CN116151551A

CN116151551A - Regulation and control method and device for electric heating comprehensive energy system and regulation and control equipment

Info

Publication number: CN116151551A
Application number: CN202211679702.8A
Authority: CN
Inventors: 马瑞; 范辉; 胡长斌; 郝晓光; 罗珊娜; 王辉; 李剑锋; 金飞; 侯倩
Original assignee: State Grid Corp of China SGCC; North China University of Technology; Electric Power Research Institute of State Grid Hebei Electric Power Co Ltd; State Grid Hebei Energy Technology Service Co Ltd
Current assignee: State Grid Corp of China SGCC; North China University of Technology; Electric Power Research Institute of State Grid Hebei Electric Power Co Ltd; State Grid Hebei Energy Technology Service Co Ltd
Priority date: 2022-12-26
Filing date: 2022-12-26
Publication date: 2023-05-23

Abstract

The invention provides a regulating and controlling method and device of an electric heating comprehensive energy system and regulating and controlling equipment. The method comprises the following steps: obtaining predicted weather data of the next time period; inputting the predicted weather data of the next time period into a preset load prediction model, and predicting to obtain predicted load data of the next time period; inputting the predicted load data of the next time period into a pre-constructed multi-objective regulation function, and performing iterative computation to obtain an optimal solution of the multi-objective regulation function; the targets of the multi-target regulation function comprise the lowest running cost, the highest wind-solar energy absorption rate and the lowest carbon emission of the electric heating comprehensive energy system; and based on the optimal solution, performing optimal regulation and control on the electric heating comprehensive energy system. The invention can improve the accuracy of the optimized regulation scheme of the electric heating comprehensive energy system.

Description

Regulation and control method and device for electric heating comprehensive energy system and regulation and control equipment

Technical Field

The invention relates to the technical field of electric power systems, in particular to a regulating and controlling method, a regulating and controlling device and regulating and controlling equipment of an electric heating comprehensive energy system.

Background

The transition of modern energy systems to clean low-carbon systems has become a mainstream trend, and integrated energy systems with electric-thermal coupling as cores provide an effective way for promoting renewable energy consumption and improving energy efficiency. With the improvement of the permeability of distributed wind power and photovoltaic, the resources such as distributed wind power, energy storage, load and the like in the electric heating comprehensive energy system begin to bear the function of reducing carbon emission while participating in system regulation, and the operation of the electric heating comprehensive energy system becomes more complex due to the access of various resources. Therefore, how to fully consider the operation control characteristics of various resources in the electric heating comprehensive energy system and play the complementary capability of the advantages, thereby making an optimized regulation and control operation scheme suitable for the electric heating comprehensive energy system, and having great significance for the low-carbonization operation of the modern comprehensive energy system.

At present, a regulation and control scheme of an electric heating comprehensive energy system is provided, an objective function with maximum operation net benefit as an objective is constructed on the basis of considering wind power, photovoltaic, photo-thermal uncertainty, load uncertainty and energy price uncertainty, and carbon emission punishment cost is calculated into a total objective to solve, so that an optimal scheme is obtained. However, the optimal solution of the objective function is solved by adopting a seasonal tentative load mode, and the accuracy of the optimal regulation and control scheme of the electric heating comprehensive energy system determined by the mode is lower due to the fact that the load uncertainty of the electric heating comprehensive energy system is larger.

Disclosure of Invention

The invention provides a regulating and controlling method, a regulating and controlling device of an electric heating comprehensive energy system, which can improve the accuracy of an optimized regulating and controlling scheme of the electric heating comprehensive energy system.

In a first aspect, the present invention provides a method for controlling an electrothermal integrated energy system, including: obtaining predicted weather data of the next time period; inputting the predicted weather data of the next time period into a preset load prediction model, and predicting to obtain predicted load data of the next time period; the load prediction model is obtained by training load data and weather data in a historical period based on the region where the electric heating comprehensive energy system is located; inputting the predicted load data of the next time period into a pre-constructed multi-objective regulation function, and performing iterative computation to obtain an optimal solution of the multi-objective regulation function; the targets of the multi-target regulation and control function comprise the lowest running cost, the highest wind-solar absorption rate and the lowest carbon emission of the electric heating comprehensive energy system, and the multi-target regulation and control function uses the electric heating comprehensive energy system to stably run as constraint conditions; and based on the optimal solution, performing optimal regulation and control on the electric heating comprehensive energy system.

In a second aspect, an embodiment of the present invention provides a control device for an electrothermal integrated energy system, including: the communication module is used for acquiring predicted weather data of the next time period; the processing module is used for inputting the predicted weather data of the next time period into a preset load prediction model, and predicting to obtain predicted load data of the next time period; the load prediction model is obtained by training load data and weather data in a historical period based on the region where the electric heating comprehensive energy system is located; inputting the predicted load data of the next time period into a pre-constructed multi-objective regulation function, and performing iterative computation to obtain an optimal solution of the multi-objective regulation function; the targets of the multi-target regulation and control function comprise the lowest running cost, the highest wind-solar absorption rate and the lowest carbon emission of the electric heating comprehensive energy system, and the multi-target regulation and control function uses the electric heating comprehensive energy system to stably run as constraint conditions; and based on the optimal solution, performing optimal regulation and control on the electric heating comprehensive energy system.

In a third aspect, an embodiment of the present invention provides a regulation device, wherein the regulation device includes a memory and a processor, the memory storing a computer program, and the processor is configured to invoke and execute the computer program stored in the memory to perform the steps of the method according to the first aspect and any possible implementation manner of the first aspect.

In a fourth aspect, an embodiment of the present invention provides a regulation system of an electric heating integrated energy system, the regulation system comprising a regulation device as described in the third aspect, the steps of the regulation method being performed as described in the first aspect and any possible implementation manner of the first aspect.

In a fifth aspect, embodiments of the present invention provide a computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to the first aspect and any one of the possible implementations of the first aspect.

The invention provides a regulating and controlling method, a regulating and controlling device of an electric heating comprehensive energy system.

1. On one hand, the load prediction model is obtained based on the load data and the weather data training in the historical period of the area where the electric heating comprehensive energy system is located, and the load data is obtained based on the load prediction model, so that the accurate prediction of the load data is realized. On the other hand, the method inputs the predicted load data of the next period into the pre-constructed multi-objective regulation function, calculates the obtained optimal solution, and meets the multi-objective requirements of lowest running cost, highest wind-solar energy absorption rate and lowest carbon emission. In conclusion, the accuracy of the multi-objective optimized regulation scheme of the electric heating comprehensive energy system is improved.

2. In the process of optimizing and regulating an electric heating comprehensive energy system, the invention introduces a load prediction and intelligent algorithm, and provides a load prediction method based on a neural network. The method uses a time series of common weather data to predict electric and thermal loads in an electrothermal integrated energy system; firstly, introducing a regression model to optimize a preprocessing model of data, and predicting electric power and thermal load by using the best derived regression model as an additional input of a neural network model; then, an improved ELM-based learning algorithm is provided for training, testing and verifying the proposed load prediction method, so that higher load prediction accuracy is realized.

