Integrated demand response method and system based on user behavior coupled modeling

Abstract

The application provides a kind of integrated demand response method and system based on user behavior coupling modeling, it is related to energy management technical field.The application obtains and pre-processes the historical data of city integrated energy system;Through the historical data after pre-processing and long short-term memory neural network, obtain UIES demand prediction model, predict multiple load prediction data and electricity price prediction data through UIES demand prediction model;Based on historical data, predicted multiple load prediction data and electricity price prediction data determine model parameters, build IB-IDR income model;Based on IB-IDR overall income model, according to multi-agent theory, adopt adaptive method to solve optimal IB-IDR strategy for each energy subsystem.The application can overcome the uncertainty of UIES demand side, realize more accurate, integrated IB-IDR incentive strategy for each consumer to obtain more demand response resources, promote UEIS supply and demand balance.

Description

Technical Field

[0001] This invention relates to the field of energy management technology, and specifically to a comprehensive demand response method and system based on user behavior coupling modeling. Background Technology

[0002] Urban integrated energy systems (UIES) can break down the multi-layered barriers between energy subsystems such as electricity, heat, and cooling, leveraging the interconnectedness and interdependence of electricity, gas, and heat to achieve cleaner, lower carbon emissions and intensive energy utilization within a region. UIES can achieve multi-energy, multi-load coordination, providing differentiated energy services based on the needs of different consumers and realizing tiered energy utilization. However, the randomness, volatility, and intermittency of renewable energy output, along with the coupling of various load types with different physical characteristics on the UIES demand side, increase the risk of supply-demand imbalance, posing potential threats to the safe operation of UIES. The development of UIES places higher demands on the reliability and efficiency of its demand-side management.

[0003] Existing incentive-based integrated demand response (IB-IDR) allows integrated energy service providers to use incentive signals to guide customers in changing their energy usage, greatly improving the flexibility of system operators. However, due to the coupling effect of consumer behavior in UIES, one type of load shedding may simultaneously lead to inconvenience for users in using other energy sources. This, in turn, increases the dissatisfaction costs for consumers participating in IB-IDR, making it difficult for existing demand response technologies to effectively achieve supply and demand balance in UIES. Summary of the Invention

[0004] (a) Technical problems to be solved

[0005] To address the shortcomings of existing technologies, this invention provides a comprehensive demand response method and system based on user behavior coupling modeling, which solves the technical problem that existing demand response technologies cannot effectively achieve supply and demand balance in urban integrated energy systems.

[0006] (II) Technical Solution

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] In a first aspect, the present invention provides a comprehensive demand response method based on user behavior coupling modeling, comprising:

[0009] S1. Acquire and preprocess historical data of the city's integrated energy system;

[0010] S2. Obtain the UIES demand forecasting model through preprocessed historical data and long short-term memory neural network, and use the UIES demand forecasting model to predict multivariate load forecasting data and electricity price forecasting data.

[0011] S3. Determine the model parameters based on historical data, predicted multivariate load forecast data, and electricity price forecast data, and construct the IB-IDR revenue model;

[0012] S4. Based on the IB-IDR overall benefit model and in accordance with multi-agent theory, an adaptive method is used to solve for the optimal IB-IDR strategy for each energy subsystem.

[0013] Preferably, the historical data includes

[0014] Historical data for urban integrated energy systems include: historical meteorological data, historical multi-load data, and historical energy price data.

[0015] Preferably, the step of determining model parameters and constructing the IB-IDR revenue model based on historical data, multivariate load forecast data, and electricity price forecast data includes:

[0016] S301. Construct a profit model for the energy subsystem based on historical data, multi-source load forecast data, and electricity price forecast data, including:

[0017]

[0018]

[0019] Where n represents the type of energy subsystem; Represents the profit of energy subsystem n; This represents the load forecast data for energy type n for consumer i in the j-th time interval; This represents the electricity price forecast data for energy type n in the j-th time interval; Δ represents the excitation signal from energy subsystem n to consumer i during the j-th time interval; i,j This represents the amount of load reduction for consumer i during the j-th time interval; The elasticity coefficient between the actual and expected load reduction levels of consumers follows a normal distribution. The expected value of the normal distribution. The standard deviation of the normal distribution;

[0020] S302. Construct a profit model for Integrated Energy Consumer Participation in IB-IDR based on historical data, multi-source load forecast data, and electricity price forecast data, including:

[0021]

[0022]

