Energy dispatch optimization method and related equipment for power system

Abstract

The present invention provides an energy dispatch optimization method and related equipment for an electric power system, which constructs a prediction model based on the historical load data, current load data and future load data of a target electric power system obtained in multiple dispatch cycles; inputs the historical load data and the current load data into the prediction model for prediction, obtains the difference between the future prediction data and the future load data, and corrects the prediction model to obtain a target prediction model; for each dispatch cycle, optimizes the control quantity through the target prediction model and the constructed system constraint conditions to obtain an optimal control sequence; selects a group of control quantities corresponding to the current dispatch cycle of the target electric power system in the optimal control sequence to dispatch the target electric power system in real time, and obtains a real-time dispatch optimization result of the target electric power system; compared with the existing technology, the operation stability and dispatch accuracy of the new electric power system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy dispatching of power systems, and in particular to an energy dispatching optimization method and related equipment for power systems. Background Art

[0002] With the rapid development of the economy, human society's demand for electricity continues to grow. In order to achieve the goal of green and low-carbon development, new power systems have begun to be vigorously promoted. The key to developing new power systems lies in the stability and accuracy of system operation.

[0003] Traditional power system dispatch methods mostly rely solely on building statistical models from historical data, which are then used for calculations. However, as the proportion of renewable energy sources such as wind and solar power in the power system gradually increases, traditional power system dispatch methods have become significantly inadequate in addressing the intermittent and volatile nature of renewable energy. The increasing proportion of renewable energy generation places higher demands on the stable operation and dispatch optimization of the power system. Accurately predicting the power generation and load demand of new power systems has become the key to optimized dispatch, but a single forecasting model cannot fully address the uncertainty of renewable energy generation, resulting in poor operational stability of the power system and low dispatch accuracy. Summary of the Invention

[0004] The present invention provides an energy dispatch optimization method and related equipment for an electric power system, the purpose of which is to improve the operational stability and dispatch accuracy of a new type of electric power system.

[0005] In order to achieve the above object, the present invention provides a method for optimizing energy dispatching of a power system, comprising:

[0006] Step 1: Obtain historical load data, current load data, and future load data of the target power system under multiple dispatch cycles;

[0007] Step 2: Build a prediction model based on historical load data, current load data, and future load data;

[0008] Step 3: Input the historical load data and the current load data into the prediction model to obtain future prediction data, and use the difference between the future prediction data and the future load data to correct the prediction model to obtain the target prediction model;

[0009] Step 4: For each scheduling cycle, the control variables are optimized using the target prediction model and the constructed system constraints to obtain the optimal control sequence. The optimal control sequence includes the control variables corresponding to all scheduling cycles. Each set of control variables includes energy scheduling instructions, valve opening adjustment, and power distribution.

[0010] Step 5: Determine the current dispatch cycle of the target power system, select a set of control quantities corresponding to the current dispatch cycle of the target power system in the optimal control sequence, and dispatch the target power system in real time to obtain the real-time dispatch optimization result of the target power system.

[0011] More specifically, the prediction model includes:

[0012] The state space equations used to describe the dynamic behavior of the power are expressed as:

[0013]

[0014] Where x represents the state variable, x1, x2, and x3 represent historical load data, current load data, or future load data, respectively, u represents the input variable, p represents the control quantity of the target power system, and represents the system parameters of the target power system. f(·) represents a function that describes the relationship between the state variable, input variables, and system parameters.

[0015] The transfer function is used to establish the relationship between the historical load data, current load data of the target power system input and the future load data of the system output. The expression is:

[0016]

[0017] Where Y(s) represents the Laplace transform result of the future load data output by the system, and U(s) represents the Laplace transform result of the historical load data and current load data input by the system;

[0018] The incremental model is used to convert the prediction model into an incremental form. The expression is:

[0019] Δx(k)=x(k)-x(k-1)

[0020] Δu(k)=u(k)-u(k-1)

[0021] Among them, Δx(k) represents the increment of the state variable at time k, Δu(k) represents the increment of the control quantity at time k, x(k) represents the state variable at time k, x(k-1) represents the state variable at time k-1, u(k) represents the control quantity at time k, and u(k-1) represents the control quantity at time k-1.

[0022] Furthermore, system constraints include state variable constraints, control quantity constraints, system output constraints, and dynamic constraints.

