Intelligent new energy network access optimization method and system

Abstract

The invention discloses an intelligent new energy network access optimization system. According to the system, the power of a traditional unit, the power of a new energy unit and the rated power of a power grid load are obtained; according to the power grid load rated power, defining the dynamic power generation total power matched with the supply and demand, and defining a target function according to the power grid load rated power; the energy storage power is regarded as an optimization variable, and the energy storage power is updated to minimize the target function; determining the energy storage power when the objective function is minimized as the optimal energy storage power at the current time point; acquiring an initial charge state of the energy storage equipment at an initial time point in a future time period; according to the optimal energy storage power and the initial charge state of each time point in the future time period, calculating the optimal charge state and making an optimal scheduling strategy according to the optimal charge state; according to the method, the objective function is optimized through double objectives, and short-term supply and demand matching and long-term system stability are both considered in the dynamic scheduling of the energy storage power.

Description

Technical Field

[0001] The present invention relates to the field of new energy network access optimization, and in particular to an intelligent new energy network access optimization system. Background Art

[0002] With the rapid development of renewable energy power generation technology, the proportion of wind power, photovoltaic and other renewable energy units connected to the grid has been increasing. However, the power generation of renewable energy has significant volatility and uncertainty, which poses a severe challenge to the stable operation of the power grid. Traditional grid dispatching methods usually rely on fixed dispatching plans or simple feedback control, which cannot effectively cope with the random fluctuations of renewable energy power. At the same time, in order to balance the supply and demand relationship of the power grid, energy storage equipment is used as a common means of grid access regulation. The patent document with patent publication number CN115764869A discloses a source-grid-load-storage operation optimization method and system based on the randomness of renewable energy, which arranges power generation plans at the lowest cost, achieves balance with a given load and meets certain constraints and backup requirements, thereby increasing the optimization degree of the source-grid-load-storage system.

[0003] However, in the above patents and the prior art, when designing the scheduling strategy for energy storage power, a single-objective optimization method is still used, such as minimizing only the instantaneous power deviation or only minimizing the total deviation; this single-objective optimization method can usually only solve the error at the current time point. If only the instantaneous deviation is minimized, supply and demand matching may be achieved in the short term, but the accumulation of the total deviation is ignored, which can easily cause system instability. If only the total deviation is minimized, the response capability to short-term precise supply and demand matching is insufficient, which may lead to inflexible grid scheduling. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an intelligent new energy grid access optimization system, which solves the technical problems raised in the background technology through a dual-objective optimization method.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0006] An intelligent new energy network access optimization method, the optimization method comprising:

[0007] S1. Obtain the power of traditional units, power of new energy units, and rated power of grid load at each time point in the future time period;

[0008] S2. According to the rated power of the grid load, define the dynamic total power generation that matches its supply and demand, and define the objective function based on this; wherein the dynamic total power generation is composed of the power of the traditional units, the power of the new energy units, and the power of the energy storage power as the optimization variable;

[0009] The definition expression of the dynamic total power generation is:

[0010] P g (t) = P gr (t)+P gt (t)+P s (t);

[0011] Among them, P g (t) represents the total dynamic power generation; P gr (t) represents the power of the new energy unit, P gt (t) represents the power of the traditional unit, P s (t) represents the energy storage power, which characterizes the energy storage power of the energy storage device at the i-th time point. It is an optimization variable used to adjust the balance between the dynamic total power generation and the rated power of the grid load.

[0012] S3, regard the energy storage power as an optimization variable, and update the energy storage power to minimize the objective function;

[0013] S4, determining the energy storage power when minimizing the objective function as the optimal energy storage power at the current time point;

[0014] S5, obtaining the initial state of charge of the energy storage device at an initial time point in the future time period;

[0015] S6. Calculate the optimal state of charge based on the optimal energy storage power and initial state of charge at each time point in the future time period and formulate an optimized scheduling strategy based on this.

[0016] In some of the embodiments, the step of obtaining the power of the conventional unit includes:

[0017] The steps for obtaining the power of the conventional unit are:

[0018] S1-A1. Define the output process of traditional unit power as a linear output process;

[0019] S1-A2, collecting the historical output power and output time points of the traditional units, and fitting the time constant and bias constant of the linear output process;

[0020] S1-A3, obtaining the power of the conventional unit in the future time period according to the fitted time constant and bias constant;

[0021] The expression of the traditional unit power is:

[0022] P gt (t) = k·t i +b;

[0023] Among them, P gt (t) represents the power of the traditional unit at the i-th time point, k and b represent the time constant and bias constant based on the historical output power and its output time point fitting, respectively.