[0023] Among them, Profit eu Profits for integrated energy consumers participating in IB-IDR; Π i,j Let η be the IB-IDR incentive strategy matrix for integrated energy consumer i during the j-th time interval; for consumer i, the attitude towards the rewards and discomfort costs associated with participating in IB-IDR is η. i B ij Θ represents the behavioral coupling matrix of consumer i within the j-th time interval; ij and Γ ij All of these are consumer-related discomfort cost parameters for consumer i within the j-th time interval;

[0024] S303. Determine the overall IB-IDR benefit model based on the profit model of the energy subsystem and the profit model of integrated energy consumer participation in IB-IDR, including:

[0025] The goal of the IB-IDR model is to maximize the total profit of the UIES subsystem and consumers:

[0026]

[0027] Preferably, the IB-IDR-based overall benefit model, based on multi-agent theory, employs an adaptive method to solve for the optimal IB-IDR strategy for each energy subsystem, including:

[0028] S401, Initialization time j=0, revenue of each energy subsystem Current iteration number k and maximum iteration number;

[0029] S402, Select excitation signal The IB-IDR excitation signal is randomly selected according to the following constraints.

[0030]

[0031] 0≤Δ i,j ≤Δ max

[0032] in, and Δ represents the lower and upper limits of the excitation signal for energy subsystem n, respectively; max Indicates the maximum load reduction;

[0033] S403. Calculate the demand response resources provided by consumers in response to the current incentive signal, i.e., the load reduction Δ. i,j ;

[0034] S404. Record the current IB-IDR state for the current time interval. Each energy subsystem follows the excitation signal. Incentivize integrated energy consumers and capture the profits from each energy subsystem's participation in IB-IDR within the current time frame. Benefits of integrated energy consumers participating in IB-IDR within the current time frame sum:

[0035]

[0036] S405. Let j = j + 1, and repeat steps S402 to S404 until one IB-IDR process is completed, i.e., j = T. Record the excitation strategy of the energy subsystem in this IB-IDR. income and cumulative return Q n,k :

[0037]

[0038] Where k is the iteration number, i = 0, ..., N, j = 0, ..., T;

[0039] S406. Let k = k + 1, and repeat steps S402 to S405 until k reaches the maximum number of iterations. If at this point, the cumulative return Q of each energy subsystem is... n,k If convergence is achieved, then the excitation signals of each energy subsystem of the current IB-IDR are the optimal IB-IDR strategy.

[0040] Preferably, in step S406, during each iteration, the incentive signal and profit are updated as follows:

[0041] In the k-th iteration, the excitation signal selected in the j-th time interval is If the corresponding profit If there is no increase compared to the previous iteration, then no update is needed; if the corresponding profit... If there is an increase compared to the previous iteration, then the excitation signal will be updated to... The corresponding profit is updated to

[0042]

[0043] in, Let γ be the profit corresponding to the excitation signal in the j-th time interval of the previous iteration, and γ∈[0,1] be the discount factor. This is the learning rate.

[0044] Preferably, the integrated demand response method further includes:

[0045] S5. Based on the optimal IB-IDR strategy, issue incentive signals for each energy subsystem to guide integrated energy consumers to participate in IB-IDR.

[0046] Secondly, the present invention provides a comprehensive demand response system based on user behavior coupling modeling, comprising:

[0047] The data acquisition module is used to acquire and preprocess historical data of the urban integrated energy system;

[0048] The forecasting module is used to obtain the UIES demand forecasting model through preprocessed historical data and long short-term memory neural networks, and then use the UIES demand forecasting model to forecast multivariate load forecasting data and electricity price forecasting data.

[0049] The revenue model building module is used to determine model parameters and build the IB-IDR revenue model based on historical data, multivariate load forecast data, and electricity price forecast data.

[0050] The strategy acquisition module is used to solve the optimal IB-IDR strategy for each energy subsystem based on the IB-IDR overall benefit model and in accordance with multi-agent theory, using an adaptive method.

[0051] Preferably, the integrated demand response system further includes:

[0052] The incentive strategy release module is used to release incentive signals for each energy subsystem based on the optimal IB-IDR strategy, guiding integrated energy consumers to participate in IB-IDR.

[0053] Thirdly, the present invention provides a computer-readable storage medium storing a computer program for integrated demand responsiveness based on user behavior coupling modeling, wherein the computer program causes a computer to execute the integrated demand responsiveness method based on user behavior coupling modeling as described above.

[0054] Fourthly, the present invention provides an electronic device, comprising:

[0055] One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including methods for performing a comprehensive demand responsiveness approach based on user behavior coupling modeling as described above.