[0023] Further, the state variable constraints include voltage constraints, current constraints, and power constraints;

[0024] The voltage constraint is expressed as:

[0025] V min ≤V(k)≤V max

[0026] The current constraint is expressed as:

[0027] I min ≤I(k)≤I max

[0028] The power constraint is expressed as:

[0029] P min ≤P(k)≤P max

[0030] Where V(k) represents the voltage value at time k, I(k) represents the current value at time k, P(k) represents the power value at time k, V min Indicates the minimum value allowed by voltage, V max Indicates the maximum allowable voltage, I min Indicates the maximum allowable current, I max Indicates the minimum allowable current, P min Indicates the maximum value of power allowed, P max Indicates the minimum allowed power value.

[0031] Furthermore, the control quantity constraints include energy dispatch instruction constraints, valve opening adjustment constraints, and power allocation constraints;

[0032] Among them, the energy dispatch instruction constraint is expressed as:

[0033]

[0034] The valve opening adjustment constraint is expressed as:

[0035]

[0036] The power allocation constraint is expressed as:

[0037]

[0038] Among them, u1(k) represents the energy dispatch instruction value at time k, u2(k) represents the valve opening adjustment value at time k, and represents the power distribution value at time k. represents the minimum value of the energy scheduling instruction allowed at time k, represents the maximum value of the energy dispatch instruction allowed at time k, Indicates the minimum value of the valve opening adjustment value allowed at time k, Indicates the maximum value of the valve opening adjustment value allowed at time k, Indicates the minimum value of the power allocation value allowed at time k, Indicates the maximum value of power allocation allowed at time k.

[0039] Furthermore, the system output constraint is to constrain the tracking reference signal, which is expressed as:

[0040] y min (k)≤y(k)≤y max (k)

[0041] Among them, y(k) represents the tracking reference signal output at time k, y min (k) represents the minimum value of the tracking reference signal allowed at time k, y max (k) represents the maximum value of the tracking reference signal allowed at time k.

[0042] Furthermore, the dynamic constraint is to constrain the rate of change of the control variable, which can be expressed as:

[0043] Δu min ≤u(k)-u(k-1)≤Δu max

[0044] Among them, u(k)-u(k-1) represents the rate of change of the control quantity, Δu min Indicates the minimum allowed rate of change of the control quantity, Δu max Indicates the maximum rate of change allowed for the controlled variable.

[0045] The present invention also provides an energy dispatch optimization device for a power system, comprising:

[0046] An acquisition module is used to obtain historical load data, current load data, and future load data of the target power system under multiple dispatch cycles;

[0047] A construction module for constructing a prediction model based on historical load data, current load data, and future load data;

[0048] The correction module is used to input the historical load data and the current load data into the prediction model for prediction to obtain future prediction data, and use the difference between the future prediction data and the future load data to correct the prediction model to obtain the target prediction model;

[0049] The optimization module is used to optimize the control variables for each scheduling cycle using the target prediction model and the constructed system constraints to obtain the optimal control sequence. The optimal control sequence includes the control variables corresponding to all scheduling cycles. Each set of control variables includes energy scheduling instructions, valve opening adjustment, and power distribution.

[0050] The scheduling module is used to determine the current scheduling cycle of the target power system, select a set of control quantities corresponding to the current scheduling cycle of the target power system in the optimal control sequence, and schedule the target power system in real time to obtain the real-time scheduling optimization result of the target power system.

[0051] The present invention also provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, an energy dispatch optimization method for the power system is implemented.

[0052] The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method for optimizing energy dispatching of a power system is implemented.

[0053] The above solution of the present invention has the following beneficial effects:

[0054] The present invention constructs a prediction model based on the historical load data, current load data and future load data of the target power system under multiple scheduling cycles; inputs the historical load data and the current load data into the prediction model for prediction to obtain future prediction data, and uses the difference between the future prediction data and the future load data to correct the prediction model to obtain a target prediction model; for each scheduling cycle, the control quantity is optimized by the target prediction model and the constructed system constraints to obtain an optimal control sequence, which includes control quantities corresponding to all scheduling cycles, and each group of control quantities includes energy scheduling instructions, valve opening adjustment, and power distribution; determines the current scheduling cycle of the target power system, selects a group of control quantities corresponding to the current scheduling cycle of the target power system in the optimal control sequence, and schedules the target power system in real time to obtain a real-time scheduling optimization result of the target power system; compared with the prior art, the present invention improves the operating stability and scheduling accuracy of the new power system by establishing a prediction model and system constraints, and uses the revised prediction model and system constraints to optimize the control quantity of the target power system and then schedules the target power system.

