New energy and distribution building energy storage combined peak operation method and device

Abstract

The invention relates to the technical field of new energy and configuration energy storage optimization operation, and particularly provides a new energy and configuration energy storage combined peak operation method and device. Comprising the following steps: substituting a system peak regulation demand time period and a new energy short-term prediction output of the new energy and configuration energy storage combined system into a new energy and energy storage combined peak operation optimization model, and solving to obtain an optimization result; based on the optimization result, obtaining a new energy and configuration energy storage combined peak operation scheme, and performing optimization scheduling on the new energy and configuration energy storage combined system based on the new energy and configuration energy storage combined peak operation scheme; wherein the optimization result comprises at least one of energy storage discharge power and energy storage charge power. According to the technical scheme provided by the invention, the new energy and energy storage assessment and income mechanism is fully considered, the energy storage peak potential is mined, and the optimal operation strategy of the new energy and energy storage is obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of optimized operation of new energy and associated energy storage, and in particular to a method and device for combined peak operation of new energy and associated energy storage. Background Art

[0002] In recent years, the scale of new energy storage has expanded rapidly. Many places have stipulated that new energy projects must be equipped with energy storage systems at 8%-15% of the installed capacity to alleviate the problem of wind and solar power curtailment and enhance the flexibility of the power grid.

[0003] New energy storage systems are characterized by flexible regulation and rapid response, and are widely used in power generation, transmission, distribution, and consumption, playing an important role in the operation and regulation of power systems. Due to their rapid response capabilities and multi-timescale regulation characteristics, new energy storage systems can quickly respond to the peak-shaving needs of the power grid, have a good peak-shaving and valley-filling effect, can alleviate the peak-shaving pressure of the power grid, and improve the utilization rate of renewable energy. However, most existing studies only consider renewable energy or energy storage optimization unilaterally, and do not delve into existing assessment mechanisms and income compensation mechanisms for renewable energy and energy storage. Therefore, it is necessary to establish a combined peak-peak operation method for renewable energy and energy storage, fully consider the assessment and income mechanisms of renewable energy and energy storage, tap into the peak potential of energy storage, and obtain the optimal operation strategy for renewable energy and energy storage. Summary of the Invention

[0004] In order to overcome the above-mentioned defects, the present invention proposes a method and device for combined peak operation of new energy and accompanying energy storage.

[0005] In a first aspect, a method for combined peak operation of new energy and associated energy storage is provided, the method comprising:

[0006] Substitute the peak-shaving demand period of the new energy and energy storage combined system and the short-term forecast output of new energy into the new energy and energy storage combined peak operation optimization model and solve it to obtain the optimization result;

[0007] Based on the optimization results, a new energy and supporting energy storage combined peak operation plan is obtained, and based on the new energy and supporting energy storage combined peak operation plan, the new energy and supporting energy storage combined system is optimized and dispatched;

[0008] The optimization result includes at least one of the following: energy storage discharge power and energy storage charging power.

[0009] Preferably, the process of obtaining the system peak-shaving demand period includes:

[0010] Using the new energy and load historical power scenarios as inputs to a pre-trained neural network model, and obtaining the new energy and load historical power scenarios divided by seasons output by the pre-trained neural network model;

[0011] Screening peak scenarios from the new energy and load historical power scenarios divided by season, and constructing a peak scenario set divided by season using the screened peak scenarios;

[0012] The time period of the scene corresponding to each season in the peak scene set divided by season is used as the system peak-shaving demand period corresponding to each season;

[0013] The new energy and load historical power scenario is composed of new energy station historical power data and load historical power data.

[0014] Furthermore, the training process of the pre-trained neural network model includes:

[0015] Construct training sample data using new energy and load historical power scenarios annotated with seasonal labels;

[0016] The training sample data is used to train an initial neural network model to obtain the pre-trained neural network model.

[0017] Furthermore, the step of selecting peak scenarios from the new energy and load historical power scenarios divided by seasons includes:

[0018] The scenario in which the system relative peak-to-valley difference change rate index is greater than 1, the peak-to-valley difference rate index is greater than 80%, and the peak power gap index is greater than 10% of the peak load in the seasonal new energy and load historical power scenarios is taken as the peak scenario.

[0019] Furthermore, the relative peak-to-valley difference change rate index λ1 of the system is as follows:

[0020]

[0021] The peak-to-valley difference index λ2 is as follows:

[0022]

[0023] The peak power gap index λ3 is as follows:

[0024]

[0025] In the above formula, and They are the maximum equivalent load and the minimum equivalent load within one day after the new energy is connected to the grid. The equivalent load is the difference between the system load and the new energy power. L max and L min are the maximum load and minimum load of the system, Gap dur is the duration of the power gap, is the maximum output power of the system.

[0026] Preferably, during the prediction process of the short-term predicted output of new energy, the corresponding confidence interval U is as follows:

[0027]

[0028] In the above formula, is the benchmark value of the short-term forecast output of new energy, Φ is the confidence level of the short-term forecast output of new energy, and are the lower and upper bounds of the confidence interval for the short-term forecast output of new energy, is the deviation within the confidence interval of the short-term forecast output of new energy, R(Φ) is the score corresponding to the confidence level Φ, and N P_pre is the sample size, Contribute to the short-term forecast of new energy, P pre_fesd The standard deviation of the short-term forecast output of new energy.

[0029] Preferably, the new energy and energy storage combined peak operation optimization model includes: a new energy and energy storage combined peak operation optimization objective function and its corresponding constraint conditions.

[0030] Furthermore, the optimization objective function of the combined peak operation of new energy and energy storage is as follows:

[0031] maxf all =M new,sale +M es,sale -W new -W es

[0032] In the above formula, f all The peak operation income of new energy and energy storage combined, M new,sale is the income from new energy grid-connected power generation, M es,sale is the energy storage grid connection income, W new is the new energy assessment fee, W es The cost of building energy storage;

[0033] The benefits of new energy grid-connected power generation are as follows:

[0034]

[0035] The benefits of energy storage grid connection are as follows:

[0036]

[0037] The new energy assessment fees are as follows:

[0038]

[0039] The cost of building energy storage is as follows:

[0040]

[0041] In the above formula, p new The on-grid electricity price for renewable energy power generation, is the grid-connected power of new energy after the combined adjustment of new energy and energy storage at time t, Δt is the time interval, T is the number of scheduling periods, and For energy storage peak-valley arbitrage, the discharge power and charging power at time t, p pl is the time-of-use electricity price, T peak The peak demand period of the system. is the charging power when the system is required to peak, H es,peak is the peak load compensation coefficient of energy storage, p es,peak The price standard for energy storage participating in peak load regulation compensation is: To assess the power consumption of new energy curve deviation, The short-term forecast output deviation of new energy is used to assess the power consumption, p new The on-grid electricity price for renewable energy power generation, is the investment cost per unit capacity of energy storage, E es is the installed capacity of energy storage, x is the market value coefficient of energy storage, y is the number of years of energy storage operation, is the unit energy operating cost of energy storage, and are the discharge power and charging power of the energy storage in period t, respectively, and Δt is the interval time.

