Flexible ac-dc microgrid adjustable element capacity configuration and operation optimization method and system

Abstract

The application discloses a kind of flexible AC / DC microgrid adjustable element capacity configuration and operation optimization method and system, by collecting microgrid power variable data, load data, energy storage data and meteorological data, and time matching, form microgrid load data set;Based on the data set, construct and train microgrid load demand prediction model, obtain load prediction result;Balancing power supply benefit maximization and power supply stability maximization are used as target to build microgrid adjustable element capacity configuration optimization model;Load prediction result is input into capacity configuration optimization model, and distribution network capacity configuration scheme is calculated, and rolling optimization mode is used to execute microgrid operation optimization scheme.The application method comprehensively considers the multiple data and factors of microgrid, realizes the efficient, economic, reliable operation of microgrid by prediction and optimization.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power grid control, in particular to a flexible AC / DC microgrid adjustable element capacity configuration and operation optimization method and system. BACKGROUND

[0002] A microgrid is a local power network composed of distributed energy resources, loads, energy storage systems, and control devices. It can operate in grid-connected or islanded mode. The development of microgrid technology provides a new approach to improving energy utilization efficiency, reducing energy costs, and enhancing grid reliability.

[0003] Traditional microgrid planning and design are mainly based on deterministic load and generation forecasts, lacking consideration of uncertainty factors. With the increasing penetration of renewable energy, stochastic optimization and robust optimization methods are needed to fully consider the uncertainty of load and renewable energy in the microgrid planning and design stage. Accurate load forecasting is the basis for optimal operation of microgrids. Traditional load forecasting methods such as regression analysis and time series 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 and artificial neural networks have been widely used to improve forecasting accuracy by mining the complex relationship between loads and influencing factors. However, traditional load forecasting methods often rely solely on load data itself, ignoring the impact of the microgrid's surrounding environment, so the load forecasting accuracy is often not high. The economic and reliable performance of microgrids largely depends on the capacity configuration planning of microgrids. 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, while with the development of microgrids, load elements can be further refined into translatable loads, flexible 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 uses deterministic optimization methods such as linear programming and mixed integer programming, so the configuration capacity accuracy obtained by traditional methods is not enough.

[0004] In view of this, the present application proposes a flexible AC / DC microgrid adjustable element capacity configuration and operation optimization method and system. SUMMARY

[0005] To achieve the above-mentioned purpose, the present application provides a flexible AC / DC microgrid adjustable element capacity configuration and operation optimization method and system, and the specific technical solutions are as follows: a flexible AC / DC microgrid adjustable element capacity configuration and operation optimization method, comprising:

[0006] The micro-grid power variable data is acquired, the micro-grid load data is collected, the micro-grid load data includes fixed load data, translatable load data and elastic load data, the micro-grid energy storage data and the historical weather data of the region where the micro-grid is located are collected, the collected micro-grid load data and the historical weather data of the region where the micro-grid is located are matched in time, and a micro-grid load data set is formed.

[0007] A micro-grid load demand prediction model is constructed, the micro-grid load demand prediction model is trained based on the micro-grid load data set, and a micro-grid load prediction result is obtained.

[0008] Based on the collected micro-grid load data and micro-grid energy storage data, a capacity configuration optimization model of the micro-grid adjustable element is constructed, and the capacity configuration optimization model of the micro-grid adjustable element takes balancing the maximum power supply benefit and the maximum power supply stability as the target.

[0009] The micro-grid load prediction result is input into the micro-grid capacity configuration optimization model, and a power distribution network capacity configuration scheme is calculated; based on the calculated power distribution network capacity configuration scheme, a rolling optimization method is used to execute a micro-grid operation optimization scheme.

[0010] Preferably, the micro-grid power 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] The micro-grid load data P load (t) is collected, and the micro-grid load data P load (t) includes fixed load data translatable load data and elastic load data

[0012] The micro-grid energy storage data is collected, including the charge and discharge power P batt (t) of the energy storage battery and the capacity data of the energy storage battery and the charge and discharge power P EV (t) of the electric vehicle energy storage battery and the capacity data of the electric vehicle energy storage battery

[0013] The historical weather data of the region where the micro-grid is located is acquired, including temperature data T(t) and humidity data H(t), and is combined with the micro-grid load data P load (t) at the same time to obtain an augmented micro-grid load data set.