[0055] Other beneficial effects of the present invention will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 Schematic diagram of a flow chart of an embodiment of the present invention;

[0057] Figure 2 This is a schematic diagram of the structure of an energy scheduling optimization device in an embodiment of the present invention;

[0058] Figure 3 Schematic diagram of the structure of the terminal device in an embodiment of the present invention. DETAILED DESCRIPTION

[0059] To make the technical problems, technical solutions, and advantages to be solved by the present invention more clear, the following is a detailed description with reference to the accompanying drawings and specific embodiments. It is obvious that the embodiments described are only some of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0060] In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0061] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood broadly. For example, they may refer to a locking connection, a detachable connection, or an integral connection; they may refer to a mechanical connection or an electrical connection; they may refer to a direct connection or an indirect connection through an intermediate medium; and they may refer to internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0062] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0063] In view of the existing problems, the present invention provides an energy dispatch optimization method and related equipment for an electric power system.

[0064] like Figure 1 As shown, an embodiment of the present invention provides an energy dispatch optimization method for a power system, comprising:

[0065] Step 1: Obtain historical load data, current load data, and future load data of the target power system under multiple dispatch cycles;

[0066] Step 2: Build a prediction model based on historical load data, current load data, and future forecast data;

[0067] Step 3: Input the historical load data and the current load data into the prediction model to obtain future prediction data, and use the difference between the future prediction data and the future load data to correct the prediction model to obtain the target prediction model;

[0068] Step 4: For each scheduling cycle, the control variables are optimized using the target prediction model and the constructed system constraints to obtain the optimal control sequence. The optimal control sequence includes the control variables corresponding to all scheduling cycles. Each set of control variables includes energy scheduling instructions, valve opening adjustment, and power distribution.

[0069] Step 5: Determine the current dispatch cycle of the target power system, select a set of control quantities corresponding to the current dispatch cycle of the target power system in the optimal control sequence, and dispatch the target power system in real time to obtain the real-time dispatch optimization result of the target power system.

[0070] In the embodiment of the present invention, the scheduling period is selected as every 24 hours. The scheduling period can be dynamically adjusted according to the accuracy of load forecasting and the volatility of renewable energy to improve the responsiveness of scheduling.

[0071] In an embodiment of the present invention, historical load data, current load data, and future load data all include voltage, current, and power. The future load data is obtained by combining historical load data and weather forecast data using time series analysis and state estimation technology. The prediction model is determined based on the characteristics of the power system and is used to describe the dynamic behavior of the target power system and predict future prediction data within a period of time. The future prediction data includes voltage data, current data, and power data. The characteristics of the power system mainly include simultaneity, integrity, rapidity, continuity, real-time, and randomness. Specifically:

[0072] The simultaneity of the power system: power generation, transmission, and consumption are completed simultaneously, and large amounts of power cannot be stored;

[0073] Integrity: Power plants, transformers, high-voltage transmission lines, distribution lines and electrical equipment form an integrated whole in the power grid;

[0074] Rapidity: The power transmission process is rapid;

[0075] Continuity: Electricity needs to be adjusted all the time;

[0076] Real-time: Power grid accidents occur quickly and involve a wide range of people, requiring constant safety monitoring;

[0077] Randomness: Random changes in load, abnormal conditions and accidents during operation.

