Flexible AC / DC micro-grid adjustable element capacity configuration and operation optimization method and system

Abstract

The invention discloses a flexible AC / DC micro-grid adjustable element capacity configuration and operation optimization method and system, and the method comprises the steps: collecting power supply variable data, load data, energy storage data and meteorological data of a micro-grid, and carrying out the time matching, and forming a micro-grid load data set; constructing and training a micro-grid load demand prediction model based on the data set, and obtaining a load prediction result; constructing a capacity configuration optimization model of the adjustable elements of the micro-grid, wherein the capacity configuration optimization model takes balance power supply income maximization and power supply stability maximization as targets; and inputting a load prediction result into the capacity configuration optimization model, calculating to obtain a power distribution network capacity configuration scheme, and executing a micro-grid operation optimization scheme by adopting a rolling optimization mode. According to the method, various data and factors of the micro-grid are comprehensively considered, and efficient, economical and reliable operation of the micro-grid is realized through prediction and optimization.

Description

Technical Field

[0001] The present invention relates to the field of power grid control technology, and in particular to a method and system for configuring the capacity of adjustable elements and optimizing operation of a flexible AC / DC microgrid. Background Art

[0002] Microgrid is a local power network composed of distributed energy, load, energy storage system and control equipment, which can be connected to the main grid or run independently. The development of microgrid technology provides a new way to improve energy efficiency, reduce energy costs and enhance grid reliability.

[0003] Traditional microgrid planning and design are mainly based on deterministic load and power generation forecasts, lacking consideration of uncertainty factors. With the increase in the penetration rate of renewable energy, it is necessary to adopt methods such as stochastic optimization and robust optimization to fully consider the uncertainty of load and renewable energy in the microgrid planning and design stage. Accurate load forecasting is the basis for the optimized operation of microgrids. Traditional load forecasting methods (such as regression analysis, time series, etc.) are difficult to capture the nonlinear and uncertain characteristics of loads. In recent years, machine learning-based load forecasting methods (such as support vector machines, artificial neural networks, etc.) have been widely used, and the prediction accuracy has been improved by mining the complex relationship between load and influencing factors. However, traditional load forecasting methods often rely only on the load data itself, while ignoring the influence of the regional environment where the microgrid is located. Therefore, the load forecasting accuracy is often not high. The economy and reliability of microgrids depend to a large extent on the capacity configuration planning of microgrids. The traditional planning objects in microgrids mainly include adjustable elements such as diesel and gas, load elements and energy storage elements. Traditional methods often plan energy storage elements and load elements as a whole. With the development of microgrids, load elements can be further refined into movable loads, elastic loads and fixed loads, and energy storage elements can be further refined into conventional energy storage batteries and electric vehicle energy storage batteries. In addition, traditional capacity configuration mainly adopts deterministic optimization methods, such as linear programming, mixed integer programming, etc., so the configuration capacity obtained by traditional methods is not accurate enough.

[0004] In view of this, the present invention proposes a method and system for configuring and optimizing the capacity of adjustable elements of a flexible AC / DC microgrid. Summary of the invention

[0005] To achieve the above-mentioned purpose, the present invention provides a method and system for configuring the capacity and optimizing the operation of adjustable elements of a flexible AC / DC microgrid. The specific technical scheme is as follows: The method for configuring the capacity and optimizing the operation of adjustable elements of a flexible AC / DC microgrid comprises:

[0006] Acquire microgrid power supply variable data, collect microgrid load data, the microgrid load data includes fixed load data, movable load data and elastic load data, collect microgrid energy storage data and historical meteorological data of the area where the microgrid is located, and match the collected microgrid load data with the historical meteorological data of the area where the microgrid is located in time to form a microgrid load data set;

[0007] Constructing a microgrid load demand prediction model, and training the microgrid load demand prediction model based on the microgrid load data set to obtain a microgrid load prediction result;

[0008] Based on the collected microgrid load data and microgrid energy storage data, a capacity configuration optimization model of the microgrid adjustable element is constructed; the capacity configuration optimization model of the microgrid adjustable element takes balancing the maximization of power supply revenue and the maximization of power supply stability as the goal;

[0009] The microgrid load forecast results are input into the microgrid capacity configuration optimization model to calculate the distribution network capacity configuration plan; based on the calculated distribution network capacity configuration plan, a rolling optimization method is adopted to execute the microgrid operation optimization plan.

[0010] Preferably, the microgrid power supply variable data includes photovoltaic panel power generation data P PV (t), diesel generator power generation data P DE (t) and gas turbine power generation data P MT (t);

[0011] Collect microgrid load data P load (t), the microgrid load data P load (t) Including fixed load data Load data can be translated And elastic load data

[0012] Collect microgrid energy storage data, including the charging and discharging power P of the energy storage battery batt (t) and energy storage battery capacity data And the charging and discharging power P of the electric vehicle energy storage battery EV (t) and electric vehicle energy storage battery capacity data

[0013] Obtain historical meteorological data of the area where the microgrid is located, including temperature data T(t) and humidity data H(t), and compare them with the microgrid load data P at the same time. load (t) Merge to obtain the augmented microgrid load dataset.

[0014] Preferably, a long short-term memory artificial neural network LSTM model is selected as the architecture of the microgrid load demand prediction model;

[0015] The microgrid load data set is sampled using the sliding time window method, with a window size of k and a sliding step of s; that is, each sample contains k consecutive historical data, and the starting positions of adjacent samples differ by s time steps;

[0016] Divide the constructed samples into training set, validation set and test set; build LSTM model and use the training set data to train the model; the loss function uses mean square error MSE;

[0017] The validation set data is used to evaluate the performance and optimize the hyperparameters of the trained LSTM model, including the number of hidden layers n. hidden , the number of hidden units n units and learning rate η;

[0018] Use the test set data to evaluate the performance of the optimal LSTM model. The evaluation indicators include mean absolute error (MAE) and root mean square error (RMSE).