[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 sliding time window method is used to construct samples for the microgrid load data set, 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] The constructed samples are divided into a training set, a validation set, and a test set; an LSTM model is built, and the training set data is used to train the model; the loss function is mean squared error (MSE);

[0017] The trained LSTM model is evaluated for performance and hyperparameters, including the number of hidden layers n hidden , the number of hidden units n units , and the learning rate η;

[0018] The optimal LSTM model is evaluated for performance using the test set data, with evaluation metrics including mean absolute error (MAE) and root mean squared error (RMSE);

[0019] The trained microgrid load demand prediction LSTM model f LSTM is obtained, which is used for microgrid load demand prediction in future time periods, and the load demand prediction value

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

[0021] max[αR supply +βR profit ]

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

[0023] The microgrid power supply variables and microgrid energy storage variables are configured, including the capacity of the photovoltaic panel the capacity of the diesel generator the capacity of the gas turbine the capacity of the energy storage battery and the capacity of the electric vehicle energy storage battery

[0024] The objective function for maximizing power supply stability is:

[0025]

[0026] wherein R supply is the power supply stability index, EENS is the expected amount of un-supplied power, E total is the total load demand, E total is predicted according to the micro-grid load demand prediction LSTM model;

[0027] The objective function for maximizing power supply revenue is:

[0028]

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

[0030] wherein T is the optimization time domain length, P shift (t) and P flex (t) are the output of the shiftable load and the flexible load at the tth moment, λ shift and λ flex are the revenue coefficients of the shiftable load and the flexible 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 the photovoltaic panel, the diesel generator, the gas turbine, the energy storage battery and the electric vehicle at the tth moment; waste(t) is the loss type negative revenue influencing factor;

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

[0032]

[0033] wherein A is the amplitude, controlling the amplitude of the periodic change; T period is the period length, indicating the period of cost change; φ is the phase, controlling the starting point of the periodic change;

[0034] The loss type negative revenue 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 time t; I idle (t) represents the equipment idle status at time t; β1 and β2 are the negative benefit weighting coefficients for energy loss and equipment idleness, respectively;

[0037] The constraints of the objective function of the capacity configuration optimization model for microgrid adjustability elements include 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, and photovoltaic panels, diesel generators, and gas turbine output constraints; load balancing constraints:

[0038]

[0039] Among them, the capacity constraints of energy storage batteries are: Energy storage battery charge and discharge power constraints: Electric vehicle energy storage battery capacity constraints: Electric vehicle energy storage battery charging and discharging power constraints: Capacity constraints for photovoltaic panels, diesel generators, and gas turbines: Output constraints of photovoltaic panels, diesel generators, and gas turbines: in, and These represent the lower and upper limits of energy storage battery capacity. and The lower and upper limits of the charging and discharging power of energy storage batteries. and These are the lower and upper limits for 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 These are the upper limits for the capacity of photovoltaic panels, diesel generators, and gas turbines, respectively.

[0040] Preferably, the prediction results of the LSTM load forecasting model are used. As input to the capacity configuration optimization model, it describes the future load demand of the microgrid; simultaneously, combined with historical meteorological data of the microgrid's location, it calculates the power supply stability of the microgrid, obtaining EENS and E. total ;

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

[0042] The micro-grid operation optimization based on model predictive control solves a micro-grid operation scheduling problem in a rolling optimization manner by using a model predictive control rolling optimization strategy;

[0043] The LSTM load prediction model f LSTM The micro-grid operation optimization control function is constructed based on the micro-grid capacity configuration optimization result.

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

[0045]

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

[0047] The calculation method of the benefit index R profit (t+i) in the prediction time domain length is:

[0048]

[0049] P shift (t+i) and P flex (t+i) are the outputs of the shiftable load and the elastic load at the future t+i time, λ shift and λ flex are corresponding benefit coefficients, C j (t+i) is the operation cost of the jth adjustable decision variable at the future t+i time;

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

[0051]

[0052] N p is the prediction time domain length, P j (t+i) is the output of the jth adjustable decision variable at the future t+i time, λ j is a corresponding operation 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 a weight coefficient of the stability target.

[0053] The constraint conditions of the micro-grid operation scheduling problem include: load balance constraint: ∑ j P j (t+i) = P load (t+i); energy storage battery capacity constraint: Energy storage battery charge and discharge power constraint: Electric vehicle energy storage battery capacity constraint: Electric vehicle energy storage battery charge and discharge power constraint: Photovoltaic panel, diesel generator and gas turbine output constraint:

[0054]

[0055] Translational load constraint:

[0056] Elastic load constraint:

[0057] Wherein, P PV (t+i) represents the actual output of the photovoltaic panel at the future i-th time (i = 1, 2, …, N p ); represents the optimal capacity configuration of the photovoltaic panel; P DE (t+i) represents the actual output of the diesel generator at the future i-th time; represents the optimal capacity configuration of the diesel generator; P MT (t+i) represents the actual output of the gas turbine at the future i-th time; represents the optimal capacity configuration of the gas turbine, is the total amount of translational load, is 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 period, the LSTM model is used to predict the load demand p at the future N time points; supply Meanwhile, the supply stability index R p (t+N c ) in the future time domain is estimated in combination with real-time operation data and weather forecast data;

[0059] Solving the optimization model, the optimal operation scheduling strategy of the micro-grid power variable at the future N c time points is obtained;

[0060] The optimization result is decoded into control instructions and issued to the control system of each adjustable element to realize real-time optimization scheduling of the micro-grid.

[0061] The flexible AC / DC microgrid adjustable element capacity configuration and operation optimization system is used for realizing a flexible AC / DC microgrid adjustable element capacity configuration and operation optimization method, and comprises 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 variable data, acquires microgrid load data, acquires microgrid energy storage data and historical weather data of a region where the microgrid is located, matches the acquired microgrid load data and the historical weather data of the region where the microgrid is located in time, and forms a microgrid load data set.