3. The invention comprehensively considers various load characteristics, electric-thermal energy storage equipment characteristics and power supply and heat supply network models in the electric heating comprehensive energy system, and is convenient for digging diversified resources to absorb the potential of wind, light and low carbon emission according to various resource factors.

4. The invention establishes an electric heating comprehensive energy system regulation comprehensive model and a carbon emission model simultaneously, and establishes a multi-objective optimized electric heating comprehensive energy system regulation objective function comprising an economical objective function, a wind-solar absorption rate function and a carbon emission function on the basis of mixed intelligent load prediction. Furthermore, a multi-objective optimized regulation and control objective function is solved by adopting a multi-universe optimization algorithm, the objective function solution improves the benefits of the electric heating comprehensive energy system in the aspects of economy, wind-solar absorption rate and carbon emission, and an electric heating comprehensive energy system optimized regulation and control scheme is provided in a feasible domain; the invention can realize the multi-target operation of the electric heating comprehensive energy system with economy, high wind power absorption rate and low carbon operation while relieving the energy supply and demand pressure of the system.

5. According to the optimal scheduling method of the electric heating comprehensive energy system, the intelligent load prediction algorithm, the multi-load characteristic analysis, the equivalent modeling of the distributed light splitting and energy conversion equipment are combined based on the multi-target regulation analysis of the improved multi-universe optimization algorithm, and the multi-target operation targets with good economical efficiency, high wind power absorption rate and low carbon emission of the electric heating comprehensive energy system are realized.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic flow chart of a method for regulating and controlling an electric heating integrated energy system according to an embodiment of the present invention;

FIG. 2 is a schematic structural diagram of a regulating device of an electrothermal integrated energy system according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of a regulating device according to an embodiment of the present invention.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

In the embodiments of the present application, words such as "exemplary" or "such as" are used to mean serving as examples, illustrations, or descriptions. Any embodiment or design described herein as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion that may be readily understood.

Furthermore, references to the terms "comprising" and "having" and any variations thereof in the description of the present application are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or modules is not limited to only those steps or modules but may, alternatively, include other steps or modules not listed or inherent to such process, method, article, or apparatus.

For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the following description will be made with reference to the accompanying drawings of the present invention by way of specific embodiments.

Fig. 1 is a schematic flow chart of a method for regulating and controlling an electric heating integrated energy system according to an embodiment of the present invention. The execution main body of the method is a regulating device. The method comprises steps S101-S104.

S101, obtaining predicted weather data of the next period.

In some embodiments, the weather data includes temperature data, humidity data, and precipitation data.

S102, inputting the predicted weather data of the next time period into a preset load prediction model, and predicting to obtain predicted load data of the next time period.

In the embodiment of the application, the load prediction model is obtained by training load data and weather data in a historical period based on an area where the electric heating comprehensive energy system is located.

In some embodiments, the load prediction model includes a fitting regression module and a neural network module.

As a possible implementation manner, the regulation and control device may determine the predicted load data of the next period based on steps S1021-S1022.

S1021, inputting the predicted weather data of the next period into a fitting regression module of the load prediction model to obtain target fitting load data.

S1022, inputting the predicted weather data and the target fitting load data of the next period into the neural network module of the load prediction model to obtain the predicted load data of the next period.

S103, inputting the predicted load data of the next time period into a pre-constructed multi-objective regulation function, and performing iterative computation to obtain an optimal solution of the multi-objective regulation function.

In the embodiment of the application, the targets of the multi-target regulation function comprise the lowest running cost, the highest wind-solar energy absorption rate and the lowest carbon emission of the electric heating comprehensive energy system.

In the embodiment of the application, the multi-objective regulation function is used as a constraint condition for stable operation of the electric heating comprehensive energy system.

In some embodiments, the constraint conditions include a system power balance constraint, a node voltage constraint, a branch power transfer constraint, a waste heat capacity constraint of the cogeneration unit, an upper and lower output limit and a ramp rate constraint of the cogeneration unit, a system standby constraint, and a predictive load balance constraint.

In some embodiments, the optimal solution is a set capacity for each device.

The regulation and control device can uniformly convert the wind-solar energy absorption rate and the carbon emission into the running cost, convert the multi-objective regulation and control function into a single-objective regulation and control function, and obtain the optimal solution with the lowest running cost. Or the regulation and control device can uniformly convert the running cost and the wind-solar energy absorption rate into carbon emission, convert the multi-objective regulation and control function into a single-objective regulation and control function, and obtain the optimal solution with the lowest carbon emission. Or the regulation and control device can uniformly convert the operation cost and the carbon emission into the wind-light absorption rate, convert the multi-objective regulation and control function into a single-objective regulation and control function, and obtain the optimal solution with the highest wind-light absorption rate.

As a possible implementation manner, the regulation and control device may uniformly convert the wind-solar absorption rate and the carbon emission into the running cost based on steps S1031 to S1036, and determine an optimal solution of the multi-objective regulation and control function.

S1031, determining a first conversion factor between the wind-solar energy consumption and the running cost. The first conversion factor is used for converting the wind-solar energy consumption into operation cost.

S1032, determining a second conversion factor between the carbon emission and the operating cost. The second conversion factor is used to convert the carbon emissions to operating costs.

S1033, converting the multi-target regulatory function into a single-target regulatory function based on the first conversion factor and the second conversion factor.

In some embodiments, the single target regulatory function targets the lowest running cost.

Illustratively, the regulation and control device can process and price the wind-light consumption and the carbon emission; setting price rewarding factors for the wind and light consumption and price punishment factors for the carbon emission.

Illustratively, price pricing is performed for each distributed power source and energy conversion device; and determining the price rewarding factor of the wind-solar energy consumption and the price punishment factor of the carbon emission according to the electricity consumption per degree and the characteristic relation between the coal consumption and the carbon emission.

Illustratively, the multi-objective planning problem is converted to a single-objective problem using process pricing of wind-solar energy consumption and carbon emissions.

Minimum cost = natural gas power generation cost + electricity buying cost

Wind-solar energy generating capacity with +wind-solar energy consumption rewarding factor H

+carbon emission penalty factor h carbon emission

S1034, carrying out iterative solution by adopting a multi-universe algorithm based on the predicted load data of the next time period and the single target regulation function to obtain the optimal solution.

The regulation and control device can solve the single-target regulation and control function based on the multi-universe algorithm through the steps one to nine to obtain the optimal solution.

Step one: and initializing parameters.

Setting the number of the equipment to be regulated in the single objective function as the universe number of the multi-universe algorithm; setting the setting capacity of each device to be regulated as a decision variable in the multi-universe algorithm; and setting the maximum iteration times of the multi-element universe algorithm, the maximum value and the minimum value of the existence probability of the worm holes, and the upper limit and the lower limit of decision variables.

For example, the control device may input fan, photovoltaic output and load forecast data, time-of-use electricity prices, natural gas prices, and efficiency and cost parameters of the associated equipment for typical days of the respective seasons.

