Regional power grid-oriented low-carbon regulation and control method and system, terminal equipment and storage medium

Abstract

The invention discloses a low-carbon regulation and control method and system for a regional power grid, terminal equipment and a storage medium, and the method comprises the steps: predicting the future carbon emission of a thermal power generating unit through constructing a future carbon emission prediction model, and combining the real-time operation data of each unit; according to the method, active balance constraints and constraint conditions of a power grid lowest operation cost objective function and a power grid lowest carbon emission objective function are constructed, then output power of each unit meeting the objective function and the constraint conditions is calculated, and a power grid regulation and control strategy is determined according to the output power of each unit, so that the rationality of the power grid regulation and control strategy is improved; in the prior art, a low-carbon regulation strategy determined only according to the carbon emission generated by each generator set during power generation lacks the consideration of the operation cost required by each generator set during operation in a power grid system, so that the reasonability of the regulation strategy is low; and the operation cost required by the power grid system in the low-carbon regulation and control process is too high.

Description

Technical Field

[0001] The present invention relates to the field of low-carbon regulation, and in particular to a low-carbon regulation method, system, terminal equipment and storage medium for a regional power grid. Background Art

[0002] In the field of power grid dispatching and control, real-time power balance and carbon emission control have always been key research directions. With the widespread application of renewable energy (such as wind power and solar energy), how to balance the power supply of traditional energy and renewable energy in the power grid while reducing carbon emissions has become a major challenge in power grid dispatching.

[0003] The existing technology usually calculates the carbon emissions generated by each generator set when generating electricity according to the operating conditions of each generator set in the power grid system, and then controls the operation of each generator set according to the carbon emissions to achieve low-carbon regulation. However, this method only obtains a low-carbon regulation strategy based on the carbon emissions generated by each generator set when generating electricity, and lacks consideration of the operating costs required for the operation of each generator set in the power grid system, resulting in low rationality of the regulation strategy. Therefore, the low-carbon regulation strategy formulated by this method does not take into account the operating costs of the generator sets, resulting in excessively high operating costs of the power grid system. Summary of the invention

[0004] The present invention provides a low-carbon control method, system, terminal device and storage medium for regional power grids, which can solve the problem that the low-carbon control strategy in the prior art is determined only according to the carbon emissions generated by each generator set when generating electricity, resulting in low rationality of the control strategy due to the lack of consideration of the operating costs required for the operation of each generator set in the power grid system, which in turn leads to excessively high operating costs required for the power grid system during the low-carbon control process.

[0005] In order to solve the above technical problems, an embodiment of the present invention provides a low-carbon control method for a regional power grid, including:

[0006] Acquire the operation data and load demand data of each unit in the regional power grid; wherein the operation data of each unit includes the operation data of the thermal power generating unit and the operation data of the hydropower generating unit;

[0007] According to the operation data of the thermal power generating unit, the future carbon emission of the thermal power generating unit is predicted by using the trained future carbon emission prediction model;

[0008] According to the operation data of each generator set, load demand data and future carbon emissions of thermal power generator sets, the minimum operation cost objective function of the power grid, the minimum carbon emission objective function of the power grid and constraint conditions are constructed; wherein the constraint conditions include active balancing constraints, hydropower generator set constraints, thermal power generator set constraints, energy storage constraints and line constraints;

[0009] Under the constraints, the objective function of the lowest operation cost of the power grid and the objective function of the lowest carbon emission of the power grid are solved to obtain the output power of each generator set when the operation cost and carbon emission are the lowest;

[0010] The regional power grid is regulated according to the output power of each generator set.

[0011] Furthermore, the model training of the future carbon emission prediction model includes:

[0012] Obtain historical operating data and historical carbon emissions of each thermal power generating unit in the regional power grid;

[0013] According to the historical operation data and historical carbon emission data of each thermal power generating unit, a characteristic relationship diagram of each thermal power generating unit is constructed through the input layer of the future carbon emission prediction model to be trained;

[0014] The feature relationship graph of each thermal power generating unit is convolved through the convolution layer of the future carbon emission prediction model to be trained to obtain the feature matrix of each thermal power generating unit after convolution;

[0015] The feature matrix of each thermal power generating unit after convolution is fully connected through the fully connected layer of the future carbon emission prediction model to be trained to obtain the future carbon emission of each thermal power generating unit;

[0016] The loss value is calculated by comparing the future carbon emissions and historical carbon emissions of each thermal power generating unit, and the parameters of the future carbon emissions prediction model to be trained are optimized according to the loss value until the loss value converges to obtain a trained future carbon emissions prediction model.