[0024] In some of the embodiments, the step of obtaining the power of the new energy unit includes:

[0025] The steps for obtaining the power of the new energy unit are:

[0026] S1-B1, collecting meteorological conditions in the future time period, quantifying them as input features, and pre-training a new energy power prediction model;

[0027] S1-B2, sliding the time window from the initial time point t1 to the end time point t2 of the future time period, and outputting the power of the new energy unit point by point using the new energy power prediction model.

[0028] In some embodiments, the step of defining the objective function includes:

[0029] S2-1. Define the deviation between the dynamic total power generation and the grid load power as the instantaneous power deviation;

[0030] The instantaneous power deviation expression is:

[0031] ΔP(t)=P g (t)-P l (t)=(P gr (t)+P gt (t)+P s (t))-P l (t);

[0032] Among them, ΔP(t) represents the instantaneous power deviation, which represents the deviation between the total dynamic power generation and the grid load power at the i-th time point in the future time period; P l (t) represents the rated power of the grid load;

[0033] S2-2, define a function for minimizing instantaneous power deviation and a function for minimizing total deviation;

[0034] The minimized instantaneous deviation function is:

[0035]

[0036] Wherein, t1 represents the initial time point in the future time period, t2 represents the terminal time point in the future time period, ΔP(t) represents the instantaneous power deviation at time point t, and |ΔP(t)| represents the absolute value of the instantaneous power deviation, which is used to avoid the mutual cancellation of positive and negative deviations.

[0037] The minimized total deviation function is:

[0038]

[0039] Where |ΔP(t)| 2 Indicates the square of the instantaneous power deviation, which is used to amplify the influence weight of the deviation and increase the sensitivity to large deviations;

[0040] S2-3, combining the minimization of the instantaneous power deviation function and the minimization of the total deviation function, and defining them as the objective function;

[0041] The objective function is:

[0042]

[0043] Among them, J represents the objective function, which is used to quantify the matching degree between the dynamic total power generation and the grid load power; λ represents the penalty weight, which represents the influence of the instantaneous deviation square term;

[0044] In some embodiments, the step of updating the energy storage power includes:

[0045] S3-1, calculating the instantaneous power deviation between the total dynamic power generation and the grid load power at the current time point;

[0046] S3-2, substituting the instantaneous power deviation at the current time point into the objective function, and calculating the objective function value;

[0047] S3-3, according to the objective function value, determine whether to generate a minimized objective function;

[0048] If the minimized objective function is not generated, the energy storage power is dynamically adjusted to iterate the instantaneous power deviation;

[0049] S3-4. Substitute the iterative instantaneous power deviation after iteration into the objective function until the objective function is minimized.

[0050] In some of the embodiments, the step of generating the optimal scheduling strategy for the energy storage device includes:

[0051] S6-1, obtaining the optimal energy storage power at each time point in the future time period;

[0052] S6-2. Calculate the optimal state of charge of the energy storage device at each time point in the future time period based on the initial state of charge and the optimal energy storage power;

[0053] The expression of the optimal state of charge is:

[0054]

[0055] Among them, E s (t) represents the optimal state of charge of the energy storage device at time point t, E s (t1) represents the initial charge state of the energy storage device, Represents the optimal energy storage power P from the initial time point t1 to time point t s The cumulative integral of (τ) reflects the change of the state of charge of the energy storage device over time; τ represents the intermediate time variable within the integration interval, which is used to distinguish the dynamically changing energy storage power within the integration interval at the current time point;

[0056] S6-3, based on the optimal energy storage power and the optimal state of charge E at each time point in the future time period s (t), generate the optimal scheduling strategy for energy storage equipment.

[0057] In some of the embodiments, the determination conditions for optimizing the scheduling strategy include:

[0058] S6-3-1. If the optimal energy storage power is greater than 0, the operating state of the energy storage device is marked as a charging state;

[0059] S6-3-2, if the optimal energy storage power is less than 0, mark the operating state of the energy storage device as a discharge state;

[0060] S6-3-3. If the optimal energy storage power is equal to 0, mark the operating state of the energy storage device as standby state;

[0061] S6-3-4, drawing a charge state change curve of the optimal charge state from the initial time point t1 to the final time point t2;

[0062] S6-3-5. Calculate the cumulative charge and discharge capacity of the energy storage device in the future time period;

[0063] S6-3-6. Export the operating status, charge state change curve and accumulated charge and discharge volume of the energy storage equipment into an optimized scheduling strategy.