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

[0064] The capacity configuration optimization module constructs a capacity configuration optimization model of a microgrid adjustable element based on the acquired microgrid load data and the microgrid energy storage data, and takes balancing maximum power supply benefit maximization and maximum power supply stability maximization as a target.

[0065] The scheduling operation module inputs the microgrid load prediction result into the microgrid capacity configuration optimization model, calculates a power distribution network capacity configuration scheme, and executes a microgrid operation optimization scheme in a rolling optimization manner based on the calculated power distribution network capacity configuration scheme.

[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, when the instructions are run on a computer, the computer executes the flexible AC / DC microgrid adjustable element capacity configuration and operation optimization method.

[0068] The present application has the following beneficial effects: the present application forms a comprehensive and time-consistent microgrid load data set by collecting and matching various data, and provides a reliable data foundation for subsequent load prediction and optimization scheduling.

[0069] The present application trains a load demand prediction model by using historical load data, can accurately predict future load demand, and provides important input information for optimization scheduling.

[0070] The capacity configuration optimization model considering power supply benefits and power supply stability is constructed, and the optimal capacity configuration scheme balancing the two targets can be obtained, thereby improving the economic benefits and operation reliability of the microgrid.

[0071] The load prediction result is combined with the capacity configuration optimization, and the operation optimization scheme is executed in a rolling optimization manner, so that the operation strategy can be dynamically adjusted to adapt to the load change, and the overall operation efficiency and economy of the microgrid are improved while ensuring the power supply reliability. BRIEF DESCRIPTION OF DRAWINGS

[0072] Figure 1 A flexible AC / DC microgrid adjustable element capacity configuration and operation optimization method flowchart is provided for the present application.

[0073] Figure 2 A flexible AC / DC microgrid adjustable element capacity configuration and operation optimization system structure diagram is provided for the present application.

[0074] Figure 3 It is an electronic device structure schematic diagram provided by an embodiment of the present application.

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

[0076] In order to better understand the present application, various aspects of the present application will be described in more detail with reference to the accompanying drawings. It should be understood that these detailed descriptions are only descriptions of exemplary embodiments of the present application, and do not limit the scope of the present application 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 drawings, the size, dimensions and shapes of the elements have been slightly adjusted for ease of illustration. The drawings are merely exemplary and are not strictly drawn to scale. As used in this document, the terms "approximately", "about", and similar terms are used as terms of approximation and not as terms of degree, and are intended to account for the inherent deviations in a measuring or computing value that would be recognized by those of ordinary skill in the art. In addition, in the present application, the order of the steps described does not necessarily represent the order in which the processes appear in actual operation, unless otherwise explicitly limited or derivable from the context.

[0078] It should also be understood that all references to specifications, parameters, devices, and elements are intended to mean that at least one of these specifications, parameters, devices, and elements are used or intended to be used, consistent with a spirit of claimed subject matter. Throughout this application, the term "may" is used in a permissive sense (i.e., meaning having the potential to), rather than a mandatory sense (i.e., meaning must). Similarly, the terms "include," "including," and "includes" should be interpreted broadly to mean "including but not limited to or comprising." Also, it is to be understood that where the application, or portions thereof, is / are described with respect to a method, various steps of the method can be performed in any order. Also, each step, sub-step, and / or sub-sub-step can be performed simultaneously with, or at least partially overlapping with, one or more of the other steps, sub-steps, and / or sub-sub-steps. Moreover, when a phrase similar to "at least one of X, Y, and Z" is used in the claims, it will be understood that such a phrase is equivalent to "at least one of the group consisting of X, Y, and Z."

[0079] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an overly literal or overly formal sense.

[0080] It should be noted that the embodiments and features of the present application can be combined with each other, without conflict, in the case of no conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0081] Embodiment 1

[0082] Reference Figure 1 For a first embodiment of the present application, a flexible AC / DC microgrid adjustable element capacity configuration and operation optimization method is provided.

[0083] S1: Obtain microgrid power variable data, collect microgrid load data, the microgrid load data including fixed load data, translatable load data and elastic load data, collect microgrid energy storage data and historical weather data of the region where the microgrid is located, and match the collected microgrid load data and historical weather data of the region 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 variables and microgrid energy storage variables; wherein the microgrid power variables include the capacity of the photovoltaic panel, the capacity of the diesel generator, and the capacity of the gas turbine; the microgrid energy storage variables include the capacity of the energy storage battery and the capacity of the electric vehicle energy storage battery.

[0084] The microgrid power 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] Collecting micro-grid load data P load (t), micro-grid load data P load (t) includes fixed load data Translatable load data And flexible load data

[0086] Collecting micro-grid energy storage data, including the charge and discharge power P batt (t) and energy storage battery capacity data And electric vehicle energy storage battery charge and discharge power P EV (t) and electric vehicle energy storage battery capacity data

[0087] Obtain the historical meteorological data of the area where the micro-grid is located, including temperature data T(t) and humidity data H(t), and combine it with the micro-grid load data P load (t) at the same time, to obtain the augmented micro-grid load data set.