[0056] (III) Beneficial Effects

[0057] This invention provides a comprehensive demand response method and system based on user behavior coupling modeling. Compared with existing technologies, it has the following advantages:

[0058] This invention acquires and preprocesses historical data from the integrated urban energy system (UIES); uses the preprocessed historical data and a long short-term memory (LSTM) neural network to obtain a UIES demand forecasting model; uses the UIES demand forecasting model to predict multi-variable load forecasts and electricity price forecasts; determines model parameters based on historical data, predicted multi-variable load forecasts, and electricity price forecasts, and constructs an IB-IDR revenue model; based on the overall IB-IDR revenue model, and according to multi-agent theory, uses an adaptive method to solve for the optimal IB-IDR strategy for each energy subsystem. This invention uses multi-variable load forecasts and electricity price forecasts as input data to the overall IB-IDR revenue model for demand response, thereby obtaining a demand response strategy. This overcomes the uncertainty on the demand side of UIES, enabling the acquisition of a more accurate and integrated IB-IDR incentive strategy for each consumer, thus obtaining more demand response resources and promoting supply and demand balance in the UEIS (Urban Integrated Energy System). Attached Figure Description

[0059] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0060] Figure 1 This is a block diagram of a comprehensive demand response method based on user behavior coupling modeling according to an embodiment of the present invention;

[0061] Figure 2 This is a block diagram of a comprehensive demand response system based on user behavior coupling modeling, according to an embodiment of the present invention. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are described clearly and completely. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0063] This application provides a comprehensive demand response method and system based on user behavior coupling modeling, which solves the technical problem that existing demand response technologies cannot effectively achieve the supply and demand balance of urban integrated energy systems. It enables the acquisition of more accurate and integrated IB-IDR incentive strategies for each consumer, thereby obtaining more demand response resources and promoting the supply and demand balance of UEIS.

[0064] The technical solution in this application is to solve the above-mentioned technical problems, and the general idea is as follows:

[0065] Traditional IBDR in power systems neglects the complex interactions between multiple energy loads, and therefore cannot be directly applied to UIES (Unified Energy Utilization System). Integrated demand response (IDR) helps break down barriers between different energy sectors, enabling energy consumers to adjust their energy usage strategies according to their individual needs and habits. Incentive-based integrated demand response (IB-IDR) allows integrated energy service providers to use incentive signals to guide customers in changing their energy usage, greatly improving the flexibility of system operators. However, due to the coupling effect of consumer behavior in UIES, one type of load shedding may simultaneously lead to inconvenience for users in using other energy sources, which in turn increases the dissatisfaction costs for consumers participating in IB-IDR, making it difficult for integrated energy service providers to develop personalized incentive strategies for consumers with different consumption behaviors. Considering the diversity of energy types and the coupling effect of consumer behavior in UIES, existing IBDR methods in power systems cannot be directly used to obtain IB-IDR incentive strategies. The diversity and coupling characteristics of consumer energy consumption behavior both pose challenges to obtaining IB-IDR incentive strategies. To address the shortcomings of existing technologies, this invention proposes a comprehensive demand response method and system based on user behavior coupling modeling, in order to improve the accuracy of the IB-IDR strategy and promote supply and demand balance.

[0066] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0067] This invention provides a comprehensive demand response method based on user behavior coupling modeling, such as... Figure 1 As shown, the method includes:

[0068] S1. Acquire and preprocess historical data of the city's integrated energy system;

[0069] S2. Obtain the UIES demand forecasting model through preprocessed historical data and long short-term memory neural network, and use the UIES demand forecasting model to predict multivariate load forecasting data and electricity price forecasting data.

[0070] S3. Determine the model parameters based on historical data, predicted multivariate load forecast data, and electricity price forecast data, and construct the IB-IDR revenue model;

[0071] S4. Based on the IB-IDR overall benefit model and in accordance with multi-agent theory, an adaptive method is used to solve for the optimal IB-IDR strategy for each energy subsystem.

[0072] This invention uses multivariate load forecast data and electricity price forecast data as input data for the overall revenue model of demand response IB-IDR, thereby obtaining a demand response strategy. This can overcome the uncertainty of the demand side of UIES and achieve a more accurate and integrated IB-IDR incentive strategy for each consumer, so as to obtain more demand response resources and promote the supply and demand balance of UEIS.

[0073] The following is a detailed explanation of each step:

[0074] In step S1, historical data of the urban integrated energy system is acquired and preprocessed. The specific implementation process is as follows:

[0075] Historical data for urban integrated energy systems include: historical meteorological data, historical multi-load data, and historical energy price data.

[0076] Preprocessing includes normalization, expressed as follows:

[0077]

[0078] Where p′ represents the normalized historical data, p represents the original historical data, max(p) represents the maximum value in the original historical data, and min(p) represents the minimum value in the original historical data.