[0064] Compared with the prior art, the intelligent new energy grid access optimization method of the present invention takes into account both short-term supply and demand matching and long-term system stability in the dynamic scheduling of energy storage power through a dual-objective optimization objective function. Furthermore, the control of instantaneous power deviation ensures real-time response to instantaneous supply and demand deviation, significantly improving the dynamic adjustment capability of energy storage equipment to new energy power fluctuations; through weighted penalty of total deviation, the adverse effect of long-term total deviation accumulation on the stability of the power grid system is reduced, making the scheduling process more robust.

[0065] In addition, dual-objective optimization enables the power grid to not only match real-time load demand when facing fluctuations in renewable energy power generation, but also smooth out the system's comprehensive power fluctuations, thereby increasing the power grid's absorption ratio of renewable energy power generation and significantly enhancing the stability of the power grid system operation.

[0066] In a second aspect, the present invention provides an intelligent new energy network access optimization system, comprising:

[0067] A power acquisition module is used to obtain the power of traditional units, the power of new energy units and the rated power of grid loads at each time point in the future time period;

[0068] The target definition module is used to define the dynamic total power generation, energy storage power and target function according to the power of new energy units and traditional units;

[0069] An optimization variable updating module is used to regard the energy storage power as an optimization variable and update the energy storage power to minimize the objective function;

[0070] An optimal energy storage power determination module, used to determine the energy storage power when minimizing the objective function as the optimal energy storage power at the current time point;

[0071] An initial state of charge acquisition module is used to acquire the initial state of charge of the energy storage device at an initial time point;

[0072] The strategy formulation module is used to calculate the optimal state of charge based on the optimal energy storage power and initial state of charge at each time point in the future time period and formulate an optimized scheduling strategy based on this.

[0073] Compared with the prior art, the intelligent new energy network access optimization system of the present invention has the same beneficial effects as the above-mentioned intelligent new energy network access optimization method, so it will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 This is a flow chart of an intelligent new energy grid access optimization method of the present invention;

[0075] Figure 2 It is a flow chart for defining the objective function of the present invention;

[0076] Figure 3 A schematic diagram of the determination conditions for optimizing the scheduling strategy of the present invention;

[0077] Figure 4 This is a structural block diagram of an intelligent new energy grid access optimization system of the present invention. DETAILED DESCRIPTION

[0078] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in 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 creative work are within the scope of protection of the present invention.

[0079] Example 1: Please refer to Figures 1 to 3 The present invention provides an intelligent new energy network access optimization method, comprising the following steps:

[0080] S1. Obtain the power of traditional units, power of new energy units, and rated power of grid load at each time point in the future time period;

[0081] Specifically, the power of new energy units refers to the instantaneous output power of new energy equipment such as wind energy and photovoltaics at several future time points. It has strong volatility and needs to be predicted in combination with meteorological conditions (such as wind speed, light intensity, etc.). This embodiment calculates the instantaneous power in the future time period point by point by using a pre-trained new energy power prediction model.

[0082] Traditional unit power refers to the power output of traditional units such as thermal power and hydropower in the future period, and its change pattern is relatively stable. The power of traditional units is based on historical operation data and is calculated through fitting models to provide basic power support to meet the power generation needs in the future period.

[0083] The grid load rated power refers to the electricity demand in a future time period, which is clearly set by the grid dispatch plan and serves as the balancing target of the power generation system.

[0084] S2. According to the rated power of the grid load, define the dynamic total power generation that matches its supply and demand, and define the objective function based on this; wherein the dynamic total power generation is composed of the power of the traditional units, the power of the new energy units, and the power of the energy storage power as the optimization variable;

[0085] The definition expression of the dynamic total power generation is:

[0086] P g (t) = P gr (t)+P gt (t)+P s (t);

[0087] Among them, P g (t) represents the total dynamic power generation; P gr (t) represents the power of the new energy unit, P gt (t) represents the power of the traditional unit, P s (t) represents the energy storage power, which characterizes the energy storage power of the energy storage device at the i-th time point. It is an optimization variable used to adjust the balance between the dynamic total power generation and the rated power of the grid load.

[0088] The dynamic total power generation is defined as the sum of the power of traditional units, the power of new energy units and the power of energy storage in the future period. It is the comprehensive power output on the power generation side of the power grid, which is used to meet the needs of the power grid load and serves as a key variable for matching supply and demand. Specifically:

[0089] The dynamic total power generation is composed of the power of traditional units, the power of new energy units and the energy storage power; among them, the power of new energy units and the power of traditional units are obtained by step S1 and are currently known inputs, while the energy storage power is the optimization variable. The energy storage power represents the charging or discharging power of the energy storage device (such as a battery) at a certain point in time. By dynamically adjusting its value, the supply and demand matching of the total power generation power and the grid load power can be achieved. The objective function is used to quantify the difference between the dynamic total power generation power and the grid load power. The core of the objective function is to minimize the deviation between the total power generation power and the grid load power by adjusting the energy storage power, thereby achieving supply and demand matching.