[0017] Furthermore, the calculation formula of the convolutional layer of the future carbon emission prediction model to be trained is as follows:

[0018]

[0019] Among them, the H (l+1) represents the convolution feature matrix output by the l+1th convolution layer; the σ represents the activation function of the convolution layer: A is the adjacency matrix of the characteristic relationship graph of each thermal power generating unit, and I N represents the identity matrix; express The degree matrix of The H (l) Represents the features of the output of the I-th fully connected layer; the W (l) represents the weight matrix of the I-th convolutional layer; the b (l) Represents the bias vector of the I-th convolutional layer.

[0020] Furthermore, the calculation formula of the fully connected layer of the future carbon emission prediction model to be trained is as follows:

[0021] y (q+1) =g(y (q) W (q) +b (q) );

[0022] Among them, the y (q+1) represents the output result of the q+1th fully connected layer; g represents the activation function of the fully connected layer; y (q) represents the output result of the qth fully connected layer; the W (q) represents the weight matrix of the qth fully connected layer; the b (q) Represents the offset vector of the qth fully connected layer.

[0023] Furthermore, the minimum grid operation cost objective function, the minimum grid carbon emission objective function and constraint conditions are constructed based on the operation data of each generator set, the load demand data and the future carbon emission of the thermal power generator set, including:

[0024] The grid minimum operating cost objective function is:

[0025]

[0026] Wherein, j represents the jth unit; F Gj Represents the operating cost of thermal power generating units; hj represents the operating cost of the hydroelectric generator set; Cj Represents the unit operating cost of energy storage; the F lossj represents the line loss cost; the N G 、N h 、N C and N loss Respectively represent the total number of thermal generating units, hydro generating units, energy storage units and lines;

[0027] The grid minimum carbon emission objective function is:

[0028]

[0029] Among them, the represents the output power of the jth thermal power generating unit at the tth time; represents the future carbon emissions of the j-th thermal power generating unit at time t;

[0030] The active balance constraint is:

[0031] ∑P gen =∑P load +Ploss ;

[0032] Among them, the P gen Represents the generated power; the P load Indicates the load demand power; the P loss Indicates line loss power;

[0033] The constraints of the hydroelectric generator set are:

[0034] P hydro，min ≤P hydro ≤P hydro，max ;

[0035] Among them, the P hydro Represents the output power of the hydroelectric generator set; the P hydro，min and P hydro，max Respectively represent the minimum output power and maximum output power of the hydroelectric generating unit;

[0036] The constraints of the thermal power generating set are:

[0037] P thermal，min ≤P thermal ≤P thermal，max ;

[0038] Among them, the P thermal Represents the output power of the thermal power generating unit; the P thermal，min and P thermal，max Respectively represent the minimum output power and maximum output power of the thermal power generating unit;

[0039] The energy storage unit constraint is:

[0040] P ES，min ≤P ES ≤P ES，max ;

[0041] Among them, the P ES Indicates the charging and discharging power of the energy storage unit; the P ES，min and P ES，max They represent the minimum charging and discharging power and the maximum charging and discharging power of the energy storage unit respectively;

[0042] The line constraints are:

[0043] P line ≤P line，max ;

[0044] Among them, the P line Indicates the actual transmission power of the line; the P line，max Indicates the maximum transmission power of the line.

[0045] Furthermore, the calculation method of the thermal power generating unit operation cost, the hydropower generating unit operation cost, the energy storage unit operation cost and the line loss cost is as follows:

[0046] The calculation method of the operating cost of the thermal power generating unit is:

[0047]

[0048] Among them, the F Gj represents the operating cost of the jth thermal power generating unit; Gj represents the output power of the jth thermal power generating unit; j 、b j and c j represent the first cost coefficient, the second cost coefficient and the third cost coefficient of the j-th thermal power generating unit respectively;

[0049] The calculation method of the operating cost of the hydroelectric generating unit is:

[0050] F hj =d j ·P hj +e j ;

[0051] Among them, the F hj represents the operating cost of the j-th hydroelectric generating unit; hj represents the output power of the jth hydroelectric generating unit; the d j and e j denote the first cost coefficient and the second cost coefficient of the j-th hydroelectric generating unit respectively;

[0052] The calculation method of the energy storage unit operating cost is:

[0053]

[0054] Among them, the F Cj represents the operating cost of the j-th energy storage unit; represents the charging power of the jth energy storage unit; represents the discharge power of the jth energy storage unit; the f j and g j denote the first cost coefficient and the second cost coefficient of the j-th energy storage unit respectively;

[0055] The line loss cost is calculated as follows:

[0056] F lossj =h j ·P j ;

[0057] Among them, the Flossj represents the line loss cost of the jth generator set; j represents the output power of the jth generator set; j Represents the line loss coefficient of the j-th generator set.

