System configuration method and apparatus based on probability prediction and credible adjustment potential quantification

Abstract

This invention relates to a system configuration method and apparatus based on probabilistic prediction and quantification of reliable adjustment potential. It inputs source-load data from typical scenarios into a trained QRLSTM model to obtain source-load probabilistic prediction results. It describes the temporal correlation between photovoltaics and loads through a small number of scenarios and effectively quantifies prediction uncertainty. A robust optimization algorithm is used to aggregate the flexibility resources of the heating and cooling networks sequentially, achieving decoupling of the scheduling of thermal power, thermal-cooling, and cooling-power systems. It accurately quantifies the maximum up / down adjustable potential and reliable adjustment potential of the heating and cooling networks to the power grid, overcoming the problem of strong information barriers between energy systems. This invention constructs a two-layer, multi-scenario collaborative optimization configuration model with source-load probabilistic prediction and the reliable adjustment potential of flexible resources as boundaries, aiming to minimize costs. It accurately characterizes the uncertainty of source-loads, quantifies the adjustment capability of flexible resources, and comprehensively improves the economy and flexibility of integrated energy system planning and operation.

Description

Technical Field

[0001] This invention relates to the field of integrated energy system optimization configuration technology, and in particular to a system configuration method and apparatus based on probabilistic prediction and quantification of reliable adjustment potential. Background Technology

[0002] With the rapid development of integrated energy systems, these systems encompass various energy forms such as electricity, heat, and cooling, forming a complex and highly coupled network. In actual operation and scheduling, information barriers exist between the various energy systems, making it particularly difficult to simultaneously obtain the global parameters of the electricity-heat-cooling network. Furthermore, the large-scale integration of new energy sources such as photovoltaics significantly increases the uncertainty within the system, placing higher demands on its flexibility. This increased uncertainty and flexibility requirements pose a significant challenge to the safe and stable operation of integrated energy systems.

[0003] Currently, source load forecasting primarily employs deterministic short-term forecasting methods. While these methods provide some predictive information, they struggle to fully reflect the changing characteristics and uncertainties of source loads. Furthermore, deterministic short-term forecasting mainly serves the daily operation of the system and is difficult to directly apply to long-term planning scenarios for integrated energy systems. Simultaneously, research on the flexibility of integrated energy systems is largely based on deterministic forecasting results, lacking in-depth research on the uncertainties of source load forecasting, making it difficult to accurately quantify the reliable regulation potential of multi-energy synergy.

[0004] Therefore, how to conduct source-load probability prediction and quantitative research on the credible regulation potential of multi-energy synergy on medium- and long-term time scales has become an urgent problem to be solved in integrated energy system planning. Summary of the Invention

[0005] In view of this, it is necessary to provide a system configuration method and apparatus based on probability prediction and credible adjustment potential quantification to address the aforementioned deficiencies of the prior art.

[0006] To address the aforementioned problems, in a first aspect, embodiments of the present invention provide a system configuration method based on probability prediction and credible adjustment potential quantification, comprising:

[0007] Collect historical data of the load source and corresponding meteorological data, and perform data preprocessing;

[0008] A QRLSTM model combining quantile regression and long short-term memory neural networks was established, and the model was trained and tested using preprocessed data.

[0009] Based on the DTW dynamic time warping algorithm, typical light-load joint time series scenarios are generated. The source-load data of the typical scenarios are input into the trained QRLSTM model to obtain the source-load probability prediction results.

[0010] Identify the flexible resources in the integrated energy system and establish an integrated energy system network model that includes electricity, heat, and cooling;

[0011] Based on the integrated energy system network model of electricity-heat-cooling, a robust optimization algorithm is used to aggregate the flexible resources of heating and cooling networks, realize the decoupling of scheduling of heating and power, heating and cooling, and cooling and power, and quantify the maximum adjustable potential and reliable adjustment potential of heating and cooling networks to the power grid.

[0012] With the goal of minimizing the cost of integrated energy systems, a two-layer, multi-scenario collaborative optimization configuration model is constructed.

[0013] Based on system operating parameters, source-load probability prediction results, the maximum power support range of the heating and cooling network to the power grid, and preset constraints, the two-layer optimization configuration model is solved, and the equipment configuration results of the integrated energy system are output.

[0014] Furthermore, the data preprocessing includes:

[0015] Data cleaning was performed on the historical source load data and corresponding meteorological data: the Z-score algorithm was used to detect outliers in the data and replace the detected outliers with zeros; linear interpolation was used to fill in missing values.

[0016] Furthermore, the establishment of a QRLSTM model combining quantile regression and long short-term memory neural networks, and the training and testing of the model using preprocessed data, specifically includes:

[0017] In the Tensorflow framework, a QRLSTM model is constructed by combining quantile regression and long short-term memory neural networks;

[0018] The preprocessed data samples are divided into training and test sets. A quantile loss function is defined, and the QRLSTM model is trained using the training set with the goal of minimizing the quantile loss function.