Step two: and randomly setting the capacity of each device to be regulated corresponding to the initial universe population.

Illustratively, the regulating device can randomly initialize the universe population according to the capacity limit of each device, and complete the initialization of the universe population.

Step three: judging whether the termination condition is met, if not, executing the fourth step; and if so, outputting the optimal preference type and the optimal benefit of each device.

The termination condition includes that the running cost is smaller than the set cost, the error between the running cost corresponding to the current iteration number and the running cost in the last iteration is smaller than the set error, or the iteration number is larger than the set number.

Step four: and inputting the universe population of the iteration into the single target regulation and control function, and determining the current running cost.

Step five: comparing whether the current running cost is smaller than the running cost corresponding to the current optimal universe population; if yes, executing the step six, and if not, executing the step seven.

Step six: and determining the universe population of the iteration as the current optimal universe population.

Step seven: white holes and black holes are generated by using a roulette selection mechanism, and the existence probability of the worm holes is randomly generated.

Step eight: updating the universe population based on the white holes, the black holes and the existence probability of the worm holes, and determining the updated universe population as the universe population at the next iteration.

Illustratively, the capacities of the randomly generated devices are brought into the underlying model and used as constraints for the operation of the devices; decomposing the lower uncertain model into an optimal submodel and a worst submodel; calling a solver to solve the optimal submodel and the worst submodel, and obtaining an interval value of the running net benefit of the lower model; calculating an average value and an interval of running net benefits; calculating the total equipment investment cost according to the capacity of each piece of equipment randomly generated by the upper layer model, calculating the expansion rate of each universe and selecting the optimal universe; using a roulette selection mechanism to generate white holes and black holes, transferring objects between different universe through the white holes/black holes, and updating the position of the universe; transferring an object from the current optimal universe to other universe through the worm tunnel, and updating the position of the universe.

Step nine: and repeating the third step to the ninth step until the iterative process is exited.

And S104, based on the optimal solution, performing optimal regulation and control on the electric heating comprehensive energy system.

The invention provides a regulating and controlling method, a regulating and controlling device of an electric heating comprehensive energy system, and in one aspect, the invention trains and obtains a load prediction model based on load data and weather data in a historical period of an area where the electric heating comprehensive energy system is positioned, predicts and obtains the load data based on the load prediction model, and realizes accurate prediction of the load data. On the other hand, the method inputs the predicted load data of the next period into the pre-constructed multi-objective regulation function, calculates the obtained optimal solution, and meets the multi-objective requirements of lowest running cost, highest wind-solar energy absorption rate and lowest carbon emission. In conclusion, the accuracy of the multi-objective optimized regulation scheme of the electric heating comprehensive energy system is improved.

Optionally, the method for regulating and controlling the electric heating integrated energy system provided by the embodiment of the invention further includes steps S201 to S202 before step S102.

S201, acquiring load data and weather data in a historical period of an area where the electric heating comprehensive energy system is located.

In some embodiments, the load data includes electrical load data and thermal load data, and the weather data includes temperature data, humidity data, and precipitation data.

And S202, carrying out data fitting and neural network training based on the load data and the weather data in the historical period to obtain the load prediction model.

As a possible implementation, the regulating device may be based on steps S2021-S2025.

S2021, performing data fitting by taking weather data in the historical period as an independent variable and taking load data in the historical period as a dependent variable to obtain the fitting regression module.

It should be noted that, assuming that L is a vector of electric loads over a certain period of time and x is a weather parameter vector in a corresponding time series, the relationship between L and x may be expressed as: l=f (x, β) +ε, where f (·) is a relational function, β is a parameter vector, ε is an unavoidable random error and satisfies ε L (0, δ2), where δ is the standard deviation. Analysis was performed using two commonly used regression models, including a quadratic index and an n-degree polynomial regression, the relationship function of which is expressed as: f (x, βpol) =β0pol+β1polx+β2polx2+, +βnpolxn; the relationship function of the quadratic exponential regression is expressed as: f (x, βex) =β0ex+β1exexp (β exx) +β3exp (β exx); the power load and weather parameters typically collected on the total day can be expressed as (Lk, xk), k=1.

The regulation and control device can comprehensively consider the root mean square error RMSE, the average absolute percentage error MAPE and the correlation coefficient R-square, and judge and analyze a regression model between the vector L of the power load and the temperature, the humidity and the precipitation in a certain period.

Exemplary, the calculation of the root mean square error RMSE; RMSE is very sensitive to error values, and can reflect the accuracy of prediction, and its calculation method is:

wherein f _k The prediction value obtained by the regression model is the weight applied to each data point, and the closer the numerical value of the RMSE is to 0, the higher the regression prediction precision is, and the better the regression model prediction effect is;

exemplary, mean absolute percentage error MAPE calculation; MAPE represents the degree to which the predicted value in the regression model deviates from the true value on average, taking into account not only the error between the predicted value and the true value, but also the ratio between the error and the true value; the MAPE calculating method comprises the following steps:

MAPE expresses the effect of prediction by calculating the absolute error percentage, the smaller the value, the better the model;

illustratively, the correlation coefficient R-square is calculated; the correlation coefficient R-square is taken as a decision coefficient, and represents the degree of correlation between an input variable and an output variable, and the calculation formula of the correlation coefficient R-square is as follows:

In which x is _av Is the mean value of the original data and is related toThe value range of the coefficient R-square is 0 to 1, and the closer to 1 is that the larger the variance ratio of the regression model is;

s2022, inputting weather data in the historical period into the fitting regression module to obtain fitting load data.

S2023, taking weather data in the historical period and the fitting load data as inputs, and taking load data in the historical period as output, and generating a training sample.

And S2024, training the neural network based on the training sample to obtain the neural network module.

For example, the modulation device may perform neural network training based on steps A1-A6. .

A1, training the neural network based on the multi-layer perceptron MLP neural network. The MLP neural network of the multi-layer perceptron is an artificial neural network consisting of an input layer, an implicit layer and an output layer, can learn the complex relation between input vectors and output vectors, sends the input vectors into the input layer, and takes the output of neurons of the previous layer as input; the mathematical expression of the MLP neural network output is:

wherein x is _i (i=1,., n) is an input value, Y is an output value, ω _ij (j=1.,. The term, m) is the connection weight of the ith input neuron to the jth hidden layer neuron, u _j Connection weights for j-th hidden layer neuron to output neuron, p and b _j For the bias values of the corresponding output neuron and the j-th hidden layer neuron, F (·) and G (·) are the activation functions of the output neuron and the hidden neuron, respectively.

A2, capturing the comprehensive influence of various weather parameters in the smart grid on the load by using the MLP neural network; the MLP neural network and the parameter regression model are fused, and the MLP neural network and the parameter regression model are used for representing the comprehensive influence of common weather parameters on the power load; the input layer includes T _max 、T _ave 、T _min And H and P, and deriving corresponding daily power loads from their regression models, and outputting the daily power loads as predicted power loads L.