[0058] Furthermore, solving the objective function of the minimum operation cost of the power grid and the objective function of the minimum carbon emission of the power grid under the constraint conditions to obtain the output power of each generator set when the operation cost is the lowest and the carbon emission is the lowest includes:

[0059] Under the constraints, the Hippo optimization algorithm is used to solve the objective function of the minimum operating cost of the power grid and the objective function of the minimum carbon emissions of the power grid, and the output power of each generator set when the operating cost and carbon emissions are the lowest is obtained.

[0060] Based on the above method embodiment, the present invention provides a corresponding system embodiment;

[0061] An embodiment of the present invention provides a low-carbon control system for a regional power grid, comprising: a data acquisition module, a carbon emission prediction module for thermal power units, an objective function and constraint construction module, a generator output power calculation module and a control module;

[0062] The data acquisition module is used to obtain the operating data and load demand data of each unit in the regional power grid; wherein the operating data of each unit includes the operating data of the thermal power generating unit and the operating data of the hydropower generating unit;

[0063] The thermal power unit carbon emission prediction module is used to predict carbon emissions based on the operating data of the thermal power unit through a trained future carbon emission prediction model to obtain the future carbon emissions of the thermal power unit;

[0064] The objective function and constraint building module is used to build the minimum operation cost objective function of the power grid, the minimum carbon emission objective function of the power grid and the constraint conditions according to the operation data of each generator set, the load demand data and the future carbon emission of the thermal power generator set; wherein the constraint conditions include active balance constraints, hydropower generator set constraints, thermal power generator set constraints, energy storage constraints and line constraints;

[0065] The generator set output power calculation module is used to solve the minimum operation cost objective function of the power grid and the minimum carbon emission objective function of the power grid under the constraint conditions, and obtain the output power of each generator set when the operation cost is the lowest and the carbon emission is the lowest;

[0066] The power grid control module is used to control the regional power grid according to the output power of each generator set.

[0067] Based on the above-mentioned method embodiment, the present invention provides a corresponding terminal device embodiment, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, a low-carbon control method for a regional power grid as described in the present invention is implemented.

[0068] Based on the above-mentioned method embodiment, the present invention provides a corresponding computer-readable storage medium embodiment, including: a stored computer program, which controls the device where the computer-readable storage medium is located to execute a low-carbon control method for a regional power grid as described in the present invention when the computer program is running.

[0069] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0070] The present invention uses a trained future carbon emission prediction model to predict carbon emissions based on the operating data of thermal power units to obtain the future carbon emissions of thermal power units, and constructs a power grid minimum operating cost objective function, a power grid minimum carbon emission objective function active balance constraints and constraint conditions based on the operating data of each unit and the future carbon emissions of the thermal power units. Finally, according to the power grid minimum operating cost objective function, the power grid minimum carbon emission objective function and the constraint conditions, the output power of each unit is calculated, and the power grid control strategy is determined according to the output power of each unit. That is, the present invention predicts the future carbon emissions of thermal power units by constructing a future carbon emission prediction model, and combines The real-time operating data of each unit is used to construct the objective function of the minimum operating cost of the power grid and the objective function of the minimum carbon emissions of the power grid to actively balance the constraints and constraints, and then calculate the output power of each unit that meets the objective function and the constraints, and determine the power grid control strategy based on the output power of each unit, which improves the rationality of the power grid control strategy and solves the problem that the existing technology only determines the low-carbon control strategy based on the carbon emissions generated by each generating unit when generating electricity, which lacks consideration of the operating costs required for the operation of each generating unit in the power grid system, resulting in low rationality of the control strategy, and then leads to excessively high operating costs required for the power grid system during the low-carbon control process. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 : A flowchart of the steps of a low-carbon control method for a regional power grid provided by an embodiment of the present invention;

[0072] Figure 2 : A system structure diagram of a low-carbon control system for a regional power grid provided by an embodiment of the present invention;

[0073] Figure 3 , which is a flow chart of generating a low-carbon control strategy based on the Hippo optimization algorithm provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0074] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0075] In the description of the present invention, it should be understood that the terms "first", "second" and "third" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features.

[0076] Embodiment 1:

[0077] Reference Figure 1 , is a flowchart of a low-carbon control method for a regional power grid provided by an embodiment of the present invention, the method comprising at least the following steps:

[0078] Step S1: acquiring operation data and load demand data of each unit in the regional power grid; wherein the operation data of each unit includes operation data of thermal power generating units and operation data of hydropower generating units;

[0079] In this embodiment, the operating data and load demand data of each unit in the regional power grid can be obtained through corresponding data sensors and monitoring equipment; wherein the operating data of each unit includes the operating data of the thermal power generating unit and the operating data of the hydropower generating unit; the operating data of the thermal power generating unit includes but is not limited to the thermal power output power, power generation, operating parameters of the thermal power generating unit, resource consumption and carbon emissions; the operating data of the hydropower generating unit includes but is not limited to the hydropower output power, power generation and operating parameters of the hydropower generating unit.