[0088] S2: Construct a micro-grid load demand prediction model, train the micro-grid load demand prediction model based on the micro-grid load data set, and use it to obtain the micro-grid load prediction result.

[0089] Select the long short-term memory artificial neural network (LSTM) model as the architecture of the micro-grid load demand prediction model; LSTM can effectively capture the long and short term dependencies in time series data through the gating mechanism and memory unit, and has strong modeling ability.

[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 value:

[0094] Memory cell state update:

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

[0096] Hidden state update: h t =o t *tanh(C t ).

[0097] where f t , i t , o t are the activation vectors of forget gate, input gate and output gate, respectively, C t is the memory cell state vector, is the memory cell candidate value, 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 matrices and bias vectors corresponding to the gates and memory cell, respectively, σ is the sigmoid activation function, tanh is the hyperbolic tangent activation function, and the symbol * denotes element-wise multiplication.

[0098] The sliding time window method is used to construct samples for the data set D2, 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.

[0099] The constructed samples are divided into training set, validation set and test set, with a ratio of p train :p val :p test ; where p train , p val , p test are the sample proportions of the training set, validation set and test set, respectively.

[0100] An LSTM model is built and trained using the training set data; the loss function uses the mean square error MSE: where 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] The trained LSTM model is evaluated for performance and hyperparameter tuning using the validation set data, including the number of hidden layers n hidden , the number of hidden units n units and the learning rate η; the optimal hyperparameter combination is found through methods such as grid search to improve the generalization performance of the model.

[0102] The optimal LSTM model is evaluated using test set data, and evaluation indicators include mean absolute error (MAE) and root mean square error (RMSE).

[0103] The calculation formula of the mean absolute error (MAE) is:

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

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

[0106] The trained microgrid load demand prediction LSTM model f LSTM is obtained, which is used for microgrid load demand prediction in future time periods, and the load demand prediction value

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

[0108] S3: 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 maximizing power supply stability and maximizing power supply stability as the target.

[0109] A capacity configuration optimization model of the microgrid adjustable element is established, which includes maximizing power supply stability and maximizing power supply income, and the calculation formula is as follows:

[0110] max [aR supply + bR profit ]

[0111] Where max [·] represents the maximum value; R supply is the power supply stability index, and a is the adjustment coefficient of the power supply stability index; R profit is the power supply income index, and b is the adjustment coefficient of the power supply income index.

[0112] The microgrid power supply variables and microgrid energy storage variables are configured, and the microgrid power supply variable data includes the capacity of the photovoltaic panel the capacity of the diesel generator the capacity of the gas turbine the capacity of the energy storage battery and the capacity of the energy storage battery of the electric vehicle

[0113] The objective function for maximizing power supply stability is:

[0114]

[0115] where R supply is the power supply stability index, EENS is the expected amount of power not supplied, E total is the total load demand, E total is obtained according to the microgrid load demand prediction LSTM model.

[0116] It should be noted that the expected amount of power not supplied EENS reflects the power supply stability of the microgrid, which is related to the capacity configuration of each adjustable element. Generally speaking, the greater the capacity of the adjustable element, the smaller the EENS, and the higher the power supply stability. The capacity (rated power) of the photovoltaic panel, diesel generator and gas turbine determines the power generation capacity. The greater the rated power, the stronger the power generation capacity, and the EENS will theoretically decrease. The rated capacity of the energy storage battery and the electric vehicle battery determines the system energy storage and regulation capacity. The greater the capacity, the more power can be provided during peak electricity 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 by the following method: based on the LSTM load prediction result, the load demand prediction value E total in the future period is obtained; then according to the capacity of each adjustable element, the maximum power supply capacity E supply of the microgrid in the period is estimated; if E supply <E total , there will be a certain amount of power not supplied, that is: EENS = E total -E supply .

[0117] The objective function for maximizing power supply revenue is:

[0118]

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

[0120] where T is the optimization time domain length, P shift (t) and P adjust (t) are the outputs of the shiftable load and the flexible load at the tth time, λ shift and λ adjustC is the benefit coefficient of the translatable load and the elastic load total C is the total operating cost PV C is the benefit coefficient of the translatable load and the elastic load DE C is the benefit coefficient of the translatable load and the elastic load MT C is the benefit coefficient of the translatable load and the elastic load batt C is the benefit coefficient of the translatable load and the elastic load EV C is the benefit coefficient of the translatable load and the elastic load

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

[0122]

[0123] where A is the amplitude, controlling the magnitude of the periodic change; T period is the period length, representing the period of cost change; φ is the phase, controlling the starting point of the periodic change; the three parameters can be set and adjusted according to actual conditions.