[0042] Furthermore, the new energy curve deviation assessment power is as follows:

[0043]

[0044] The short-term forecast output deviation assessment power of new energy is as follows:

[0045]

[0046] In the above formula, P real (t) is the actual output of new energy at time t, P allwd (t) is the deviation range of renewable energy power generation allowed by the load instruction at time t, It is the assessment standard value for the accuracy of short-term forecast output of new energy. The accuracy of the short-term forecast output of new energy on the previous day, is the rated capacity of the new energy station, H new The assessment coefficient set for the short-term forecast output of new energy on the previous day;

[0047] The load instruction at time t allows the deviation range of renewable energy actual power generation as follows:

[0048]

[0049] The accuracy of the short-term forecast output of new energy sources mentioned above is as follows:

[0050]

[0051] In the above formula, P cmd (t) is the load command power at time t, is the actual output of new energy at time t; Contribute to the short-term forecast of new energy sources at time t; is the available capacity of new energy power stations; N P_pre is the sample size for the renewable energy power generation period.

[0052] Furthermore, the constraint condition includes at least one of the following:

[0053] Constraints on the combined output of new energy and energy storage:

[0054]

[0055] Energy storage power and energy allocation constraints:

[0056]

[0057]

[0058] Charge and discharge state constraints:

[0059]

[0060] Charge and discharge power constraints:

[0061]

[0062] State of charge constraints:

[0063]

[0064] In the above formula, To contribute to the joint efforts of new energy and energy storage, Contribute to the short-term forecast of new energy, To participate in the energy storage discharge power adjustment of new energy output, The energy storage charging power that participates in the adjustment of new energy output, E es,all is the total installed capacity of energy storage, Allocate capacity for energy storage to participate in peak-valley arbitrage, The allocation capacity for energy storage to participate in the regulation of new energy output, The allocated rated power for the energy storage system to participate in peak-valley arbitrage, The allocated rated power of the energy storage system participating in the regulation of new energy output, is the charging state of the energy storage at time t, 0 indicates non-charging state, 1 indicates charging state, Indicates the discharge state of the energy storage at time t, 0 indicates non-discharge state, 1 indicates discharge state, and are the charging power and discharging power of the energy storage at time t, E es,pl (t) is the remaining amount of energy stored at time t, E es,pl (t-1) is the remaining power of the energy storage at time t-1, and are the charging power and discharging power of the energy storage at time t, is the initial energy storage capacity, is the final amount of energy stored, and are the upper and lower limits of energy storage capacity, η is the energy storage self-loss coefficient, η c is the energy storage charging loss coefficient, η d is the energy storage discharge loss coefficient, Δt is the time interval, To build energy storage rated power.

[0065] In a second aspect, a new energy and energy storage combined peak operation device is provided, the new energy and energy storage combined peak operation device comprising:

[0066] The analysis module is used to substitute the peak-shaving demand period of the new energy and energy storage combined system and the short-term predicted output of new energy into the new energy and energy storage combined peak operation optimization model and solve it to obtain the optimization result;

[0067] a scheduling module configured to obtain a peak operation plan for the new energy and energy storage system based on the optimization results, and to optimize the scheduling of the new energy and energy storage system based on the peak operation plan;

[0068] The optimization result includes at least one of the following: energy storage discharge power and energy storage charging power.

[0069] Preferably, the process of obtaining the system peak-shaving demand period includes:

[0070] Using the new energy and load historical power scenarios as inputs to a pre-trained neural network model, and obtaining the new energy and load historical power scenarios divided by seasons output by the pre-trained neural network model;

[0071] Screening peak scenarios from the new energy and load historical power scenarios divided by season, and constructing a peak scenario set divided by season using the screened peak scenarios;

[0072] The time period of the scene corresponding to each season in the peak scene set divided by season is used as the system peak-shaving demand period corresponding to each season;

[0073] The new energy and load historical power scenario is composed of new energy station historical power data and load historical power data.

[0074] Furthermore, the training process of the pre-trained neural network model includes:

[0075] Construct training sample data using new energy and load historical power scenarios annotated with seasonal labels;

[0076] The training sample data is used to train an initial neural network model to obtain the pre-trained neural network model.

[0077] Furthermore, the step of selecting peak scenarios from the new energy and load historical power scenarios divided by seasons includes:

[0078] The scenario in which the system relative peak-to-valley difference change rate index is greater than 1, the peak-to-valley difference rate index is greater than 80%, and the peak power gap index is greater than 10% of the peak load in the seasonal new energy and load historical power scenarios is taken as the peak scenario.

[0079] Furthermore, the relative peak-to-valley difference change rate index λ1 of the system is as follows:

[0080]

[0081] The peak-to-valley difference index λ2 is as follows:

[0082]

[0083] The peak power gap index λ3 is as follows:

[0084]

[0085] In the above formula, and They are the maximum equivalent load and the minimum equivalent load within one day after the new energy is connected to the grid. The equivalent load is the difference between the system load and the new energy power. L max and L min are the maximum load and minimum load of the system, Gap dur is the duration of the power gap, is the maximum output power of the system.

[0086] Preferably, during the prediction process of the short-term predicted output of new energy, the corresponding confidence interval U is as follows:

[0087] in,

[0088] In the above formula, is the benchmark value of the short-term forecast output of new energy, Φ is the confidence level of the short-term forecast output of new energy, and are the lower and upper bounds of the confidence interval for the short-term forecast output of new energy, is the deviation within the confidence interval of the short-term forecast output of new energy, R(Φ) is the score corresponding to the confidence level Φ, and N P_pre is the sample size, Contribute to the short-term forecast of new energy, P pre_fesd The standard deviation of the short-term forecast output of new energy.

[0089] Furthermore, the new energy and energy storage combined peak operation optimization model includes: a new energy and energy storage combined peak operation optimization objective function and its corresponding constraints.