[0080] Step S2: According to the operation data of the thermal power generating unit, the future carbon emission of the thermal power generating unit is predicted by using the trained future carbon emission prediction model to obtain the future carbon emission of the thermal power generating unit;

[0081] In this embodiment, the future carbon emission prediction model adopts the GCN neural network.

[0082] In this embodiment, the model training of the future carbon emission prediction model includes:

[0083] Obtain historical operating data and historical carbon emissions of each thermal power generating unit in the regional power grid;

[0084] According to the historical operation data and historical carbon emission data of each thermal power generating unit, a characteristic relationship diagram of each thermal power generating unit is constructed through the input layer of the future carbon emission prediction model to be trained;

[0085] The feature relationship graph of each thermal power generating unit is convolved through the convolution layer of the future carbon emission prediction model to be trained to obtain the feature matrix of each thermal power generating unit after convolution;

[0086] The feature matrix of each thermal power generating unit after convolution is fully connected through the fully connected layer of the future carbon emission prediction model to be trained to obtain the future carbon emission of each thermal power generating unit;

[0087] The loss value is calculated by comparing the future carbon emissions and historical carbon emissions of each thermal power generating unit, and the parameters of the future carbon emissions prediction model to be trained are optimized according to the loss value until the loss value converges to obtain a trained future carbon emissions prediction model.

[0088] In this embodiment, the expression for constructing the characteristic relationship diagram of each thermal power generating unit is:

[0089] In this embodiment, the calculation formula of the convolutional layer of the future carbon emission prediction model to be trained is as follows:

[0090]

[0091] Among them, the H (l+1) represents the convolution feature matrix output by the l+1th convolution layer; the σ represents the activation function of the convolution layer; the A is the adjacency matrix of the characteristic relationship graph of each thermal power generating unit, and I N represents the identity matrix; express The degree matrix of The H (l) Represents the features of the output of the lth fully connected layer; the W (l) represents the weight matrix of the lth convolutional layer; the b (l) Represents the bias vector of the lth convolutional layer.

[0092] In this embodiment, the calculation formula of the fully connected layer of the future carbon emission prediction model to be trained is as follows:

[0093] y (q+1) =g(y (q) W (q) +b (q) );

[0094] Among them, the y (q+1) represents the output result of the q+1th fully connected layer; g represents the activation function of the fully connected layer; y (q) represents the output result of the qth fully connected layer; the W (q)represents the weight matrix of the qth fully connected layer; the b (q) Represents the offset vector of the qth fully connected layer.

[0095] In this embodiment, the loss function for calculating the loss value includes but is not limited to the mean square error function and the mean absolute error function; the method for optimizing the parameters of the future carbon emission prediction model to be trained includes but is not limited to the gradient descent method and the Adam optimizer.

[0096] Step S3: constructing a grid minimum operation cost objective function, a grid minimum carbon emission objective function and constraint conditions according to the operation data of each generator set, load demand data and future carbon emissions of the thermal generator set; wherein the constraint conditions include active balancing constraints, hydroelectric generator set constraints, thermal generator set constraints, energy storage constraints and line constraints;

[0097] In this embodiment, the grid minimum operating cost objective function is:

[0098]

[0099] Wherein, j represents the jth unit; F Gj Represents the operating cost of thermal power generating units; hj represents the operating cost of the hydroelectric generator set; Cj Represents the unit operating cost of energy storage; the F lossj represents the line loss cost; the N G 、N h 、N C and N loss Respectively represent the total number of thermal power generating units, hydropower generating units, energy storage units and lines.

[0100] In this embodiment, the grid minimum carbon emission objective function is:

[0101]

[0102] Among them, the represents the output power of the jth thermal power generating unit at the tth time; Represents the future carbon emissions of the j-th thermal power generating unit at the t-th time.

[0103] In this embodiment, the active balancing constraint is:

[0104] ∑P gen =∑P load +P loss ;

[0105] Among them, the P gen Represents the generated power; the Pload Indicates the load demand power; the P loss Indicates the line loss power.

[0106] In this embodiment, the constraints of the hydroelectric generator set are:

[0107] P hydro，min ≤P hydro ≤P hydro，max ;

[0108] Among them, the P hydro Represents the output power of the hydroelectric generator set; the P hydro，min and P hydro，max They represent the minimum output power and maximum output power of the hydroelectric generating unit respectively.

[0109] In this embodiment, the constraints of the thermal power generating set are:

[0110] P thermal，min ≤P thermal ≤P thermal，max ;

[0111] Among them, the P thermal Represents the output power of the thermal power generating unit; the P thermal，min and P thermal，max They respectively represent the minimum output power and maximum output power of the thermal power generating unit.