[0090] S3, regard the energy storage power as an optimization variable, and update the energy storage power to minimize the objective function;

[0091] Updating the energy storage power means dynamically adjusting the charging or discharging power of the energy storage device at each future time point according to the optimization requirements of the objective function, so as to achieve supply and demand matching between the dynamic total power generation and the grid load power. Specifically, the updating process is centered on minimizing the objective function, comprehensively considering the operating constraints of the energy storage device (such as charging capacity limit, maximum charging and discharging power) and the actual needs of supply and demand matching, to ensure that the adjustment results meet both the optimization objectives and the actual operating conditions of the energy storage device. Through continuous iterative updating of the energy storage power, the dynamic total power generation can be gradually optimized so that the objective function value converges to the minimized state.

[0092] S4, determining the energy storage power when minimizing the objective function as the optimal energy storage power at the current time point;

[0093] When the objective function value is minimized, the charging and discharging power of the energy storage device at each time point in the future time period is determined as the optimal energy storage power at that time point. The optimal energy storage power is the solution that minimizes the deviation between the dynamic total power generation and the grid load power, while satisfying the operating constraints of the energy storage device (such as the maximum charging and discharging power limit and the state of charge range). This result provides the optimal operation plan for the scheduling of energy storage equipment, ensuring accurate matching of supply and demand balance and improving the overall operation efficiency of the system.

[0094] S5, obtaining the initial state of charge of the energy storage device at an initial time point in the future time period;

[0095] The initial state of charge is the remaining stored energy of the energy storage device at the beginning of the optimized scheduling time period. It indicates the energy level that the energy storage device can currently use for charging and discharging, and is an important starting point for future scheduling strategies.

[0096] Specifically, the initial state of charge is obtained through the energy management system (EMS) or control system of the energy storage device, usually in the following ways:

[0097] Direct measurement: The current state of charge of the energy storage device is obtained in real time through the device sensor;

[0098] Historical records: query the state of charge at the initial time point based on the operating history data of the energy storage device;

[0099] Estimation method: Calculate the initial state of charge by combining the operating characteristics of the energy storage device and the most recent charge and discharge records.

[0100] After obtaining the initial state of charge, it is used as an input parameter and combined with the optimal energy storage power in the future time period to calculate the evolution of the state of charge of the energy storage device. The evolution process needs to ensure that the state of charge of the energy storage device is always kept within the allowable range (such as preventing overcharging or over-discharging) during the entire scheduling period to meet the operational safety and scheduling requirements of the energy storage device.

[0101] S6. Calculate the optimal state of charge based on the optimal energy storage power and initial state of charge at each time point in the future time period and formulate an optimized scheduling strategy based on this.

[0102] According to the optimal energy storage power and initial state of charge in the future time period, the change of the state of charge of the energy storage device is dynamically calculated to ensure that the state of charge always meets the operating constraints (such as the maximum and minimum charge range) during the entire operation period. Specifically, by analyzing the charging and discharging power of the energy storage device at each time point, the operating state of the energy storage device is dynamically marked, including charging (power greater than 0), discharging (power less than 0) or standby (power equal to 0). Based on the calculation results, the optimal scheduling strategy of the energy storage device is generated, the main contents include:

[0103] Operation status mark of energy storage equipment;

[0104] Curve of state of charge changing with time;

[0105] The cumulative charge and discharge volume of energy storage equipment in the future period.

[0106] This optimized scheduling strategy can achieve efficient operation of energy storage equipment in future time periods, ensuring that it can increase the proportion of new energy consumption while meeting the dynamic needs of the power grid load and enhance the overall operational stability of the power grid system.

[0107] The steps for obtaining the power of the conventional unit are:

[0108] S1-A1. Define the output process of traditional unit power as a linear output process;

[0109] S1-A2, collecting the historical output power and output time points of the traditional units, and fitting the time constant and bias constant of the linear output process;

[0110] S1-A3, obtaining the power of the conventional unit in the future time period according to the fitted time constant and bias constant;

[0111] The expression of the traditional unit power is:

[0112] P gt (t) = k·t i +b;

[0113] Among them, P gt (t) represents the power of the traditional unit at the i-th time point, k and b represent the time constant and bias constant based on the historical output power and its output time point fitting, respectively.

[0114] According to the characteristics of traditional units, their output power usually has high stability and linear change law. Therefore, the prediction of traditional unit power can simplify its change into a linear function form to reduce the complexity of modeling and improve the calculation efficiency. Then, based on the historical operation data (historical output power and its output time point), the time constant k and bias constant b of the traditional unit are fitted to represent the power change rate and the basic power level respectively. Finally, the power of the traditional unit at each time point in the future time period is quickly calculated according to the fitted linear function.

