analyzed, and t is the time period.

[0042] Furthermore, the dimension numbers of the two data matrices are aligned and concatenated to obtain the three-dimensional tensor.

[0043] Preferably, the power balance optimization model includes: an objective function with the goal of maximizing the power generation from renewable energy and its corresponding constraints.

[0044] Furthermore, the objective function is as follows:

[0045]

[0046] In the above formula, T is the optimization period, N is the number of regions, and P w (t,n) is the wind power generation power in area n during period t, P pv (t,n) is the photovoltaic power generation power of region n in period t, λ is the penalty term, e L,Curt (t,n) is the power shortage in area n during period t.

[0047] Furthermore, the constraints include: power balance constraints, thermal power output range constraints, hydropower output range constraints, new energy output constraints, thermal power ramp constraints, inter-regional line transmission capacity constraints, and reserve constraints.

[0048] Furthermore, the power balance constraint is as follows:

[0049]

[0050] The thermal power output range is constrained as follows:

[0051] P G,min (t,n)≤P G (t,n)≤P G,max (t,n)

[0052] The hydropower output range is constrained as follows:

[0053] P H,min (t,n)≤P H (t,n)≤P H,max (t,n)

[0054] The new energy output constraints are as follows:

[0055]

[0056] The thermal power ramping constraints are as follows:

[0057] P G,down ≤P G (t,n)-P G (t-1,n)≤P G,up

[0058] The inter-area line transmission capacity constraints are as follows:

[0059] L i,min ≤L i (t)≤L i,max

[0060] The alternate constraints are as follows:

[0061]

[0062] In the above formula, P G (t,n) is the total output of the n thermal power units in the region at time t, P H (t,n) is the total output of regional n hydropower units at time t, P CX (t,n) is the planned output of pumped storage unit n in region at time t, P CN (t,n) is the planned output of energy storage in area n at time t, L i (t) is the transmission power of the i-th section transmission line at time t, I is the number of sections, P l (t,n) is the energy storage load in area n at time t, P line (t,n) is the transmission interconnection line power of energy storage in area n at time t, P G,min (t,n) is the total minimum technical output of n thermal power units in the region at time t, P G,max (t,n) is the total maximum technical output of n thermal power units in the region at time t, P H,min (t,n) is the total minimum technical output of regional n hydropower units at time t, P H,max (t,n) is the total maximum technical output of the n hydropower units in the region at time t, is the predicted output of wind power at time t, is the predicted output of photovoltaic power generation at time t, P G,downis the downward climbing amount of the thermal power unit, P G,up is the upward climbing amount of the thermal power unit, P G (t-1,n) is the total output of the thermal power units in the region n at time t-1, L i,max , L i,min are the upper and lower limits of the transmission capacity of the i-th transmission line, respectively, P re (t,n) is the positive reserve of area n at time t, N re (t,n) is the negative reserve of region n at time t, and N is the number of regions.

[0063] Preferably, the evaluation module is specifically used for:

[0064] Determine the power system balance risk warning index based on the power supply shortage in each renewable energy output scenario;

[0065] When the power system balance risk warning indicator exceeds a preset range, a power system balance risk warning is issued.

[0066] Furthermore, the power system balance risk warning indicators are as follows:

[0067]

[0068] In the above formula, R t is the power system balance risk warning indicator, S is the set of new energy output scenarios, Pr(S i ) is the new energy output scenario S i The probability of power shortage risk caused by i ) is the new energy output scenario S i The power supply is insufficient.

[0069] In a third aspect, a computer device is provided, comprising: one or more processors;

[0070] The processor is configured to execute one or more programs;

[0071] When the one or more programs are executed by the one or more processors, the power system balance risk quantitative assessment method is implemented.

[0072] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed, the method for quantitatively assessing the balance risk of a power system is implemented.