A3, forming an extreme learning machine ELM, and reducing the calculated amount by randomly setting parameters of an input layer and an hidden layer once; the connection weight between the hidden layer and the output layer is determined by solving a matrix equation, and the mathematical expression of the ELM is:

wherein H is E R ^n×m For implicit layer output matrix, u= [ u ] ₁ ,...,u _m ] ^T Representing an output weight vector; omega of each hidden layer neuron _ij (i=1,., n) and b _j J=1,..a., m is randomly determined, the ELM algorithm determines the connection weight between the hidden layer and the output layer in the MLP model by calculating u; given a training set { X, Y }, X= { X ₁ ，...，x _n U may pass through u=h ⁺ Y derived, H ⁺ Is the generalized inverse of Moor-Penrose of H, H= (H) ^T H) ^-1 H ^T 。

A4, calculating H ⁺ When the adaptive parameter mu is introduced, the adaptive parameter mu is defined as mu= |Y|| ^δ ，δ∈[1,2]And substitutes it into the diagonal element H ^T H，H ⁺ ＝(H ^T H+μ) ^-1 H ^T Further, the improvement problem of the MLP model is converted into a least square problem defined as:

wherein delta ₁ ,δ ₂ >0; the improved ELM algorithm aims to minimize training errors and output weight norms, where μ is a parameter that balances both.

A6, realize f (x, beta) ^pol )＝β ₀ ^pol +β ₁ ^pol x+β ₂ ^pol x ² +....+β _n ^pol x ⁿ N=1, 2,3 for polynomial regression analysis; executing f (x, beta) ^ex )＝β ₀ ^ex +β ₁ ^％ex exp(β ₂ ^ex x)+β ₃ ^ex exp(％β ₄ ^ex x) performing a secondary exponential regression analysis; analyzing the fitting goodness of the derived regression model; obtaining predictions by regression modelsIs provided.

S406: the learning algorithm is improved based on an extreme learning machine ELM, and for each hidden layer neuron j=1, &..m, its input layer weight ω is randomly determined _ij (j=1,., n) and offset value b _j The method comprises the steps of carrying out a first treatment on the surface of the Calculating an implicit layer output matrix H by using the common meteorological parameter data obtained in the stage 1 and the corresponding power load L; defining a self-adjusting parameter mu= |y|| ^δ ，δ∈[1,2]The method comprises the steps of carrying out a first treatment on the surface of the Obtaining an output weight vector u by solving the problem: u=h ⁺ Y，H＝(H ^T H) ^-1 H ^T ，

S2025, determining the load prediction model based on the fitting regression module and the neural network module.

Optionally, the method for regulating and controlling the electric heating integrated energy system provided by the embodiment of the invention further includes steps S301 to S308 before step S103.

S301, establishing an equivalent model of each device in the electric heating comprehensive energy system; the equivalent models of the equipment comprise a wind power generation equivalent model, a photovoltaic power generation equivalent model, an energy storage system equivalent model, a fuel oil generator set equivalent model, a cogeneration unit equivalent model and an electric heating equipment equivalent model.

As a possible implementation manner, the regulation and control device determines the equivalent model of wind power generation based on the following formula.

Wherein A is _eq The cross-over area (m 2) of the equivalent wind driven generator; c (C) _p-eq Is a power coefficient; v (V) _v-eq Is equal to the wind speed (m/s); p (P) _e-eq Is the mechanical power (W) of the equivalent wind driven generator,J' _eq the inertia coefficient (kg/m 2) of the equivalent wind driven generator; w (W) _r The rotor speed (rad/s) of the equivalent wind driven generator; h is the system inertia time constant (S) of the equivalent wind driven generator; p (P) _N Is the rated power (kW) of the equivalent wind driven generator.

The invention uses the generator rotor equivalent method to determine the wind power generation equivalent model. The core idea of the generator rotor equivalence method is to consider all wind driven generators to be equivalent to a simple model under the condition of not considering the model difference and the input wind speed change of the wind driven generators, and research the model. And carrying out applicability correction on the existing generator rotor equivalent method so that the generator rotor equivalent method is suitable for a wind power generation system.

For equivalent wind power generator sweep area A _eq The sum of the radiuses of all the wind power generators is the radius of the equivalent wind power generator; to minimize errors and simplify computation, the power coefficient C _p-eq Equal to the optimal power coefficient of all wind turbines.

As a possible implementation, the core element of the photovoltaic power generation technology is a photo-generated semiconductor, which absorbs solar energy and converts it into electrical energy by its photoelectric effect on light. In a photovoltaic power generation system, a photovoltaic cell is the most basic electric energy generation unit, and a photovoltaic cell equivalent circuit model is formed by connecting a photo-generated current source and a diode in parallel. The output power of a photovoltaic cell is related to ambient temperature and illumination intensity. The regulation and control device determines a photovoltaic power generation equivalent model based on the following formula.

Wherein G is _T Is the illumination intensity; k (k) _c Is the temperature coefficient; t (T) _c Is the actual working temperature; GSTC, TSTC, PSTC are rated illumination intensity, operating temperature and output power, respectively. The detailed relationship between the available output power Ppv and G, T is that the greater the illumination intensity, the greater the output power, within a certain range at constant temperature. Constant illumination intensityIn a certain range, the temperature increases, and the maximum output power decreases.

As one possible implementation, the storage form of the electrical energy source generally includes electromagnetic, mechanical kinetic energy, electrochemical energy, water potential energy, and the like. The energy conversion technology is utilized to convert redundant electric energy into a storable energy form, namely an energy storage technology. In the process of applying energy storage technology, attention needs to be paid to the capacity of the energy storage system to store energy and the conversion efficiency of the energy. The energy storage system is an indispensable device for stabilizing the fluctuation of the output of the renewable micro-source, an independent micro-grid or a micro-grid running in an island mode, and the energy storage system and the renewable energy source are used for jointly supplying power so as to improve the reliability of the system and the electric energy quality. The energy storage system in the AC micro-grid can continuously supply power to the load in the process that the load forms an island after the element fails, so that the power failure time and the power failure times of the load are reduced. Three important constraint factors based on energy storage system operation: a charge-discharge cycle process, a state of charge (SOC) constraint, and a maximum charge-discharge power constraint. The regulation and control device determines an equivalent model of the energy storage system based on the following formula. The equivalent model of the energy storage system comprises a charging model and a discharging model.

The charging power of the energy storage system BESS at the t hour is represented by Pc BESS (t), the maximum charging power of the energy storage system BESS is represented by PBCmax, the discharging power of the energy storage system BESS at the t hour is represented by Pd BESS (t), the maximum discharging power of the energy storage system BESS at the t hour is represented by PBDmax, the SOC of the energy storage system BESS at the t hour is represented by Soc (t), the SOC of the energy storage system BESS at the t+1hour is represented by Soc (t+1), the maximum value of the SOC of the energy storage system during operation is Socmax, the minimum value of the SOC of the energy storage system during operation is Socmin, and Snom represents the rated capacity of the energy storage system during operation. In different scenarios, the BESS charge and discharge power is also related to the specific charge and discharge strategy in the scenario.