[0115] The steps for obtaining the power of the new energy unit are as follows:

[0116] S1-B1, collecting meteorological conditions in the future time period, quantifying them as input features, and pre-training a new energy power prediction model;

[0117] S1-B2, sliding the time window from the initial time point t1 to the end time point t2 of the future time period, and outputting the power of the new energy unit point by point using the new energy power prediction model.

[0118] The new energy power prediction model needs to clarify its input characteristics and target output to achieve accurate prediction of the power of new energy units in the future time period. In this embodiment, a general neural network model can be used as the prediction model, and its pre-training steps are as follows:

[0119] Quantify the meteorological conditions (such as wind speed, wind direction, light intensity, temperature, etc.) that affect the power generation of renewable energy units in the future time period as the core input features of the model;

[0120] For example:

[0121] For wind power generation: quantify wind speed and direction per unit time;

[0122] For photovoltaic power generation: quantify the light intensity and ambient temperature per unit time.

[0123] According to the time series rules in the future time period, auxiliary input features are added to each quantified core input feature, that is, time labels are added. The time features help capture the periodic changes of renewable energy power generation (such as diurnal cycles and seasonal fluctuations).

[0124] The target output is the power forecast value of the new energy unit at each time point in the future time period (such as wind turbine power output or photovoltaic power output); the target label is the actual power output value of the new energy unit in the historical time period;

[0125] When training the model, the model parameters are optimized by minimizing the deviation between the power prediction values ​​and the actual power output values.

[0126] In the model prediction process, a sliding time window mechanism is adopted, that is, the time window is moved step by step to predict the future power output point by point from the initial time point to the end time point; the sliding time window can effectively capture the time series characteristics and avoid the deviation accumulation problem that may be caused by direct full-time period prediction.

[0127] The objective function is defined as follows:

[0128] S2-1. Define the deviation between the dynamic total power generation and the grid load power as the instantaneous power deviation;

[0129] The instantaneous power deviation expression is:

[0130] ΔP(t)=P g (t)-P l (t)=(P gr (t)+P gt (t)+P s (t))-P l (t);

[0131] Among them, ΔP(t) represents the instantaneous power deviation, which represents the deviation between the total dynamic power generation and the grid load power at the i-th time point in the future time period; P l (t) represents the rated power of the grid load;

[0132] S2-2, define a function for minimizing instantaneous power deviation and a function for minimizing total deviation;

[0133] The minimized instantaneous deviation function is:

[0134]

[0135] Wherein, t1 represents the initial time point in the future time period, t2 represents the terminal time point in the future time period, ΔP(t) represents the instantaneous power deviation at time point t, and |ΔP(t)| represents the absolute value of the instantaneous power deviation, which is used to avoid the mutual cancellation of positive and negative deviations.

[0136] The minimization of the instantaneous deviation function is to measure the sum of the absolute deviations between the total dynamic power generation and the grid load power at each time point in the future time period, focusing on reducing the instantaneous deviation at each time point to achieve a more accurate supply and demand balance.

[0137] The minimized total deviation function is:

[0138]

[0139] Where |ΔP(t)| 2 Indicates the square of the instantaneous power deviation, which is used to amplify the influence weight of the deviation and increase the sensitivity to large deviations;

[0140] The significance of minimizing the total deviation function is to square the instantaneous power deviation and penalize larger deviation values ​​to a greater extent. By minimizing the total deviation function, the impact of large deviations can be reduced during the optimization process.

[0141] S2-3, combining the minimization of the instantaneous power deviation function and the minimization of the total deviation function, and defining them as the objective function;

[0142] The objective function is:

[0143]

[0144] Among them, J represents the objective function, which is used to quantify the matching degree between the dynamic total power generation and the grid load power; λ represents the penalty weight, which represents the influence of the instantaneous deviation square term;

[0145] Specifically, the objective function consists of two parts: minimizing the instantaneous power deviation function and minimizing the total deviation function, which are used to measure the absolute value of the instantaneous deviation and the square of the deviation respectively. In the objective function, the sensitivity of the deviation is adjusted by introducing a weight coefficient, and it is finally defined as the objective function. The objective function takes into account the accuracy of the supply and demand balance and the stability of the optimization results by weighted combination of the instantaneous deviation function and the total deviation function. The ultimate goal is to dynamically adjust the energy storage power by minimizing the objective function so that the total dynamic power generation power and the grid load power reach the optimal matching state.