[0019] Get the trained microgrid load demand prediction LSTM model f LSTM , used to predict the load demand of the microgrid in the future time period, and obtain the load demand prediction value

[0020] Preferably, a capacity configuration optimization model of the microgrid adjustable element is established, wherein the capacity configuration optimization model of the microgrid adjustable element includes maximizing power supply stability and maximizing power supply revenue, and the calculation formula is as follows:

[0021] max[αR supply +βR profit ]

[0022] Among them, R supply is the power supply stability index, α is the adjustment coefficient of the power supply stability index; R profit is the power supply revenue index, β is the adjustment coefficient of the power supply revenue index;

[0023] Configure the microgrid power supply variables and microgrid energy storage variables, wherein the microgrid power supply variable data includes the capacity of the photovoltaic power generation panel Diesel generator capacity Gas turbine capacity Energy storage battery capacity and the capacity of electric vehicle energy storage batteries

[0024] The objective function to maximize power supply stability is:

[0025]

[0026] Among them, R supply is the power supply stability index, EENS is the expected unpowered power supply, E total is the total load demand, E total It is predicted based on the LSTM model of microgrid load demand prediction;

[0027] The objective function to maximize the power supply revenue is:

[0028]

[0029] C total =C PV (t)+C DE (t)+C MT (t)+C batt (t)+C EV (t)

[0030] Among them, T is the optimized time domain length, P shift (t) and P flex (t) are the output of the translatable load and the elastic load at the tth moment, λ shift and λ flex is the benefit factor of the translatable load and elastic load, C total is the total operating cost, C PV (t), C DE (t), C MT (t), C batt (t) and C EV (t) are the operating costs of photovoltaic panels, diesel generators, gas turbines, energy storage batteries and electric vehicles at the tth moment; waste(t) is the negative income influencing factor of loss;

[0031] f(t) is the periodic probability adjustment function of the operating cost, expressed as:

[0032]

[0033] Among them, A is the amplitude, which controls the amplitude of periodic changes; T period is the cycle length, indicating the cycle of cost change; φ is the phase, controlling the starting point of the periodic change;

[0034] The negative income influencing factor waste(t) is expressed as:

[0035] waste(t)=β1·E waste (t)+β2·I idle (t);

[0036] Among them, E waste (t) represents the energy loss at the tth moment; I idle (t) represents the idle status of equipment at the tth moment; β1 and β2 are the negative benefit weight coefficients of energy loss and equipment idleness, respectively;

[0037] The constraints of the objective function of the capacity configuration optimization model of the microgrid adjustability element include load balance constraints, energy storage battery capacity constraints, energy storage battery charging and discharging power constraints, electric vehicle energy storage battery capacity constraints, electric vehicle energy storage battery charging and discharging power constraints, photovoltaic panels, diesel generators and gas turbine capacity constraints, and photovoltaic panels, diesel generators and gas turbine output constraints; load balance constraints:

[0038]

[0039] Among them, the energy storage battery capacity constraints are: Energy storage battery charging and discharging power constraints: Electric vehicle energy storage battery capacity constraints: Electric vehicle energy storage battery charging and discharging power constraints: Photovoltaic panels, diesel generators and gas turbine capacity constraints: Output constraints of photovoltaic panels, diesel generators and gas turbines: in, and are the lower and upper limits of the energy storage battery capacity, and are the lower and upper limits of the charging and discharging power of the energy storage battery, and is the lower and upper limits of the energy storage battery capacity of electric vehicles, and The lower and upper limits of the charging and discharging power of electric vehicle energy storage batteries, and They are the upper limits of the capacity of photovoltaic panels, diesel generators and gas turbines respectively;

[0040] Preferably, the prediction results of the LSTM load forecasting model are As the input of the capacity configuration optimization model, it is used to describe the future load demand of the microgrid. At the same time, combined with the historical meteorological data of the area where the microgrid is located, the power supply stability of the microgrid is calculated to obtain EENS and E total ;

[0041] Solve the microgrid capacity configuration optimization model to obtain the optimal capacity configuration scheme for the microgrid power supply variables and microgrid energy storage variables and

[0042] Microgrid operation optimization based on model predictive control, using model predictive control rolling optimization strategy to solve microgrid operation scheduling problems in a rolling optimization manner;

[0043] Using LSTM load forecasting model f LSTM Based on the optimization results of microgrid capacity configuration, a microgrid operation optimization control function is constructed.

[0044] Preferably, a model predictive control rolling optimization strategy is adopted to solve the microgrid operation scheduling problem in a rolling optimization manner. The objective function of the microgrid operation scheduling problem is to maximize the balance between power supply stability and power supply benefits in the prediction time domain:

[0045]

[0046] Among them, N p To predict the time domain length, R supply (t+i) is the power supply stability index at the future t+i moment, R profit (t+i) is the profit index at the future t+i moment, ω1 and ω2 are the weight coefficients of the stability target and the profit target respectively;

[0047] The profit index R within the forecast time domain length profit (t+i) is calculated as:

[0048]

[0049] Among them, P shift (t+i) and P flex (t+i) are the outputs of the translatable load and the elastic load at the future t+ith moment, λ shift and λ flex is the corresponding profit coefficient, C j (t+i) is the operating cost of the jth type of adjustable decision variable at the t+ith moment in the future;

[0050] The calculation method of power supply stability within the prediction time domain length is:

[0051]

[0052] Among them, N p To predict the time domain length, P j (t+i) is the output of the j-th adjustable decision variable at the future t+i-th moment, λ j is the corresponding operating cost weight coefficient; R supply (t+N p ) is the power supply stability index at the end of the prediction time domain, and ω is the weight coefficient of the stability target;

[0053] The constraints of the microgrid operation and dispatching problem include: Load balance constraint: ∑ j P j (t+i)=P load (t+i); Energy storage battery capacity constraint: Energy storage battery charging and discharging power constraints: Electric vehicle energy storage battery capacity constraints: Electric vehicle energy storage battery charging and discharging power constraints: Output constraints of photovoltaic panels, diesel generators and gas turbines:

[0054]

[0055] Translational load constraints:

[0056] Elastic load restraint:

[0057] Among them, P PV (t+i) represents the i-th moment in the future (i=1, 2, ..., N p ), the actual output of photovoltaic panels; represents the optimal capacity configuration of photovoltaic panels; P DE (t+i) represents the actual output of the diesel generator at the i-th moment in the future; represents the optimal capacity configuration of diesel generators; P MT (t+i) represents the actual output of the gas turbine at the i-th moment in the future; represents the optimal capacity configuration of the gas turbine, is the total amount of load that can be translated, The upper limit of elastic load.