[0073] The above one or more technical solutions of the present invention have at least one or more of the following beneficial effects:

[0074] The present invention provides a method and device for quantitatively assessing the balance risk of a power system, including: using a pre-trained conditional generative adversarial network to generate a new energy output scenario; constructing a power balance optimization model for the new energy output scenario, and solving the power balance optimization model to obtain the power shortage amount under the new energy output scenario; and conducting a power system balance risk assessment based on the power shortage amount under each new energy output scenario. The technical solution provided by the present invention can scientifically assess the power supply shortage and absorption risks of the power system, provide technical support for solving the power supply security problem after a high proportion of new energy is connected in the future, and has broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 It is a flowchart of the main steps of the method for quantitatively assessing the balance risk of a power system according to an embodiment of the present invention;

[0076] Figure 2 is a data structure diagram of a three-dimensional tensor according to an embodiment of the present invention;

[0077] Figure 3 It is an overall structural diagram of the conditional generative adversarial network of an embodiment of the present invention. DETAILED DESCRIPTION

[0078] The specific implementation modes of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0079] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0080] As disclosed in the background technology, new energy is showing an accelerated development trend. With the further increase in the proportion of new energy installed capacity and power generation, higher requirements are put forward for system safety, power supply and clean energy consumption. The operation of the power grid may face the dilemma of "difficulty in absorbing new energy with large startup" and "difficulty in ensuring power supply with small startup". In terms of power and electricity balance, according to current plans, the supply and demand relationship of the power system will become tighter in the future, and weather events such as heat waves, cold waves, rainstorms, and sandstorms will become more frequent and stronger. The low output of new energy and the peak load in extreme weather will increase the difficulty of balance. At the same time, the diversification of power balance scenarios has profoundly changed the complexity of power balance risks. On the one hand, it is because the power balance risk is difficult to accurately assess. On the other hand, it is because the redundant configuration of resources and large-scale power abandonment measures taken by risk defense often bring conflicts between safety margins and economic benefits. Therefore, it is of great significance to construct a reasonable quantitative assessment and early warning method for balance risks to ensure the safety, stability and economic operation of the power system.

[0081] In the prior art, the paper "Risk Analysis of Insufficient Flexibility of Regulation Resources in High-Proportion New Energy Power System" aims at the problem of insufficient flexibility of regulation resources in high-proportion new energy power system, constructs an index system for risk analysis of insufficient flexibility of regulation resources from the two aspects of ramp speed and regulation depth, and proposes a risk analysis method for insufficient flexibility. Based on the theory of adaptive kernel density estimation, a new energy and load data-driven model is established, and the adaptive kernel density estimation bandwidth is solved by the sequential optimization principle. Considering the small sample situation where the source and load power is outside the confidence interval, a training sample data enhancement method based on the cloud model is proposed to improve the accuracy of kernel density estimation risk analysis. According to the established kernel density estimation model, the risk interval of the source and load probability distribution is determined and the risk index value is calculated. However, this technical solution does not consider the restrictions of the inter-regional grid, and it is difficult to consider the impact of the transmission capacity restrictions between channels on the balance risk of the power system. At the same time, when generating scenarios, the correlation of the output of multiple fields / groups of new energy is not considered. It is believed that each new energy area is independent of each other, and the spatial correlation between the output of new energy in multiple regions is ignored. The constructed scenario is difficult to effectively describe the spatiotemporal correlation of the output of new energy, which will lead to the insufficient precision of the risk assessment results based on the scenario.

[0082] In order to improve the above problems, the present invention provides a method and device for quantitatively assessing the balance risk of a power system, including: using a pre-trained conditional generative adversarial network to generate a new energy output scenario; constructing a power balance optimization model for the new energy output scenario, and solving the power balance optimization model to obtain the power shortage in the new energy output scenario; and conducting a power system balance risk assessment based on the power shortage in each new energy output scenario. The technical solution provided by the present invention can scientifically assess the power supply shortage and absorption risks of the power system, provide technical support for solving the power supply security problem after a high proportion of new energy is connected in the future, and has broad application prospects.

[0083] The above scheme is described in detail below.

[0084] Example 1

[0085] See attached Figure 1 , Figure 1 FIG. 1 is a flow chart showing the main steps of a method for quantitatively assessing power system balance risk according to an embodiment of the present invention. Figure 1 As shown, the power system balance risk quantitative assessment method in the embodiment of the present invention mainly includes the following steps:

[0086] Step S101: Generate a new energy output scenario using a pre-trained conditional generative adversarial network;

[0087] Step S102: constructing a power balance optimization model for the new energy output scenario, and solving the power balance optimization model to obtain the power shortage in the new energy output scenario;

[0088] Step S103: Performing a power system balance risk assessment based on the power supply shortage in each renewable energy output scenario.