[0124] The loss-type negative benefit influencing factor waste(t) is expressed as:

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

[0126] where E waste (t) represents the energy loss at the tth moment, which can be calculated or estimated according to actual conditions; I idle (t) represents the equipment idle condition at the tth moment, which can be measured by the inverse of equipment utilization; β1 and β2 are the negative benefit weight coefficients of energy loss and equipment idle, respectively, representing their influence 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] where the energy storage battery capacity constraint is: The energy storage battery charge and discharge power constraint is: The electric vehicle energy storage battery capacity constraint is: The electric vehicle energy storage battery charge and discharge power constraint is: The photovoltaic panel, diesel generator and gas turbine capacity constraint is: The photovoltaic panel, diesel generator and gas turbine output constraint is:

[0130] wherein, and are the lower and upper limits of the energy storage battery capacity, and are the lower and upper limits of the energy storage battery charge and discharge power, and are the lower and upper limits of the energy storage battery capacity of the electric vehicle, and are the lower and upper limits of the energy storage battery charge and discharge power of the electric vehicle, and are the upper limits of the diesel generator and gas turbine capacity, respectively.

[0131] The prediction result of the LSTM load prediction model is taken as an input of the capacity configuration optimization model, to describe the future load demand of the microgrid; at the same time, the historical meteorological data of the region where the microgrid is located are combined, to calculate the power supply stability of the microgrid, and obtain the EENS and EENS. total

[0132] The microgrid capacity configuration optimization model is solved, to obtain the optimal capacity configuration scheme of the microgrid power variable and the microgrid energy storage variable and

[0133] S4: The microgrid load prediction result is input into the microgrid capacity configuration optimization model, to calculate the distribution network capacity configuration scheme; based on the calculated distribution network capacity configuration scheme, the rolling optimization strategy is adopted, to execute the microgrid operation optimization scheme.

[0134] The microgrid operation optimization based on the model prediction control solves the microgrid operation scheduling problem in a rolling optimization manner, by using the model prediction control rolling optimization strategy.

[0135] The LSTM load prediction model f LSTM and the microgrid capacity configuration optimization result are taken as the basis, to construct the microgrid operation optimization control function.

[0136] The model prediction 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 the power supply stability and the power supply benefit in the prediction time domain:

[0137]

[0138] wherein, N p is the prediction time domain length, R supply (t+i) is the power supply stability index at the future t+i moment.​​profit (t+i) is the revenue index at the future t+i time, ω1 and ω2 are the weight coefficients of stability target and revenue target respectively;

[0139] The calculation method of the revenue index R profit (t+i) is as follows:

[0140]

[0141] Wherein, P shift (t+i) and P flex (t+i) are the output of the movable load and the elastic load at the future t+i time, λ shift and λ flex are the corresponding revenue coefficients, C j (t+i) is the operation cost of the jth adjustable decision variable at the future t+i time; the adjustable decision variable includes 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 the power supply stability in the prediction time domain length is as follows:

[0143]

[0144] Wherein, N p is the prediction time domain length, P j (t+i) is the output of the jth adjustable decision variable at the future t+i time, λ j is the corresponding operation 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 constraint conditions of the microgrid operation scheduling 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 constraint: Electric vehicle energy storage battery capacity constraint: Electric vehicle energy storage battery charging and discharging power constraint: Photovoltaic panel, diesel generator and gas turbine output constraint:

[0146]

[0147] Movable load constraint:

[0148] Elastic load constraints:

[0149] P PV (t+i) represents the actual output of the photovoltaic panel at the i-th future time (i = 1, 2, …, N p ). P DE (t+i) represents the actual output of the diesel generator at the i-th future time. P MT (t+i) represents the actual output of the gas turbine at the i-th future time. P is the total amount of translatable load, is the upper limit of the elastic load.

[0150] The real-time rolling optimization process of the rolling optimization strategy is as follows: in each control period, the LSTM model is used to predict the load demand at the future N p time points At the same time, combined with real-time operation data and weather forecast data, the power supply stability index R supply (t+N p ) in the future time domain is estimated.

[0151] Solving the optimization model, the optimal operation scheduling strategy of the microgrid power variable at the future N c time points (N c ≤N p ) is obtained: and

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

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

[0154] Embodiment 2

[0155] Referring to Figure 2 , a second embodiment of the present application is provided, which 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 forecasting module, a capacity configuration optimization module, and a scheduling and operation module.

[0157] The data acquisition module acquires microgrid power supply variable data, microgrid load data (including fixed load data, movable load data, and flexible load data), microgrid energy storage data, and historical meteorological data of the microgrid's location. It then performs time-based matching between the acquired microgrid load data and the historical meteorological data of the microgrid's location to form a microgrid load dataset.

[0158] The microgrid load demand forecasting module constructs a microgrid load demand forecasting model. Based on the microgrid load dataset, it trains the microgrid load demand forecasting model to obtain microgrid load forecasting results.

[0159] The capacity configuration optimization module constructs a capacity configuration optimization model for microgrid adjustable elements based on the collected microgrid load data and microgrid energy storage data. The capacity configuration optimization model for microgrid adjustable elements aims to balance maximizing power supply revenue and maximizing power supply stability.