[0058] Preferably, the real-time rolling optimization process of the rolling optimization strategy is as follows: In each control cycle, the LSTM model is used to predict the future N p Load demand at a moment At the same time, combined with real-time operation data and meteorological forecast data, the power supply stability index R in the future time domain is supply (t+N p ) to make an estimate;

[0059] Solve the optimization model and get the future N c The optimal operation and dispatching strategy of microgrid power supply variables at each moment;

[0060] The optimization results are decoded into control instructions and sent to the control systems of each adjustable element to achieve real-time optimization and scheduling of the microgrid.

[0061] A flexible AC / DC microgrid adjustable element capacity configuration and operation optimization system, which is used to implement a flexible AC / DC microgrid adjustable element capacity configuration and operation optimization method, including: a data acquisition module, a microgrid load demand prediction module, a capacity configuration optimization module and a scheduling operation module;

[0062] The data acquisition module acquires microgrid power supply variable data, collects microgrid load data, the microgrid load data includes fixed load data, shiftable load data and elastic load data, collects microgrid energy storage data and historical meteorological data of the area where the microgrid is located, and performs temporal matching of the collected microgrid load data and the historical meteorological data of the area where the microgrid is located to form a microgrid load data set;

[0063] The microgrid load demand prediction module constructs a microgrid load demand prediction model, and trains the microgrid load demand prediction model based on the microgrid load data set to obtain a microgrid load prediction result;

[0064] The capacity configuration optimization module constructs a capacity configuration optimization model of the microgrid adjustable element based on the collected microgrid load data and microgrid energy storage data; the capacity configuration optimization model of the microgrid adjustable element takes balancing the maximization of power supply revenue and the maximization of power supply stability as the goal;

[0065] The dispatching and operation module inputs the microgrid load forecast result into the microgrid capacity configuration optimization model to calculate the distribution network capacity configuration plan; based on the calculated distribution network capacity configuration plan, a rolling optimization method is adopted to execute the microgrid operation optimization plan.

[0066] An electronic device comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the flexible AC / DC microgrid adjustable element capacity configuration and operation optimization method by calling the computer program stored in the memory.

[0067] A computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the flexible AC / DC microgrid adjustable element capacity configuration and operation optimization method.

[0068] Beneficial effects of the present invention: The present invention forms a comprehensive and time-consistent microgrid load data set by collecting and matching various types of data, providing a reliable data basis for subsequent load forecasting and optimized scheduling.

[0069] The present invention utilizes historical load data to train a load demand forecasting model, which can accurately forecast future load demand and provide important input information for optimizing scheduling.

[0070] The present invention constructs a capacity configuration optimization model that takes into account both power supply revenue and power supply stability, which can obtain the optimal capacity configuration solution that balances the two objectives and improves the economic benefits and operational reliability of the microgrid.

[0071] The present invention combines load forecasting results with capacity configuration optimization and uses a rolling optimization method to execute the operation optimization plan. It can dynamically adjust the operation strategy while ensuring power supply reliability, adapt to load changes, and improve the overall operation efficiency and economy of the microgrid. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 A flow chart of the adjustable element capacity configuration and operation optimization method of the flexible AC / DC microgrid provided by the present invention;

[0073] Figure 2 A structural diagram of the adjustable element capacity configuration and operation optimization system of the flexible AC / DC microgrid provided by the present invention;

[0074] Figure 3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention;

[0075] Figure 4 It is a schematic diagram of the structure of a computer-readable storage medium provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0076] In order to better understand the present invention, a more detailed description will be made of various aspects of the present invention with reference to the accompanying drawings. It should be understood that these detailed descriptions are only descriptions of exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0077] In the accompanying drawings, the size, dimensions and shapes of the elements have been slightly adjusted for ease of illustration. The accompanying drawings are for illustration only and are not strictly drawn to scale. As used herein, the terms "substantially", "approximately" and similar terms are used as terms of approximation, not as terms of degree, and are intended to illustrate the inherent deviations in measurements or calculations that will be recognized by those of ordinary skill in the art. In addition, in the present invention, the order in which the steps are described does not necessarily represent the order in which these processes occur in actual operation, unless otherwise specified or can be derived from the context.

[0078] It should also be understood that expressions such as "comprises", "including", "having", "includes" and / or "comprising" are open rather than closed expressions in this specification, which indicate the presence of the stated features, elements and / or components, but do not exclude the presence of one or more other features, elements, components and / or combinations thereof. In addition, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features rather than just the individual elements in the list. In addition, when describing embodiments of the present invention, "may" is used to mean "one or more embodiments of the present invention". And, the term "exemplary" is intended to refer to an example or illustration.

[0079] Unless otherwise defined, all words (including engineering terms and scientific and technological terms) used in this article have the same meaning as those commonly understood by ordinary technicians in the field to which the present invention belongs. It should also be understood that unless there is a clear explanation in the present invention, the words defined in the commonly used dictionary should be interpreted as having the same meaning as their meaning in the context of the relevant technology, and should not be interpreted in an idealized or overly formal sense.

[0080] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments of the present invention can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0081] Example 1

[0082] Reference Figure 1 , which is the first embodiment of the present invention, provides a method for capacity configuration and operation optimization of adjustable elements of a flexible AC / DC microgrid.

[0083] S1: Obtain microgrid power supply variable data, collect microgrid load data, microgrid load data includes fixed load data, movable load data and elastic load data, collect microgrid energy storage data and historical meteorological data of the area where the microgrid is located, and match the collected microgrid load data with the historical meteorological data of the area where the microgrid is located in time to form a microgrid load data set. The data collected in this step are all massive historical data. Among them, the adjustable elements include microgrid power supply variables and microgrid energy storage variables; among them, the microgrid power supply variables include the capacity of photovoltaic panels, the capacity of diesel generators, and the capacity of gas turbines; the microgrid energy storage variables include the capacity of energy storage batteries and the capacity of electric vehicle energy storage batteries.