[0089] In this embodiment, the input of the discriminator during the training process of the pre-trained conditional generative adversarial network includes: a three-dimensional tensor of a data matrix consisting of actual power data of new energy and a data matrix consisting of conditional information, or a three-dimensional tensor of a data matrix consisting of new energy output scenario data generated by the generator and a data matrix consisting of conditional information. The input of the generator includes: a three-dimensional tensor of a data matrix consisting of noise and a data matrix consisting of conditional information, wherein the conditional information is new energy power prediction data, the noise is the prediction error of the new energy power prediction data, and the dimension of the data matrix is ​​m×t, m is the number of areas to be analyzed, and t is the time period.

[0090] In one embodiment, the dimension numbers of the two data matrices are aligned and concatenated to obtain the three-dimensional tensor. m and c m denote the random sampling sequence of wind power / PV prediction errors and power prediction data of the mth region respectively, then the input sequence set of noise z is z = {z1,z2,…,z m-1 ,z m}, the input sequence set of condition information c is c={c1,c2,…,c m-1 ,c m}. After the conditional value sequence z and the noise sequence c of the m regions are spliced ​​vertically, m plane matrices are formed. Then, the m plane matrices are spliced ​​horizontally, and the input data finally forms a three-dimensional matrix tensor. The structure of the network input data after splicing is as follows: Figure 2 As shown in the figure, z mt and c mt They represent the random sampling sequence of wind power / photovoltaic prediction errors and power prediction data of the mth region in period t respectively.

[0091] In a specific implementation, the pre-trained conditional generative adversarial network selects a 3×3×3 convolution kernel to perform convolution calculation on the network input. When generating wind power / photovoltaic output scenarios, in order to ensure that the output and input sizes remain unchanged after each convolution calculation, the present invention first performs edge padding on the input three-dimensional data before convolution calculation. For example, if convolution calculation is performed on time t2 of area 2, the wind power output scenario value at time t2 is The mathematical expression of is shown below.

[0092]

[0093] In the formula, c ij is the conditional value of region i at time j, z ij The noise value of region i at time j.

[0094] Based on the convolutional network, a wind power / photovoltaic output scenario generation network is built. The convolutional network is used to design the conditional generation network structure. The overall network structure is as follows: Figure 3 As shown in the figure, the hierarchical structure of the convolutional neural network mainly includes convolutional layers, batch normalization, and activation functions. mt and x′ mt They respectively represent the actual output of the mth area in period t and the new energy output scenario data generated by the generator.

[0095] In this embodiment, the power balance optimization model includes: an objective function with the goal of maximizing the power generation of new energy and its corresponding constraints.

[0096] In one embodiment, the objective function is as follows:

[0097]

[0098] In the above formula, T is the optimization period, N is the number of regions, and P w (t,n) is the wind power generation power in area n during period t, P pv (t,n) is the photovoltaic power generation power of region n in period t, λ is the penalty term, e L,Curt (t,n) is the power shortage in area n during period t.

[0099] In one embodiment, the constraints include: power balance constraints, thermal power output range constraints, hydropower output range constraints, new energy output constraints, thermal power ramp constraints, inter-regional line transmission capacity constraints, and reserve constraints.

[0100] In one embodiment, the power balance constraint is as follows:

[0101]

[0102] The thermal power output range is constrained as follows:

[0103] P G,min (t,n)≤P G (t,n)≤P G,max (t,n)

[0104] The hydropower output range is constrained as follows:

[0105] P H,min (t,n)≤P H (t,n)≤P H,max (t,n)

[0106] The new energy output constraints are as follows:

[0107]

[0108] The thermal power ramping constraints are as follows:

[0109] P G,down ≤P G (t,n)-P G (t-1,n)≤P G,up

[0110] The inter-area line transmission capacity constraints are as follows:

[0111] L i,min ≤L i (t)≤L i,max

[0112] The alternate constraints are as follows:

[0113]