[0160] The scheduling and operation module inputs the microgrid load forecast results into the microgrid capacity configuration optimization model to calculate the distribution network capacity configuration scheme; based on the calculated distribution network capacity configuration scheme, it executes the microgrid operation optimization scheme using a rolling optimization method.

[0161] Example 3

[0162] Figure 3 This is a schematic diagram of an electronic device structure provided in one 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 code, which, when executed by the one or more processors, can perform the above-described method for adjusting the capacity configuration and operation optimization of adjustable elements in a flexible AC / DC microgrid.

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

[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, etc.

[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 micro-grid adjustable element capacity configuration and operation optimization method provided by the present application.

[0166] The flexible AC / DC micro-grid adjustable element capacity configuration and operation optimization method comprises the following steps: acquiring micro-grid power variable data, collecting micro-grid load data, the micro-grid load data comprising fixed load data, translatable load data and elastic load data, collecting micro-grid energy storage data and historical weather data of a region where the micro-grid is located, matching the collected micro-grid load data and the historical weather data of the region where the micro-grid is located in time to form a micro-grid load data set; constructing a micro-grid load demand prediction model, training the micro-grid load demand prediction model based on the micro-grid load data set to obtain a micro-grid load prediction result; constructing a capacity configuration optimization model of a micro-grid adjustable element based on the collected micro-grid load data and the micro-grid energy storage data; the capacity configuration optimization model of the micro-grid adjustable element taking the maximization of power supply benefit and the maximization of power supply stability as the target; inputting the micro-grid load prediction result into the micro-grid capacity configuration optimization model to calculate a power distribution network capacity configuration scheme; and executing a micro-grid operation optimization scheme in a rolling optimization manner based on the calculated power distribution network capacity configuration scheme.

[0167] Further, the electronic device 500 can further include a user interface 508. Of course, Figure 3 The architecture shown is only exemplary, and when implementing different devices, some components shown in the electronic device can be omitted Figure 3 according to actual needs.

[0168] Embodiment 4

[0169] Figure 4 is a structural diagram of a computer readable storage medium provided by one embodiment of the present application.

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

[0171] The computer readable storage medium 600 stores computer readable instructions.

[0172] When the computer readable instructions are run by the processor, the flexible AC / DC micro-grid adjustable element capacity configuration and operation optimization method according to the embodiment of the present application described with reference to the above figures can be executed.

[0173] The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory, for example, can include random access memory (RAM), cache memory, and the like. The non-volatile memory, for example, can include read only memory (ROM), hard disk, flash memory, and the like. In addition, according to the embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as a computer software program.

[0174] For example, the present application provides a non-transitory machine readable storage medium, the non-transitory machine readable storage medium stores machine readable instructions, the machine readable instructions can be run by a processor to execute instructions corresponding to the method steps provided by the present application, for example: obtaining micro-grid power supply variable data, collecting micro-grid load data, the micro-grid load data including fixed load data, translatable load data and elastic load data, collecting micro-grid energy storage data and historical weather data of the region where the micro-grid is located, matching the collected micro-grid load data and historical weather data of the region where the micro-grid is located in time to form a micro-grid load data set; constructing a micro-grid load demand prediction model, training the micro-grid load demand prediction model based on the micro-grid load data set, for obtaining micro-grid load prediction results; based on the collected micro-grid load data and micro-grid energy storage data, constructing a capacity configuration optimization model of micro-grid adjustable elements; the capacity configuration optimization model of micro-grid adjustable elements takes balancing the maximum of power supply benefit and the maximum of power supply stability as the target; inputting the micro-grid load prediction results into the micro-grid capacity configuration optimization model, calculating the power distribution network capacity configuration scheme; based on the calculated power distribution network capacity configuration scheme, using rolling optimization method, executing micro-grid operation optimization scheme.

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

[0176] The above-mentioned order of steps for the method is only for illustration, and the steps of the method of the present application are not limited to the above-mentioned specific order, unless otherwise specifically described.

[0177] In addition, in some embodiments, the present application 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 application. Therefore, the present application also covers the recording medium storing the program for executing the method according to the present application.