[0090] Furthermore, the optimization objective function of the combined peak operation of new energy and energy storage is as follows:

[0091] maxf all =M new,sale +M es,sale -W new -W es

[0092] In the above formula, f all The peak operation income of new energy and energy storage combined, M new,sale is the income from new energy grid-connected power generation, M es,sale is the energy storage grid connection income, W new is the new energy assessment fee, W es The cost of building energy storage;

[0093] The benefits of new energy grid-connected power generation are as follows:

[0094]

[0095] The benefits of energy storage grid connection are as follows:

[0096]

[0097] The new energy assessment fees are as follows:

[0098]

[0099] The cost of building energy storage is as follows:

[0100]

[0101] In the above formula, p new The on-grid electricity price for renewable energy power generation, is the grid-connected power of new energy after the combined adjustment of new energy and energy storage at time t, Δt is the time interval, T is the number of scheduling periods, and For energy storage peak-valley arbitrage, the discharge power and charging power at time t, p pl is the time-of-use electricity price, T peak The peak demand period of the system. is the charging power when the system is required to peak, H es,peak is the peak load compensation coefficient of energy storage, p es,peak The price standard for energy storage participating in peak load regulation compensation is: To assess the power consumption of new energy curve deviation, The short-term forecast output deviation of new energy is used to assess the power consumption, p new The on-grid electricity price for renewable energy power generation, is the investment cost per unit capacity of energy storage, E es is the installed capacity of energy storage, x is the market value coefficient of energy storage, y is the number of years of energy storage operation, is the unit energy operating cost of energy storage, and are the discharge power and charging power of the energy storage in period t, respectively, and Δt is the interval time.

[0102] Furthermore, the new energy curve deviation assessment power is as follows:

[0103]

[0104] The short-term forecast output deviation assessment power of new energy is as follows:

[0105]

[0106] In the above formula, P real (t) is the actual output of new energy at time t, P allwd (t) is the deviation range of renewable energy power generation allowed by the load instruction at time t, DAAR is the assessment standard value for the accuracy of short-term forecast output of new energy. Ppnreew The accuracy of the short-term forecast output of new energy on the previous day, is the rated capacity of the new energy station, H new The assessment coefficient set for the short-term forecast output of new energy on the previous day;

[0107] The load instruction at time t allows the deviation range of renewable energy actual power generation as follows:

[0108]

[0109] The accuracy of the short-term forecast output of new energy sources mentioned above is as follows:

[0110]

[0111] In the above formula, P cmd (t) is the load command power at time t, is the actual output of new energy at time t; Contribute to the short-term forecast of new energy sources at time t; is the available capacity of new energy power stations; N P_pre is the sample size for the renewable energy power generation period.

[0112] Furthermore, the constraint condition includes at least one of the following:

[0113] Constraints on the combined output of new energy and energy storage:

[0114]

[0115] Energy storage power and energy allocation constraints:

[0116]

[0117] Charge and discharge state constraints:

[0118]

[0119] Charge and discharge power constraints:

[0120]

[0121] State of charge constraints:

[0122]

[0123]

[0124] In the above formula, To contribute to the joint efforts of new energy and energy storage, Contribute to the short-term forecast of new energy, To participate in the energy storage discharge power adjustment of new energy output, The energy storage charging power that participates in the adjustment of new energy output, E es,all is the total installed capacity of energy storage, Allocate capacity for energy storage to participate in peak-valley arbitrage, The allocation capacity for energy storage to participate in the regulation of new energy output, The allocated rated power for the energy storage system to participate in peak-valley arbitrage, The allocated rated power of the energy storage system participating in the regulation of new energy output, is the charging state of the energy storage at time t, 0 indicates non-charging state, 1 indicates charging state, Indicates the discharge state of the energy storage at time t, 0 indicates non-discharge state, 1 indicates discharge state, and are the charging power and discharging power of the energy storage at time t, E es,pl (t) is the remaining amount of energy stored at time t, E es,pl (t-1) is the remaining power of the energy storage at time t-1, and are the charging power and discharging power of the energy storage at time t, is the initial energy storage capacity, is the final amount of energy stored, and are the upper and lower limits of energy storage capacity, η is the energy storage self-loss coefficient, η c is the energy storage charging loss coefficient, η d is the energy storage discharge loss coefficient, Δt is the time interval, To build energy storage rated power.

[0125] In a third aspect, a computer device is provided, comprising: one or more processors;

[0126] The processor is configured to execute one or more programs;

[0127] When the one or more programs are executed by the one or more processors, the new energy and accompanying energy storage combined peak operation method is implemented.

[0128] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed, the method for combined peak operation of new energy and accompanying energy storage is implemented.

[0129] The above one or more technical solutions of the present invention have at least one or more of the following beneficial effects:

[0130] The present invention provides a method and apparatus for combined peak operation of new energy and accompanying energy storage, comprising: substituting the system peak-shaving demand period and the short-term predicted output of the new energy and accompanying energy storage system into a combined peak operation optimization model for new energy and energy storage, solving the model and obtaining an optimization result; obtaining a combined peak operation plan for new energy and accompanying energy storage based on the optimization result; and optimizing and scheduling the combined new energy and accompanying energy storage system based on the combined peak operation plan for new energy and accompanying energy storage; wherein the optimization result includes at least one of the following: energy storage discharge power and energy storage charging power. The technical solution provided by the present invention fully considers the assessment and revenue mechanism of new energy and energy storage, taps into the peak potential of energy storage, and obtains the optimal operation strategy for new energy and energy storage. BRIEF DESCRIPTION OF THE DRAWINGS

[0131] Figure 1 This is a flow chart of the main steps of the new energy and energy storage combined peak operation method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0132] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0133] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only 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 making creative efforts shall fall within the scope of protection of the present invention.

[0134] As disclosed in the background technology, the scale of energy storage for new energy has expanded rapidly in recent years. Many places have stipulated that new energy projects must be equipped with energy storage systems at 8%-15% of the installed capacity to alleviate the problem of wind and solar power curtailment and enhance the flexibility of the power grid.

[0135] New energy storage systems are characterized by flexible regulation and rapid response, and are widely used in power generation, transmission, distribution, and consumption, playing an important role in the operation and regulation of power systems. Due to their rapid response capabilities and multi-timescale regulation characteristics, new energy storage systems can quickly respond to the peak-shaving needs of the power grid, have a good peak-shaving and valley-filling effect, can alleviate the peak-shaving pressure of the power grid, and improve the utilization rate of renewable energy. However, most existing studies only consider renewable energy or energy storage optimization unilaterally, and do not delve into existing assessment mechanisms and income compensation mechanisms for renewable energy and energy storage. Therefore, it is necessary to establish a combined peak-peak operation method for renewable energy and energy storage, fully consider the assessment and income mechanisms of renewable energy and energy storage, tap into the peak potential of energy storage, and obtain the optimal operation strategy for renewable energy and energy storage.