[0019] Use the test set to verify whether the probability prediction accuracy of the trained QRLSTM model meets the preset accuracy requirements. If yes, the model training is complete; otherwise, repeat the above steps until the preset accuracy requirements are met.

[0020] Furthermore, the generation of typical light-load joint time series scenarios based on the DTW dynamic time warping algorithm, and the input of source-load data of the typical scenarios into the trained QRLSTM model to obtain source-load probability prediction results, specifically includes:

[0021] By characterizing the temporal correlation between the source and the load, a photovoltaic-load joint scenario is generated;

[0022] The number of typical scenarios is determined based on the quadratic sum of intra-cluster errors and the contour coefficient method, and the typical scenarios and their corresponding probabilities are determined based on the DTW dynamic time warping algorithm.

[0023] Input the source load data corresponding to typical scenarios into the trained QRLSTM model to obtain the source load probability prediction results.

[0024] Furthermore, the determination of flexible resources in the integrated energy system and the establishment of an integrated energy system network model including electricity, heat, and cooling specifically include:

[0025] The flexible resources in the integrated energy system include combined cooling, heating and power (CCHP) units, gas-fired boiler equipment (GB), thermal energy storage equipment (HS), electric chiller equipment (EC), cold energy storage equipment (CS), photovoltaic units (PV), and electric energy storage equipment (ES).

[0026] A heat network and cold network model is established using a quality regulation method. In the model, the water supply flow rate is constant, and the inflow flow rate at each node equals the outflow flow rate at each node. For the heat network, the heat provided by the heating equipment enters the thermal system through a heat exchange station. The expression for this process is:

[0027]

[0028] In the formula, and Let be the heating power of CCHP and GB at time t, respectively. and The exothermic and charge-heating power of HS at time t are respectively, and c w The specific heat capacity of water, The traffic injected into node k at time t. and These are the heat source supply temperature and return water network temperature at node k at time t, respectively.

[0029] The expression for the dynamic change of water supply network temperature is:

[0030]

[0031] In the formula, and Let be the average temperatures of the water supply pipe and the return pipe p at time t, respectively. and Let be the outlet temperature and inlet temperature of water supply pipe p at time t, respectively. and These are the outlet and inlet temperatures of the return water pipe p at time t, respectively, where Δt is the time interval, and S is the inlet temperature. p L p and λ p These represent the cross-sectional area, length, and heat transfer coefficient of pipe p, respectively, and T. tW The ambient temperature around the pipeline, m p,t Let be the flow rate of pipe p at time t;

[0032] When hot water flows from multiple pipes to a node or from a node to multiple pipes, the mixing temperature at the node should satisfy the node temperature constraint. The expression for the node mixing temperature is:

[0033]

[0034] In the formula, Let t be the mixed water temperature at node k in the water supply network. and Each represents a set of pipes in the water supply / return network with node k as both the endpoint and the starting point.

[0035] The expression for the heat exchange process on the load side is:

[0036]

[0037] In the formula, H k,t Let be the heat load of node k at time t. Let be the regeneration temperature of node k at time t;

[0038] For a cold network, the cooled air supplied by the cooling equipment enters the cooling system through a cooling exchange station. The expression for this process is:

[0039]

[0040] In the formula, and Let be the cooling power of CCHP and EC at time t, respectively. and Let be the cooling discharge and charging power of CS at time t, respectively. and These are the cooling source supply temperature and the return water network temperature of node k at time t, respectively.

[0041] The modeling process for the cold network is similar to that for the heating network, and will not be repeated here. The expression for the cooling capacity exchange process of the load-side cold network is as follows:

[0042]

[0043] In the formula, C k,t Let be the cooling load of node k at time t. Let be the recooling temperature of node k at time t.

[0044] Furthermore, the integrated energy system network model based on electricity-heat-cooling employs a robust optimization algorithm to aggregate the flexibility resources of the heating and cooling networks, achieving decoupling of the scheduling of heating and power, heating and cooling, and cooling and power. Specifically, quantifying the maximum adjustable potential and reliable adjustment potential of the heating and cooling networks to the power grid includes:

[0045] A robust optimization algorithm is employed to establish a flexible aggregation model for the heating network, aiming to maximize the difference between the feasible upper and lower bounds of the aggregated CCHP output under the worst-case scenario.

[0046]

[0047] In the formula, and H CCHP Let ξ be the vector consisting of the feasible upper and lower bounds of CCHP output at each time step. t Let x(ξ) represent the uncertainty of CCHP output at time t, and U be the set of uncertainties of CCHP output at all times; t ) is a vector consisting of decision variables other than CCHP output at time t, including GB output, HS charging power, heat release power and HS charging and heat release state;

[0048] Solving the aforementioned heat network flexibility aggregation model yields the optimized results after heat network power aggregation. Utilizing the electro-thermal coupling relationship of CCHP Decoupling yields the regulation potential range provided by the heating network to the power grid. Utilizing the thermal-cold coupling relationship of CCHP Decoupling provides the heating network with a flexible power support range for the cooling network.