As a possible implementation manner, the equivalent model of the fuel generator set is generally considered as a low-power generator with adjustable power output, and capacity upper and lower limit constraints, climbing constraints and the like are considered in modeling. The regulation and control device determines an equivalent model of the fuel generator set based on the following formula.

Wherein PDGS (t) -the diesel generator output power (kW) at hour t; pdmin—minimum output power (kW) of diesel generator; pdmax—maximum output power (kW) of a diesel generator; the active power output of the Rup- (t-1, t) period diesel engine can be increased or decreased by a maximum value (kW).

As one possible implementation, an electro-thermal network as a municipal energy architecture has implicit coupling relationships in the energy flow, conversion and consumption process. The connection link of the two networks mainly comprises a cogeneration unit and electric heating equipment, and the cogeneration unit and the electric heating equipment are used as energy conversion equipment together. The regulation and control device determines an equivalent model of the cogeneration unit based on the following formula.

Wherein alpha, χ and γ are the cogeneration characteristic coefficients; g is the number of the cogeneration unit; m is the number of cogeneration units; pg, tCHP is cogeneration power supply; pminCHP, pmaxCHP is the minimum/maximum power of cogeneration power supply; phi g, tCHP is cogeneration heating power; phi minCHP and phi maxCHP are respectively the minimum and maximum power of heat supply of cogeneration; Δpu and Δpd are respectively the upward and downward climbing forces of the cogeneration unit; ag. bg and cg are cogeneration power supply cost coefficients; sigma CHP is the reduction value of electric power when extracting unit steam quantity under fixed steam inlet quantity; CCHP provides energy costs for cogeneration units.

As a possible implementation mode, the electric heating equipment can reduce the heat supply burden of the coal-fired unit, and provides high-grade heat energy for heat users by consuming electric energy, thereby providing an additional way for wind-solar electric energy consumption. The regulation and control device determines an equivalent model of the electric heating equipment based on the following formula.

Wherein phi h, tEB is the heating power of the electric heating equipment h, ph, tEB is the electric power of the electric heating equipment h; pnEB is the rated power of the electric heating equipment; epsilon EB is the electrothermal conversion efficiency of the electrothermal equipment; ωeb is an electric energy conversion cost coefficient of the electric heating device; CEB is the cost of electrical energy conversion for electrical heating equipment.

The loads of the electric heating comprehensive energy system comprise a manufacturing industry controllable load model, a papermaking industry controllable load model, an agricultural and sideline product processing industry load model and a metallurgical industry load model. The electric energy storage device widely used in the electric heating comprehensive energy system at present comprises a super capacitor, a battery for storing energy and the like, wherein the heat storage device comprises water heat storage, phase change heat storage and the like; the energy can be dynamically absorbed and timely released in the electric/thermal energy storage operation process, the fluctuation of wind-light output is stabilized, and the capacity of the electric heating comprehensive energy system for absorbing renewable energy sources is indirectly enlarged. In order to meet the electric load demand, the generated power and the heat supply power can be increased, and a unified model is established for the response characteristics and the restraint of the electric/thermal energy storage, wherein the model is as follows:

Wherein Ee, tESS is the energy storage capacity of the e-th energy storage device in t time period; emax and Emin are the upper and lower limits of the capacity of the energy storage device; pe, tESS, ca, pe, tESS, da is the charging/discharging power of the e-th energy storage device in the t period; pe, maxESS, ca, pe and minESS, wherein ca is the upper limit and the lower limit of the charging power of the energy storage device; pe, maxESS, da, pe, minESS, da supplying power upper and lower limits to the energy storage device; μe, caESS, μe, daESS is the energy charging/discharging efficiency of the e-th energy storage device; delta tESS, ca and delta tESS, da represent energy storage charging/discharging states, wherein the state is a non-working state when 0 is taken, and the state is a working state when 1 is taken; t is the total operation time; nD is the energy storage quantity; the CESS is the charge/discharge energy regulation cost of the energy storage equipment. Through the description of all the models, the cost of various loads and electric heating energy storage in the electric heating comprehensive energy system participating in operation under the regulation and control of the system is mainly from the transfer of the electricity consumption for load production, the cost is reduced, and the energy storage cost is mainly from the regulation and control cost of the system on the charging/discharging energy.

S302, a heat supply model and a power supply model in the electric heating comprehensive energy system are established, and the heat supply model is used for limiting the relation among the pipeline flow, the water supply temperature and the backwater temperature in a heat supply network.

Illustratively, building a heating model; the heat supply network mainly comprises a water supply network and a water return network, heat energy in the water supply network is transferred between a heat source node and a heat load node by means of hot water or hot steam, a unitary function relation between the heat source and the heat load pipeline flow is established, and a simplified heat supply model is as follows:

Wherein, ts and To are respectively the water supply and return temperatures of the nodes; ta is ambient temperature; mk is the pipeline k flow, defining n1=m1/mk, n2=m2/mk, …, nk-1=mk-1/mk, nk=1; λk is the heat transfer coefficient; lk is the length of the heating pipeline k; cw is the specific heat capacity of water;

the thermal load of the node i at the moment t; nH is the total number of nodes of the heat supply network; after the heat source node heat supply output is obtained, the pipeline flow in the heat supply network can be solved under the constraint of meeting the node heat load demand, and the heat energy flow result of the heat supply network is obtained; setting the backwater temperature of each node of the heat supply network to be constant, and setting the heat power required by all load nodes of the heat supply network in the same period to be the same.

Exemplary, a power supply model is established; the power supply model adopts a classical alternating current power flow model, and a power flow equation under polar coordinates is as follows:

wherein Pi and Qi are respectively the active power and reactive power injected into the node i; ui and Uj are voltage amplitudes of nodes i and j respectively; gij and Bij are the conductance and susceptance corresponding to the nodes i and j in the node admittance matrix respectively; θ _ij The voltage phase difference between the nodes i and j; n is the number of power system nodes.

S303, constructing a first objective function with the lowest running cost based on the equivalent model of each device, the heat supply model and the power supply model.

Illustratively, the economical objective function of the electric heating comprehensive energy system is established, and the aim is to minimize the economic operation cost of the electric heating comprehensive energy system in the heating period in winter.

C ₁ ＝C ^MI +C ^PM +C ^FS +C ^FM +C ^ESS +C ^LOSS +C ^CHP +C ^EB +C ^OM +C ^INV +C ^grid

Wherein CINV is the equipment investment cost converted to the average day; COM is the operation and maintenance cost of various devices; CLOSS is the electrothermal network loss cost; cgrid is the electricity purchasing cost; phi LOSS is the power LOSS of the heat supply network; PLOSS is grid loss power; zh and zg are the unit heat supply network and the power grid loss cost respectively; delta Tk, t is the temperature difference of the head and the tail of the heat supply pipeline k in the period t; rs, i is the branch impedance connected to node i; v is a cogeneration unit, an electric heating device, a distributed power supply and an electric/thermal energy storage device; k is the total number of heat supply branches; w is the total number of various devices; phi vnk is the operation and maintenance cost coefficient of the equipment v; pv, tnk is the power of various devices at the time t; yi is the construction cost of the unit capacity of the ith equipment; bi is the construction capacity of the ith equipment; r is the interest rate; xi is the lifetime of the ith device.