[0084] Microgrid power supply variable data includes photovoltaic panel power generation data P PV (t), diesel generator power generation data P DE (t) and gas turbine power generation data P MT (t).

[0085] Collect microgrid load data P load (t), microgrid load data P load (t) Including fixed load data Load data can be translated And elastic load data

[0086] Collect microgrid energy storage data, including the charging and discharging power P of the energy storage battery batt (t) and energy storage battery capacity data And the charging and discharging power P of the electric vehicle energy storage battery EV (t) and electric vehicle energy storage battery capacity data

[0087] Obtain historical meteorological data of the area where the microgrid is located, including temperature data T(t) and humidity data H(t), and compare them with the microgrid load data P at the same time. load (t) Merge to obtain the augmented microgrid load dataset.

[0088] S2: Build a microgrid load demand prediction model. Based on the microgrid load data set, train the microgrid load demand prediction model to obtain the microgrid load prediction results.

[0089] The long short-term memory artificial neural network (LSTM) model is selected as the architecture of the microgrid load demand prediction model. LSTM can effectively capture the long-term and short-term dependencies in time series data through gating mechanisms and memory units, and has strong modeling capabilities.

[0090] The forward propagation formula of LSTM is:

[0091] Forget gate: f t =σ(W f ·[h t-1 , x t ]+b f );

[0092] Input gate: i t =σ(W i ·[h t-1 , x t ]+b i );

[0093] Memory cell candidate values:

[0094] Memory unit status update:

[0095] Output gate: o t =σ(W o ·[ht-1, xt ]+b o );

[0096] Hide status update:h t =o t *tanh(C t ).

[0097] Among them, f t ,i t , o t are the activation vectors of the forget gate, input gate, and output gate, respectively, and C t is the memory unit state vector, is the candidate value of the memory unit, h t is the hidden state vector, W f , W i , W C , W o and b f , b i , b C , b o are the weight matrix and bias vector of the corresponding gate and memory unit respectively, σ is the sigmoid activation function, tanh is the hyperbolic tangent activation function, and the symbol * represents element-wise multiplication.

[0098] The sliding time window method is used to construct samples of the data set D2, with a window size of k and a sliding step size of s; that is, each sample contains k continuous historical data, and the starting positions of adjacent samples differ by s time steps.

[0099] Divide the constructed samples into training set, validation set and test set with a ratio of p train ∶p val ∶p test ; Among them, p train , p val , p test are the sample proportions of the training set, validation set, and test set, respectively.

[0100] Build an LSTM model and use the training set data to train the model; the loss function uses the mean square error MSE: Among them, y i is the true load value of the i-th sample, is the model prediction value, and n is the number of samples.

[0101] Use the validation set data to evaluate the performance and optimize the hyperparameters of the trained LSTM model. The hyperparameters include the number of hidden layers n. hidden , the number of hidden units n units and learning rate η; find the optimal hyperparameter combination through grid search and other methods to improve the generalization performance of the model.

[0102] The test set data is used to evaluate the performance of the optimal LSTM model. The evaluation indicators include mean absolute error (MAE) and root mean square error (RMSE).

[0103] The calculation formula for the mean absolute error MAE is:

[0104] The calculation formula of root mean square error RMSE is:

[0105] Among them, y i is the true load value of the i-th sample, is the model prediction value, and n is the number of samples.

[0106] Get the trained microgrid load demand prediction LSTM model f LSTM , used to predict the load demand of the microgrid in the future time period, and obtain the load demand prediction value

[0107] A data-driven microgrid load forecasting model is constructed using the long short-term memory artificial neural network (LSTM) model. By mining the complex nonlinear relationship between load and influencing factors, accurate prediction of future load can be achieved.

[0108] S3: Based on the collected microgrid load data and microgrid energy storage data, a capacity configuration optimization model of the microgrid adjustable elements is constructed; the capacity configuration optimization model of the microgrid adjustable elements aims to balance the maximization of power supply benefits and the maximization of power supply stability.

[0109] The capacity configuration optimization model of the microgrid adjustable elements is established. The capacity configuration optimization model of the microgrid adjustable elements includes maximizing power supply stability and maximizing power supply benefits. The calculation formula is as follows:

[0110] max[αR supply +βR profit ]

[0111] Among them, max[·] means taking the maximum value of the synergy; R supply is the power supply stability index, α is the adjustment coefficient of the power supply stability index; R profit is the power supply revenue indicator, and β is the adjustment coefficient of the power supply revenue indicator.

[0112] Configure the microgrid power supply variables and microgrid energy storage variables. The microgrid power supply variable data includes the capacity of the photovoltaic panels. Diesel generator capacity Gas turbine capacity Energy storage battery capacity and the energy storage battery capacity of electric vehicles

[0113] The objective function to maximize power supply stability is:

[0114]

[0115] Among them, R supply is the power supply stability index, EENS is the expected unpowered power supply, E total is the total load demand, E total It is predicted based on the LSTM model for microgrid load demand prediction.

[0116] It should be noted that the expected unavailable power EENS reflects the power supply stability of the microgrid, which is related to the capacity configuration of each adjustable element. Generally speaking, the larger the capacity of the adjustable element, the smaller the EENS and the higher the power supply stability. The capacity (rated power) of photovoltaic panels, diesel generators, and gas turbines determines the power generation capacity. The larger the rated power, the stronger the power generation capacity, and the lower the EENS will theoretically be. The rated capacity of energy storage batteries and electric vehicle batteries determines the system's energy storage and regulation capabilities. The larger the capacity, the more power can be provided during peak power consumption, which helps to reduce EENS. Reasonable configuration of these decision variables can improve the system's ability to cope with load fluctuations, reduce power supply shortages, and reduce EENS. Specifically, EENS can be estimated in the following way: Based on the LSTM load forecasting results, the load demand forecast value E for a period of time in the future is obtained. total ; Then, according to the capacity of each adjustable element, the maximum power supply capacity E of the microgrid during this period is estimated supply If E supply <E total , there will be a certain amount of unpowered electricity, that is: EENS = E total -E supply .