[0136] In order to improve the above-mentioned problems, the present invention provides a method and device for the combined peak operation of new energy and supporting energy storage, comprising: substituting the system peak-shaving demand period and the short-term predicted output of new energy of the combined system of new energy and supporting energy storage into the combined peak operation optimization model of new energy and supporting energy storage and solving it to obtain an optimization result; based on the optimization result, obtaining a combined peak operation plan of new energy and supporting energy storage, and optimizing and scheduling the combined system of new energy and supporting energy storage based on the combined peak operation plan of new energy and supporting energy storage; wherein, the optimization result includes at least one of the following: energy storage discharge power, energy storage charging power. The technical solution provided by the present invention fully considers the assessment and benefit mechanism of new energy and energy storage, taps the peak potential of energy storage, and obtains the optimal operation strategy of new energy and energy storage.

[0137] The above scheme is described in detail below.

[0138] Example 1

[0139] See attached Figure 1 , Figure 1 This is a flow chart of the main steps of the new energy and energy storage combined peak operation method according to an embodiment of the present invention. Figure 1 As shown, the method for combined peak operation of new energy and energy storage in the embodiment of the present invention mainly includes the following steps:

[0140] Step S101: Substitute the peak-shaving demand period of the new energy and energy storage combined system and the short-term predicted output of the new energy into the new energy and energy storage combined peak operation optimization model and solve it to obtain the optimization result;

[0141] Step S102: Based on the optimization results, a new energy and energy storage combined peak operation plan is obtained, and based on the new energy and energy storage combined peak operation plan, the new energy and energy storage combined system is optimized and scheduled;

[0142] The optimization result includes at least one of the following: energy storage discharge power and energy storage charging power.

[0143] In this embodiment, the process of obtaining the system peak-shaving demand period includes:

[0144] Using the new energy and load historical power scenarios as inputs to a pre-trained neural network model, and obtaining the new energy and load historical power scenarios divided by seasons output by the pre-trained neural network model;

[0145] Screening peak scenarios from the new energy and load historical power scenarios divided by season, and constructing a peak scenario set divided by season using the screened peak scenarios;

[0146] The time period of the scene corresponding to each season in the peak scene set divided by season is used as the system peak-shaving demand period corresponding to each season;

[0147] The new energy and load historical power scenario is composed of new energy station historical power data and load historical power data.

[0148] In one embodiment, the training process of the pre-trained neural network model includes:

[0149] Construct training sample data using new energy and load historical power scenarios annotated with seasonal labels;

[0150] The training sample data is used to train an initial neural network model to obtain the pre-trained neural network model.

[0151] In a specific implementation, abnormal data and missing data in the collected historical data are processed; due to the uncertainty of new energy output, new energy data allows for mutations and fluctuations, so it is necessary to design and process abnormal value screening logic in combination with new energy characteristics; for missing data, different processing methods are given according to the degree of missingness. For data sets with less missing data, linear interpolation can be used to supplement them, and for data sets with larger missing data, data with similar data characteristics are used to supplement them.

[0152] The collected and processed historical data are divided into spring, summer, autumn and winter seasons to establish a historical scene sample library with seasonal characteristics; then, the scene data in the historical scene sample library is brought into the neural network for training to establish the coupling relationship between new energy output and load, thereby establishing a new energy output-load joint data-driven model.

[0153] In one embodiment, screening peak scenarios from the new energy and load historical power scenarios divided by season includes:

[0154] The scenario in which the system relative peak-to-valley difference change rate index is greater than 1, the peak-to-valley difference rate index is greater than 80%, and the peak power gap index is greater than 10% of the peak load in the seasonal new energy and load historical power scenarios is taken as the peak scenario.

[0155] In one embodiment, the system relative peak-to-valley difference change rate indicator λ1 is as follows:

[0156]

[0157] The peak-to-valley difference index λ2 is as follows:

[0158]

[0159] The peak power gap index λ3 is as follows:

[0160]

[0161] In the above formula, and They are the maximum equivalent load and the minimum equivalent load within one day after the new energy is connected to the grid. The equivalent load is the difference between the system load and the new energy power. L max and L min are the maximum load and minimum load of the system, Gap dur is the duration of the power gap, is the maximum output power of the system.

[0162] In this embodiment, during the prediction process of the short-term predicted output of new energy, the corresponding confidence interval U is as follows:

[0163] in,

[0164] In the above formula, is the benchmark value of the short-term forecast output of new energy, Φ is the confidence level of the short-term forecast output of new energy, and are the lower and upper bounds of the confidence interval for the short-term forecast output of new energy, is the deviation within the confidence interval of the short-term forecast output of new energy, R(Φ) is the score corresponding to the confidence level Φ, and N P_pre is the sample size, Contribute to the short-term forecast of new energy, P pre_fesd The standard deviation of the short-term forecast output of new energy.

[0165] In this embodiment, the new energy and energy storage combined peak operation optimization model includes: a new energy and energy storage combined peak operation optimization objective function and its corresponding constraint conditions.

[0166] In one embodiment, the optimization objective function for the combined peak operation of new energy and energy storage is as follows:

[0167] maxf all =M new,sale +M es,sale -W new -W es

[0168] In the above formula, f all The peak operation income of new energy and energy storage combined, M new,sale is the income from new energy grid-connected power generation, M es,sale is the energy storage grid connection income, W new is the new energy assessment fee, W esThe cost of building energy storage;

[0169] The benefits of new energy grid-connected power generation are as follows:

[0170]

[0171] The benefits of energy storage grid connection are as follows:

[0172]

[0173] New energy stations have two operating modes: one is the unlimited output mode; the other is the limited output mode; each corresponds to a different assessment standard. In the unlimited output mode, the new energy station reports the next day's new energy output curve and accepts the assessment of the accuracy of the new energy short-term forecast output; in the limited output mode, the new energy station reports the next day's new energy output curve, and the power dispatching center sends a load instruction to the new energy station, and the new energy station accepts the load instruction deviation assessment. Therefore, the new energy assessment fees are as follows:

[0174]

[0175] The cost of building energy storage is as follows:

[0176]

[0177] In the above formula, p new The on-grid electricity price for renewable energy power generation, is the grid-connected power of new energy after the combined adjustment of new energy and energy storage at time t, Δt is the time interval, T is the number of scheduling periods, and For energy storage peak-valley arbitrage, the discharge power and charging power at time t, p pl is the time-of-use electricity price, T peak The peak demand period of the system. is the charging power when the system is required to peak, H es,peak is the peak load compensation coefficient of energy storage, p es,peak The price standard for energy storage participating in peak load regulation compensation is: To assess the power consumption of new energy curve deviation, The short-term forecast output deviation of new energy is used to assess the power consumption, p new The on-grid electricity price for renewable energy power generation, is the investment cost per unit capacity of energy storage, E es is the installed capacity of energy storage, x is the market value coefficient of energy storage, y is the number of years of energy storage operation, is the unit energy operating cost of energy storage, and are the discharge power and charging power of the energy storage in period t, respectively, and Δt is the interval time.