S304, constructing a second objective function with the highest wind-solar absorption rate based on the equivalent model of each device, the heat supply model and the power supply model.

By way of example, an objective function of the wind-solar absorption rate of the electric heating comprehensive energy system is established, and the wind-solar absorption rate of the electric heating comprehensive energy system is targeted at the highest.

/>

Wherein p is _t ^X The distributed power source output power used for the period t; p is p _t ^RE All power is sent by each distributed power supply in the t period.

S305, constructing a carbon emission flow topology model based on the equivalent model of each device, the heat supply model and the power supply model.

Illustratively, carbon embedded in various energy sources is transferred in adherence to electrothermal integrated energy transfer during energy transfer and conversion; with the conversion of energy forms, carbon emission flows in different energy systems; because the energy consumed by each node in the network can be traced back to each power supply, the corresponding carbon emission can also be traced back to each power supply, a related topology model is established, and the process of accumulating the carbon emission from the energy source generation and conversion party to the demand party is intuitively presented; the carbon emission amount flowing through each line is related to the line trend, and the branch carbon emission intensity is equal to the power inflow node carbon emission intensity.

Wherein, the liquid crystal display device comprises a liquid crystal display device,

the carbon emission intensity is the node i; />

The carbon emission intensity of the branch connected with the node i; p (P) _i ^N Active power for node i; />

Transmitting power for the branch ij; />

Carbon emission flow for node i; />

The branch carbon emission flow is represented by the carbon emission flow flowing through the node j from the node i; the carbon emission intensity of each node is determined by the active power injection amount of the transmission line and the generator connected to the node.

output power for power supply g; />

The carbon emission intensity is g for the power supply; nG and nL are the power supply and branch number of the connection node; the total carbon emission of the system follows the law of conservation of carbon emission, namely the total carbon emission of the source-load side is equal, and the carbon emission generated by branch loss does not account for the node carbon emission, so as to obtain a carbon emission flow topology model.

Wherein SNODE is the total amount of node carbon emissions; slass is the total amount of carbon emissions generated by the depletion; SCHP, SGRID, SWT, SPT is the total carbon emission amount of a cogeneration unit, an upper power grid, wind power and photovoltaic power supply in the system respectively; nN is the total number of nodes.

S306, constructing a third objective function with the lowest carbon emission based on the equivalent model of each device, the heat supply model, the power supply model and the carbon emission flow topology model.

Illustratively, an electric heating integrated energy system carbon emission objective function is established, targeting the lowest carbon emission of the electric heating integrated energy system.

Wherein ρG is the power supply carbon emission coefficient of the CHP unit; ρgrid is the power supply carbon emission coefficient of the upper power grid; ptgrid is the electricity purchasing power of the regional power grid to the upper power grid at the moment t; GEN is the number of power sources in the system.

S307, constructing constraint conditions of the multi-objective regulation and control function based on the equivalent model of each device, the heat supply model and the power supply model.

By way of example, the system power balance constraint may be expressed as the following equation:

wherein Pi, tDG is the output power of the distributed power source i at time t; ptsystem is the power consumption of the regional power grid at the moment t; pe, tBES is the charge/discharge power of the electricity storage device e at time t; phi e, tTES is the charge/discharge power of the heat storage equipment e at the moment t; pi, tLOSS is the power grid branch t moment network loss with the first node being i; phi k, tLOSS is the network loss of the heat supply network branch k at the moment t; nDG, nCHP, nBES, nEB, nTES, nH is the total number of load nodes of the distributed power supply, the cogeneration unit, the electric energy storage, the electric heating, the heat energy storage and the heat supply network respectively.

By way of example, the node voltage constraint may be expressed as the following equation:

U _i,min ≤U _i,t ≤U _i,max ；

wherein Ui, max, ui, min are the upper and lower limits of the inode voltage, respectively.

Illustratively, the branch power transfer constraint may be expressed as the following formula.

Wherein, PSHij, t, PSHij, max, PSHij, min are the upper limit and lower limit of the transmission power of the branch ij, respectively.

The heat and power cogeneration unit burns natural gas to generate electricity, and the discharged high-temperature flue gas is used for heating through the bromine cooler. The waste heat amount constraint of the electric power unit can be expressed as the following formula.

Wherein Q is _CHP (t) is the residual heat of the cogeneration unit in the t period,

generating efficiency eta of the cogeneration unit in t period ¹ For heat dissipation loss rate, < >>

Is the heat coefficient, eta of the bromine refrigeration mechanism ^h Is the flue gas recovery rate.

For example, the upper and lower limits of the output and the ramp rate constraint of the cogeneration unit can be expressed as the following formulas.

P _CHP，min ≤P _CHP (t)≤P _CHP，max

Q _CHP，min ≤Q _CHP (t)≤Q _CHP，max

Wherein P is _CHP，max And P _CHP，min Respectively represent the upper limit and the lower limit of the power supply power of the cogeneration unit, Q _CHP，max And Q _CHP，min Respectively representing the upper limit and the lower limit of the heat supply power of the cogeneration unit, v _CHP,P,max And v _CHP,P,min Respectively representing the lifting speed limit and v of the power supply power of the cogeneration unit _CHP,H,max And v _CHP,H,min Respectively representing the lifting rate limit of the heat supply power of the cogeneration unit.

Illustratively, the system standby constraint, which is a necessary constraint for ensuring the security of the system, can be expressed as the following formula.

Wherein P is _G,max Representing the maximum output of a power supply unit of the system; k (k) _r Representing the system spare capacity coefficient.

Illustratively, a load balancing constraint is predicted; at each scheduling time in the scheduling period, the power and heat load supply and demand balance of each user should be satisfied, and based on the load prediction based on the multi-layer perceptron MLP neural network and the extreme learning machine ELM in the step 4, the predicted load balance constraint can be expressed as the following formula.

Wherein P is _load (t) and Q _load (t) predicting the electrical load sum for the system at time t, respectivelyThe thermal load is predicted.

S308, constructing the multi-target regulation function based on the first target function, the second target function, the third target function and the constraint condition of the multi-target regulation function.

It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.

The following are device embodiments of the invention, for details not described in detail therein, reference may be made to the corresponding method embodiments described above.

Fig. 2 shows a schematic structural diagram of a regulating device of an electrothermal integrated energy system according to an embodiment of the present invention. The regulating device 400 comprises a communication module 401 and a processing module 402.