[0114] In the above formula, P G (t,n) is the total output of the n thermal power units in the region at time t, P H (t,n) is the total output of regional n hydropower units at time t, P CX (t,n) is the planned output of pumped storage unit n in region at time t, P CN (t,n) is the planned output of energy storage in area n at time t, L i (t) is the transmission power of the i-th section transmission line at time t, I is the number of sections, P l (t,n) is the energy storage load in area n at time t, P line(t,n) is the transmission interconnection line power of energy storage in area n at time t, P G,min (t,n) is the total minimum technical output of n thermal power units in the region at time t, P G,max (t,n) is the total maximum technical output of n thermal power units in the region at time t, P H,min (t,n) is the total minimum technical output of regional n hydropower units at time t, P H,max (t,n) is the total maximum technical output of the n hydropower units in the region at time t, is the predicted output of wind power at time t, is the predicted output of photovoltaic power generation at time t, P G,down is the downward climbing amount of the thermal power unit, P G,up is the upward climbing amount of the thermal power unit, P G (t-1,n) is the total output of the n thermal power units in the region at time t-1, L i,max , L i,min are the upper and lower limits of the transmission capacity of the ith transmission line, respectively, P re (t,n) is the positive reserve of area n at time t, N re (t,n) is the negative reserve of region n at time t, and N is the number of regions.

[0115] In a specific implementation, the conventional power supply startup plan for each region formulated by the dispatcher is read, including the startup capacity, maximum output, minimum output of conventional units, maximum output, minimum output of hydropower, energy storage power station charging and discharging plan, pumped storage power station pumping and discharging plan and other planning data. A multi-scenario optimization model is established to optimize wind power / photovoltaic output, conventional power output, and regional intermittent output. The cplex solver is used to solve the optimization model to obtain the power shortage in each scenario, and the amplitude and probability of power shortage and power abandonment risks at each moment can be obtained through statistics.

[0116] In this embodiment, the power system balance risk assessment based on the power supply shortage in each renewable energy output scenario includes:

[0117] Determine the power system balance risk warning index based on the power supply shortage in each renewable energy output scenario;

[0118] When the power system balance risk warning indicator exceeds a preset range, a power system balance risk warning is issued.

[0119] The present invention carries out early warning of power system balance risk by dividing early warning intervals into different levels, seeing in which interval the value of the risk early warning indicator is located, that is, the corresponding risk level, and carrying out risk early warning.

[0120] In one embodiment, the power system balance risk warning indicator is as follows:

[0121]

[0122] In the above formula, R t is the power system balance risk warning indicator, S is the set of new energy output scenarios, Pr(S i ) is the new energy output scenario S i The probability of power shortage risk caused by i ) is the new energy output scenario S i The power supply is insufficient.

[0123] Example 2

[0124] Based on the same inventive concept, the present invention also provides a power system balance risk quantitative assessment device, the power system balance risk quantitative assessment device comprising:

[0125] A simulation module for generating renewable energy output scenarios using a pre-trained conditional generative adversarial network;

[0126] An analysis module is used to construct a power balance optimization model for the new energy output scenario, and solve the power balance optimization model to obtain the power shortage in the new energy output scenario;

[0127] The assessment module is used to assess the risk of power system balance based on the power shortage in each renewable energy output scenario.

[0128] Preferably, the input of the discriminator during the training process of the pre-trained conditional generative adversarial network includes: a three-dimensional tensor of a data matrix consisting of actual power data of new energy and a data matrix consisting of conditional information, or a three-dimensional tensor of a data matrix consisting of new energy output scenario data generated by the generator and a data matrix consisting of conditional information. The input of the generator includes: a three-dimensional tensor of a data matrix consisting of noise and a data matrix consisting of conditional information, wherein the conditional information is new energy power prediction data, the noise is the prediction error of the new energy power prediction data, and the dimension of the data matrix is ​​m×t, m is the number of areas to be analyzed, and t is the time period.

[0129] Furthermore, the dimension numbers of the two data matrices are aligned and concatenated to obtain the three-dimensional tensor.

[0130] Preferably, the power balance optimization model includes: an objective function with the goal of maximizing the power generation from renewable energy and its corresponding constraints.

[0131] Furthermore, the objective function is as follows:

[0132]

[0133] In the above formula, T is the optimization period, N is the number of regions, and P w (t,n) is the wind power generation power in area n during period t, P pv (t,n) is the photovoltaic power generation power of region n in period t, λ is the penalty term, e L,Curt (t,n) is the power shortage in area n during period t.