[0049] A robust optimization algorithm is used to establish a cold network flexibility aggregation model, aiming to maximize the difference between the feasible upper and lower bounds of the aggregated EC output under the worst-case scenario.

[0050]

[0051] In the formula, and C EC Let ζ be the vector consisting of the feasible upper and lower bounds of EC output at each time step. t Let x(ζ) represent the uncertainty of EC output at time t, and D be the set of uncertainties of EC output at all times; t ) is a vector consisting of decision variables other than EC output at time t, including CCHP output after thermal-cold decoupling, CS charging and cooling power, cooling power, and CS charging and cooling states;

[0052] Solving the aforementioned cold network flexibility aggregation model yields the optimized results after cold network power aggregation. Utilizing EC electrical-cold coupling relationship Decoupling yields the power regulation range of the cold network.

[0053] In an integrated energy system, flexibility resources can provide upward / downward flexibility, expressed as:

[0054]

[0055]

[0056] In the formula, F t CCHP,up F t ES,up F t EC,up and F t PV,up F represents the upward flexible adjustment capability of CCHP, ES, EC, and PV at time t. t CCHP,dn F t ES,dn F t EC,dn and F t PV,dn The downward flexible adjustment capabilities of CCHP, ES, EC, and PV at time t are respectively, r CCHP and r EC The gradeability rates for CCHP and EC are respectively. and These are the charging efficiency and discharging efficiency of the ES, respectively. and These are the maximum charging power and maximum discharging power of ES, respectively. ES For the capacity of ES, SOC t Let be the energy storage state of ES at time t. and SOC ES These represent the maximum and minimum energy storage states of an energy storage system (ES), P. t PV For the output of PV at time t, The maximum output of PV at time t. Let be the minimum output of PV at time t;

[0057] Flexibility resources in an integrated energy system can provide the maximum upside potential F t m,up The expression is:

[0058] F tm,up =F t CCHP,up +F t ES,up +F t PV,up +F t EC,up

[0059] Flexibility resources in an integrated energy system can provide the maximum downside adjustability potential F t m,dn The expression is:

[0060] F t m,dn =F t CCHP,dn +F t ES,dn +F t PV,dn +F t EC,dn

[0061] Because photovoltaic power is an uncontrollable source, its output fluctuates and is uncontrollable. Flexible resources within an integrated energy system can provide reliable upward adjustment potential. t b,up The expression is:

[0062] F t b,up =F t CCHP,up +F t ES,up -F t PV,dn +F t EC,up

[0063] Flexible resources in an integrated energy system can provide reliable downside regulation potential F t b,dn The expression is:

[0064] F t b,dn =F t CCHP,dn +F t ES,dn -F t PV,up +F t EC,dn .

[0065] Furthermore, the two-layer multi-scenario collaborative optimization configuration model includes an upper-layer model and a lower-layer model;

[0066] The upper-level model aims to minimize the total system investment cost and annual operating cost. The objective function of the upper-level model is:

[0067] min(C inv +C ope )

[0068] In the formula, C inv C represents the total investment cost. ope The annual operating cost of the system;

[0069] The lower-level model aims to minimize the annual operating cost of the system, and its objective function is:

[0070] minC ope

[0071] The two-layer, multi-scenario collaborative optimization configuration model, consisting of an upper-layer model and a lower-layer model, is as follows:

[0072]

[0073] In the formula, s represents a typical scenario, S represents the set of typical scenarios, and π represents the total number of scenarios. s Let be the dual variable of scenario s;

[0074] Total investment cost C of integrated energy system inv The expression is:

[0075]

[0076] In the formula, j is the j-th type of device among CCHP, GB, EC, ES, HS, CS, and PV, and k j Let M be the discount period for the j-th type of equipment. j Let j be the installation capacity of the j-th type of equipment. Let $\frac{j}{\frac ...

[0077] System annual operating cost C ope The expression is:

[0078]

[0079] In the formula, ρ s Let be the probability of a typical scenario s. and These represent the system's electricity purchase cost, gas purchase cost, and operation and maintenance cost of flexible resources under scenario s. Let be the penalty cost for insufficient system flexibility in scenario s, and let a and b be the weighting coefficients of economic cost and penalty cost for insufficient flexibility, respectively.

[0080] The expression for the penalty cost of insufficient system flexibility is:

[0081]

[0082] In the formula, F t def,up F t def,dn and F t def F represents the system's insufficient upward, downward, and overall flexibility at time t. t load,up and F t load,dn c represents the upward and downward adjustment demand of the electrical load at time t. def This is the penalty cost coefficient.

[0083] Secondly, embodiments of the present invention provide a system configuration apparatus based on probability prediction and credible adjustment potential quantification, comprising:

[0084] The data acquisition and preprocessing module is used to collect historical source load data and corresponding meteorological data, and to perform data preprocessing.

[0085] The model training module is used to build a QRLSTM model that combines quantile regression and long short-term memory neural networks, and to train and test the model using preprocessed data.