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

[0179] The specific embodiments described above are further explained in connection with the purposes, technical solutions, and beneficial effects of the present application. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for capacity configuration and operation optimization of adjustable elements in a flexible AC / DC microgrid, characterized in that, The method comprises the following steps: acquiring micro-grid power variable data, collecting micro-grid load data, the micro-grid load data including fixed load data, translatable load data and elastic load data, collecting micro-grid energy storage data and historical weather data of the region where the micro-grid is located, matching the collected micro-grid load data and the historical weather data of the region where the micro-grid is located in time to form a micro-grid load data set; constructing a micro-grid load demand prediction model, training the micro-grid load demand prediction model based on the micro-grid load data set to obtain a micro-grid load prediction result; based on the collected micro-grid load data and micro-grid energy storage data, constructing a capacity configuration optimization model of the micro-grid adjustable element; the capacity configuration optimization model of the micro-grid adjustable element takes maximizing power supply stability and maximizing power supply benefit as the target; inputting the micro-grid load prediction result into the micro-grid capacity configuration optimization model to calculate a power distribution network capacity configuration scheme; based on the calculated power distribution network capacity configuration scheme, a rolling optimization method is used to execute a micro-grid operation optimization scheme; establishing a capacity configuration optimization model of the micro-grid adjustable element, the capacity configuration optimization model of the micro-grid adjustable element including maximizing power supply stability and maximizing power supply benefit, the calculation formula being as follows: max[aR supply + βR profit ] wherein R supply is the power supply stability index, and a is the adjustment coefficient of the power supply stability index; R profit is the power supply benefit index, and β is the adjustment coefficient of the power supply benefit index; Configuring microgrid power source variables and microgrid energy storage variables, including the capacity of photovoltaic panels The capacity of diesel generators The capacity of gas turbines The capacity of energy storage batteries And the capacity of energy storage batteries of electric vehicles the target function of maximizing power supply stability is: Wherein, R supply is the power supply stability index, EENS is the expected not power supply, E total is the total load demand, E total According to the micro-grid load demand prediction LSTM model prediction the target function of maximizing power supply benefit is: C total = C PV (t) + C DE (t) + C MT (t) + C batt (t) + C EV (t) where T is the optimized time length, P shift (t) and P flex (t) are the output of the movable load and the elastic load at the tth time, respectively, λ shift and λ flex are the benefit coefficients of the movable load and the 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 the photovoltaic panel, the diesel generator, the gas turbine, the energy storage battery and the electric vehicle at the tth time, respectively; waste(t) is a loss type negative benefit impact factor; f(t) is a periodic probability adjustment function of operation cost, expressed as: where A is the amplitude, controlling the magnitude of the periodic variation; T period is the period length, indicating the period of the cost variation; and φ is the phase, controlling the starting point of the periodic variation. the loss type negative benefit influencing factor waste(t) is expressed as: waste(t) = β1 · E waste (t) + β2 · I idle (t); wherein E waste (t) represents the energy loss amount at the tth time; I idle (t) represents the equipment idle condition at the tth time; β1 and β2 are the negative benefit weight coefficients of energy loss and equipment idle, respectively. 2.The flexible AC / DC microgrid adjustable element capacity configuration and operation optimization method of claim 1, wherein, The micro-grid 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). Collecting microgrid load data P load (t), the microgrid load data P load (t) comprising fixed load data Translatable load data and elastic load data Collecting microgrid energy storage data, including the charge and discharge power P batt (t) of the energy storage battery and the electric vehicle energy storage battery charge and discharge power P EV (t) and the electric vehicle energy storage battery capacity data The historical meteorological data of the area where the micro-grid is located is acquired, including temperature data T(t) and humidity data H(t), and is combined with the micro-grid load data P loah (t) at the same time to obtain an augmented micro-grid load data set. 3.The method of claim 2, wherein, a long short-term memory artificial neural network (LSTM) model is selected as the architecture of the micro-grid load demand prediction model; a sliding time window method is used to construct samples of the micro-grid load data set, the window size being k and the sliding step being s; that is, each sample contains k consecutive historical data, and the starting positions of adjacent samples are different by s time steps; the constructed samples are divided into a training set, a validation set and a test set; an LSTM model is built, and the model is trained using the training set data; a mean square error (MSE) is used as the loss function; Performance evaluation and hyperparameter tuning of the trained LSTM model using validation set data, the hyperparameters including the number of hidden layers n gidden , the number of hidden units n units , and the learning rate η; the test set data is used to evaluate the performance of the optimal LSTM model, and the evaluation indexes include mean absolute error (MAE) and root mean square error (RMSE); obtain the trained micro-grid load demand prediction LSTM model f LSTM obtain the load demand prediction value for the future time period of the micro-grid load demand prediction 4. The flexible AC / DC micro-grid adjustable element capacity configuration and operation optimization method according to claim 3, characterized in that the constraint conditions of the target function of the capacity configuration optimization model of the micro-grid adjustable 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 panel, diesel generator and gas turbine capacity constraints, and photovoltaic panel, diesel generator and gas turbine output constraints; wherein Load balancing 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: Photovoltaic panels, diesel generators and gas turbines power output constraints: wherein, and are lower and upper limits of the energy storage battery capacity, and are lower and upper limits of the energy storage battery charge and discharge power, and are lower and upper limits of the energy storage battery capacity of the electric vehicle, and are lower and upper limits of the energy storage battery charge and discharge power of the electric vehicle, and are upper limits of the photovoltaic panel, diesel generator and gas turbine capacities, respectively.