[0178] In one embodiment, the new energy curve deviation assessment power is as follows:

[0179]

[0180] The short-term forecast output deviation assessment power of new energy is as follows:

[0181]

[0182] In the above formula, P real (t) is the actual output of new energy at time t, P allwd (t) is the deviation range of renewable energy power generation allowed by the load instruction at time t, It is the assessment standard value for the accuracy of short-term forecast output of new energy. The accuracy of the short-term forecast output of new energy on the previous day, is the rated capacity of the new energy station, H new The assessment coefficient set for the short-term forecast output of new energy on the previous day;

[0183] The load instruction at time t allows the deviation range of renewable energy actual power generation as follows:

[0184]

[0185] The accuracy of the short-term forecast output of new energy sources mentioned above is as follows:

[0186]

[0187] In the above formula, P cmd (t) is the load command power at time t, is the actual output of new energy at time t; Contribute to the short-term forecast of new energy sources at time t; is the available capacity of new energy power stations; N P_pre is the sample size for the renewable energy power generation period.

[0188] In one embodiment, the constraint condition includes at least one of the following:

[0189] Constraints on the combined output of new energy and energy storage:

[0190]

[0191] Energy storage power and energy allocation constraints:

[0192]

[0193]

[0194] Charge and discharge state constraints:

[0195]

[0196] Charge and discharge power constraints:

[0197]

[0198] State of charge constraints:

[0199]

[0200]

[0201] In the above formula, To contribute to the joint efforts of new energy and energy storage, Contribute to the short-term forecast of new energy, To participate in the energy storage discharge power adjustment of new energy output, The energy storage charging power that participates in the adjustment of new energy output, E es,all is the total installed capacity of energy storage, Allocate capacity for energy storage to participate in peak-valley arbitrage, The allocation capacity for energy storage to participate in the regulation of new energy output, The allocated rated power for the energy storage system to participate in peak-valley arbitrage, The allocated rated power of the energy storage system participating in the regulation of new energy output, is the charging state of the energy storage at time t, 0 indicates non-charging state, 1 indicates charging state, Indicates the discharge state of the energy storage at time t, 0 indicates non-discharge state, 1 indicates discharge state, and are the charging power and discharging power of the energy storage at time t, E es,pl (t) is the remaining amount of energy stored at time t, E es,pl (t-1) is the remaining power of the energy storage at time t-1, and are the charging power and discharging power of the energy storage at time t, is the initial energy storage capacity, is the final amount of energy stored, and are the upper and lower limits of energy storage capacity, η is the energy storage self-loss coefficient, η c is the energy storage charging loss coefficient, η d is the energy storage discharge loss coefficient, Δt is the time interval, To build energy storage rated power.

[0202] The technical solution of the present invention can effectively solve the problem of optimizing peak operation of new energy and energy storage under the assessment mechanism. The present invention has the following beneficial effects:

[0203] 1) This invention considers the characteristics of renewable energy and loads in different seasons to generate typical peak scenarios. By establishing peak-to-valley difference change rate indicators, peak-to-valley difference indicators, and peak power gap indicators, it effectively screens out more representative typical seasonal peak scenarios, providing a data foundation for formulating energy storage peak optimization operation strategies.

[0204] 2) The present invention obtains the confidence interval of the predicted new energy output through historical new energy actual output and forecast data, which can more realistically reflect the randomness and volatility of new energy output;

[0205] 3) The present invention takes into account new energy assessment indicators and incorporates them into the energy storage optimization scheduling model. Taking into account the peak operation scenario, a new energy and energy storage combined peak operation optimization model is established, and the model is solved through the linear programming method. The optimization results can help the new energy and energy storage combined power station improve the energy storage utilization rate, increase energy storage revenue, and reduce the new energy assessment costs.

[0206] Example 2

[0207] Based on the same inventive concept, the present invention also provides a new energy and energy storage combined peak operation device, the new energy and energy storage combined peak operation device comprising:

[0208] The analysis module is used to substitute the peak-shaving demand period of the new energy and energy storage combined system and the short-term predicted output of new energy into the new energy and energy storage combined peak operation optimization model and solve it to obtain the optimization result;

[0209] a scheduling module configured to obtain a peak operation plan for the new energy and energy storage system based on the optimization results, and to optimize the scheduling of the new energy and energy storage system based on the peak operation plan;

[0210] The optimization result includes at least one of the following: energy storage discharge power and energy storage charging power.

[0211] Preferably, the process of obtaining the system peak-shaving demand period includes:

[0212] Using the new energy and load historical power scenarios as inputs to a pre-trained neural network model, and obtaining the new energy and load historical power scenarios divided by seasons output by the pre-trained neural network model;

[0213] Screening peak scenarios from the new energy and load historical power scenarios divided by season, and constructing a peak scenario set divided by season using the screened peak scenarios;

[0214] The time period of the scene corresponding to each season in the peak scene set divided by season is used as the system peak-shaving demand period corresponding to each season;

[0215] The new energy and load historical power scenario is composed of new energy station historical power data and load historical power data.

[0216] Furthermore, the training process of the pre-trained neural network model includes:

[0217] Construct training sample data using new energy and load historical power scenarios annotated with seasonal labels;

[0218] The training sample data is used to train an initial neural network model to obtain the pre-trained neural network model.

[0219] Furthermore, the step of selecting peak scenarios from the new energy and load historical power scenarios divided by seasons includes:

[0220] The scenario in which the system relative peak-to-valley difference change rate index is greater than 1, the peak-to-valley difference rate index is greater than 80%, and the peak power gap index is greater than 10% of the peak load in the seasonal new energy and load historical power scenarios is taken as the peak scenario.

[0221] Furthermore, the relative peak-to-valley difference change rate index λ1 of the system is as follows:

[0222]

[0223] The peak-to-valley difference index λ2 is as follows:

[0224]

[0225] The peak power gap index λ3 is as follows:

[0226]

[0227] In the above formula, and They are the maximum equivalent load and the minimum equivalent load within one day after the new energy is connected to the grid. The equivalent load is the difference between the system load and the new energy power. L max and L min are the maximum load and minimum load of the system, Gap dur is the duration of the power gap, is the maximum output power of the system.