[0146] The step of updating the energy storage power includes:

[0147] S3-1, calculating the instantaneous power deviation between the total dynamic power generation and the grid load power at the current time point;

[0148] S3-2, substituting the instantaneous power deviation at the current time point into the objective function, and calculating the objective function value;

[0149] S3-3, according to the objective function value, determine whether to generate a minimized objective function;

[0150] If the minimized objective function is not generated, the energy storage power is dynamically adjusted to iterate the instantaneous power deviation;

[0151] S3-4. Substitute the iterative instantaneous power deviation after iteration into the objective function until the objective function is minimized.

[0152] Through the iterative optimization process of calculating instantaneous power deviation, objective function and dynamically adjusting energy storage power, the optimal scheduling of energy storage equipment and the supply and demand matching of dynamic total power generation and grid load power are achieved.

[0153] Furthermore, in this embodiment, the step of generating an optimized scheduling strategy for energy storage equipment includes:

[0154] S6-1, obtaining the optimal energy storage power at each time point in the future time period;

[0155] S6-2. Calculate the optimal state of charge of the energy storage device at each time point in the future time period based on the initial state of charge and the optimal energy storage power;

[0156] The expression of the optimal state of charge is:

[0157]

[0158] Among them, E s (t) represents the optimal state of charge of the energy storage device at time point t, E s (t1) represents the initial charge state of the energy storage device, Represents the optimal energy storage power P from the initial time point t1 to time point t s The cumulative integral of (τ) reflects the change of the charge state of the energy storage device over time; τ represents the intermediate time variable within the integration interval, which is used to distinguish the dynamically changing energy storage power within the integration interval at the current time point.

[0159] Of course, in order to avoid overcharging or over-discharging of energy storage devices, it is necessary to constrain the optimal state of charge, such as the lower and upper limits of the state of charge of the energy storage device, to ensure the safety and stability of the operation of the energy storage device.

[0160] S6-3, based on the optimal energy storage power and the optimal state of charge E at each time point in the future time period s (t), generate the optimal scheduling strategy for energy storage equipment.

[0161] Furthermore, in this embodiment, the determination conditions for optimizing the scheduling strategy include:

[0162] S6-3-1. If the optimal energy storage power is greater than 0, the operating state of the energy storage device is marked as a charging state;

[0163] S6-3-2, if the optimal energy storage power is less than 0, mark the operating state of the energy storage device as a discharge state;

[0164] S6-3-3. If the optimal energy storage power is equal to 0, mark the operating state of the energy storage device as standby state;

[0165] S6-3-4, drawing a charge state change curve of the optimal charge state from the initial time point t1 to the final time point t2;

[0166] S6-3-5. Calculate the cumulative charge and discharge capacity of the energy storage equipment in the future time period;

[0167] S6-3-6. Export the operating status, charge state change curve and accumulated charge and discharge volume of the energy storage equipment into an optimized scheduling strategy.

[0168] Specifically, according to the optimal energy storage power and initial state of charge at each time point in the future time period, the evolution of the state of charge of the energy storage device in the entire time period can be calculated, and the optimization scheduling strategy can be further generated; wherein, the generation steps are:

[0169] First, based on the initial state of charge and the optimal energy storage power in the future time period, the optimal state of charge at each time point is dynamically calculated by integrating the charging and discharging power of the energy storage device. The calculation of the state of charge must meet the operating constraints to avoid overcharging or over-discharging of the energy storage device to ensure the safety and stability of the equipment's operation.

[0170] Secondly, according to the optimal energy storage power of the energy storage device at each time point, its operating status is dynamically marked:

[0171] The charging state indicates that the energy storage device is absorbing excess power;

[0172] The discharge state indicates that the energy storage device is releasing the stored electrical energy;

[0173] The standby state means that the energy storage device is in a stationary state.

[0174] Plot the state of charge curve:

[0175] At the same time, based on the optimal state of charge from the initial time point to the final time point, a curve of the charge state of the energy storage device changing with time is generated, which intuitively shows the charge change trend of the energy storage device during the scheduling cycle.

[0176] Then, the cumulative charge and discharge volume of the energy storage equipment in the future time period is summarized, and the charging and discharging contribution of the energy storage equipment in the entire scheduling cycle is evaluated to provide data reference for system operation.

[0177] Finally, the operating status mark, charge state change curve and cumulative charge and discharge volume of energy storage equipment are integrated into an optimized scheduling strategy to provide guidance for the efficient operation of energy storage equipment in the future time period. The optimized scheduling strategy can ensure the operating safety of energy storage equipment, increase the proportion of new energy consumption, and enhance the overall stability and reliability of the power grid system.