[0079] In step S2, the UIES demand forecasting model is obtained using preprocessed historical data and a long short-term memory neural network. This UIES model is then used to predict multivariate load forecasting data and electricity price forecasting data. The specific implementation process is as follows:

[0080] A long short-term memory neural network is trained using preprocessed historical data to obtain a UIES demand prediction model. The training process of this model is existing technology and will not be described in detail here.

[0081] The UIES demand forecasting model is used to predict multivariate load forecasting data and electricity price forecasting data.

[0082] When forecasting load, the UIES demand forecasting model inputs historical meteorological data and historical multi-load data (multi-load refers to load data composed of electricity, heating, and natural gas pipelines, etc. The model can only forecast one type of load data at a time, so it outputs forecast data for only one type of load at a time. The output of the forecasting model for different load types is the corresponding type of load data); when forecasting electricity prices, the model inputs historical meteorological data and historical energy price data.

[0083] In step S3, model parameters are determined based on historical data, multivariate load forecast data, and electricity price forecast data to construct the IB-IDR revenue model. The specific implementation process is as follows:

[0084] The main participants in IB-IDR include integrated energy service providers and integrated energy consumers. Integrated energy service providers offer incentives to integrated energy consumers and guide them to reduce electricity demand or replace electricity with other forms of energy through energy subsystems.

[0085] S301. Construct a profit model for the energy subsystem based on historical data, multi-source load forecast data, and electricity price forecast data. Details are as follows:

[0086] The reduction in energy purchase costs per energy subsystem due to consumer participation in IB-IDR, minus the incentives received by consumers, is considered the profit for each energy subsystem.

[0087]

[0088]

[0089] Where n represents the subsystem type, This represents the load forecast data for consumer i for energy type n in the j-th time interval. This represents the electricity price forecast data for energy type n in the j-th time interval. Δ represents the excitation signal from energy subsystem n to consumer i during the j-th time interval. i,j This represents the amount of load reduction for consumer i during the j-th time interval. Consumer comfort decreases when consumers change their energy demands to obtain rewards. The elasticity coefficient between the actual and expected load reduction levels of consumers follows a normal distribution. The expected value of the normal distribution. is the standard deviation of the normal distribution.

[0090] S302. Construct a profit model for integrated energy consumer participation in the IB-IDR based on historical data, multi-source load forecast data, and electricity price forecast data. Profit of integrated energy consumer participation in the IB-IDR. eu The profit from IB-IDR participation by integrated energy consumers is reduced by the consumer's discomfort costs. get:

[0091]

[0092]

[0093] Among them, Π i,j Let η be the IB-IDR incentive strategy matrix for integrated energy consumer i in the j-th time interval. For consumer i, the attitude towards the rewards and discomfort costs associated with participating in IB-IDR is η. i B ij Let B represent the behavioral coupling matrix of consumer i within the j-th time interval. ij It is a diagonally dominant matrix; Θ ij and Γ ij All of these are consumer-related discomfort cost parameters for consumer i within the j-th time interval.

[0094] S303. Determine the overall IB-IDR revenue model based on the profit model of the energy subsystem and the profit model of integrated energy consumer participation in IB-IDR. Specifically:

[0095] The goal of the IB-IDR model is to maximize the total profit of the UIES subsystem and consumers:

[0096]

[0097] In step S4, based on the IB-IDR overall benefit model and according to multi-agent theory, an adaptive method is used to solve for the optimal IB-IDR strategy for each energy subsystem. The specific implementation process is as follows:

[0098] S401, Initialization time j=0, revenue of each energy subsystem The current iteration number k and the maximum iteration number.

[0099] S402, Select excitation signal The IB-IDR excitation signal is randomly selected according to the following constraints.

[0100]

[0101] 0≤Δ i,j ≤Δ max

[0102] in, and Δ represents the lower and upper limits of the excitation signal for energy subsystem n, respectively; max This indicates the maximum load reduction.

[0103] S403. Calculate the demand response resources that the consumer can currently provide, that is, calculate the demand response resources that the consumer provides in response to the current incentive signal, i.e., the load reduction amount Δ. i,j That is, through randomly selected excitation signals. Substitute into step S301 Calculate the load reduction Δ i,j .

[0104] S404. Record the current IB-IDR state for the current time interval. Each energy subsystem follows the excitation signal. Incentivize integrated energy consumers and obtain the total profit from implementing IB-IDR in the current time interval, i.e., the profit of each energy subsystem participating in IB-IDR in the current time interval. Benefits of integrated energy consumers participating in IB-IDR within the current time frame sum:

[0105]

[0106] S405. Obtain the incentive strategy for one IB-IDR. Let j = j + 1, repeat steps S402 to S404 until one IB-IDR process is completed, i.e., j = T. Record the incentive strategy of the energy subsystem in this IB-IDR. income and cumulative return Q n,k :

[0107]

[0108] Where k is the iteration number, i = 0, ..., N, j = 0, ..., T.