[0112] In this embodiment, the energy storage unit constraint is:

[0113] P ES，min ≤P ES ≤P ES，max ;

[0114] Among them, the P ES Indicates the charging and discharging power of the energy storage unit; the P ES，min and P ES，max They respectively represent the minimum charging and discharging power and the maximum charging and discharging power of the energy storage unit.

[0115] In this embodiment, the line constraints are:

[0116] P line ≤P line，max ;

[0117] Among them, the P line Indicates the actual transmission power of the line; the P line，max Indicates the maximum transmission power of the line.

[0118] In this embodiment, the calculation method of the thermal power generating unit operation cost, the hydropower generating unit operation cost, the energy storage unit operation cost and the line loss cost is as follows:

[0119] The calculation method of the operating cost of the thermal power generating unit is:

[0120]

[0121] Among them, the F Gj represents the operating cost of the jth thermal power generating unit; Gj represents the output power of the jth thermal power generating unit; j 、b j and c j Respectively represent the first cost coefficient, the second cost coefficient and the third cost coefficient of the j-th thermal power generating set, and the first cost coefficient, the second cost coefficient and the third cost coefficient of the thermal power generating set can be set by those skilled in the art according to actual conditions;

[0122] The calculation method of the operating cost of the hydroelectric generating unit is:

[0123] F hj =d j ·P hj +e j ;

[0124] Among them, the F hj represents the operating cost of the j-th hydroelectric generating unit; hj represents the output power of the jth hydroelectric generating unit; the d j and e j They respectively represent the first cost coefficient and the second cost coefficient of the j-th hydroelectric generating set, and the first cost coefficient and the second cost coefficient of the hydroelectric generating set can be set by those skilled in the art according to actual conditions;

[0125] The calculation method of the energy storage unit operating cost is:

[0126]

[0127] Among them, the F Cj represents the operating cost of the j-th energy storage unit; represents the charging power of the jth energy storage unit; represents the discharge power of the jth energy storage unit; the f j and g j Respectively represent the first cost coefficient and the second cost coefficient of the j-th energy storage unit, and the first cost coefficient and the second cost coefficient of the energy storage unit can be set by those skilled in the art according to actual conditions;

[0128] The line loss cost is calculated as follows:

[0129] Flossj =h j ·P j ;

[0130] Among them, the F lossj represents the line loss cost of the jth generator set; j represents the output power of the jth generator set; j represents the line loss coefficient of the j-th generator set, and the line loss coefficient of the generator set can be set by those skilled in the art according to actual conditions.

[0131] Step S4: solving the objective function of the minimum operation cost of the power grid and the objective function of the minimum carbon emission of the power grid under the constraint conditions, and obtaining the output power of each generator set when the operation cost is the lowest and the carbon emission is the lowest;

[0132] Step S5: regulating the regional power grid according to the output power of each generator set.

[0133] In this embodiment, under the constraints, the Hippo optimization algorithm is used to solve the grid minimum operating cost objective function and the grid minimum carbon emission objective function to obtain the output power of each generator set when the operating cost is the lowest and the carbon emission is the lowest.

[0134] In this embodiment, the stages of the Hippo optimization algorithm are as follows:

[0135] 1. Hippo position update (exploration phase):

[0136] In the process of multi-objective supervision of the power grid, the position of the hippo group is initialized, expressed as the power output scheme of different generators, and the fitness of the group is calculated based on the operating cost and carbon emission targets. The hippos will randomly explore in space to find potential optimal solutions. In this stage, the hippos in the hippo group will explore by moving in the river or pond. The hippo group usually consists of multiple adult female hippos, young hippos, adult male hippos and a dominant male hippo. The dominant male hippo is responsible for protecting the territory, and its position is determined by the objective function value in the current iteration.

[0137] The position of the hippopotamus is represented as a vector of decision variables, and the position of the entire group is represented by a matrix. In the initial stage, the algorithm is initialized by randomly generating the positions of the hippopotamus. The specific formula is:

[0138] χ i，j =lb j +r·(ub j -lb j );

[0139] Among them, the x i，j is the position of the i-th candidate solution; the ubj and lb j represent the upper and lower bounds of the j-th decision variable respectively; r is a random number between 0 and 1.

[0140] In order to simulate the random movement of hippos in the water, the position update of the hippopotamus also refers to the position of the dominant hippopotamus, and the formula is as follows:

[0141] χ i，j = x i，j +y1·(D hippo -I1·χ i，j );

[0142] Among them, the x i，j is the position of the i-th candidate solution; y1 represents a random number; D hippo Indicates the position of the current optimal hippopotamus; I1 is a random number, taking a value of 1 or 2.