[0078] Most preferably, the prediction model comprises:

[0079] The state space equations used to describe the dynamic behavior of the power are expressed as:

[0080]

[0081] Where x represents the state variable, x1, x2, and x3 represent the historical load data, current load data, and future load data, respectively; u represents the input variable; p represents the control variable of the target power system, represents the system parameters of the target power system, such as voltage, current, and power, and represents the fixed characteristics of the power system; f(· represents a function used to describe the relationship between the state variable and the input variables and system parameters;

[0082] The embodiment of the present invention monitors the dynamic behavior of the target power system in real time through a state space method, thereby determining the dynamic changes of voltage, current and power, and displaying the changes of system parameters based on the dynamic changes;

[0083] The transfer function is used to describe the dynamic behavior of the system when the linearity is invariant, and to establish the relationship between the historical load data, current load data of the target power system input, and the future load data of the system output. The expression is:

[0084]

[0085] Where Y(s) represents the Laplace transform result of the future load data output by the system, and U(s) represents the Laplace transform result of the historical load data and current load data input by the system;

[0086] The embodiment of the present invention uses transfer functions to analyze the frequency response, stability and other characteristics of the target circuit system to ensure the stable operation of the power system;

[0087] The incremental model is used to convert the prediction model into an incremental form. The expression is:

[0088] Δx(k)=x(k)-x(k-1)

[0089] Δu(k)=u(k)-u(k-1)

[0090] Among them, Δx(k) represents the increment of the state variable at time k, Δu(k) represents the increment of the control quantity at time k, x(k) represents the state variable at time k, x(k-1) represents the state variable at time k-1, u(k) represents the control quantity at time k, and u(k-1) represents the control quantity at time k-1;

[0091] The embodiment of the present invention can intuitively capture the dynamic changes of the system by describing the changes of state variables and control inputs in the form of increments, so that dynamic changes can be controlled according to the change rate range based on the change rate constraints in the constraints, thereby improving the utilization rate of energy after scheduling while ensuring the stable operation of the power system.

[0092] In practical applications, due to model errors, interference, and uncertainty, the predicted values may deviate from the actual values. Therefore, it is necessary to use the actual future load data to correct the prediction model to reduce the error, as described in step 3:

[0093] Input historical load data and current load data into the forecasting model to obtain future forecast data;

[0094] Calculate the difference between future forecast data and future load data. The expression is:

[0095] E(t)=P pred (t)-P actual (t)

[0096] Among them, E(t) represents the prediction error at time t, P pred (t) represents the predicted data (predicted value) at time t, P actual (t) represents the actual data (true value) at time t;

[0097] This formula calculates the difference between the predicted value and the actual value at time t;

[0098] The specific process of correcting the prediction model based on the difference and obtaining the target prediction model is as follows:

[0099] The system uses the actual output y mcas (t) and the model prediction The error between them is used to update the model, and y is set mcas (t) is the future load data of the system output obtained by direct measurement, and is the future prediction data based on the prediction output of the model at time t, and е(t) is the error value at time t.

[0100] First, calculate the error between the predicted output and the actual output:

[0101]

[0102] Then, the error is used to update the parameters of the model, such as energy scheduling instructions, valve opening adjustment, and power allocation strategy, to obtain the target prediction model, so as to reduce the error in the next control scheduling cycle.

[0103] In order to evaluate the overall prediction accuracy of the system, the mean square error (MSE) is used as a measurement standard. The expression of the mean square error is:

[0104]

[0105] Where N represents the total number of time steps and MSE represents the mean squared error between the predicted value and the actual value.

[0106] This feedback correction method can improve the robustness and adaptability of the prediction model, enabling it to better cope with the dynamic changes of the power system, and correct the prediction results by iterating the data of the prediction model to improve the accuracy of the prediction.

[0107] Most preferably, the system constraints include state variable constraints, control quantity constraints, system output constraints and dynamic constraints.

[0108] Most preferably, the state variable constraints include voltage constraints, current constraints, and power constraints;

[0109] The voltage constraint is expressed as:

[0110] V min ≤V(k)≤V max

[0111] The current constraint is expressed as:

[0112] I min ≤I(k)≤I max

[0113] The power constraint is expressed as:

[0114] P min ≤P(k)≤P max

[0115] Where V(k) represents the voltage value at time k, I(k) represents the current value at time k, P(k) represents the power value at time k, V min Indicates the minimum value allowed by voltage, V max Indicates the maximum allowable voltage, I min Indicates the maximum allowable current, I max Indicates the minimum allowable current, P min Indicates the maximum value of power allowed, P max Indicates the minimum allowed power value.

[0116] The embodiments of the present invention constrain the maximum and minimum values of voltage, current, power, etc. at a certain moment, thereby preventing state variables such as voltage, current, and power from exceeding the range of variation when energy is scheduled for grid connection, thereby improving the utilization rate of energy after scheduling while ensuring the stable operation of the power system.