[0109] S406. Let k = k + 1, and repeat steps S402 to S405 until k reaches the maximum number of iterations. If at this point, the cumulative return Q of each energy subsystem is... n,k Upon convergence, the excitation signals for each energy subsystem of the current IB-IDR strategy represent the optimal IB-IDR strategy. In each iteration, the excitation signals and profits are updated as follows:

[0110] In the k-th iteration, the excitation signal selected in the j-th time interval is If the corresponding profit If there is no increase compared to the previous iteration, then no update is needed; if the corresponding profit... If there is an increase compared to the previous iteration, then the excitation signal will be updated to... The corresponding profit is updated to

[0111]

[0112] in. Let γ be the profit corresponding to the excitation signal in the j-th time interval of the previous iteration, and γ∈[0,1] be the discount factor. This is the learning rate.

[0113] In the specific implementation process, the method also includes: S5, issuing incentive signals for each energy subsystem according to the optimal IB-IDR strategy to guide integrated energy consumers to participate in IB-IDR.

[0114] The following embodiments further describe the specific implementation of the present invention in detail. For a UIES with three energy subsystems—electricity, gas, and heat—an incentive strategy for the next 24 hours is provided to the integrated energy consumer. Specifically, it is implemented according to the following scheme:

[0115] 1. Data Preprocessing. Collect and preprocess historical UIES data, including historical meteorological data, historical multivariate load data, and historical energy price data, and normalize this data.

[0116]

[0117] Where p′ represents the normalized historical data, p represents the original historical data, max(p) represents the maximum value in the original historical data, and min(p) represents the minimum value in the original historical data;

[0118] 2. Based on the preprocessed historical data, a UIES demand forecasting model is trained using a long short-term memory neural network to obtain multivariate load forecasting data and electricity price forecasting data.

[0119] 3. Construct the revenue function (i.e., the profit model of the energy subsystem) for each energy subsystem:

[0120]

[0121]

[0122]

[0123]

[0124]

[0125]

[0126] in, Indicates the profit of the power subsystem. Indicates the profit of the natural gas subsystem. p represents the profit of the thermal subsystem. j e This represents the electricity price forecast data for the j-th time interval. The wholesale price of natural gas in the j-th time interval, in UIES, both combined heat and power units and gas-fired boilers use natural gas, therefore... Let ΔE represent the excitation signals from the electricity, natural gas, and heat energy subsystems to consumer i during the j-th time interval; i,j ,ΔG i,j ,ΔH i,j These represent the decreases in electricity load, natural gas load, and heat load for consumer i during the j-th time interval, respectively. These represent the elasticity coefficients between the actual reduction levels of electricity load, natural gas load, and heat load by consumers and their corresponding expected reduction levels, respectively. These represent the predicted data for the electricity load, natural gas load, and heat load of integrated energy consumer i in the j-th time interval, respectively. Follows a normal distribution Normal distribution Expectations Normal distribution standard deviation Follows a normal distribution Normal distribution Expectations Normal distribution standard deviation Follows a normal distribution Normal distribution Expectations Normal distribution The standard deviation.

[0127] 4. Constructing the integrated energy consumer revenue function (profit model for integrated energy consumers participating in IB-IDR):

[0128]

[0129]

[0130]

[0131]

[0132]

[0133] Where, Δ i,j =[ΔE i,j ΔG i,j ΔH i,j [ ] represents the multivariate load reduction matrix for integrated energy consumer i in the j-th time interval. Let η be the IB-IDR incentive strategy matrix for integrated energy consumer i in the j-th time interval. For consumer i, the attitude towards the rewards and discomfort costs associated with participating in IB-IDR is η.i B ij Let B represent the behavioral coupling matrix of consumer i within the j-th time interval. ij It is a diagonally dominant matrix, whose diagonal elements The values ​​can be randomly selected from the interval [0.7, 0.8], and their off-diagonal elements can be randomly selected from the interval [0.1, 0.2]. If the off-diagonal elements are set to 0, it indicates that the consumer does not exhibit behavioral coupling effects; Θ ij and Γ ij These are all consumer-related discomfort cost parameters for consumer i within the j-th time interval, and their elements θ can be randomly selected from the interval according to statistical laws. e ∈[0.3,0.6], θ h ∈[0.7,1.0], θ g ∈[0.5,0.8], λ e ∈[0.4,0.5], λ h ∈[0.2,0.3], λ g ∈[0.2,0.3].