[0117] The objective function to maximize the power supply revenue is:

[0118]

[0119] C total =C PV (t)+C DE (t)+C MT (t)+C batt (t)+C EV (t)

[0120] Among them, T is the optimized time domain length, P shift (t) and P adjust (t) are the output of the translatable load and the elastic load at the tth moment, λ shift and λ adjustis the benefit factor of the translatable load and elastic load, C total is the total operating cost, C PV (t), C DE (t), C MT (t), C batt (t) and C EV (t) are the operating costs of photovoltaic panels, diesel generators, gas turbines, energy storage batteries and electric vehicles at the tth moment; waste(t) is the negative profit influencing factor of loss.

[0121] f(t) is the periodic probability adjustment function of the operating cost, expressed as:

[0122]

[0123] Among them, A is the amplitude, which controls the amplitude of periodic changes; T period is the cycle length, indicating the cycle of cost change; φ is the phase, controlling the starting point of the periodic change; these three parameters can be set and adjusted according to actual conditions.

[0124] The negative income influencing factor waste(t) is expressed as:

[0125] waste(t)=β1·E waste (t)+β2·I idle (t)

[0126] Among them, E waste (t) represents the energy loss at the tth moment, which can be calculated or estimated according to the actual situation; I idle (t) represents the equipment idleness at the tth moment, which can be measured by the inverse of the equipment utilization rate; β1 and β2 are the negative benefit weight coefficients of energy loss and equipment idleness, respectively, indicating their impact on the total benefit, which can be set according to actual conditions.

[0127] The constraint condition of the objective function of the capacity configuration optimization model of the microgrid adjustability element is the load balance constraint:

[0128]

[0129] Among them, the energy storage battery capacity constraints are: Energy storage battery charging and discharging power constraints: Electric vehicle energy storage battery capacity constraints: Electric vehicle energy storage battery charging and discharging power constraints: Photovoltaic panels, diesel generators and gas turbine capacity constraints: Output constraints of photovoltaic panels, diesel generators and gas turbines:

[0130] in, and are the lower and upper limits of the energy storage battery capacity, and are the lower and upper limits of the charging and discharging power of the energy storage battery, and is the lower and upper limits of the energy storage battery capacity of electric vehicles, and The lower and upper limits of the charging and discharging power of electric vehicle energy storage batteries, and are the upper limits of diesel generator and gas turbine capacities respectively.

[0131] The prediction results of the LSTM load forecasting model As the input of the capacity configuration optimization model, it is used to describe the future load demand of the microgrid. At the same time, combined with the historical meteorological data of the area where the microgrid is located, the power supply stability of the microgrid is calculated to obtain EENS and E total .

[0132] Solve the microgrid capacity configuration optimization model to obtain the optimal capacity configuration scheme for the microgrid power supply variables and microgrid energy storage variables and

[0133] S4: Input the microgrid load forecast results into the microgrid capacity configuration optimization model to calculate the distribution network capacity configuration plan; based on the calculated distribution network capacity configuration plan, a rolling optimization method is used to execute the microgrid operation optimization plan.

[0134] Microgrid operation optimization based on model predictive control uses the model predictive control rolling optimization strategy to solve the microgrid operation scheduling problem in a rolling optimization manner.

[0135] Using LSTM load forecasting model f LSTM Based on the optimization results of microgrid capacity configuration, a microgrid operation optimization control function is constructed.

[0136] The model predictive control rolling optimization strategy is adopted to solve the microgrid operation and scheduling problem in a rolling optimization manner. The objective function of the microgrid operation and scheduling problem is to maximize the balance between power supply stability and power supply benefits in the prediction time domain:

[0137]

[0138] Among them, N p To predict the time domain length, R supply (t+i) is the power supply stability index at the future t+i moment, Rprofit (t+i) is the profit index at the future t+i moment, ω1 and ω2 are the weight coefficients of the stability target and the profit target respectively;

[0139] The return index R within the forecast time domain length profit (t+i) is calculated as:

[0140]

[0141] Among them, P shift (t+i) and P flex (t+i) are the outputs of the translatable load and the elastic load at the future t+ith moment, λ shift and λ flex is the corresponding profit coefficient, C j (t+i) is the operating cost of the jth type of adjustable decision variable at the t+ith moment in the future; the adjustable decision variables include the real-time output power of the diesel generator, the real-time output power of the gas turbine, the real-time output power of the energy storage battery and the real-time output power of the electric vehicle energy storage battery.

[0142] The calculation method of power supply stability within the prediction time domain length is:

[0143]

[0144] Among them, N p To predict the time domain length, P j (t+i) is the output of the j-th adjustable decision variable at the future t+i-th moment, λ j is the corresponding operating cost weight coefficient; R supply (t+N p ) is the power supply stability index at the end of the prediction time domain, and ω is the weight coefficient of the stability target.

[0145] The constraints of the microgrid operation and dispatching problem include: Load balance constraint: ∑ j P j (t+i)=P load (t+i); Energy storage battery capacity constraint: Energy storage battery charging and discharging power constraints: Electric vehicle energy storage battery capacity constraints: Electric vehicle energy storage battery charging and discharging power constraints: Output constraints of photovoltaic panels, diesel generators and gas turbines:

[0146]

[0147] Translational load constraints:

[0148] Elastic load restraint:

[0149] Among them, P PV (t+i) represents the i-th moment in the future (i=1, 2, ..., N p ), the actual output of photovoltaic panels; represents the optimal capacity configuration of photovoltaic panels; P DE (t+i) represents the actual output of the diesel generator at the i-th moment in the future; represents the optimal capacity configuration of diesel generators; P MT (t+i) represents the actual output of the gas turbine at the i-th moment in the future; represents the optimal capacity configuration of the gas turbine, is the total amount of load that can be translated, The upper limit of elastic load.