[0143] 2. Hippopotamus' defensive behavior (defense phase):

[0144] In the second stage, the hippos will display defensive behavior when threatened by predators. When the hippos are threatened by a "predator" with high carbon emissions or high operating costs, the algorithm calculates the distance between each hippo and the predator, and if the predator approaches, the hippo will try to adjust the power output to reduce carbon emissions or costs.

[0145] The predator's position update formula is:

[0146] Predator j =lb j +r8·(ub j -lb j );

[0147] Where: r8 is a random number used to determine the location of the predator; ub j and lb j They represent the upper and lower bounds of the j-th decision variable respectively.

[0148] The distance between the hippopotamus and the predator D i The calculation formula is:

[0149] D i =|Predator j -x i，j |;

[0150] If the predator is close to the hippo, the hippo will move quickly towards the predator and make it retreat. This process can be expressed by the following formula:

[0151]

[0152] Wherein, the RL is a random vector with Lévy distribution, which is used to simulate the random movement of the predator; the f is a random number between 2 and 4; the c is a random number between 1 and 1.5; the d is a constant; and the g is a random number between -1 and 1.

[0153] Lévy flight is a commonly used random walk model with the characteristics of long-distance jumps, which can effectively enhance the global search capability of the algorithm. The characteristics of Lévy flight simulate the sudden position change of hippos when facing predators, helping hippos quickly move away from danger.

[0154] The random motion of Lévy distribution can be expressed as follows:

[0155]

[0156] Wherein, θ is a constant of Lévy distribution; w and v are random numbers that obey uniform distribution; σ w is the scale parameter of Lévy flight, which is calculated as: Wherein, Γ is a gamma function.

[0157] Lévy maneuvers avoid being stuck in local optima by simulating long jumps, helping hippos find better positions during the defense and escape phases.

[0158] 3. Hippo escapes from predators (escape phase):

[0159] When the hippopotamus cannot repel the predator through defensive behavior, the hippopotamus will update its position to escape the "predator", that is, by re-adjusting the power output and scheduling strategy of the generator set, and continue to look for a better low-carbon regulation solution. This stage simulates the local search behavior of the hippopotamus, with the goal of finding a safer area. This behavior is achieved by generating a random new position near the hippopotamus' current position. If the new position can improve the objective function value, the hippopotamus will move to this new position.

[0160] The escape behavior of a hippopotamus can be expressed by the following formula:

[0161]

[0162] Among them, the and are the local upper and lower boundaries of the current dimension respectively; the r 10 is a random number; s1 is a randomly selected vector used to determine the scope of the local search.

[0163] In this embodiment, refer to Figure 3, which is a flowchart of generating a low-carbon control strategy based on the Hippopotamus optimization algorithm provided by an embodiment of the present invention. The Hippopotamus optimization algorithm continuously updates the position and scheduling scheme of the Hippopotamus, and repeatedly executes the exploration, defense and escape stages until the set number of iterations is met or the optimal solution is found. Each iteration evaluates the current control strategy and saves the optimal solution, thereby obtaining a power grid control strategy with the lowest power grid operation cost and the lowest power grid carbon emissions.

[0164] Embodiment 2:

[0165] Reference Figure 2 , is a system structure diagram of a low-carbon control system for a regional power grid provided by an embodiment of the present invention, the system comprising: a data acquisition module, a carbon emission prediction module for thermal power units, an objective function and constraint construction module, a generator unit output power calculation module and a control module;

[0166] The data acquisition module is used to obtain the operating data and load demand data of each unit in the regional power grid; wherein the operating data of each unit includes the operating data of the thermal power generating unit and the operating data of the hydropower generating unit;

[0167] The thermal power unit carbon emission prediction module is used to predict carbon emissions based on the operating data of the thermal power unit through a trained future carbon emission prediction model to obtain the future carbon emissions of the thermal power unit;

[0168] The objective function and constraint building module is used to build the minimum operation cost objective function of the power grid, the minimum carbon emission objective function of the power grid and the constraint conditions according to the operation data of each generator set, the load demand data and the future carbon emission of the thermal power generator set; wherein the constraint conditions include active balance constraints, hydropower generator set constraints, thermal power generator set constraints, energy storage constraints and line constraints;

[0169] The generator set output power calculation module is used to solve the minimum operation cost objective function of the power grid and the minimum carbon emission objective function of the power grid under the constraint conditions, and obtain the output power of each generator set when the operation cost is the lowest and the carbon emission is the lowest;

[0170] The power grid control module is used to control the regional power grid according to the output power of each generator set.

[0171] Based on the above method embodiment, another embodiment is provided;

[0172] Another embodiment of the present invention provides a low-carbon control terminal device for a regional power grid, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements a low-carbon control method for a regional power grid as described in any one of the above method embodiments of the present invention.

[0173] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the low-carbon regulation terminal device for regional power grids.