[0134] 5. Construct the IB-IDR total return function (i.e., the IB-IDR total return model):

[0135]

[0136] 6. Initialize the revenue of each energy subsystem and excitation signals

[0137] 7. Randomly select IB-IDR excitation signals simultaneously according to the following constraints.

[0138]

[0139]

[0140]

[0141] 0≤ΔE i,j ≤ΔE max

[0142] 0≤ΔG i,j ≤ΔG max

[0143] 0≤ΔH i,j ≤ΔH max

[0144] in: These represent the excitation signals for the power subsystem, natural gas subsystem, and thermal subsystem, respectively. These represent the lower limits of the excitation signals for the power subsystem, natural gas subsystem, and thermal subsystem, respectively. These represent the upper limits of the excitation signals for the power subsystem, natural gas subsystem, and thermal subsystem, respectively; ΔE max ΔG max ΔH max These represent the maximum reductions in electricity, natural gas, and heat loads, respectively.

[0145] 8. Calculate the demand response resources provided by consumers in response to the current incentive signals, i.e., the load reduction amount ΔE. i,j ,ΔG i,j ,ΔH i,j .

[0146] 9. Each energy subsystem operates according to the excitation signal. Incentivize integrated energy consumers and capture the total profit from implementing IB-IDR in the current time period, i.e., the profit from the participation of the power subsystem, gas subsystem, and heat subsystem in IB-IDR within the current time period. Profits for integrated energy consumers participating in IB-IDR within the current time frame sum

[0147]

[0148]

[0149] 10. Repeat steps 7-9 until one IB-IDR process is completed, i.e., j=24, and record the excitation strategy of the power subsystem in this IB-IDR. profit and cumulative profit Q e,k Incentive strategy for the natural gas subsystem in this IB-IDR profit and cumulative profit Q g,k Incentive strategy for the power subsystem in this IB-IDR profit and cumulative profit Q h,k

[0150]

[0151]

[0152]

[0153] Where k is the iteration number, i = 0, ..., 100, j = 0, ..., 24.

[0154] 11. Let k = k + 1, and repeat steps 7 to 10 until k reaches the maximum number of iterations, 20000. If at this point, the cumulative return Q of each energy subsystem is... e,k Q g,k Q h,k If convergence is achieved, the excitation signals for each energy subsystem of the current IB-IDR strategy represent the optimal IB-IDR strategy. In each iteration, the excitation signals and profits are updated as follows:

[0155] In the k-th iteration, the excitation signal selected in the j-th time interval is If the corresponding profit If there is no increase compared to the previous iteration, then no update is needed; if the corresponding profit... If there is an increase compared to the previous iteration, then the excitation signal will be updated to... The corresponding profit is updated to

[0156]

[0157] in. Let γ be the profit corresponding to the excitation signal in the j-th time interval of the previous iteration, and γ∈[0,1] be the discount factor. This is the learning rate.

[0158] This invention also provides a comprehensive demand response system based on user behavior coupling modeling, such as... Figure 2 As shown, the system includes:

[0159] The data acquisition module is used to acquire and preprocess historical data of the urban integrated energy system;

[0160] The forecasting module is used to obtain the UIES demand forecasting model through preprocessed historical data and long short-term memory neural networks, and then use the UIES demand forecasting model to forecast multivariate load forecasting data and electricity price forecasting data.

[0161] The revenue model building module is used to determine model parameters and build the IB-IDR revenue model based on historical data, multivariate load forecast data, and electricity price forecast data.

[0162] The strategy acquisition module is used to solve the optimal IB-IDR strategy for each energy subsystem based on the IB-IDR total benefit model and in accordance with multi-agent theory, using an adaptive method.

[0163] The incentive strategy release module is used to release incentive signals for each energy subsystem based on the optimal IB-IDR strategy, guiding integrated energy consumers to participate in IB-IDR.

[0164] It is understood that the integrated demand response system based on user behavior coupling modeling provided in this embodiment of the invention corresponds to the integrated demand response method based on user behavior coupling modeling described above. The explanations, examples, and beneficial effects of the relevant content can be referred to the corresponding content in the integrated demand response method based on user behavior coupling modeling, and will not be repeated here.

[0165] This invention also provides a computer-readable storage medium storing a computer program for integrated demand response based on user behavior coupling modeling, wherein the computer program causes a computer to execute the integrated demand response method based on user behavior coupling modeling as described above.

[0166] This invention also provides an electronic device, comprising:

[0167] One or more processors;

[0168] Memory; and

[0169] One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including a comprehensive demand response method based on user behavior coupling modeling as described above.