[0150] The real-time rolling optimization process of the rolling optimization strategy is as follows: In each control cycle, the LSTM model is used to predict the future N p Load demand at a moment At the same time, combined with real-time operation data and meteorological forecast data, the power supply stability index R in the future time domain is supply (t+N p ) for estimation.

[0151] Solve the optimization model and get the future N c Moments (N c ≤N p )’s optimal operation dispatch strategy for microgrid power supply variables: and

[0152] The optimization results are decoded into control instructions and sent to the control systems of each adjustable element to achieve real-time optimization and scheduling of the microgrid.

[0153] By incorporating power supply stability and economic benefit indicators into the optimization of microgrid adjustable element capacity configuration and operation optimization control, the economy and stability of the microgrid can be better balanced, the power supply continuity of important loads can be improved, and the system's ability to resist risks can be enhanced. At the same time, the rolling optimization strategy can dynamically adjust the operation strategy according to real-time status changes, and has stronger robustness and adaptability.

[0154] Example 2

[0155] Reference Figure 2 , which is the second embodiment of the present invention, provides a flexible AC / DC microgrid adjustable element capacity configuration and operation optimization system.

[0156] The system includes a data acquisition module, a microgrid load demand prediction module, a capacity configuration optimization module and a scheduling operation module.

[0157] The data acquisition module obtains the microgrid power supply variable data and collects the microgrid load data. The microgrid load data includes fixed load data, movable load data and elastic load data. It collects the microgrid energy storage data and the historical meteorological data of the area where the microgrid is located. The collected microgrid load data and the historical meteorological data of the area where the microgrid is located are matched in time to form a microgrid load data set.

[0158] The microgrid load demand prediction module builds a microgrid load demand prediction model and trains the microgrid load demand prediction model based on the microgrid load data set to obtain the microgrid load prediction results.

[0159] The capacity configuration optimization module constructs a capacity configuration optimization model for the microgrid's adjustable elements based on the collected microgrid load data and microgrid energy storage data; the capacity configuration optimization model for the microgrid's adjustable elements aims to balance the maximization of power supply benefits and the maximization of power supply stability.

[0160] The dispatching and operation module inputs the microgrid load forecast results into the microgrid capacity configuration optimization model to calculate the distribution network capacity configuration plan; based on the calculated distribution network capacity configuration plan, a rolling optimization method is used to execute the microgrid operation optimization plan.

[0161] Example 3

[0162] Figure 3 FIG. 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, according to another aspect of the present invention, an electronic device 500 is also provided. The electronic device 500 may include one or more processors and one or more memories. The memories store computer readable codes, and when the computer readable codes are executed by one or more processors, the above flexible AC / DC microgrid adjustable element capacity configuration and operation optimization method can be executed.

[0163] The method or system according to the embodiment of the present invention can also be used by Figure 3 The architecture of the electronic device shown is implemented.

[0164] like Figure 3 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, and the like.

[0165] The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, can store the flexible AC / DC microgrid adjustable element capacity configuration and operation optimization method provided by the present invention.

[0166] The invention discloses a method for capacity configuration and operation optimization of adjustable elements of a flexible AC / DC microgrid, comprising: obtaining microgrid power supply variable data, collecting microgrid load data, the microgrid load data including fixed load data, shiftable load data and elastic load data, collecting microgrid energy storage data and historical meteorological data of the area where the microgrid is located, temporally matching the collected microgrid load data with the historical meteorological data of the area where the microgrid is located to form a microgrid load data set; constructing a microgrid load demand prediction model, and training the microgrid load demand prediction model based on the microgrid load data set to obtain microgrid load prediction results; constructing a capacity configuration optimization model of the adjustable elements of the microgrid based on the collected microgrid load data and microgrid energy storage data; the capacity configuration optimization model of the adjustable elements of the microgrid takes the maximization of balanced power supply benefits and the maximization of power supply stability as the goal; inputting the microgrid load prediction results into the microgrid capacity configuration optimization model to calculate the capacity configuration plan of the distribution network; and executing the microgrid operation optimization plan by adopting a rolling optimization method based on the calculated distribution network capacity configuration plan.

[0167] Furthermore, the electronic device 500 may also include a user interface 508. Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 3 One or more components of an electronic device are shown.

[0168] Example 4

[0169] Figure 4 It is a schematic diagram of the structure of a computer-readable storage medium provided by an embodiment of the present invention.

[0170] like Figure 4 As shown, a computer readable storage medium 600 according to one embodiment of the present invention.

[0171] Computer readable storage medium 600 has computer readable instructions stored thereon.

[0172] When the computer-readable instructions are executed by the processor, the method for configuring and optimizing the capacity of adjustable elements of a flexible AC / DC microgrid and operating the method according to the embodiments of the present invention described with reference to the above drawings can be executed.

[0173] The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. In addition, according to an embodiment of the present invention, the process described above with reference to the flowchart may be implemented as a computer software program.

[0174] For example, the present invention provides a non-temporary machine-readable storage medium, which stores machine-readable instructions. The machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided by the present invention, such as: obtaining microgrid power supply variable data, collecting microgrid load data, the microgrid load data including fixed load data, shiftable load data and elastic load data, collecting microgrid energy storage data and historical meteorological data of the area where the microgrid is located, temporally matching the collected microgrid load data with the historical meteorological data of the area where the microgrid is located to form a microgrid load data set; constructing a microgrid load demand prediction model, and training the microgrid load demand prediction model based on the microgrid load data set to obtain a microgrid load prediction result; constructing a capacity configuration optimization model for a microgrid adjustable element based on the collected microgrid load data and microgrid energy storage data; the capacity configuration optimization model for a microgrid adjustable element takes the goal of balancing the maximization of power supply revenue and the maximization of power supply stability; inputting the microgrid load prediction result into the microgrid capacity configuration optimization model to calculate the distribution network capacity configuration plan; based on the calculated distribution network capacity configuration plan, a rolling optimization method is used to execute the microgrid operation optimization plan.