[0117] Most preferably, the control quantity constraints include energy dispatch instruction constraints, valve opening adjustment constraints, and power distribution constraints;

[0118] Among them, the energy dispatch instruction constraint is expressed as:

[0119]

[0120] The valve opening adjustment constraint is expressed as:

[0121]

[0122] The power allocation constraint is expressed as:

[0123]

[0124] Among them, u1(k) represents the energy dispatch instruction value at time k, u2(k) represents the valve opening adjustment value at time k, and represents the power distribution value at time k. represents the minimum value of the energy scheduling instruction allowed at time k, represents the maximum value of the energy dispatch instruction allowed at time k, Indicates the minimum value of the valve opening adjustment value allowed at time k, Indicates the maximum value of the valve opening adjustment value allowed at time k, Indicates the minimum value of the power allocation value allowed at time k, Indicates the maximum value of power allocation allowed at time k.

[0125] The embodiments of the present invention limit the range of energy scheduling instructions and valve opening adjustments, narrow the scope of new energy scheduling space, and improve the control accuracy of new energy scheduling and grid connection, so as to more reasonably optimize energy scheduling, avoid waste, and reduce carbon emissions.

[0126] Most preferably, the system output constraint is to constrain the tracking reference signal, which is expressed as:

[0127] y min (k)≤y(k)≤y max (k)

[0128] Among them, y(k) represents the tracking reference signal output at time k, y min (k) represents the minimum value of the tracking reference signal allowed at time k, y max (k) represents the maximum value of the tracking reference signal allowed at time k.

[0129] The embodiments of the present invention can more accurately ensure the stability of the signal by constraining the tracking reference signal in the power system, thereby reducing signal fluctuations and avoiding communication delays, so that the control strategy can be conveyed more quickly and the accuracy of the optimized grid connection of new energy in the power system can be improved.

[0130] Most preferably, the dynamic constraint is a constraint on the rate of change of the controlled variable, which is expressed as:

[0131] Δu min ≤u(k)-u(k-1)≤Δu max

[0132] Among them, u(k)-u(k-1) represents the rate of change of the control quantity, Δu min Indicates the minimum allowed rate of change of the control quantity, Δu max Indicates the maximum rate of change allowed for the controlled variable.

[0133] The embodiments of the present invention constrain the input change rate of energy in the power system to avoid insufficient power supply due to insufficient input and excessive energy input that causes load on the power system and reduces utilization, thereby improving energy utilization through reasonable constraint control and improving stability in the energy scheduling process.

[0134] The embodiment of the present invention constructs a prediction model based on the historical load data, current load data and future load data of the target power system under multiple scheduling cycles; inputs the historical load data and the current load data into the prediction model for prediction to obtain future prediction data, and uses the difference between the future prediction data and the future load data to correct the prediction model to obtain a target prediction model; for each scheduling cycle, the control quantity is optimized by the target prediction model and the constructed system constraints to obtain an optimal control sequence, which includes control quantities corresponding to all scheduling cycles, and each group of control quantities includes energy scheduling instructions, valve opening adjustment, and power distribution; determines the current scheduling cycle of the target power system, selects a group of control quantities corresponding to the current scheduling cycle of the target power system in the optimal control sequence, and schedules the target power system in real time to obtain a real-time scheduling optimization result of the target power system; compared with the prior art, the embodiment of the present invention improves the operation stability and scheduling accuracy of the new power system by establishing a prediction model and system constraints, and using the revised prediction model and system constraints to optimize the control quantity of the target power system and then schedule the target power system.

[0135] The present invention also provides an energy dispatch optimization device for a power system, such as Figure 2 As shown, the energy scheduling optimization device 100 includes:

[0136] An acquisition module 101 is configured to acquire historical load data, current load data, and future load data of a target power system under multiple dispatch cycles;

[0137] A construction module 102 is used to construct a prediction model based on historical load data, current load data and future prediction data;

[0138] The correction module 103 is used to input the historical load data and the current load data into the prediction model for prediction to obtain future prediction data, and to correct the prediction model using the difference between the future prediction data and the future load data to obtain a target prediction model;

[0139] The optimization module 104 is used to optimize the control variables for each scheduling cycle using the target prediction model and the constructed system constraints to obtain an optimal control sequence. The optimal control sequence includes the control variables corresponding to all scheduling cycles. Each set of control variables includes energy scheduling instructions, valve opening adjustment, and power distribution.