[0174] The low-carbon control terminal device for regional power grids can be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The low-carbon control terminal device for regional power grids can include, but is not limited to, a processor and a memory. Those skilled in the art can understand that, for example, the low-carbon control terminal device for regional power grids can also include input and output devices, network access devices, buses, etc.

[0175] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the low-carbon control terminal device for the regional power grid, and uses various interfaces and lines to connect the various parts of the entire low-carbon control terminal device for the regional power grid.

[0176] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the low-carbon control terminal device for regional power grid by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0177] Based on the above method embodiment, another embodiment is provided;

[0178] A storage medium provided in another embodiment of the present invention includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute a low-carbon control method for a regional power grid as described in any one of the above method embodiments of the present invention.

[0179] Wherein, the above-mentioned storage medium is a computer-readable storage medium. The module / unit integrated with the low-carbon control system / terminal device for regional power grids can be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as an independent product. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-O nly Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0180] It should be noted that the above-mentioned terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that the above-mentioned terminal device is merely an example and does not constitute a limitation on the terminal device. It may include more or fewer components, or a combination of certain components, or different components.

[0181] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A low-carbon control method for a regional power grid, characterized in that: include: Acquire the operation data and load demand data of each unit in the regional power grid; wherein the operation data of each unit includes the operation data of the thermal power generating unit and the operation data of the hydropower generating unit; According to the operation data of the thermal power generating unit, the carbon emission is predicted by using the trained future carbon emission prediction model to obtain the future carbon emission of the thermal power generating unit; According to the operation data of each generator set, load demand data and future carbon emissions of thermal power generator sets, the minimum operation cost objective function of the power grid, the minimum carbon emission objective function of the power grid and constraint conditions are constructed; wherein the constraint conditions include active balancing constraints, hydropower generator set constraints, thermal power generator set constraints, energy storage constraints and line constraints; Under the constraints, the objective function of the lowest operation cost of the power grid and the objective function of the lowest carbon emission of the power grid are solved to obtain the output power of each generator set when the operation cost and carbon emission are the lowest; The regional power grid is regulated according to the output power of each generator set.

2. A low-carbon control method for regional power grids according to claim 1, characterized in that: The model training of the future carbon emission prediction model includes: Obtain the historical operation data and historical carbon emissions of each thermal power generating unit in the regional power grid; According to the historical operation data and historical carbon emission data of each thermal power generating unit, a characteristic relationship diagram of each thermal power generating unit is constructed through the input layer of the future carbon emission prediction model to be trained; The feature relationship graph of each thermal power generating unit is convolved through the convolution layer of the future carbon emission prediction model to be trained to obtain the feature matrix of each thermal power generating unit after convolution; The feature matrix of each thermal power generating unit after convolution is fully connected through the fully connected layer of the future carbon emission prediction model to be trained to obtain the future carbon emission of each thermal power generating unit; The loss value is calculated by comparing the future carbon emissions and historical carbon emissions of each thermal power generating unit, and the parameters of the future carbon emissions prediction model to be trained are optimized according to the loss value until the loss value converges to obtain a trained future carbon emissions prediction model.

3. A low-carbon control method for regional power grids according to claim 2, characterized in that: The calculation formula of the convolutional layer of the future carbon emission prediction model to be trained is as follows: Among them, the H (l+1) represents the convolution feature matrix output by the I+1th convolution layer; σ represents the activation function of the convolution layer; A is the adjacency matrix of the characteristic relationship graph of each thermal power generating unit, and I N represents the identity matrix; express The degree matrix of The H (l) Represents the features of the output of the I-th fully connected layer; the W (l) represents the weight matrix of the I-th convolutional layer; the b (l) Represents the bias vector of the I-th convolutional layer.

4. A low-carbon control method for regional power grids according to claim 3, characterized in that: The calculation formula of the fully connected layer of the future carbon emission prediction model to be trained is as follows: y (q+1) =g(y (q) W (q) +b (q) ); Among them, the y (q+1) represents the output result of the q+1th fully connected layer; g represents the activation function of the fully connected layer; y (q) represents the output result of the qth fully connected layer; the W (q) represents the weight matrix of the qth fully connected layer; the b (q) Represents the offset vector of the qth fully connected layer.