[0134] Furthermore, the constraints include: power balance constraints, thermal power output range constraints, hydropower output range constraints, new energy output constraints, thermal power ramp constraints, inter-regional line transmission capacity constraints, and reserve constraints.

[0135] Furthermore, the power balance constraint is as follows:

[0136]

[0137] The thermal power output range is constrained as follows:

[0138] P G,min (t,n)≤P G (t,n)≤P G,max (t,n)

[0139] The hydropower output range is constrained as follows:

[0140] P H,min (t,n)≤P H (t,n)≤P H,max (t,n)

[0141] The new energy output constraints are as follows:

[0142]

[0143] The thermal power ramping constraints are as follows:

[0144] P G,down ≤P G (t,n)-P G (t-1,n)≤P G,up

[0145] The inter-area line transmission capacity constraints are as follows:

[0146] L i,min ≤L i (t)≤L i,max

[0147] The alternate constraints are as follows:

[0148]

[0149] In the above formula, PG (t,n) is the total output of the n thermal power units in the region at time t, P H (t,n) is the total output of regional n hydropower units at time t, P CX (t,n) is the planned output of pumped storage unit n in region at time t, P CN (t,n) is the planned output of energy storage in area n at time t, L i (t) is the transmission power of the i-th section transmission line at time t, I is the number of sections, P l (t,n) is the energy storage load in area n at time t, P line (t,n) is the transmission interconnection line power of energy storage in area n at time t, P G,min (t,n) is the total minimum technical output of n thermal power units in the region at time t, P G,max (t,n) is the total maximum technical output of n thermal power units in the region at time t, P H,min (t,n) is the total minimum technical output of regional n hydropower units at time t, P H,max (t,n) is the total maximum technical output of the n hydropower units in the region at time t, is the predicted output of wind power at time t, is the predicted output of photovoltaic power generation at time t, P G,down is the downward climbing amount of the thermal power unit, P G,up is the upward climbing amount of the thermal power unit, P G (t-1,n) is the total output of the n thermal power units in the region at time t-1, L i,max , L i,min are the upper and lower limits of the transmission capacity of the ith transmission line, respectively, P re (t,n) is the positive reserve of area n at time t, N re (t,n) is the negative reserve of region n at time t, and N is the number of regions.

[0150] Preferably, the evaluation module is specifically used for:

[0151] Determine the power system balance risk warning index based on the power supply shortage in each renewable energy output scenario;

[0152] When the power system balance risk warning indicator exceeds a preset range, a power system balance risk warning is issued.

[0153] Furthermore, the power system balance risk warning indicators are as follows:

[0154]

[0155] In the above formula, R t is the power system balance risk warning indicator, S is the set of new energy output scenarios, Pr(S i) is the new energy output scenario S i The probability of power shortage risk caused by i ) is the new energy output scenario S i The power supply is insufficient.

[0156] Example 3

[0157] Based on the same inventive concept, the present invention also provides a computer device, which includes a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function, so as to implement the steps of a method for quantitatively assessing the balance risk of a power system in the above embodiment.

[0158] Example 4

[0159] Based on the same inventive concept, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It can be understood that the computer-readable storage medium here can include both built-in storage media in a computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by a processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the steps of a method for quantitatively assessing the balance risk of a power system in the above embodiment.

[0160] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0161] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0162] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0163] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0164] 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. Any modification or equivalent replacement that does 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 method for quantitatively assessing power system balance risk, characterized in that: The method comprises: Generate new energy output scenarios using pre-trained conditional generative adversarial networks; Constructing a power balance optimization model for the renewable energy output scenario, and solving the power balance optimization model to obtain the insufficient power supply under the renewable energy output scenario; The power system balance risk assessment is carried out based on the power supply shortage in each renewable energy output scenario.