[0140] The scheduling module 105 is used to determine the current scheduling cycle of the target power system, select a set of control quantities corresponding to the current scheduling cycle of the target power system in the optimal control sequence, and schedule the target power system in real time to obtain the real-time scheduling optimization result of the target power system.

[0141] In some embodiments, the predictive model includes:

[0142] The state space equations used to describe the dynamic behavior of the power are expressed as:

[0143]

[0144] Where x represents the state variable, x1, x2, and x3 represent historical load data, current load data, and future load data, respectively; u represents the input variable; p represents the control variable of the target power system, represents the system parameters of the target power system, such as voltage, current, and power, and represents the fixed characteristics of the power system; f(·) represents a function used to describe the relationship between the state variable and the input variables and system parameters;

[0145] The transfer function is used to describe the dynamic behavior of the system when the linearity is invariant, and to establish the relationship between the historical load data, current load data of the target power system input, and the future load data of the system output. The expression is:

[0146]

[0147] Where Y(s) represents the Laplace transform result of the future load data output by the system, and U(s) represents the Laplace transform result of the historical load data and current load data input by the system;

[0148] The incremental model is used to convert the prediction model into an incremental form. The expression is:

[0149] Δx(k)=x(k)-x(k-1)

[0150] Δu(k)=u(k)-u(k-1)

[0151] Among them, Δx(k) represents the increment of the state variable at time k, Δu(k) represents the increment of the control quantity at time k, x(k) represents the state variable at time k, x(k-1) represents the state variable at time k-1, u(k) represents the control quantity at time k, and u(k-1) represents the control quantity at time k-1.

[0152] In some embodiments, the system constraints include state variable constraints, control quantity constraints, system output constraints, and dynamic constraints.

[0153] In some embodiments, the state variable constraints include voltage constraints, current constraints, and power constraints;

[0154] The voltage constraint is expressed as:

[0155] V min ≤V(k)≤V max

[0156] The current constraint is expressed as:

[0157] I min ≤I(k)≤I max

[0158] The power constraint is expressed as:

[0159] P min ≤P(k)≤P max

[0160] Where V(k) represents the voltage value at time k, I(k) represents the current value at time k, P(k) represents the power value at time k, V min Indicates the minimum value allowed by voltage, V max Indicates the maximum allowable voltage, I min Indicates the maximum allowable current, I max Indicates the minimum allowable current, P min Indicates the maximum value of power allowed, P max Indicates the minimum allowed power value.

[0161] In some embodiments, the control quantity constraints include energy scheduling instruction constraints, valve opening adjustment constraints, and power allocation constraints;

[0162] Among them, the energy dispatch instruction constraint is expressed as:

[0163]

[0164] The valve opening adjustment constraint is expressed as:

[0165]

[0166] Among them, u1(k) represents the energy dispatch instruction at time k, u2(k) represents the valve opening adjustment value at time k, represents the minimum value of the energy scheduling instruction allowed at time k, represents the maximum value of the energy dispatch instruction allowed at time k, Indicates the minimum value of the valve opening adjustment value allowed at time k, Indicates the maximum value of the valve opening adjustment value allowed at time k.

[0167] In some embodiments, the system output constraint is to constrain the tracking reference signal, which is expressed as:

[0168] y min (k)≤y(k)≤y max (k)

[0169] Among them, y(k) represents the tracking reference signal output at time k, y min (k) represents the minimum value of the tracking reference signal allowed at time k, y max (k) represents the maximum value of the tracking reference signal allowed at time k.

[0170] In some embodiments, the dynamic constraint is a constraint on the rate of change of the controlled variable, which is expressed as:

[0171] Δu min ≤u(k)-u(k-1)≤Δu max

[0172] Among them, u(k)-u(k-1) represents the rate of change of the control quantity, Δu min Indicates the minimum allowed rate of change of the control quantity, Δu max Indicates the maximum rate of change allowed for the controlled variable.