[0170] In summary, compared with existing technologies, it has the following beneficial effects:

[0171] 1. In this embodiment of the invention, multi-source load forecast data and electricity price forecast data are used as input data for the overall revenue model of demand response IB-IDR, thereby obtaining demand response strategies. This can overcome the uncertainty of the demand side of UIES and realize a more accurate and integrated IB-IDR incentive strategy for each consumer, so as to obtain more demand response resources and promote the supply and demand balance of UEIS.

[0172] 2. Based on the constructed IB-IDR revenue model, the embodiments of the present invention adopt an adaptive approach to simultaneously seek the optimal IB-IDR incentive strategy for UIES that includes incentive signals from all energy subsystems, so as to improve the accuracy and efficiency of obtaining the IB-IDR incentive strategy.

[0173] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0174] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A comprehensive demand response method based on user behavior coupling modeling, characterized in that, include: S1. Acquire and preprocess historical data of the city's integrated energy system; S2. Obtain the UIES demand forecasting model through preprocessed historical data and long short-term memory neural network, and use the UIES demand forecasting model to predict multivariate load forecasting data and electricity price forecasting data. S3. Based on the historical data, predicted multivariate load forecast data, and electricity price forecast data, determine the model parameters and construct the IB-IDR revenue model; including: S301. Construct a profit model for the energy subsystem based on historical data, multi-source load forecast data, and electricity price forecast data, including: in, n Indicates the type of energy subsystem; Represents energy subsystem n Profits; Consumers i In the j For energy types within a time interval n Load forecast data; Indicates energy type n In the j Electricity price forecast data for each time period; Represents energy subsystem n In the j Consumers within a certain time interval i The excitation signal; Indicates the first j Consumers in a time interval i The amount of load reduction; The elasticity coefficient between the actual and expected load reduction levels of consumers follows a normal distribution. , The expected value of the normal distribution. The standard deviation of the normal distribution; S302. Construct a profit model for Integrated Energy Consumer Participation in IB-IDR based on historical data, multi-source load forecast data, and electricity price forecast data, including: in, Profits for integrated energy consumers participating in IB-IDR; For integrated energy consumers i In the j IB-IDR incentive strategy matrix within a time interval; for consumers i What is the attitude towards the rewards and discomfort costs associated with participating in IB-IDR? ; Indicates the first j Consumers within a time interval i The behavior coupling matrix; and All are the first j Consumers within a time interval i Consumer-related discomfort cost parameters; S303. Determine the overall IB-IDR benefit model based on the profit model of the energy subsystem and the profit model of integrated energy consumer participation in IB-IDR, including: The goal of the IB-IDR model is to maximize the total profit of the UIES subsystem and consumers: S4. Based on the aforementioned IB-IDR overall benefit model, and according to multi-agent theory, an adaptive method is used to solve for the optimal IB-IDR strategy for each energy subsystem; including: S401, Initialization Time j =0, revenue of each energy subsystem Current iteration number k and maximum number of iterations; S402, Select excitation signal IB-IDR excitation signals are randomly selected simultaneously according to the following constraints. : in, and Representing energy subsystems n The lower and upper limits of the excitation signal; Indicates the maximum load reduction; S403. Calculate the demand response resources provided by consumers in response to the current incentive signals, i.e., load shedding. ; S404. Record the current IB-IDR state for the current time interval. Each energy subsystem follows the excitation signal. Incentivize integrated energy consumers and capture the profits from each energy subsystem's participation in IB-IDR within the current time frame. The benefits for integrated energy consumers participating in IB-IDR within the current time frame. sum: S405, Order j = j +1, repeat steps S402~S404 until one IB-IDR process is completed, i.e. j =T, record the incentive strategy of this energy subsystem in this IB-IDR. ,income and cumulative returns : in, k For the number of iterations, , ; S406, Order k = k +1, repeat steps S402~S405 until... k If the maximum number of iterations is reached, and at this point, the cumulative return of each energy subsystem is... If convergence is achieved, then the excitation signals of each energy subsystem of the current IB-IDR are the optimal IB-IDR strategy.

2. The comprehensive demand response method based on user behavior coupling modeling as described in claim 1, characterized in that, The historical data includes Historical data for urban integrated energy systems include: historical meteorological data, historical multi-load data, and historical energy price data.