2. The method according to claim 1, characterized in that During the training process of the pre-trained conditional generative adversarial network, the input of the discriminator includes: a three-dimensional tensor of a data matrix consisting of actual power data of new energy and a data matrix consisting of conditional information, or a three-dimensional tensor of a data matrix consisting of new energy output scenario data generated by the generator and a data matrix consisting of conditional information. The input of the generator includes: a three-dimensional tensor of a data matrix consisting of noise and a data matrix consisting of conditional information, wherein the conditional information is new energy power prediction data, the noise is the prediction error of the new energy power prediction data, and the dimension of the data matrix is ​​m×t, m is the number of areas to be analyzed, and t is the time period.

3. The method according to claim 2, characterized in that The dimension numbers of the two data matrices are aligned and concatenated to obtain the three-dimensional tensor.

4. The method according to claim 1, characterized in that The power balance optimization model includes: an objective function with the goal of maximizing the power generation of new energy and its corresponding constraints.

5. The method according to claim 4, characterized in that The objective function is as follows: In the above formula, T is the optimization period, N is the number of regions, and P w (t,n) is the wind power generation power in area n during period t, P pv (t,n) is the photovoltaic power generation power of region n in period t, λ is the penalty term, e L,Curt (t,n) is the power shortage in area n during period t.

6. The method according to claim 5, characterized in that The constraints include: power balance constraints, thermal power output range constraints, hydropower output range constraints, new energy output constraints, thermal power ramp constraints, inter-regional line transmission capacity constraints, and reserve constraints.

7. The method according to claim 6, characterized in that The power balance constraints are as follows: The thermal power output range is constrained as follows: P G,min (t,n)≤P G (t,n)≤P G,max (t,n) The hydropower output range is constrained as follows: P H,min (t,n)≤P H (t,n)≤P H,max (t,n) The new energy output constraints are as follows: The thermal power ramping constraints are as follows: P G,down ≤P G (t,n)-P G (t-1,n)≤P G,up The inter-area line transmission capacity constraints are as follows: L i,min ≤L i (t)≤L i,max The alternate constraints are as follows: In the above formula, P G (t,n) is the total output of the n thermal power units in the region at time t, P H (t,n) is the total output of regional n hydropower units at time t, P CX (t,n) is the planned output of pumped storage unit n in region at time t, P CN (t,n) is the planned output of energy storage in area n at time t, L i (t) is the transmission power of the i-th section transmission line at time t, I is the number of sections, P l (t,n) is the energy storage load in area n at time t, P line (t,n) is the transmission interconnection line power of energy storage in area n at time t, P G,min (t,n) is the total minimum technical output of n thermal power units in the region at time t, P G,max (t,n) is the total maximum technical output of n thermal power units in the region at time t, P H,min (t,n) is the total minimum technical output of regional n hydropower units at time t, P H,max (t,n) is the total maximum technical output of the n hydropower units in the region at time t, is the predicted wind power output at time t, is the predicted output of photovoltaic power generation at time t, P G,down is the downward climbing amount of the thermal power unit, P G,up is the upward climbing amount of the thermal power unit, P G (t-1,n) is the total output of the n thermal power units in the region at time t-1, L i,max , L i,min are the upper and lower limits of the transmission capacity of the ith transmission line, respectively, P re (t,n) is the positive reserve of area n at time t, N re (t,n) is the negative reserve of region n at time t, and N is the number of regions.

8. The method according to claim 1, characterized in that The power system balance risk assessment based on the power supply shortage in each renewable energy output scenario includes: Determine the power system balance risk warning index based on the power supply shortage in each renewable energy output scenario; When the power system balance risk warning indicator exceeds a preset range, a power system balance risk warning is issued.

9. The method according to claim 8, characterized in that The power system balance risk early warning indicators are as follows: In the above formula, R t is the power system balance risk warning indicator, S is the set of new energy output scenarios, Pr(S i ) is the new energy output scenario S i The probability of power shortage risk caused by i ) is the new energy output scenario S i The power supply is insufficient.

10. A device for quantitatively assessing power system balance risk, characterized in that: The device comprises: A simulation module for generating renewable energy output scenarios using a pre-trained conditional generative adversarial network; An analysis module is used to construct a power balance optimization model for the new energy output scenario, and solve the power balance optimization model to obtain the power shortage in the new energy output scenario; The assessment module is used to assess the risk of power system balance based on the power shortage in each renewable energy output scenario.