[0086] The source-load probability prediction module is used to generate typical light-load joint time series scenarios based on the DTW dynamic time warping algorithm. The source-load data of the typical scenarios are input into the trained QRLSTM model to obtain the source-load probability prediction results.

[0087] The system modeling module is used to identify flexible resources in an integrated energy system and establish an integrated energy system network model that includes electricity, heat, and cooling.

[0088] The scheduling decoupling module is used for the integrated energy system network model based on electricity-heat-cooling. It adopts a robust optimization algorithm to aggregate the flexibility resources of the heating network and the cooling network, realize the scheduling decoupling of heat and power, heat and cooling, and cooling and power, and quantify the maximum adjustable potential and reliable adjustment potential of the heating and cooling network to the power grid.

[0089] The cost optimization module is used to construct a two-layer, multi-scenario collaborative optimization configuration model with the goal of minimizing the cost of the integrated energy system.

[0090] The collaborative optimization configuration module is used to solve the two-layer optimization configuration model based on system operating parameters, source load probability prediction results, the maximum power support range of the heating and cooling network to the power grid, and preset constraints, and output the equipment configuration results of the integrated energy system.

[0091] Thirdly, the present invention also provides an electronic device, including a memory and a processor, wherein,

[0092] The memory is used to store programs;

[0093] The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the system configuration method based on probability prediction and credible adjustment potential quantification as described in the first aspect embodiment of the present invention.

[0094] Fourthly, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instructions, which, when executed by a processor, enable the implementation of the steps in the system configuration method based on probability prediction and credible adjustment potential quantification as described in the first aspect embodiment of the present invention.

[0095] This invention generates typical photovoltaic-load joint time-series scenarios based on the DTW algorithm. The source-load data of these typical scenarios are input into a trained QRLSTM model to obtain source-load probability prediction results. This allows for the description of the temporal correlation between photovoltaics and load through a small number of scenarios, and also enables the effective quantification of prediction uncertainty, providing crucial data support for integrated energy system analysis and decision-making. A robust optimization algorithm is employed to aggregate the flexibility resources of the heating and cooling networks sequentially, achieving decoupling of the scheduling of thermal power, thermal-cooling, and cooling-power systems. This accurately quantifies the maximum up / down adjustability and reliable adjustment potential of the heating and cooling networks to the power grid. This overcomes the problem of strong information barriers between energy systems and quantifies the reliable adjustment potential of multi-energy synergy, balancing the economy and flexibility of system operation. Using source-load probability prediction and the reliable adjustment potential of flexible resources as boundaries, and aiming at minimizing costs, this invention constructs a two-layer, multi-scenario collaborative optimization configuration model. This accurately characterizes the uncertainty of source and load, quantifies the adjustment capability of flexible resources, and comprehensively improves the economy and flexibility of integrated energy system planning and operation. Attached Figure Description

[0096] Figure 1 A flowchart of the system configuration method based on probability prediction and credible adjustment potential quantification provided by the present invention;

[0097] Figure 2 This is a schematic diagram of the load probability prediction results of the QRLSTM model provided by the present invention at different confidence levels.

[0098] Figure 3 A comprehensive energy system model diagram provided for this invention;

[0099] Figure 4 A structural block diagram of a system configuration device based on probability prediction and credible adjustment potential quantification provided by the present invention;

[0100] Figure 5 This is a structural block diagram of the electronic device provided by the present invention. Detailed Implementation

[0101] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0102] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0103] Currently, source load forecasting primarily employs deterministic short-term forecasting methods. While these methods provide some predictive information, they struggle to fully reflect the changing characteristics and uncertainties of source loads. Furthermore, deterministic short-term forecasting mainly serves the daily operation of the system and is difficult to directly apply to long-term planning scenarios for integrated energy systems. Simultaneously, research on the flexibility of integrated energy systems is largely based on deterministic forecasting results, lacking in-depth research on the uncertainties of source load forecasting, making it difficult to accurately quantify the reliable regulation potential of multi-energy synergy.

[0104] In view of this, the present invention provides a system configuration method based on probabilistic prediction and quantification of reliable adjustment potential. Using source load probabilistic prediction and the reliable adjustment potential of flexible resources as boundaries, and aiming at minimizing costs, a two-layer, multi-scenario collaborative optimization configuration model is constructed. This accurately characterizes the uncertainty of source loads, quantifies the adjustment capability of flexible resources, and comprehensively improves the economy and flexibility of integrated energy system planning and operation. The following will elaborate and describe this method through several embodiments.

[0105] Figure 1 The flowchart illustrates the system configuration method based on probability prediction and credible adjustment potential quantification provided by this invention. Figure 1 As shown, the system configuration method based on probability prediction and credible adjustment potential quantification includes at least the following steps:

[0106] Historical data on source load and corresponding meteorological data were collected and preprocessed.