[0178] Embodiment 2: The technical solution of Embodiment 2 is different from that of Embodiment 1 in that an intelligent new energy grid access optimization system is also disclosed, which is used to implement the above-mentioned method embodiments, and will not be repeated hereafter. The terms "module", "unit", "subunit", etc. used below refer to a combination of software and / or hardware that can implement predetermined functions. Although the systems described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0179] like Figure 4 As shown, Figure 4 This is a structural block diagram of an intelligent new energy grid access optimization system of the present invention, which includes:

[0180] A power acquisition module is used to obtain the power of traditional units, the power of new energy units and the rated power of grid loads at each time point in the future time period;

[0181] The target definition module is used to define the dynamic total power generation, energy storage power and target function according to the power of new energy units and traditional units;

[0182] An optimization variable updating module is used to regard the energy storage power as an optimization variable and update the energy storage power to minimize the objective function;

[0183] An optimal energy storage power determination module, used to determine the energy storage power when minimizing the objective function as the optimal energy storage power at the current time point;

[0184] An initial state of charge acquisition module is used to acquire the initial state of charge of the energy storage device at an initial time point;

[0185] The strategy formulation module is used to calculate the optimal state of charge based on the optimal energy storage power and initial state of charge at each time point in the future time period and formulate an optimized scheduling strategy based on this.

[0186] In the above system, the power acquisition module is used to obtain the power of the traditional unit, the power of the new energy unit and the rated power of the grid load; the target definition module is used to define the total power generation power, the energy storage power and the objective function; the energy storage power is updated through the optimization variable update module; the optimal energy storage power at the current time point is determined through the optimal energy storage power determination module; the initial state of charge is obtained through the initial state of charge acquisition module; and the optimization scheduling strategy is formulated through the strategy formulation module, thereby solving the problem of difficulty in balancing the accumulation of total deviations and insufficient response to short-term supply and demand matching.

[0187] The above embodiments can be implemented in whole or in part by software, hardware, firmware or other arbitrary combinations. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable systems. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center.

[0188] The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0189] In the several embodiments provided in the present application, it should be understood that the disclosed systems, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the units is only a logical function division of a waterway underwater terrain change analysis system and method. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the system or unit can be electrical, mechanical or other forms.

[0190] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. An intelligent new energy network access optimization method, characterized in that: include: S1. Obtain the power of traditional units, power of new energy units, and rated power of grid load at each time point in the future time period; S2. According to the rated power of the grid load, define the dynamic total power generation that matches its supply and demand, and define the objective function based on this; wherein the dynamic total power generation is composed of the power of the traditional units, the power of the new energy units, and the power of the energy storage power as the optimization variable; The definition expression of the dynamic total power generation is: P g (t)=P gr (t)+P gt (t)+P s (t); Among them, P g (t) represents the total dynamic power generation; P gr (t) represents the power of the new energy unit, P gt (t) represents the power of the traditional unit, P s (t) represents the energy storage power, which characterizes the energy storage power of the energy storage device at the i-th time point. It is an optimization variable used to adjust the balance between the dynamic total power generation and the rated power of the grid load; S3, regard the energy storage power as an optimization variable, and update the energy storage power to minimize the objective function; S4, determining the energy storage power when minimizing the objective function as the optimal energy storage power at the current time point; S5, obtaining the initial state of charge of the energy storage device at an initial time point in the future time period; S6. Calculate the optimal state of charge based on the optimal energy storage power and initial state of charge at each time point in the future time period and formulate an optimized scheduling strategy based on this.

2. According to claim 1, an intelligent new energy network access optimization method is characterized in that: The step of obtaining the power of the conventional unit comprises: The steps for obtaining the power of the conventional unit are: S1-A1. Define the output process of traditional unit power as a linear output process; S1-A2, collecting the historical output power and output time points of the traditional units, and fitting the time constant and bias constant of the linear output process; S1-A3, obtaining the power of the conventional unit in the future time period according to the fitted time constant and bias constant; The expression of the traditional unit power is: P gt (t)=k·t i +b; Among them, P gt (t) represents the power of the traditional unit at the i-th time point, k and b represent the time constant and bias constant based on the historical output power and its output time point fitting, respectively.

3. According to claim 1, an intelligent new energy network access optimization method is characterized in that: The step of obtaining the power of the new energy unit includes: The steps for obtaining the power of the new energy unit are: S1-B1, collecting meteorological conditions in the future time period, quantifying them as input features, and pre-training a new energy power prediction model; S1-B2, sliding the time window from the initial time point t1 to the end time point t2 of the future time period, and outputting the power of the new energy unit point by point using the new energy power prediction model.