A communication module 401, configured to obtain predicted weather data of a next period;

the processing module 402 is configured to input the predicted weather data of the next period into a preset load prediction model, and predict to obtain predicted load data of the next period; the load prediction model is obtained by training load data and weather data in a historical period based on the region where the electric heating comprehensive energy system is located; inputting the predicted load data of the next time period into a pre-constructed multi-objective regulation function, and performing iterative computation to obtain an optimal solution of the multi-objective regulation function; the targets of the multi-target regulation and control function comprise the lowest running cost, the highest wind-solar absorption rate and the lowest carbon emission of the electric heating comprehensive energy system, and the multi-target regulation and control function uses the electric heating comprehensive energy system to stably run as constraint conditions; and based on the optimal solution, performing optimal regulation and control on the electric heating comprehensive energy system.

In a possible implementation manner, the communication module 401 is further configured to obtain load data and weather data in a historical period in an area where the electrothermal integrated energy system is located; the load data comprises electric load data and thermal load data, and the weather data comprises temperature data, humidity data and precipitation data; the processing module 402 is further configured to perform data fitting and neural network training based on the load data and the weather data in the historical period, to obtain the load prediction model.

In one possible implementation, the load prediction model includes a fitting regression module and a neural network module; the processing module 402 is specifically configured to perform data fitting with weather data in the historical period as an independent variable and load data in the historical period as a dependent variable, so as to obtain the fitting regression module; inputting weather data in the historical period into the fitting regression module to obtain fitting load data; taking weather data and the fitting load data in the historical period as input and taking the load data in the historical period as output to generate a training sample; based on the training sample, performing neural network training to obtain the neural network module; and determining the load prediction model based on the fitting regression module and the neural network module.

In a possible implementation manner, the processing module 402 is specifically configured to input the predicted weather data of the next period into a fitting regression module of the load prediction model to obtain target fitting load data; and inputting the predicted weather data and the target fitting load data of the next period into a neural network module of the load prediction model to obtain the predicted load data of the next period.

In a possible implementation manner, the processing module 402 is further configured to establish an equivalent model of each device in the electrothermal integrated energy system; the equivalent models of the equipment comprise a wind power generation equivalent model, a photovoltaic power generation equivalent model, an energy storage system equivalent model, a fuel oil generator set equivalent model, a cogeneration unit equivalent model and an electric heating equipment equivalent model; establishing a heat supply model and a power supply model in the electric heating comprehensive energy system, wherein the heat supply model is used for limiting the relation among the pipeline flow, the water supply temperature and the backwater temperature in a heat supply network; constructing a first objective function with the lowest running cost based on the equivalent model of each device, the heat supply model and the power supply model; constructing a second objective function with the highest wind-solar absorption rate based on the equivalent model of each device, the heat supply model and the power supply model; constructing a carbon emission flow topology model based on the equivalent model of each device, the heat supply model and the power supply model; constructing a third objective function with the lowest carbon emission based on the equivalent model of each device, the heat supply model, the power supply model and the carbon emission flow topology model; based on the equivalent model of each device, the heating model and the power supply model construct constraint conditions of the multi-objective regulation and control function; the multi-objective regulatory function is constructed based on the first objective function, the second objective function, the third objective function, and constraints of the multi-objective regulatory function.

In one possible implementation, the processing module 402 is specifically configured to determine a first conversion factor between the wind-solar energy consumption and the running cost; the first conversion factor is used for converting the wind-solar energy consumption into operation cost; determining a second conversion factor between carbon emissions and operating costs; the second conversion factor is used for converting the carbon emission into operation cost; converting the multi-target regulatory function to a single-target regulatory function based on the first conversion factor and the second conversion factor; the single-target regulation and control function aims at the lowest running cost; and carrying out iterative solution by adopting a multi-element universe algorithm based on the predicted load data of the next time period and the single target regulation function to obtain the optimal solution.

In one possible implementation, the processing module 402 is specifically configured to perform the following steps: step one: initializing parameters; setting the number of the equipment to be regulated in the single objective function as the universe number of the multi-universe algorithm; setting the setting capacity of each device to be regulated as a decision variable in the multi-universe algorithm; setting the maximum iteration times of the multi-element universe algorithm, the maximum value and the minimum value of the existence probability of the worm holes, and determining the upper limit and the lower limit of the variable; step two: randomly setting the capacity of each device to be regulated corresponding to the initial universe population; step three: judging whether the termination condition is met, if not, executing the fourth step; if yes, outputting the optimal preference type and the optimal benefit of each device; the termination condition comprises that the running cost is smaller than the set cost, the error between the running cost corresponding to the current iteration number and the running cost in the last iteration is smaller than the set error, or the iteration number is larger than the set number; step four: inputting the universe population of the iteration into the single target regulation function, and determining the current running cost; step five: comparing whether the current running cost is smaller than the running cost corresponding to the current optimal universe population; if yes, executing the step six, and if not, executing the step seven; step six, a step of performing a step of; determining the universe population of the iteration as the current optimal universe population; step seven: generating white holes and black holes by using a roulette selection mechanism, and randomly generating the existence probability of the insect holes; step eight: updating the universe population based on the white holes, the black holes and the existence probability of the worm holes, and determining the updated universe population as the universe population at the next iteration; step nine: and repeating the third step to the ninth step until the iterative process is exited.

Fig. 3 is a schematic structural diagram of a regulating device according to an embodiment of the present invention. As shown in fig. 3, the regulating device 500 of this embodiment includes: a processor 501, a memory 502 and a computer program 503 stored in said memory 502 and executable on said processor 501. The steps of the method embodiments described above, such as steps 101 to 104 shown in fig. 1, are implemented when the processor 501 executes the computer program 503. Alternatively, the processor 501 may implement the functions of the modules/units in the above-described device embodiments when executing the computer program 503, for example, the functions of the communication module 401 and the processing module 402 shown in fig. 2.

Illustratively, the computer program 503 may be split into one or more modules/units that are stored in the memory 502 and executed by the processor 501 to accomplish the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions for describing the execution of the computer program 503 in the regulating device 500. For example, the computer program 503 may be divided into the communication module 401 and the processing module 402 shown in fig. 2.

The processor 501 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 502 may be an internal storage unit of the regulating device 500, such as a hard disk or a memory of the regulating device 500. The memory 502 may also be an external storage device of the controlling device 500, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the controlling device 500. Further, the memory 502 may also include both internal and external memory units of the regulatory device 500. The memory 502 is used for storing the computer program and other programs and data required by the terminal. The memory 502 may also be used to temporarily store data that has been output or is to be output.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal and method may be implemented in other manners. For example, the apparatus/terminal embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.

The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.

Claims

1. A regulation and control method of an electrothermal integrated energy system is characterized by comprising the following steps:

obtaining predicted weather data of the next time period;

inputting the predicted weather data of the next time period into a preset load prediction model, and predicting to obtain predicted load data of the next time period; the load prediction model is obtained by training load data and weather data in a historical period based on the region where the electric heating comprehensive energy system is located;

inputting the predicted load data of the next time period into a pre-constructed multi-objective regulation function, and performing iterative computation to obtain an optimal solution of the multi-objective regulation function; the targets of the multi-target regulation and control function comprise the lowest running cost, the highest wind-solar absorption rate and the lowest carbon emission of the electric heating comprehensive energy system, and the multi-target regulation and control function uses the electric heating comprehensive energy system to stably run as constraint conditions;

And based on the optimal solution, performing optimal regulation and control on the electric heating comprehensive energy system.