[0107] In this embodiment, "source and load" refers to the collective term for energy supply (source) and energy demand (load). Here, energy supply mainly refers to equipment or systems that can provide electricity, heat, or cooling, such as photovoltaic (PV) units and combined cooling, heating, and power (CCHP) units; energy demand refers to various loads, such as electrical load, heat load, and cooling load.

[0108] Specifically, the first step is to collect historical source-load data and corresponding meteorological data. Historical source-load data forms the basis for building predictive models. By collecting historical data, we can understand the patterns and trends of source-load changes, providing data support for subsequent forecasting and configuration. Meteorological data has a significant impact on source-load; for example, meteorological factors such as sunlight intensity and temperature directly affect the power generation of photovoltaic units and load demand. Therefore, collecting relevant meteorological data and combining it with historical source-load data can improve the accuracy and reliability of predictive models.

[0109] Next, the historical source load data and corresponding meteorological data are cleaned: the Z-score algorithm is used to detect outliers in the data, and the detected outliers are replaced with zeros; linear interpolation is used to fill in missing values. It is understandable that the raw data may contain outliers and missing values, which can affect the performance and accuracy of the prediction model. Data preprocessing, such as cleaning outliers and filling in missing values, can improve the quality and usability of the data, thereby further improving the accuracy and stability of the prediction model.

[0110] A QRLSTM model combining quantile regression and long short-term memory neural networks was established, and the model was trained and tested using preprocessed data.

[0111] In a preferred embodiment of the present invention, the specific steps may include:

[0112] In the Tensorflow framework, a QRLSTM model is constructed by combining quantile regression and long short-term memory neural networks.

[0113] Here, TensorFlow is a widely used deep learning framework that provides a rich set of neural network layers and optimization algorithms. Quantile regression is a statistical method used to estimate the values ​​of conditional quantiles, such as conditional medians or conditional quartiles. In the QRLSTM model, the quantile regression layer outputs the probability distribution of the source payload data, i.e., the predicted values ​​at different quantiles. Long Short-Term Memory (LSTM) neural networks have the ability to remember long-sequence information. In the QRLSTM model, LSTM neural networks are used to capture the time-series characteristics of the source payload data and pass historical information to the quantile regression layer. By combining the quantile regression layer and the LSTM neural network, the QRLSTM model can simultaneously consider the probability distribution and time-series characteristics of the source payload data, thereby improving the accuracy of predictions.

[0114] The preprocessed data samples are divided into training and test sets. A quantile loss function is defined, and the QRLSTM model is trained using the training set with the goal of minimizing the quantile loss function.

[0115] In this embodiment, the preprocessed data samples are divided into a training set and a test set. The training set is used to train the model, i.e., to adjust the model's parameters to minimize the loss function; the test set is used to test the model, i.e., to evaluate the model's performance. The quantile loss function is a function that measures the difference between the model's predicted values ​​and the actual values. In the QRLSTM model, the quantile loss function is used to measure the difference between the model's predicted values ​​at different quantiles and the actual source payload data. By minimizing the quantile loss function, the model can learn the probability distribution characteristics of the source payload data and output more accurate predicted values.

[0116] Use the test set to verify whether the probability prediction accuracy of the trained QRLSTM model meets the preset accuracy requirements. If yes, the model training is complete; otherwise, repeat the above steps until the preset accuracy requirements are met.

[0117] Specifically, after training is complete, a test set is needed to evaluate the model's performance. In this embodiment, the model's performance is evaluated by calculating the difference between the predicted and actual values ​​of the QRLSTM model on the test set. If the model's prediction accuracy meets the accuracy requirements (e.g., the mean squared error, mean absolute error, etc. reach preset thresholds), then the model training is complete; otherwise, the process described above needs to be repeated, i.e., readjusting the model parameters or adding training data, to improve the model's prediction accuracy.

[0118] In this embodiment, by combining quantile regression and LSTM neural networks, the QRLSTM model can simultaneously consider the probability distribution and time series characteristics of the source load data, thereby improving prediction accuracy. By dividing the data samples into training and test sets and defining a quantile loss function for training, the QRLSTM model can learn the inherent patterns and characteristics of the source load data and possesses good generalization ability.

[0119] Based on the DTW dynamic time warping algorithm, typical light-load joint time series scenarios are generated. The source-load data of the typical scenarios are input into the trained QRLSTM model to obtain the source-load probability prediction results.

[0120] In a preferred embodiment of the present invention, the specific steps may include:

[0121] By characterizing the temporal correlation between the source and the load, a photovoltaic-load joint scenario is generated.

[0122] Specifically, source-load data can include photovoltaic (PV) output data and load data, which are correlated over time. For example, PV output is higher during the day and lower at night, while load data may also exhibit a similar diurnal variation pattern. By analyzing the temporal correlation of source-load data, a series of PV-load joint scenarios can be generated, representing possible combinations of PV output and load at different points in time.

[0123] The number of typical scenarios is determined by the quadratic sum of intra-cluster errors method and the contour coefficient method, and the typical scenarios and their corresponding probabilities are determined by the DTW dynamic time warping algorithm.