[0228] Preferably, during the prediction process of the short-term predicted output of new energy, the corresponding confidence interval U is as follows:

[0229]

[0230] In the above formula, is the benchmark value of the short-term forecast output of new energy, Φ is the confidence level of the short-term forecast output of new energy, and are the lower and upper bounds of the confidence interval for the short-term forecast output of new energy, is the deviation within the confidence interval of the short-term forecast output of new energy, R(Φ) is the score corresponding to the confidence level Φ, and N P_pre is the sample size, Contribute to the short-term forecast of new energy, P pre_fesd The standard deviation of the short-term forecast output of new energy.

[0231] Furthermore, the new energy and energy storage combined peak operation optimization model includes: a new energy and energy storage combined peak operation optimization objective function and its corresponding constraints.

[0232] Furthermore, the optimization objective function of the combined peak operation of new energy and energy storage is as follows:

[0233] maxf all =M new,sale +M es,sale -W new -W es

[0234] In the above formula, f all The peak operation income of new energy and energy storage combined, M new,sale is the income from new energy grid-connected power generation, M es,sale is the energy storage grid connection income, W new is the new energy assessment fee, W es The cost of building energy storage;

[0235] The benefits of new energy grid-connected power generation are as follows:

[0236]

[0237] The benefits of energy storage grid connection are as follows:

[0238]

[0239] The new energy assessment fees are as follows:

[0240]

[0241] The cost of building energy storage is as follows:

[0242]

[0243] In the above formula, p newThe on-grid electricity price for renewable energy power generation, is the grid-connected power of new energy after the combined adjustment of new energy and energy storage at time t, Δt is the time interval, T is the number of scheduling periods, and For energy storage peak-valley arbitrage, the discharge power and charging power at time t, p pl is the time-of-use electricity price, T peak The peak demand period of the system. is the charging power when the system is required to peak, H es,peak is the peak load compensation coefficient of energy storage, p es,peak The price standard for energy storage participating in peak load regulation compensation is: To assess the power consumption of new energy curve deviation, The short-term forecast output deviation of new energy is used to assess the power consumption, p new The on-grid electricity price for renewable energy power generation, is the investment cost per unit capacity of energy storage, E es is the installed capacity of energy storage, x is the market value coefficient of energy storage, y is the number of years of energy storage operation, is the unit energy operating cost of energy storage, and are the discharge power and charging power of the energy storage in period t, respectively, and Δt is the interval time.

[0244] Furthermore, the new energy curve deviation assessment power is as follows:

[0245]

[0246] The short-term forecast output deviation assessment power of new energy is as follows:

[0247]

[0248] In the above formula, P real (t) is the actual output of new energy at time t, P allwd (t) is the deviation range of renewable energy power generation allowed by the load instruction at time t, It is the assessment standard value for the accuracy of short-term forecast output of new energy. The accuracy of the short-term forecast output of new energy on the previous day, is the rated capacity of the new energy station, H new The assessment coefficient set for the short-term forecast output of new energy on the previous day;

[0249] The load instruction at time t allows the deviation range of renewable energy actual power generation as follows:

[0250]

[0251] The accuracy of the short-term forecast output of new energy sources mentioned above is as follows:

[0252]

[0253] In the above formula, P cmd (t) is the load command power at time t, is the actual output of new energy at time t; Contribute to the short-term forecast of new energy sources at time t; is the available capacity of new energy power stations; N P_pre is the sample size for the renewable energy power generation period.

[0254] Furthermore, the constraint condition includes at least one of the following:

[0255] Constraints on the combined output of new energy and energy storage:

[0256]

[0257] Energy storage power and energy allocation constraints:

[0258]

[0259]

[0260] Charge and discharge state constraints:

[0261]

[0262] Charge and discharge power constraints:

[0263]

[0264] State of charge constraints:

[0265]

[0266]

[0267] In the above formula, To contribute to the joint efforts of new energy and energy storage, Contribute to the short-term forecast of new energy, To participate in the energy storage discharge power adjustment of new energy output, The energy storage charging power that participates in the adjustment of new energy output, E es,all is the total installed capacity of energy storage, Allocate capacity for energy storage to participate in peak-valley arbitrage, The allocation capacity for energy storage to participate in the regulation of new energy output, The allocated rated power for the energy storage system to participate in peak-valley arbitrage, The allocated rated power of the energy storage system participating in the regulation of new energy output, is the charging state of the energy storage at time t, 0 indicates non-charging state, 1 indicates charging state, Indicates the discharge state of the energy storage at time t, 0 indicates non-discharge state, 1 indicates discharge state, and are the charging power and discharging power of the energy storage at time t, E es,pl (t) is the remaining amount of energy stored at time t, E es,pl (t-1) is the remaining power of the energy storage at time t-1, and are the charging power and discharging power of the energy storage at time t, is the initial energy storage capacity, is the final amount of energy stored, and are the upper and lower limits of energy storage capacity, η is the energy storage self-loss coefficient, η c is the energy storage charging loss coefficient, η d is the energy storage discharge loss coefficient, Δt is the time interval, To build energy storage rated power.

[0268] Example 3

[0269] 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 may be 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, 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 new energy and energy storage combined peak operation method in the above embodiment.

[0270] Example 4

[0271] 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 the 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 the processor are also stored in the storage space. 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 new energy and energy storage combined peak operation method in the above embodiment.

[0272] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, 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 magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0273] 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 flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to 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 flowcharts and / or block diagrams. 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.

[0274] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory 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 The function specified in one or more boxes.

[0275] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0276] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the 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 by the scope of protection of the claims of the present invention.

Claims

1. A method for combined peak operation of new energy and energy storage, characterized in that: The method comprises: Substitute the peak-shaving demand period of the new energy and energy storage combined system and the short-term forecast output of new energy into the new energy and energy storage combined peak operation optimization model and solve it to obtain the optimization result; Based on the optimization results, a new energy and supporting energy storage combined peak operation plan is obtained, and based on the new energy and supporting energy storage combined peak operation plan, the new energy and supporting energy storage combined system is optimized and dispatched; The optimization result includes at least one of the following: energy storage discharge power and energy storage charging power.

2. The method according to claim 1, wherein The process of obtaining the system peak-shaving demand period includes: Using the new energy and load historical power scenarios as inputs to a pre-trained neural network model, and obtaining the new energy and load historical power scenarios divided by seasons output by the pre-trained neural network model; Screening peak scenarios from the new energy and load historical power scenarios divided by season, and constructing a peak scenario set divided by season using the screened peak scenarios; The time period of the scene corresponding to each season in the peak scene set divided by season is used as the system peak-shaving demand period corresponding to each season; The new energy and load historical power scenario is composed of new energy station historical power data and load historical power data.

3. The method according to claim 2, wherein The training process of the pre-trained neural network model includes: Construct training sample data using new energy and load historical power scenarios annotated with seasonal labels; The training sample data is used to train an initial neural network model to obtain the pre-trained neural network model.