5. The flexible AC / DC microgrid adjustability element capacity configuration and operation optimization method according to claim 4, characterized in that, The prediction result of the LSTM load prediction model As the input of the capacity configuration optimization model, it is used to describe the future load demand situation of the micro-grid; at the same time, combined with the historical meteorological data of the region where the micro-grid is located, the power supply stability of the micro-grid is calculated, and the EENS and E total ; Solving the micro-grid capacity configuration optimization model, obtaining the optimal capacity configuration scheme of the micro-grid power supply variable and the micro-grid energy storage variable and the micro-grid operation optimization based on model predictive control solves the micro-grid operation scheduling problem in a rolling optimization manner by using a model predictive control rolling optimization strategy. With the LSTM load prediction model f LSTM And micro-grid capacity configuration optimization results, build micro-grid operation optimization control function. 6.The method of claim 5, wherein, Adopt a model predictive control rolling optimization strategy to solve the micro-grid operation scheduling problem in a rolling optimization manner. The objective function of the micro-grid operation scheduling problem is to maximize the balance of power supply stability and power supply income in the prediction time domain: wherein N p is the prediction horizon length, R supply (t+i) is the power supply stability index at the future t+i time, R profit (t+i) is the benefit index at the future t+i time, and ω1 and ω2 are the weight coefficients of the stability target and the benefit target, respectively. The revenue indicator R in the prediction time domain length profit The calculation of (t+i) is as follows: where P shift (t+i) and P flex (t+i) are the outputs of the shiftable load and the elastic load at the future time t+i, respectively, λ shift and λ flex are the corresponding benefit coefficients, and C j (t+i) is the operating cost of the jth adjustable decision variable at the future time t+i. The calculation method of power supply stability in the prediction time domain length is: where N p is the prediction horizon length, P j is the output of the jth adjustable decision variable at the future time t + i, λ j is the corresponding operating cost weight coefficient; R supply is the supply stability index at the end of the prediction horizon, and ω is the weight coefficient of the stability target. p is the output of the jth adjustable decision variable at the future time t + i, λ j is the corresponding operating cost weight coefficient; R supply is the supply stability index at the end of the prediction horizon, and ω is the weight coefficient of the stability target. The constraint conditions of the micro-grid operation scheduling problem include: load balance constraint: ∑ j P j (t+i)=P load (t+i); energy storage battery capacity constraint: energy storage battery charge and discharge power constraint: electric vehicle energy storage battery capacity constraint: electric vehicle energy storage battery charge and discharge power constraint: photovoltaic panel, diesel generator and gas turbine output constraint: Translational load constraint: Elastic load constraints: where P PV (t+i) represents the actual output of the photovoltaic panel at the future i-th time instant (i = 1, 2,..., N p (t+i) represents the actual output of the photovoltaic panel at the future i-th time instant (i = 1, 2,..., N Popt represents the optimal capacity configuration of the photovoltaic panel, DE (t+i) represents the actual output of the diesel generator at the future i-th time instant (i = 1, 2,..., N Popt represents the optimal capacity configuration of the diesel generator, MT (t+i) represents the actual output of the gas turbine at the future i-th time instant (i = 1, 2,..., N Popt represents the optimal capacity configuration of the gas turbine, is the total amount of shiftable load, is the upper limit of the elastic load. 7.The method of claim 6, wherein, The real-time rolling optimization process of the rolling optimization strategy is as follows: in each control period, the load demand at N future time points is predicted by using an LSTM model p At the same time, the power supply stability index R supply (t+N p ) in the future time domain is estimated in combination with real-time operation data and meteorological prediction data.​ Solving the optimization model, obtaining the optimal operation scheduling strategy of micro-grid power supply variables and micro-grid energy storage variables at future N c time points; decoding the optimization results into control instructions and issuing them to the control systems of each adjustable element to realize real-time optimization scheduling of the micro-grid.

8. A system for capacity configuration and operation optimization of a flexible AC / DC microgrid adjustable elements, which is used to implement the method for capacity configuration and operation optimization of a flexible AC / DC microgrid adjustable elements according to any one of claims 1 to 7, characterized in that, It includes: A data acquisition module, a micro-grid load demand prediction module, a capacity configuration optimization module, and a scheduling operation module; The data acquisition module acquires micro-grid power supply variable data, acquires micro-grid load data, acquires micro-grid energy storage data, and acquires historical weather data of the region where the micro-grid is located, matches the collected micro-grid load data and the historical weather data of the region where the micro-grid is located in time to form a micro-grid load data set; The micro-grid load demand prediction module constructs a micro-grid load demand prediction model, trains the micro-grid load demand prediction model based on the micro-grid load data set, and obtains a micro-grid load prediction result; The capacity configuration optimization module constructs a capacity configuration optimization model of the micro-grid adjustable element based on the collected micro-grid load data and micro-grid energy storage data, and takes the balance of maximum power supply income and maximum power supply stability as the target; The scheduling operation module inputs the micro-grid load prediction result into the micro-grid capacity configuration optimization model, calculates the distribution network capacity configuration scheme, and adopts a rolling optimization method to execute the micro-grid operation optimization scheme based on the calculated distribution network capacity configuration scheme.

9. An electronic device, comprising: It includes: 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 micro-grid adjustable element capacity configuration and operation optimization method of any one of claims 1-7 by calling the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: An instruction is stored, which, when executed on a computer, causes the computer to execute the flexible AC / DC micro-grid adjustable element capacity configuration and operation optimization method of any one of claims 1-7.

Images