[0124] Specifically, the Sum of Squared Errors within Clusters (SSE) is a metric for evaluating clustering performance. It calculates the sum of squared distances from each data point within a cluster to the centroid of that cluster. A smaller SSE indicates better clustering performance.

[0125] The silhouette coefficient is used to evaluate the reasonableness of clustering, taking into account both the compactness within clusters and the separation between clusters. A higher silhouette coefficient value indicates a better clustering effect.

[0126] In this embodiment, by combining the quadratic sum of intra-cluster errors method and the contour coefficient method, a suitable number of typical scenarios can be determined so that these scenarios can fully represent the variation characteristics of the source load data, while avoiding an increase in computational complexity due to too many scenarios.

[0127] Furthermore, the DTW (Dynamic Time Warping) algorithm is used to measure the similarity between two time series. It allows the time series to be scaled along the time axis to find the optimal alignment. In this embodiment, the DTW algorithm is used to select the most representative typical scenarios from the generated photovoltaic-load joint scenarios. These typical scenarios reflect the main variation patterns and characteristics of the source-load data. Each typical scenario is assigned a corresponding probability, representing the likelihood of that scenario occurring in reality. This helps to account for the uncertainties of different scenarios in subsequent prediction and optimization processes.

[0128] Input the source load data corresponding to typical scenarios into the trained QRLSTM model to obtain the source load probability prediction results.

[0129] Specifically, a QRLSTM model combining quantile regression and long short-term memory neural networks was established, and preprocessed data was used for training and testing. Source load data from selected typical scenarios were input into the trained QRLSTM model, which then outputs the source load probability prediction results for these scenarios.

[0130] In this embodiment, source-load data from typical scenarios are input into a trained QRLSTM model to obtain source-load probability prediction results. This not only describes the temporal correlation between photovoltaics and loads through a small number of scenarios, but also effectively quantifies prediction uncertainty, providing key data support for integrated energy system analysis and decision-making.

[0131] Figure 2 This diagram illustrates the load probability prediction results of the QRLSTM model provided by this invention under different confidence levels. Taking load as an example, the trained QRLSTM model is tested based on test set data to obtain load probability prediction results under different confidence levels.

[0132] Identify the flexible resources in the integrated energy system and establish an integrated energy system network model that includes electricity, heat, and cooling.

[0133] Figure 3 A schematic diagram of the integrated energy system provided for this invention. (Refer to...) Figure 3 The integrated energy system includes the main power grid, gas grid, energy hubs, network model, and electrical, cooling, and heating loads. The network model includes cooling network, heating network, and distribution network models. The energy hubs contain various flexible resources, which in the integrated energy system include combined cooling, heating, and power (CCHP) units, gas-fired boilers (GB), thermal energy storage devices (HS), electric chillers (EC), cold energy storage devices (CS), photovoltaic (PV) units, and electric energy storage devices (ES).

[0134] Specifically, a heat network and cold network model is established using a quality regulation method. In the model, the water supply flow rate is constant, and the inflow flow rate at each node equals the outflow flow rate at each node. For the heat network, the heat provided by the heating equipment enters the thermal system through a heat exchange station. The expression for this process is:

[0135]

[0136] In the formula, and Let be the heating power of CCHP and GB at time t, respectively. and The exothermic and charge-heating power of HS at time t are respectively, and c w The specific heat capacity of water, The traffic injected into node k at time t. and These are the heat source supply temperature and return water network temperature at node k at time t, respectively.

[0137] To reflect the time delay in heat transfer from the heat source to the load side, a quasi-dynamic model is used to represent the temperature changes in the supply and return water networks of the heating network. The expression for the dynamic temperature change of the supply water network is as follows:

[0138]

[0139] In the formula, and Let be the average temperatures of the water supply pipe and the return pipe p at time t, respectively. and Let be the outlet temperature and inlet temperature of water supply pipe p at time t, respectively. and These are the outlet and inlet temperatures of the return water pipe p at time t, respectively, where Δt is the time interval, and S is the inlet temperature. p L p and λ p These represent the cross-sectional area, length, and heat transfer coefficient of pipe p, respectively, and T. t W The ambient temperature around the pipeline, m p,t Let be the flow rate of pipe p at time t;

[0140] When hot water flows from multiple pipes to a node or from a node to multiple pipes, the mixing temperature at the node should satisfy the node temperature constraint. The expression for the node mixing temperature is:

[0141]

[0142] In the formula, Let t be the mixed water temperature at node k in the water supply network. and Each represents a set of pipes in the water supply / return network with node k as both the endpoint and the starting point.

[0143] The expression for the heat exchange process on the load side is:

[0144]

[0145] In the formula, H k,t Let be the heat load of node k at time t. Let be the regeneration temperature of node k at time t; for a cold network, the cold air supplied by the cooling equipment enters the cooling system through the cooling exchange station, and the expression for this process is:

[0146]

[0147] In the formula, and Let be the cooling power of CCHP and EC at time t, respectively. and Let be the cooling discharge and charging power of CS at time t, respectively. and These are the cooling source supply temperature and the return water network temperature of node k at time t, respectively.