4. According to claim 1, the intelligent new energy network access optimization method is characterized in that: The objective function definition step comprises: S2-1. Define the deviation between the dynamic total power generation and the grid load power as the instantaneous power deviation; The instantaneous power deviation expression is: ΔP(t)=P g (t)-P l (t)=(P gr (t)+P gt (t)+P s (t))-P l (t); Among them, ΔP(t) represents the instantaneous power deviation, which represents the deviation between the total dynamic power generation and the grid load power at the i-th time point in the future time period; P l (t) represents the rated power of the grid load; S2-2, define a function for minimizing instantaneous power deviation and a function for minimizing total deviation; The minimized instantaneous deviation function is: Wherein, t1 represents the initial time point in the future time period, t2 represents the terminal time point in the future time period, ΔP(t) represents the instantaneous power deviation at time point t, and |ΔP(t)| represents the absolute value of the instantaneous power deviation, which is used to avoid the mutual cancellation of positive and negative deviations. The minimized total deviation function is: Where |ΔP(t)| 2 Indicates the square of the instantaneous power deviation, which is used to amplify the influence weight of the deviation and increase the sensitivity to large deviations; S2-3, combining the minimization of the instantaneous power deviation function and the minimization of the total deviation function, and defining them as the objective function; The objective function is: Among them, J represents the objective function, which is used to quantify the matching degree between the dynamic total power generation and the grid load power; λ represents the penalty weight, which represents the influence of the instantaneous square deviation term.

5. According to claim 1, the intelligent new energy network access optimization method is characterized in that: The steps for updating the energy storage power include: S3-1, calculating the instantaneous power deviation between the total dynamic power generation and the grid load power at the current time point; S3-2, substituting the instantaneous power deviation at the current time point into the objective function, and calculating the objective function value; S3-3, according to the objective function value, determine whether to generate a minimized objective function; If the minimized objective function is not generated, the energy storage power is dynamically adjusted to iterate the instantaneous power deviation; S3-4. Substitute the iterative instantaneous power deviation after iteration into the objective function until the objective function is minimized.

6. The intelligent new energy network access optimization method according to claim 1 is characterized in that: The steps for generating the optimal dispatching strategy for energy storage equipment include: S6-1, obtaining the optimal energy storage power at each time point in the future time period; S6-2. Calculate the optimal state of charge of the energy storage device at each time point in the future time period based on the initial state of charge and the optimal energy storage power; The expression of the optimal state of charge is: Among them, E s (t) represents the optimal state of charge of the energy storage device at time point t, E s (t1) represents the initial charge state of the energy storage device, Represents the optimal energy storage power P from the initial time point t1 to time point t s The cumulative integral of (τ) reflects the change of the state of charge of the energy storage device over time; τ represents the intermediate time variable within the integration interval, which is used to distinguish the dynamically changing energy storage power within the integration interval at the current time point; S6-3, based on the optimal energy storage power and the optimal state of charge E at each time point in the future time period s (t), generate the optimal scheduling strategy for energy storage equipment.

7. The intelligent new energy network access optimization method according to claim 1 is characterized in that: The criteria for optimizing the scheduling strategy include: S6-3-1. If the optimal energy storage power is greater than 0, the operating state of the energy storage device is marked as a charging state; S6-3-2, if the optimal energy storage power is less than 0, mark the operating state of the energy storage device as a discharge state; S6-3-3. If the optimal energy storage power is equal to 0, mark the operating state of the energy storage device as standby state; S6-3-4, drawing a charge state change curve of the optimal charge state from the initial time point t1 to the final time point t2; S6-3-5. Calculate the cumulative charge and discharge capacity of the energy storage device in the future time period; S6-3-6. Export the operating status, charge state change curve and accumulated charge and discharge volume of the energy storage equipment into an optimized scheduling strategy.

8. An intelligent new energy network access optimization system, applying an intelligent new energy network access optimization method according to any one of claims 1 to 7, comprising: A power acquisition module is used to obtain the power of traditional units, the power of new energy units and the rated power of grid loads at each time point in the future time period; The target definition module is used to define the dynamic total power generation, energy storage power and target function according to the power of new energy units and traditional units; An optimization variable updating module is used to regard the energy storage power as an optimization variable and update the energy storage power to minimize the objective function; An optimal energy storage power determination module, used to determine the energy storage power when minimizing the objective function as the optimal energy storage power at the current time point; An initial state of charge acquisition module is used to acquire the initial state of charge of the energy storage device at an initial time point; The strategy formulation module is used to calculate the optimal state of charge based on the optimal energy storage power and initial state of charge at each time point in the future time period and formulate an optimized scheduling strategy based on this.

Images