4. The method according to claim 2, wherein The step of selecting peak scenarios from the new energy and load historical power scenarios divided by season includes: The scenario in which the system relative peak-to-valley difference change rate index is greater than 1, the peak-to-valley difference rate index is greater than 80%, and the peak power gap index is greater than 10% of the peak load in the seasonal new energy and load historical power scenarios is taken as the peak scenario.

5. The method according to claim 4, wherein The relative peak-to-valley difference change rate index λ1 of the system is as follows: In the above formula, and They are the maximum equivalent load and the minimum equivalent load within one day after the new energy is connected to the grid. The equivalent load is the difference between the system load and the new energy power. L max and L min are the maximum load and minimum load of the system respectively.

6. The method according to claim 4, wherein The peak-to-valley difference index λ2 is as follows: In the above formula, and They are the maximum equivalent load and the minimum equivalent load within one day after the new energy is connected to the grid.

7. The method according to claim 4, wherein The peak power gap index λ3 is as follows: In the above formula, Gap is the maximum equivalent load within one day after the new energy is connected to the grid. dur is the duration of the power gap, is the maximum output power of the system.

8. The method according to claim 1, wherein During the prediction process of the new energy short-term output, the corresponding confidence interval U is as follows: in, In the above formula, is the benchmark value of the short-term forecast output of new energy, Φ is the confidence level of the short-term forecast output of new energy, and are the lower and upper bounds of the confidence interval for the short-term forecast output of new energy, is the deviation within the confidence interval of the short-term forecast output of new energy, R(Φ) is the score corresponding to the confidence level Φ, and N P_pre is the sample size, Contribute to the short-term forecast of new energy, P pre_fesd The standard deviation of the short-term forecast output of new energy.

9. The method according to claim 1, wherein The new energy and energy storage combined peak operation optimization model includes: a new energy and energy storage combined peak operation optimization objective function and its corresponding constraint conditions.

10. The method according to claim 9, wherein The optimization objective function of the combined peak operation of new energy and energy storage is as follows: max all =M new,sale +M es,sale -W new -W es In the above formula, f all The peak operation income of new energy and energy storage is M new,sale is the income from new energy grid-connected power generation, M es,sale is the energy storage grid connection income, W new is the new energy assessment fee, W es The cost of building energy storage.

11. The method according to claim 10, wherein The benefits of new energy grid-connected power generation are as follows: The benefits of energy storage grid connection are as follows: The new energy assessment fees are as follows: The cost of building energy storage is as follows: In the above formula, p new The on-grid electricity price for renewable energy power generation, is the grid-connected power of new energy after the combined adjustment of new energy and energy storage at time t, Δt is the time interval, T is the number of scheduling periods, and For energy storage peak-valley arbitrage, the discharge power and charging power at time t, p pl is the time-of-use electricity price, T peak The peak demand period of the system. is the charging power when the system is required to peak, H es,peak is the peak load compensation coefficient of energy storage, p es,peak The price standard for energy storage participating in peak load regulation compensation is: To assess the power consumption of new energy curve deviation, The short-term forecast output deviation of new energy is used to assess the power consumption, p new The on-grid electricity price for renewable energy power generation, is the investment cost per unit capacity of energy storage, E es is the installed capacity of energy storage, x is the market value coefficient of energy storage, y is the number of years of energy storage operation, is the unit energy operating cost of energy storage, and are the discharge power and charging power of the energy storage in period t, respectively, and Δt is the interval time.

12. The method according to claim 11, wherein The new energy curve deviation assessment power is as follows: The short-term forecast output deviation assessment power of new energy is as follows: In the above formula, P real (t) is the actual output of new energy at time t, P allwd (t) is the deviation range of renewable energy power generation allowed by the load instruction at time t, It is the assessment standard value for the accuracy of short-term forecast output of new energy. The accuracy of the short-term forecast output of new energy on the previous day, is the rated capacity of the new energy station, H new The assessment coefficient set for the short-term forecast output of new energy on the previous day; The load instruction at time t allows the deviation range of renewable energy actual power generation as follows: The accuracy of the short-term forecast output of new energy sources mentioned above is as follows: In the above formula, P cmd (t) is the load command power at time t, is the actual output of new energy at time t; Contribute to the short-term forecast of new energy sources at time t; is the available capacity of new energy power stations; N P_pre is the sample size for the renewable energy power generation period.

13. The method according to claim 10, wherein The constraint conditions include at least one of the following: Constraints on the combined output of new energy and energy storage: Energy storage power and energy allocation constraints: Charge and discharge state constraints: Charge and discharge power constraints: State of charge constraints: In the above formula, To contribute to the joint efforts of new energy and energy storage, Contribute to the short-term forecast of new energy, To participate in the energy storage discharge power adjustment of new energy output, The energy storage charging power that participates in the adjustment of new energy output, E es,all is the total installed capacity of energy storage, Allocate capacity for energy storage to participate in peak-valley arbitrage, The allocation capacity for energy storage to participate in the regulation of new energy output, The allocated rated power for the energy storage system to participate in peak-valley arbitrage, The allocated rated power of the energy storage system participating in the regulation of new energy output, is the charging state of the energy storage at time t, 0 indicates non-charging state, 1 indicates charging state, Indicates the discharge state of the energy storage at time t, 0 indicates non-discharge state, 1 indicates discharge state, and are the charging power and discharging power of the energy storage at time t, E es,pl (t) is the remaining amount of energy stored at time t, E es,pl (t-1) is the remaining power of the energy storage at time t-1, and are the charging power and discharging power of the energy storage at time t, is the initial energy storage capacity, is the final amount of energy stored, and are the upper and lower limits of energy storage capacity, η is the energy storage self-loss coefficient, η c is the energy storage charging loss coefficient, η d is the energy storage discharge loss coefficient, Δt is the time interval, To build energy storage rated power.

14. A new energy and energy storage combined peak operation device, characterized in that: The device comprises: The analysis module is used to substitute the peak-shaving demand period of the new energy and energy storage combined system and the short-term predicted output of new energy into the new energy and energy storage combined peak operation optimization model and solve it to obtain the optimization result; a scheduling module configured to obtain a peak operation plan for the new energy and energy storage system based on the optimization results, and to optimize the scheduling of the new energy and energy storage system based on the peak operation plan; The optimization result includes at least one of the following: energy storage discharge power and energy storage charging power.