5. A low-carbon control method for regional power grids according to claim 4, characterized in that: The objective function of the minimum operation cost of the power grid, the objective function of the minimum carbon emission of the power grid and the constraint conditions are constructed according to the operation data of each power generating unit, the load demand data and the future carbon emission of the thermal power generating unit, including: The grid minimum operating cost objective function is: Wherein, j represents the jth unit; F Gj Represents the operating cost of thermal power generating units; hj represents the operating cost of the hydroelectric generator set; Cj Represents the unit operating cost of energy storage; the F lossj represents the line loss cost; the N G 、N h 、N C and N loss Respectively represent the total number of thermal generating units, hydro generating units, energy storage units and lines; The grid minimum carbon emission objective function is: Among them, the represents the output power of the jth thermal power generating unit at the tth time; represents the future carbon emissions of the j-th thermal power generating unit at time t; The active balance constraint is: ∑P gen =∑P load +P loss ; Among them, the P gen Represents the generated power; the P load Indicates the load demand power; the P loss Indicates line power loss: The constraints of the hydroelectric generator set are: P hydro，min ≤P hydro ≤P hydro，max ; Among them, the P hydro Represents the output power of the hydroelectric generator set; the P hydro，min and P hydro，max Respectively represent the minimum output power and maximum output power of the hydroelectric generating unit; The constraints of the thermal power generating set are: P thermal，min ≤P thermal ≤P thermal，max ; Among them, the P thermal Represents the output power of the thermal power generating unit; the P thermal，min and P thermal，max Respectively represent the minimum output power and maximum output power of the thermal power generating unit; The energy storage unit constraint is: P ES，min ≤P ES ≤P ES，max ; Among them, the P ES Indicates the charging and discharging power of the energy storage unit; the P ES，min and P ES，max They represent the minimum charging and discharging power and the maximum charging and discharging power of the energy storage unit respectively; The line constraints are: P line ≤P line，max ; Among them, the P line Indicates the actual transmission power of the line; the P line，max Indicates the maximum transmission power of the line.

6. A low-carbon control method for regional power grids according to claim 5, characterized in that: The calculation method of the thermal power generating unit operation cost, the hydropower generating unit operation cost, the energy storage unit operation cost and the line loss cost is as follows: The calculation method of the operating cost of the thermal power generating unit is: Among them, the F Gj represents the operating cost of the jth thermal power generating unit; Gj represents the output power of the jth thermal power generating unit; j 、b j and c j represent the first cost coefficient, the second cost coefficient and the third cost coefficient of the j-th thermal power generating unit respectively; The calculation method of the operating cost of the hydroelectric generating unit is: F hj =d j ·P hj +e j ; Among them, the F hj represents the operating cost of the j-th hydroelectric generating unit; hj represents the output power of the jth hydroelectric generating unit; the d j and e j denote the first cost coefficient and the second cost coefficient of the j-th hydroelectric generating unit respectively; The calculation method of the energy storage unit operating cost is: Among them, the F Cj represents the operating cost of the j-th energy storage unit; represents the charging power of the jth energy storage unit; represents the discharge power of the jth energy storage unit; the f j and g j denote the first cost coefficient and the second cost coefficient of the j-th energy storage unit respectively; The line loss cost is calculated as follows: F lossj =h j ·P j ; Among them, the F lossj represents the line loss cost of the jth generator set; j represents the output power of the jth generator set; j Represents the line loss coefficient of the j-th generator set.

7. A low-carbon control method for regional power grids according to claim 6, characterized in that: The method of solving the objective function of the minimum operation cost of the power grid and the objective function of the minimum carbon emission of the power grid under the constraint conditions to obtain the output power of each generator set when the operation cost is the lowest and the carbon emission is the lowest includes: Under the constraints, the Hippo optimization algorithm is used to solve the objective function of the minimum operating cost of the power grid and the objective function of the minimum carbon emissions of the power grid, and the output power of each generator set when the operating cost and carbon emissions are the lowest is obtained.

8. A low-carbon control system for regional power grids, characterized in that: include: Data acquisition module, thermal power unit carbon emission prediction module, objective function and constraint construction module, generator unit output power calculation module and control module; The data acquisition module is used to obtain the operating data and load demand data of each unit in the regional power grid; wherein the operating data of each unit includes the operating data of the thermal power generating unit and the operating data of the hydropower generating unit; The thermal power unit carbon emission prediction module is used to predict carbon emissions based on the operating data of the thermal power unit through a trained future carbon emission prediction model to obtain the future carbon emissions of the thermal power unit; The objective function and constraint building module is used to build the minimum operation cost objective function of the power grid, the minimum carbon emission objective function of the power grid and the constraint conditions according to the operation data of each generator set, the load demand data and the future carbon emission of the thermal power generator set; wherein the constraint conditions include active balance constraints, hydropower generator set constraints, thermal power generator set constraints, energy storage constraints and line constraints; The generator set output power calculation module is used to solve the minimum operation cost objective function of the power grid and the minimum carbon emission objective function of the power grid under the constraint conditions, and obtain the output power of each generator set when the operation cost is the lowest and the carbon emission is the lowest; The power grid control module is used to control the regional power grid according to the output power of each generator set.

9. A low-carbon control terminal device for a regional power grid, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements a low-carbon control method for a regional power grid as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to execute a low-carbon control method for a regional power grid as described in any one of claims 1 to 7.

Images