3. The comprehensive demand response method based on user behavior coupling modeling as described in claim 1, characterized in that, In step S406, during each iteration, the incentive signal and profit are updated as follows: In the k In the nth iteration, the 1st j The excitation signal selected within each time interval is If the corresponding profit If there is no increase compared to the previous iteration, then no update is needed; if the corresponding profit... If there is an increase compared to the previous iteration, then the excitation signal will be updated to... The corresponding profit is updated to : in, For the th iteration in the previous iteration j The profit corresponding to the incentive signal in each time interval. As a discount factor, This is the learning rate.

4. The comprehensive demand response method based on user behavior coupling modeling as described in any one of claims 1 to 3, characterized in that, The integrated demand response method also includes: S5. Based on the optimal IB-IDR strategy, issue incentive signals for each energy subsystem to guide integrated energy consumers to participate in IB-IDR.

5. A comprehensive demand response system based on user behavior coupling modeling, characterized in that, include: The data acquisition module is used to acquire and preprocess historical data of the urban integrated energy system; The forecasting module is used to obtain the UIES demand forecasting model through preprocessed historical data and a long short-term memory neural network, and to forecast multivariate load forecasting data and electricity price forecasting data through the UIES demand forecasting model. The revenue model construction module is used to determine model parameters and construct an IB-IDR revenue model based on the historical data, multivariate load forecast data, and electricity price forecast data; it includes: S301. Construct a profit model for the energy subsystem based on historical data, multi-source load forecast data, and electricity price forecast data, including: in, n Indicates the type of energy subsystem; Represents energy subsystem n Profits; Consumers i In the j For energy types within a time interval n Load forecast data; Indicates energy type n In the j Electricity price forecast data for each time period; Represents energy subsystem n In the j Consumers within a certain time interval i The excitation signal; Indicates the first j Consumers in a time interval i The amount of load reduction; The elasticity coefficient between the actual and expected load reduction levels of consumers follows a normal distribution. , The expected value of the normal distribution. The standard deviation of the normal distribution; S302. Construct a profit model for Integrated Energy Consumer Participation in IB-IDR based on historical data, multi-source load forecast data, and electricity price forecast data, including: in, Profits for integrated energy consumers participating in IB-IDR; For integrated energy consumers i In the j IB-IDR incentive strategy matrix within a time interval; for consumers i What is the attitude towards the rewards and discomfort costs associated with participating in IB-IDR? ; Indicates the first j Consumers within a time interval i The behavior coupling matrix; and All are the first j Consumers within a time interval i Consumer-related discomfort cost parameters; S303. Determine the overall IB-IDR benefit model based on the profit model of the energy subsystem and the profit model of integrated energy consumer participation in IB-IDR, including: The goal of the IB-IDR model is to maximize the total profit of the UIES subsystem and consumers: The strategy acquisition module is used to solve for the optimal IB-IDR strategy for each energy subsystem based on the overall IB-IDR profit model, according to multi-agent theory, and using an adaptive method; it includes: S401, Initialization Time j =0, revenue of each energy subsystem Current iteration number k and maximum number of iterations; S402, Select excitation signal IB-IDR excitation signals are randomly selected simultaneously according to the following constraints. : in, and Representing energy subsystems n The lower and upper limits of the excitation signal; Indicates the maximum load reduction; S403. Calculate the demand response resources provided by consumers in response to the current incentive signals, i.e., load shedding. ; S404. Record the current IB-IDR state for the current time interval. Each energy subsystem follows the excitation signal. Incentivize integrated energy consumers and capture the profits from each energy subsystem's participation in IB-IDR within the current time frame. The benefits for integrated energy consumers participating in IB-IDR within the current time frame. sum: S405, Order j = j +1, repeat steps S402~S404 until one IB-IDR process is completed, i.e. j =T, record the incentive strategy of this energy subsystem in this IB-IDR. ,income and cumulative returns : in, k For the number of iterations, , ; S406, Order k = k +1, repeat steps S402~S405 until... k If the maximum number of iterations is reached, and at this point, the cumulative return of each energy subsystem is... If convergence is achieved, then the excitation signals of each energy subsystem of the current IB-IDR are the optimal IB-IDR strategy.

6. The integrated demand response system based on user behavior coupling modeling as described in claim 5, characterized in that, The integrated demand response system also includes: The incentive strategy release module is used to release incentive signals for each energy subsystem based on the optimal IB-IDR strategy, guiding integrated energy consumers to participate in IB-IDR.

7. A computer-readable storage medium, characterized in that, It stores a computer program for integrated demand responsiveness based on user behavior coupling modeling, wherein the computer program causes a computer to execute the integrated demand responsiveness method based on user behavior coupling modeling as described in any one of claims 1 to 4.

8. An electronic device, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including methods for performing a comprehensive demand responsiveness method based on user behavior coupling modeling as described in any one of claims 1 to 4.

Images