[0175] When the computer program is executed by the central processing unit (CPU), the above functions defined in the method of the present invention are performed. The method, apparatus, and device of the present invention may be implemented in many ways. For example, the method, apparatus, and device of the present invention may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware.

[0176] The above sequence for the steps of the method is for illustration only, and the steps of the method of the present invention are not limited to the sequence specifically described above unless otherwise specifically stated.

[0177] In addition, in some embodiments, the present invention can also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present invention. Therefore, the present invention also covers a recording medium storing a program for executing the method according to the present invention.

[0178] In addition, the parts of the above technical solutions provided in the embodiments of the present invention that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0179] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for configuring the capacity and optimizing the operation of adjustable elements of a flexible AC / DC microgrid, characterized in that: include: Acquire microgrid power supply variable data, collect microgrid load data, the microgrid load data includes fixed load data, movable load data and elastic load data, collect microgrid energy storage data and historical meteorological data of the area where the microgrid is located, and match the collected microgrid load data with the historical meteorological data of the area where the microgrid is located in time to form a microgrid load data set; Constructing a microgrid load demand prediction model, and training the microgrid load demand prediction model based on the microgrid load data set to obtain a microgrid load prediction result; Based on the collected microgrid load data and microgrid energy storage data, a capacity configuration optimization model of the microgrid adjustable element is constructed; the capacity configuration optimization model of the microgrid adjustable element takes balancing the maximization of power supply revenue and the maximization of power supply stability as the goal; The microgrid load forecast results are input into the microgrid capacity configuration optimization model to calculate the distribution network capacity configuration plan; based on the calculated distribution network capacity configuration plan, a rolling optimization method is adopted to execute the microgrid operation optimization plan.

2. The method for configuring and optimizing the capacity of adjustable elements of a flexible AC / DC microgrid according to claim 1 is characterized in that: The microgrid power supply variable data includes photovoltaic panel power generation data P PV (t), diesel generator power generation data P DE (t) and gas turbine power generation data P MT (t); Collect microgrid load data P load (t), the microgrid load data P load (t) Including fixed load data Load data can be translated And elastic load data Collect microgrid energy storage data, including the charging and discharging power P of the energy storage battery batt (t) and energy storage battery capacity data And the charging and discharging power P of the electric vehicle energy storage battery EV (t) and electric vehicle energy storage battery capacity data Obtain historical meteorological data of the area where the microgrid is located, including temperature data T(t) and humidity data H(t), and compare them with the microgrid load data P at the same time. load (t) Merge to obtain the augmented microgrid load dataset.

3. The method for configuring and optimizing the capacity of adjustable elements of a flexible AC / DC microgrid according to claim 2 is characterized in that: The long short-term memory artificial neural network LSTM model is selected as the architecture of the microgrid load demand prediction model; The microgrid load data set is sampled using the sliding time window method, with a window size of k and a sliding step of s; that is, each sample contains k consecutive historical data, and the starting positions of adjacent samples differ by s time steps; Divide the constructed samples into training set, validation set and test set; build LSTM model and train the model using training set data; The loss function uses mean square error MSE; The validation set data is used to evaluate the performance and optimize the hyperparameters of the trained LSTM model, including the number of hidden layers n. hidden , the number of hidden units n units and learning rate η; Use the test set data to evaluate the performance of the optimal LSTM model. The evaluation indicators include mean absolute error (MAE) and root mean square error (RMSE). Get the trained microgrid load demand prediction LSTM model f LSTM , used to predict the load demand of the microgrid in the future time period, and obtain the load demand prediction value 4. The method for configuring and optimizing the capacity of adjustable elements of a flexible AC / DC microgrid according to claim 3 is characterized in that: A capacity configuration optimization model of the microgrid adjustable element is established. The capacity configuration optimization model of the microgrid adjustable element includes maximizing power supply stability and maximizing power supply benefits. The calculation formula is as follows: max[αR supply +βR profit ] Among them, R supply is the power supply stability index, α is the adjustment coefficient of the power supply stability index; R profit is the power supply revenue index, β is the adjustment coefficient of the power supply revenue index; Configure microgrid power supply variables and microgrid energy storage variables, including the capacity of photovoltaic panels Diesel generator capacity Gas turbine capacity Energy storage battery capacity and the energy storage battery capacity of electric vehicles The objective function to maximize power supply stability is: Among them, R supply is the power supply stability index, EENS is the expected unpowered power supply, E total is the total load demand, E total It is predicted based on the LSTM model of microgrid load demand prediction; The objective function to maximize the power supply revenue is: C total =C PV (t)+C DE (t)+C MT (t)+C batt (t)+C EV (t) Among them, T is the optimized time domain length, P shift (t) and P flex (t) are the output of the translatable load and the elastic load at the tth moment, λ shift and λ flex is the benefit factor of the translatable load and elastic load, C total is the total operating cost, C PV (t), C DE (t), C MT (t), C batt (t) and C EV (t) are the operating costs of photovoltaic panels, diesel generators, gas turbines, energy storage batteries and electric vehicles at the tth moment; waste(t) is the negative income influencing factor of loss; f(t) is the periodic probability adjustment function of the operating cost, expressed as: Among them, A is the amplitude, which controls the amplitude of periodic changes; T period is the cycle length, indicating the cycle of cost change; φ is the phase, controlling the starting point of the periodic change; The negative income influencing factor waste(t) is expressed as: waste(t)=β1·E waste (t)+β2·I idle (t); Among them, E waste (t) represents the energy loss at the tth moment; I idle (t) represents the idle status of equipment at the tth moment; β1 and β2 are the negative benefit weight coefficients of energy loss and equipment idleness, respectively; The constraints of the objective function of the capacity configuration optimization model of the microgrid adjustability element include load balance constraints, energy storage battery capacity constraints, energy storage battery charge and discharge power constraints, electric vehicle energy storage battery capacity constraints, electric vehicle energy storage battery charge and discharge power constraints, photovoltaic panels, diesel generators and gas turbine capacity constraints, and photovoltaic panels, diesel generators and gas turbine output constraints; among them, Load balancing constraints: Energy storage battery capacity constraints: Energy storage battery charging and discharging power constraints: Electric vehicle energy storage battery capacity constraints: Electric vehicle energy storage battery charging and discharging power constraints: Photovoltaic panels, diesel generators and gas turbine capacity constraints: Output constraints of photovoltaic panels, diesel generators and gas turbines: in, and are the lower and upper limits of the energy storage battery capacity, and are the lower and upper limits of the charging and discharging power of the energy storage battery, and are the lower and upper limits of the energy storage battery capacity of electric vehicles, and The lower and upper limits of the charging and discharging power of electric vehicle energy storage batteries, and They are the upper limits of the capacity of photovoltaic panels, diesel generators and gas turbines respectively.