11. The device according to claim 10, characterized in that During the training process of the pre-trained conditional generative adversarial network, the input of the discriminator includes: a three-dimensional tensor of a data matrix consisting of actual power data of new energy and a data matrix consisting of conditional information, or a three-dimensional tensor of a data matrix consisting of new energy output scenario data generated by the generator and a data matrix consisting of conditional information. The input of the generator includes: a three-dimensional tensor of a data matrix consisting of noise and a data matrix consisting of conditional information, wherein the conditional information is new energy power prediction data, the noise is the prediction error of the new energy power prediction data, and the dimension of the data matrix is ​​m×t, m is the number of areas to be analyzed, and t is the time period.

12. The device according to claim 11, characterized in that The dimension numbers of the two data matrices are aligned and concatenated to obtain the three-dimensional tensor.

13. The device according to claim 10, characterized in that The power balance optimization model includes: an objective function with the goal of maximizing the power generation of new energy and its corresponding constraints.

14. The device according to claim 13, characterized in that The objective function is as follows: In the above formula, T is the optimization period, N is the number of regions, and P w (t,n) is the wind power generation power in area n during period t, P pv (t,n) is the photovoltaic power generation power of region n in period t, λ is the penalty term, e L,Curt (t,n) is the power shortage in area n during period t.

15. The device according to claim 14, characterized in that The constraints include: power balance constraints, thermal power output range constraints, hydropower output range constraints, new energy output constraints, thermal power ramp constraints, inter-regional line transmission capacity constraints, and reserve constraints.

16. The device according to claim 15, characterized in that The power balance constraints are as follows: The thermal power output range is constrained as follows: P G,min (t,n)≤P G (t,n)≤P G,max (t,n) The hydropower output range is constrained as follows: P H,min (t,n)≤P H (t,n)≤P H,max (t,n) The new energy output constraints are as follows: The thermal power ramping constraints are as follows: P G,down ≤P G (t,n)-P G (t-1,n)≤P G,up The inter-area line transmission capacity constraints are as follows: L i,min ≤L i (t)≤L i,max The alternate constraints are as follows: In the above formula, P G (t,n) is the total output of the n thermal power units in the region at time t, P H (t,n) is the total output of regional n hydropower units at time t, P CX (t,n) is the planned output of pumped storage unit n in region at time t, P CN (t,n) is the planned output of energy storage in area n at time t, L i (t) is the transmission power of the i-th section transmission line at time t, I is the number of sections, P l (t,n) is the energy storage load in area n at time t, P line (t,n) is the transmission interconnection line power of energy storage in area n at time t, P G,min (t,n) is the total minimum technical output of n thermal power units in the region at time t, P G,max (t,n) is the total maximum technical output of n thermal power units in the region at time t, P H,min (t,n) is the total minimum technical output of regional n hydropower units at time t, P H,max (t,n) is the total maximum technical output of the n hydropower units in the region at time t, is the predicted wind power output at time t, is the predicted output of photovoltaic power generation at time t, P G,down is the downward climbing amount of the thermal power unit, P G,up is the upward climbing amount of the thermal power unit, P G (t-1,n) is the total output of the n thermal power units in the region at time t-1, L i,max , L i,min are the upper and lower limits of the transmission capacity of the ith transmission line, respectively, P re (t,n) is the positive reserve of area n at time t, N re (t,n) is the negative reserve of region n at time t, and N is the number of regions.

17. The device according to claim 10, characterized in that The evaluation module is specifically used for: Determine the power system balance risk warning index based on the power supply shortage in each renewable energy output scenario; When the power system balance risk warning indicator exceeds a preset range, a power system balance risk warning is issued.

18. The device according to claim 17, characterized in that The power system balance risk early warning indicators are as follows: In the above formula, R t is the power system balance risk warning indicator, S is the set of new energy output scenarios, Pr(S i ) is the new energy output scenario S i The probability of power shortage risk caused by i ) is the new energy output scenario S i The power supply is insufficient.

19. A computer device, characterized in that: include: one or more processors; The processor is configured to execute one or more programs; When the one or more programs are executed by the one or more processors, the method for quantitatively assessing the balance risk of a power system as described in any one of claims 1 to 9 is implemented.

20. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed, the method for quantitatively assessing the balance risk of a power system as described in any one of claims 1 to 9 is implemented.

Images