[0148] The modeling process for the cold network is similar to that for the heating network, and will not be repeated here. The expression for the cooling capacity exchange process of the load-side cold network is as follows:

[0149]

[0150] In the formula, C k,t Let be the cooling load of node k at time t. Let be the recooling temperature of node k at time t.

[0151] Based on the integrated energy system network model of electricity-heat-cooling, a robust optimization algorithm is used to aggregate the flexible resources of the heating network and the cooling network, realize the decoupling of the scheduling of heating and power, heating and cooling, and cooling and power, and quantify the maximum adjustable potential and reliable adjustment potential of the heating and cooling network to the power grid.

[0152] Specifically, firstly, a robust optimization algorithm is adopted to establish a flexible aggregation model for the heating network, aiming to maximize the difference between the feasible upper and lower bounds of the aggregated CCHP output under the worst-case scenario:

[0153]

[0154] In the formula, and H CCHP Let ξ be the vector consisting of the feasible upper and lower bounds of CCHP output at each time step. t Let x(ξ) represent the uncertainty of CCHP output at time t, and U be the set of uncertainties of CCHP output at all times; t ) is a vector consisting of decision variables other than CCHP output at time t, including GB output, HS charging power, heat release power and HS charging and heat release state;

[0155] Then, the heat network flexibility aggregation model is solved to obtain the optimized results after heat network power aggregation. Utilizing the electro-thermal coupling relationship of CCHP Decoupling yields the regulation potential range provided by the heating network to the power grid. Utilizing the thermal-cold coupling relationship of CCHP Decoupling provides the heating network with a flexible power support range for the cooling network.

[0156] Next, a robust optimization algorithm is used to establish a cold network flexibility aggregation model with the objective of maximizing the difference between the upper and lower bounds of the feasible EC output after aggregation in the worst-case scenario:

[0157]

[0158] In the formula, and C EC Let ζ be the vector consisting of the feasible upper and lower bounds of EC output at each time step. t Let x(ζ) represent the uncertainty of EC output at time t, and D be the set of uncertainties of EC output at all times; t ) is a vector consisting of decision variables other than EC output at time t, including CCHP output after thermal-cold decoupling, CS charging and cooling power, cooling power, and CS charging and cooling states;

[0159] Solving the aforementioned cold network flexibility aggregation model yields the optimized results after cold network power aggregation. Utilizing EC electrical-cold coupling relationship Decoupling yields the power regulation range of the cold network.

[0160] In an integrated energy system, flexibility resources can provide upward / downward flexibility, expressed as:

[0161]

[0162] In the formula, F t CCHP,up F t ES,up F t EC,up and F t PV,up F represents the upward flexible adjustment capability of CCHP, ES, EC, and PV at time t. t CCHP,dn F t ES,dn F t EC,dn and F t PV,dn The downward flexible adjustment capabilities of CCHP, ES, EC, and PV at time t are respectively, r CCHP and r EC The gradeability rates for CCHP and EC are respectively. and These are the charging efficiency and discharging efficiency of the ES, respectively. and These are the maximum charging power and maximum discharging power of ES, respectively. ES For the capacity of ES, SOC t Let be the energy storage state of ES at time t. and SOC ESThese represent the maximum and minimum energy storage states of an energy storage system (ES), P. t PV For the output of PV at time t, Let PV be the maximum output at time t. Let be the minimum output of PV at time t;

[0163] Flexibility resources in an integrated energy system can provide the maximum upside potential F t m,up The expression is:

[0164] F t m,up =F t CCHP,up +F t ES,up +F t PV,up +F t EC,up

[0165] Flexibility resources in an integrated energy system can provide the maximum downside adjustability potential F t m,dn The expression is:

[0166] F t m,dn =F t CCHP,dn +F t ES,dn +F t PV,dn +F t EC,dn

[0167] Because photovoltaic power is an uncontrollable source, its output fluctuates and is uncontrollable. Flexible resources within an integrated energy system can provide reliable upward adjustment potential. t b,up The expression is:

[0168] F t b,up =F t CCHP,up +F t ES,up -F t PV,dn +F t EC,up

[0169] Flexible resources in an integrated energy system can provide reliable downside regulation potential F t b,dn The expression is:

[0170] Ft b,dn =F t CCHP,dn +F t ES,dn -F t PV,up +F t EC,dn .

[0171] The embodiments of this invention employ a robust optimization algorithm to aggregate the flexibility resources of the heating network and the cooling network sequentially, thereby achieving decoupling of the scheduling of thermal power, thermal cooling, and cooling power. It accurately quantifies the maximum adjustable potential and reliable adjustment potential of the heating network and the cooling network to the grid on the up / down direction. This can overcome the problem of strong information barriers between various energy systems, and also quantify the reliable adjustment potential of multi-energy collaborative systems, taking into account both the economy and flexibility of system operation.