2. The method for controlling an electric heating integrated energy system according to claim 1, wherein the step of inputting the predicted weather data of the next period into a preset load prediction model, and before predicting the predicted load data of the next period, further comprises:

acquiring load data and weather data in a historical period in an area where an electric heating comprehensive energy system is located; the load data comprises electric load data and thermal load data, and the weather data comprises temperature data, humidity data and precipitation data;

and carrying out data fitting and neural network training based on the load data and the weather data in the historical period to obtain the load prediction model.

3. The method for regulating and controlling an electrothermal integrated energy system according to claim 2, wherein the load prediction model comprises a fitting regression module and a neural network module;

and performing data fitting and neural network training based on the load data and the weather data in the historical period to obtain the load prediction model, wherein the load prediction model comprises the following steps:

taking weather data in the historical period as independent variables, and taking load data in the historical period as dependent variables, and performing data fitting to obtain the fitting regression module;

Inputting weather data in the historical period into the fitting regression module to obtain fitting load data;

taking weather data and the fitting load data in the historical period as input and taking the load data in the historical period as output to generate a training sample;

based on the training sample, performing neural network training to obtain the neural network module;

and determining the load prediction model based on the fitting regression module and the neural network module.

4. The method for controlling an electric heating integrated energy system according to claim 1, wherein inputting the predicted weather data of the next period into a preset load prediction model, predicting to obtain the predicted load data of the next period comprises:

inputting the predicted weather data of the next period into a fitting regression module of the load prediction model to obtain target fitting load data;

and inputting the predicted weather data and the target fitting load data of the next period into a neural network module of the load prediction model to obtain the predicted load data of the next period.

5. The method for controlling an electric heating integrated energy system according to claim 1, wherein the inputting the predicted load data of the next period into a pre-constructed multi-objective control function, and performing iterative computation, before obtaining the optimal solution of the multi-objective control function, further comprises:

Establishing an equivalent model of each device in the electric heating comprehensive energy system; the equivalent models of the equipment comprise a wind power generation equivalent model, a photovoltaic power generation equivalent model, an energy storage system equivalent model, a fuel oil generator set equivalent model, a cogeneration unit equivalent model and an electric heating equipment equivalent model;

establishing a heat supply model and a power supply model in the electric heating comprehensive energy system, wherein the heat supply model is used for limiting the relation among the pipeline flow, the water supply temperature and the backwater temperature in a heat supply network;

constructing a first objective function with the lowest running cost based on the equivalent model of each device, the heat supply model and the power supply model;

constructing a second objective function with the highest wind-solar absorption rate based on the equivalent model of each device, the heat supply model and the power supply model;

constructing a carbon emission flow topology model based on the equivalent model of each device, the heat supply model and the power supply model;

constructing a third objective function with the lowest carbon emission based on the equivalent model of each device, the heat supply model, the power supply model and the carbon emission flow topology model;

based on the equivalent model of each device, the heating model and the power supply model construct constraint conditions of the multi-objective regulation and control function;

The multi-objective regulatory function is constructed based on the first objective function, the second objective function, the third objective function, and constraints of the multi-objective regulatory function.

6. The method for controlling an electric heating integrated energy system according to claim 1, wherein inputting the predicted load data of the next period into a multi-objective control function constructed in advance, performing iterative computation, and obtaining an optimal solution of the multi-objective control function, comprises:

determining a first conversion factor between the wind-solar energy consumption and the running cost; the first conversion factor is used for converting the wind-solar energy consumption into operation cost;

determining a second conversion factor between carbon emissions and operating costs; the second conversion factor is used for converting the carbon emission into operation cost;

converting the multi-target regulatory function to a single-target regulatory function based on the first conversion factor and the second conversion factor; the single-target regulation and control function aims at the lowest running cost;

and carrying out iterative solution by adopting a multi-element universe algorithm based on the predicted load data of the next time period and the single target regulation function to obtain the optimal solution.

7. The method for regulating and controlling an electrothermal integrated energy system according to claim 6, wherein the iteratively solving based on the predicted load data of the next period and the single target regulating and controlling function to obtain the optimal solution comprises:

step one: initializing parameters; setting the number of the equipment to be regulated in the single objective function as the universe number of the multi-universe algorithm; setting the setting capacity of each device to be regulated as a decision variable in the multi-universe algorithm; setting the maximum iteration times of the multi-element universe algorithm, the maximum value and the minimum value of the existence probability of the worm holes, and determining the upper limit and the lower limit of the variable;

step two: randomly setting the capacity of each device to be regulated corresponding to the initial universe population;

step three: judging whether the termination condition is met, if not, executing the fourth step; if yes, outputting the optimal preference type and the optimal benefit of each device; the termination condition comprises that the running cost is smaller than the set cost, the error between the running cost corresponding to the current iteration number and the running cost in the last iteration is smaller than the set error, or the iteration number is larger than the set number;

Step four: inputting the universe population of the iteration into the single target regulation function, and determining the current running cost;

step five: comparing whether the current running cost is smaller than the running cost corresponding to the current optimal universe population; if yes, executing the step six, and if not, executing the step seven;

step six, a step of performing a step of; determining the universe population of the iteration as the current optimal universe population;

step seven: generating white holes and black holes by using a roulette selection mechanism, and randomly generating the existence probability of the insect holes;

step eight: updating the universe population based on the white holes, the black holes and the existence probability of the worm holes, and determining the updated universe population as the universe population at the next iteration;

8. A regulating device of an electrothermal integrated energy system, comprising:

the communication module is used for acquiring predicted weather data of the next time period;

the processing module is used for inputting the predicted weather data of the next time period into a preset load prediction model, and predicting to obtain predicted load data of the next time period; the load prediction model is obtained by training load data and weather data in a historical period based on the region where the electric heating comprehensive energy system is located; inputting the predicted load data of the next time period into a pre-constructed multi-objective regulation function, and performing iterative computation to obtain an optimal solution of the multi-objective regulation function; the targets of the multi-target regulation and control function comprise the lowest running cost, the highest wind-solar absorption rate and the lowest carbon emission of the electric heating comprehensive energy system, and the multi-target regulation and control function uses the electric heating comprehensive energy system to stably run as constraint conditions; and based on the optimal solution, performing optimal regulation and control on the electric heating comprehensive energy system.

9. A regulating device of an electrothermal integrated energy system, characterized in that the regulating device comprises a memory, in which a computer program is stored, and a processor for calling and running the computer program stored in the memory to perform the method according to any one of claims 1 to 8.

10. A regulation system of an electrothermal integrated energy system, characterized in that the regulation system comprises a regulation device according to claim 9, performing a regulation method according to any one of claims 1 to 7.