5. The method for configuring and optimizing the capacity of adjustable elements of a flexible AC / DC microgrid according to claim 4, characterized in that: The prediction results of the LSTM load forecasting model As the input of the capacity configuration optimization model, it is used to describe the future load demand of the microgrid. At the same time, combined with the historical meteorological data of the area where the microgrid is located, the power supply stability of the microgrid is calculated to obtain EENS and E total ; Solve the microgrid capacity configuration optimization model to obtain the optimal capacity configuration scheme for the microgrid power supply variables and microgrid energy storage variables and Microgrid operation optimization based on model predictive control, using model predictive control rolling optimization strategy to solve microgrid operation scheduling problems in a rolling optimization manner; Using LSTM load forecasting model f LSTM Based on the optimization results of microgrid capacity configuration, the microgrid operation optimization control function is constructed.

6. The method for configuring and optimizing the capacity of adjustable elements of a flexible AC / DC microgrid according to claim 5 is characterized in that: The model predictive control rolling optimization strategy is adopted to solve the microgrid operation and scheduling problem in a rolling optimization manner. The objective function of the microgrid operation and scheduling problem is to maximize the balance between power supply stability and power supply benefits in the prediction time domain: Among them, N p To predict the time domain length, R supply (t+i) is the power supply stability index at the future t+i moment, R profit (t+i) is the profit index at the future t+i moment, ω1 and ω2 are the weight coefficients of the stability target and the profit target respectively; The profit index R within the forecast time domain length profit (t+i) is calculated as: Among them, P shift (t+i) and P flex (t+i) are the outputs of the translatable load and the elastic load at the future t+ith moment, λ shift and λ flex is the corresponding profit coefficient, C j (t+i) is the operating cost of the jth type of adjustable decision variable at the t+ith moment in the future; The calculation method of power supply stability within the prediction time domain length is: Among them, N p To predict the time domain length, P j (t+i) is the output of the j-th adjustable decision variable at the future t+i-th moment, λ j is the corresponding operating cost weight coefficient; R supply (t+N p ) is the power supply stability index at the end of the prediction time domain, and ω is the weight coefficient of the stability target; The constraints of the microgrid operation and dispatching problem include: Load balance constraint: ∑ j P j (t+i)=P load (t+i); Energy storage battery capacity constraint: Energy storage battery charging and discharging power constraints: Electric vehicle energy storage battery capacity constraints: Electric vehicle energy storage battery charging and discharging power constraints: Output constraints of photovoltaic panels, diesel generators and gas turbines: Translational load constraints: Elastic load restraint: Among them, P PV (t+i) means the i-th moment in the future (i=1, 2, ..., N p ), the actual output of photovoltaic panels; represents the optimal capacity configuration of photovoltaic panels; P DE (t+i) represents the actual output of the diesel generator at the i-th moment in the future; represents the optimal capacity configuration of diesel generators; P MT (t+i) represents the actual output of the gas turbine at the i-th moment in the future; represents the optimal capacity configuration of the gas turbine, is the total amount of load that can be translated, The upper limit of elastic load.

7. The method for configuring and optimizing the capacity of adjustable elements of a flexible AC / DC microgrid according to claim 6 is characterized in that: The real-time rolling optimization process of the rolling optimization strategy is as follows: In each control cycle, the LSTM model is used to predict the future N p The load demand at a moment p At the same time, combined with real-time operation data and meteorological forecast data, the power supply stability index R in the future time domain is supply (t+N p ) to make an estimate; Solve the optimization model and get the future N c The optimal operation scheduling strategy of the microgrid power supply variables and microgrid energy storage variables at each moment; the optimization results are decoded into control instructions and sent to the control systems of each adjustable element to achieve real-time optimization scheduling of the microgrid.

8. A flexible AC / DC microgrid adjustable element capacity configuration and operation optimization system, which is used to implement the flexible AC / DC microgrid adjustable element capacity configuration and operation optimization method according to any one of claims 1 to 7, characterized in that: include: Data acquisition module, microgrid load demand forecasting module, capacity configuration optimization module and dispatching operation module; The data acquisition module acquires microgrid power supply variable data, collects microgrid load data, the microgrid load data includes fixed load data, shiftable load data and elastic load data, collects microgrid energy storage data and historical meteorological data of the area where the microgrid is located, and performs temporal matching of the collected microgrid load data and the historical meteorological data of the area where the microgrid is located to form a microgrid load data set; The microgrid load demand prediction module constructs a microgrid load demand prediction model, and trains the microgrid load demand prediction model based on the microgrid load data set to obtain a microgrid load prediction result; The capacity configuration optimization module constructs a capacity configuration optimization model of the microgrid adjustable element based on the collected microgrid load data and microgrid energy storage data; the capacity configuration optimization model of the microgrid adjustable element takes balancing the maximization of power supply revenue and the maximization of power supply stability as the goal; The dispatching and operation module inputs the microgrid load forecast result into the microgrid capacity configuration optimization model to calculate the distribution network capacity configuration plan; based on the calculated distribution network capacity configuration plan, a rolling optimization method is adopted to execute the microgrid operation optimization plan.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the flexible AC / DC microgrid adjustable element capacity configuration and operation optimization method as described in any one of claims 1 to 7 by calling the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer is caused to execute the method for configuring and optimizing the capacity of adjustable elements of a flexible AC / DC microgrid and operating the method as described in any one of claims 1 to 7.

Images