[0173] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the embodiments of the present application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0174] like Figure 3 As shown, the present invention also provides a terminal device D10, including at least one processor D100 ( Figure 3 Only one processor is shown in the figure), a memory D101, and a computer program D102 stored in the memory D101 and executable on the at least one processor D100. When the processor D100 executes the computer program D102, a method for optimizing energy dispatch in a power system is implemented. Alternatively, when the processor D100 executes the computer program D102, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0175] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0176] In some embodiments, the memory may be an internal storage unit of the terminal device, such as a hard disk or memory of the terminal device. In other embodiments, the memory may also be an external storage device of the terminal device, such as a plug-in hard disk equipped on the terminal device, a smart memory card (SMC, Smart Media Card), a secure digital (SD, Secure Digital) card, a flash card, etc. Furthermore, the memory may include both an internal storage unit of the terminal device and an external storage device. The memory is used to store an operating system, an application program, a boot loader, data, and other programs, such as the program code of the computer program. The memory may also be used to temporarily store data that has been output or is about to be output.

[0177] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0178] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the embodiments of the present application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0179] The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method for optimizing energy dispatching of a power system is implemented.

[0180] If the integrated module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned method embodiment, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying the computer program code to a construction device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electric carrier signal, a telecommunication signal and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0181] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A method for optimizing energy dispatching of a power system, characterized in that: include: Step 1: Obtain historical load data, current load data, and future load data of the target power system under multiple dispatch cycles, wherein the dispatch cycle is dynamically adjusted according to the accuracy of load forecasting and the volatility of renewable energy; Step 2: constructing a prediction model based on the historical load data, the current load data, and the future load data. The prediction model includes: The state space equations used to describe the dynamic behavior of the power are expressed as: ； ； ； in, represents the state variable, 、 、 Represents historical load data, current load data or future load data, respectively. represents the input variable, represents the control quantity of the target power system, represents the system parameters of the target power system, Represents a function that describes the relationship between state variables, input variables, and system parameters; The transfer function is used to establish the relationship between the historical load data, current load data and future load data of the target power system input, and the expression is: ； in, The Laplace transform result of the future load data output by the system is represented by Represents the Laplace transform results of the historical load data and current load data input by the system; The incremental model is used to convert the prediction model into an incremental form, and the expression is: ； ； in, Indicates that the state variable is The increment of time, Indicates the control quantity is The increment of time, Indicates The state variables at time , Indicates The state variables at time , Indicates The amount of control at the moment, Indicates The amount of control at any moment; Step 3: Inputting the historical load data and the current load data into the prediction model for prediction to obtain future prediction data, and using the difference between the future prediction data and the future load data to correct the prediction model to obtain a target prediction model, including: Input historical load data and current load data into the forecasting model to obtain future forecast data; Calculate the difference between future forecast data and future load data; The specific process of correcting the prediction model based on the difference and obtaining the target prediction model is as follows: The system uses the actual output Compared with the model prediction The error between them is used to update the model, setting is the future load data of the system output obtained by direct measurement, and It is based on the model The future prediction data of the prediction output at the moment, and for The error value at the moment; First, calculate the error between the predicted output and the actual output: ； Then, using the error Update the energy dispatch instructions, valve opening adjustment, and power allocation strategy in the model to obtain the target prediction model; Step 4: For each scheduling cycle, the control variables are optimized using the target prediction model and the constructed system constraints to obtain an optimal control sequence. The system constraints include state variable constraints, control variable constraints, system output constraints, and dynamic constraints. The optimal control sequence includes control variables corresponding to all scheduling cycles, and each set of control variables includes energy scheduling instructions, valve opening adjustment, and power distribution. Step 5: Determine the current dispatch cycle of the target power system, select a set of control quantities corresponding to the current dispatch cycle of the target power system in the optimal control sequence, and dispatch the target power system in real time to obtain a real-time dispatch optimization result of the target power system.

2. The energy dispatch optimization method for the power system according to claim 1, characterized in that: The state variable constraints include voltage constraints, current constraints and power constraints; The voltage constraint is expressed as: ； The current constraint is expressed as: ； The power constraint is expressed as: ； in, Indicates The voltage value at the moment, Indicates The current value at the moment, Indicates The power value at the moment, Indicates the minimum value allowed for voltage. Indicates the maximum value allowed for voltage. Indicates the maximum allowable current. Indicates the minimum value allowed for current. Indicates the maximum value of power allowed. Indicates the minimum allowed power value.