15. The device according to claim 14, wherein The process of obtaining the system peak-shaving demand period includes: Using the new energy and load historical power scenarios as inputs to a pre-trained neural network model, and obtaining the new energy and load historical power scenarios divided by seasons output by the pre-trained neural network model; Screening peak scenarios from the new energy and load historical power scenarios divided by season, and constructing a peak scenario set divided by season using the screened peak scenarios; The time period of the scene corresponding to each season in the peak scene set divided by season is used as the system peak-shaving demand period corresponding to each season; The new energy and load historical power scenario is composed of new energy station historical power data and load historical power data.

16. The device according to claim 15, characterized in that The training process of the pre-trained neural network model includes: Construct training sample data using new energy and load historical power scenarios annotated with seasonal labels; The training sample data is used to train an initial neural network model to obtain the pre-trained neural network model.

17. The device according to claim 15, wherein The step of selecting peak scenarios from the new energy and load historical power scenarios divided by season includes: The scenario in which the system relative peak-to-valley difference change rate index is greater than 1, the peak-to-valley difference rate index is greater than 80%, and the peak power gap index is greater than 10% of the peak load in the seasonal new energy and load historical power scenarios is taken as the peak scenario.

18. The device according to claim 17, wherein The relative peak-to-valley difference change rate index λ1 of the system is as follows: In the above formula, and They are the maximum equivalent load and the minimum equivalent load within one day after the new energy is connected to the grid. The equivalent load is the difference between the system load and the new energy power. L max and L min are the maximum load and minimum load of the system respectively.

19. The device according to claim 17, wherein The peak-to-valley difference index λ2 is as follows: In the above formula, and They are the maximum equivalent load and the minimum equivalent load within one day after the new energy is connected to the grid.

20. The device according to claim 17, wherein The peak power gap index λ3 is as follows: In the above formula, Gap is the maximum equivalent load within one day after the new energy is connected to the grid. dur is the duration of the power gap, is the maximum output power of the system.

21. The device according to claim 14, wherein During the prediction process of the new energy short-term output, the corresponding confidence interval U is as follows: In the above formula, is the benchmark value of the short-term forecast output of new energy, Φ is the confidence level of the short-term forecast output of new energy, and are the lower and upper bounds of the confidence interval for the short-term forecast output of new energy, is the deviation within the confidence interval of the short-term forecast output of new energy, R(Φ) is the score corresponding to the confidence level Φ, and N P_pre is the sample size, Contribute to the short-term forecast of new energy, P pre_fesd The standard deviation of the short-term forecast output of new energy.

22. The device according to claim 14, wherein The new energy and energy storage combined peak operation optimization model includes: a new energy and energy storage combined peak operation optimization objective function and its corresponding constraint conditions.

23. The device according to claim 22, wherein The optimization objective function of the combined peak operation of new energy and energy storage is as follows: max all =M new,sale +M es,sale -W new -W es In the above formula, f all The peak operation income of new energy and energy storage is M new,sale is the income from new energy grid-connected power generation, M es,sale is the energy storage grid connection income, W new is the new energy assessment fee, W es The cost of building energy storage.

24. The device according to claim 23, wherein The benefits of new energy grid-connected power generation are as follows: The benefits of energy storage grid connection are as follows: The new energy assessment fees are as follows: The cost of building energy storage is as follows: In the above formula, p new The on-grid electricity price for renewable energy power generation, is the grid-connected power of new energy after the combined adjustment of new energy and energy storage at time t, Δt is the time interval, T is the number of scheduling periods, and For energy storage peak-valley arbitrage, the discharge power and charging power at time t, p pl is the time-of-use electricity price, T peak The peak demand period of the system. is the charging power when the system is required to peak, H es,peak is the peak load compensation coefficient of energy storage, p es,peak The price standard for energy storage participating in peak load regulation compensation is: To assess the power consumption of new energy curve deviation, The short-term forecast output deviation of new energy is used to assess the power consumption, p new The on-grid electricity price for renewable energy power generation, is the investment cost per unit capacity of energy storage, E es is the installed capacity of energy storage, x is the market value coefficient of energy storage, y is the number of years of energy storage operation, is the unit energy operating cost of energy storage, and are the discharge power and charging power of the energy storage in period t, respectively, and Δt is the interval time.

25. The device according to claim 24, wherein The new energy curve deviation assessment power is as follows: The short-term forecast output deviation assessment power of new energy is as follows: In the above formula, P real (t) is the actual output of new energy at time t, P allwd (t) is the deviation range of renewable energy power generation allowed by the load instruction at time t, It is the assessment standard value for the accuracy of short-term forecast output of new energy. The accuracy of the short-term forecast output of new energy on the previous day, is the rated capacity of the new energy station, H new The assessment coefficient set for the short-term forecast output of new energy on the previous day; The load instruction at time t allows the deviation range of renewable energy actual power generation as follows: The accuracy of the short-term forecast output of new energy sources mentioned above is as follows: In the above formula, P cmd (t) is the load command power at time t, is the actual output of new energy at time t; Contribute to the short-term forecast of new energy sources at time t; is the available capacity of new energy power stations; N P_pre is the sample size for the renewable energy power generation period.

26. The device according to claim 24, wherein The constraint conditions include at least one of the following: Constraints on the combined output of new energy and energy storage: Energy storage power and energy allocation constraints: Charge and discharge state constraints: Charge and discharge power constraints: State of charge constraints: In the above formula, To contribute to the joint efforts of new energy and energy storage, Contribute to the short-term forecast of new energy, To participate in the energy storage discharge power adjustment of new energy output, The energy storage charging power that participates in the adjustment of new energy output, E es,all is the total installed capacity of energy storage, Allocate capacity for energy storage to participate in peak-valley arbitrage, The allocation capacity for energy storage to participate in the regulation of new energy output, The allocated rated power for the energy storage system to participate in peak-valley arbitrage, The allocated rated power of the energy storage system participating in the regulation of new energy output, is the charging state of the energy storage at time t, 0 indicates non-charging state, 1 indicates charging state, Indicates the discharge state of the energy storage at time t, 0 indicates non-discharge state, 1 indicates discharge state, and are the charging power and discharging power of the energy storage at time t, E es,pl (t) is the remaining amount of energy stored at time t, E es,pl (t-1) is the remaining power of the energy storage at time t-1, and are the charging power and discharging power of the energy storage at time t, is the initial energy storage capacity, is the final amount of energy stored, and are the upper and lower limits of energy storage capacity, η is the energy storage self-loss coefficient, η c is the energy storage charging loss coefficient, η d is the energy storage discharge loss coefficient, Δt is the time interval, To build energy storage rated power.

27. 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 new energy and accompanying energy storage combined peak operation method as described in any one of claims 1 to 13 is implemented.

28. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed, it implements the new energy and accompanying energy storage combined peak operation method as described in any one of claims 1 to 13.

Images