3. The energy dispatch optimization method for the power system according to claim 1, characterized in that: The control quantity constraints include energy dispatch instruction constraints, valve opening adjustment constraints, and power distribution constraints; Among them, the energy dispatch instruction constraint is expressed as: ； The valve opening adjustment constraint is expressed as: ； The power allocation constraint is expressed as: ； in, Indicates The energy dispatch instruction value at the moment, Indicates The valve opening adjustment value at the moment is expressed as The power allocation value at the moment, Indicates The minimum value of the energy dispatch instruction allowed at any time, Indicates The maximum value of energy dispatch instructions allowed at any time, Indicates The minimum value of the valve opening adjustment value allowed at any time, Indicates The maximum value of the valve opening adjustment value allowed at any time, Indicates The minimum power allocation value allowed at any time, Indicates The maximum value of power allocation allowed at any time.

4. The energy dispatch optimization method for the power system according to claim 1, characterized in that: The system output constraint is to constrain the tracking reference signal, which is expressed as: ； in, Indicates The tracking reference signal output at all times, Indicates The minimum value of the tracking reference signal allowed at any time, Indicates The maximum value of the tracking reference signal allowed at any time.

5. The energy dispatch optimization method for the power system according to claim 1, characterized in that: The dynamic constraint is to constrain the rate of change of the control variable, which is expressed as: ； in, It represents the rate of change of the controlled quantity, Indicates the minimum change rate allowed for the control quantity. Indicates the maximum rate of change allowed for the controlled variable.

6. An energy dispatch optimization device for a power system, characterized in that: include: An acquisition module is used to obtain historical load data, current load data, and future load data of the target power system under multiple dispatch cycles; A construction module is configured to construct a prediction model based on the historical load data, the current load data, and the future load data, wherein the prediction model includes: The state space equations used to describe the dynamic behavior of the power are expressed as: ； ； ； in, represents the state variable, 、 、 Represents historical load data, current load data or future load data, respectively. represents the input variable, represents the control quantity of the target power system, represents the system parameters of the target power system, Represents a function that describes the relationship between state variables, input variables, and system parameters; The transfer function is used to establish the relationship between the historical load data, current load data and future load data of the target power system input, and the expression is: ； in, The Laplace transform result of the future load data output by the system is represented by Represents the Laplace transform results of the historical load data and current load data input by the system; The incremental model is used to convert the prediction model into an incremental form, and the expression is: ； ； in, Indicates that the state variable is The increment of time, Indicates the control quantity is The increment of time, Indicates The state variables at time , Indicates The state variables at time , Indicates The amount of control at the moment, Indicates The amount of control at any moment; A correction module is configured to input the historical load data and the current load data into the prediction model for prediction to obtain future prediction data, and to correct the prediction model using the difference between the future prediction data and the future load data to obtain a target prediction model, including: Input historical load data and current load data into the forecasting model to obtain future forecast data; Calculate the difference between future forecast data and future load data; The specific process of correcting the prediction model based on the difference and obtaining the target prediction model is as follows: The system uses the actual output Compared with the model prediction The error between them is used to update the model, setting is the future load data of the system output obtained by direct measurement, and It is based on the model The future prediction data of the prediction output at the moment, and for The error value at the moment; First, calculate the error between the predicted output and the actual output: ； Then, using the error Update the energy dispatch instructions, valve opening adjustment, and power allocation strategy in the model to obtain the target prediction model; an optimization module for optimizing the control variables for each scheduling cycle using the target prediction model and constructed system constraints to obtain an optimal control sequence, wherein the system constraints include state variable constraints, control variable constraints, system output constraints, and dynamic constraints. The optimal control sequence includes control variables corresponding to all scheduling cycles, and each set of control variables includes energy scheduling instructions, valve opening adjustment, and power distribution; The scheduling module is used to determine the current scheduling cycle of the target power system, select a set of control quantities corresponding to the current scheduling cycle of the target power system in the optimal control sequence, and schedule the target power system in real time to obtain a real-time scheduling optimization result of the target power system.

7. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the energy dispatch optimization method for the power system according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for optimizing energy dispatch of a power system according to any one of claims 1 to 5 is implemented.

Images