[0172] With the goal of minimizing the cost of integrated energy systems, a two-layer, multi-scenario collaborative optimization configuration model is constructed.

[0173] Specifically, the two-layer, multi-scenario collaborative optimization configuration model includes an upper-layer model and a lower-layer model.

[0174] The upper-level model aims to minimize the total system investment cost and annual operating cost. The objective function of the upper-level model is:

[0175] min(C inv +C ope )

[0176] In the formula, C inv C represents the total investment cost. ope The annual operating cost of the system;

[0177] The lower-level model aims to minimize the system's annual operating cost. The objective function for the lower-level model is:

[0178] minC ope

[0179] The two-layer, multi-scenario collaborative optimization configuration model, consisting of an upper-layer model and a lower-layer model, is as follows:

[0180]

[0181] In the formula, s represents a typical scenario, S represents the set of typical scenarios, and π represents the total number of scenarios. s Let be the dual variable of scenario s;

[0182] Total investment cost C of integrated energy system inv The expression is:

[0183]

[0184] In the formula, j is the j-th type of device among CCHP, GB, EC, ES, HS, CS, and PV, and k j Let M be the discount period for the j-th type of equipment. j Let j be the installation capacity of the j-th type of equipment. Let $\frac{j}{\frac ...

[0185] System annual operating cost C ope The expression is:

[0186]

[0187] In the formula, ρ s Let be the probability of a typical scenario s. and These represent the system's electricity purchase cost, gas purchase cost, and operation and maintenance cost of flexible resources under scenario s. Let be the penalty cost for insufficient system flexibility in scenario s, and let a and b be the weighting coefficients of economic cost and penalty cost for insufficient flexibility, respectively.

[0188] The expression for the penalty cost of insufficient system flexibility is:

[0189]

[0190] In the formula, F t def,up F t def,dn and F t def F represents the system's insufficient upward, downward, and overall flexibility at time t. t load,up and F t load,dn c represents the upward and downward adjustment demand of the electrical load at time t. def This is the penalty cost coefficient.

[0191] Based on system operating parameters, source-load probability prediction results, the maximum power support range of the heating and cooling network to the power grid, and preset constraints, the two-layer optimization configuration model is solved, and the equipment configuration results of the integrated energy system are output.

[0192] In this embodiment, the two-layer optimization configuration model is solved based on system operating parameters (such as equipment efficiency, cost coefficient, etc.), source-load probability prediction results for typical scenarios (i.e., predicted values ​​of photovoltaics and loads under different scenarios), the maximum power support range of the heating and cooling networks for the power grid (i.e., the maximum regulation potential that the heating and cooling networks can provide), and preset constraints (such as equipment capacity limitations, operating limitations, etc.).

[0193] Specifically, for the upper-level model of the two-layer optimization configuration model, since the number of decisions in the upper-level model is relatively small, a real-number encoded genetic algorithm is used for optimization. This genetic algorithm can accurately encode the type and number of flexible resources and find the optimal equipment configuration scheme through iterative optimization. For the lower-level model, given the equipment type and number determined by the upper-level model, the lower-level model calls the Gurobi solver to solve the mixed-integer linear programming model. Gurobi is a highly efficient mathematical optimization solver that can quickly find the optimal operating strategy that satisfies the constraints. Finally, based on the solution results of the two-layer model, the configuration results of each device in the system are output, including the type, number, and operating strategy of the device. By solving the two-layer optimization configuration model, the optimal configuration scheme of each device in the integrated energy system can be obtained. This scheme not only considers the investment and operating costs of the equipment, but also fully considers the impact of photovoltaic and load fluctuations and the flexibility of power supply equipment on system operation. This scheme can improve the flexibility and reliability of the system while ensuring its economic efficiency.

[0194] This invention generates typical photovoltaic-load joint time-series scenarios based on the DTW algorithm. The source-load data of these typical scenarios are input into a trained QRLSTM model to obtain source-load probability prediction results. This allows for the description of the temporal correlation between photovoltaics and load through a small number of scenarios, and also enables the effective quantification of prediction uncertainty, providing crucial data support for integrated energy system analysis and decision-making. A robust optimization algorithm is employed to aggregate the flexibility resources of the heating and cooling networks sequentially, achieving decoupling of the scheduling of thermal power, thermal-cooling, and cooling-power systems. This accurately quantifies the maximum up / down adjustability and reliable adjustment potential of the heating and cooling networks to the power grid. This overcomes the problem of strong information barriers between energy systems and quantifies the reliable adjustment potential of multi-energy synergy, balancing the economy and flexibility of system operation. Using source-load probability prediction and the reliable adjustment potential of flexible resources as boundaries, and aiming at minimizing costs, this invention constructs a two-layer, multi-scenario collaborative optimization configuration model. This accurately characterizes the uncertainty of source and load, quantifies the adjustment capability of flexible resources, and comprehensively improves the economy and flexibility of integrated energy system planning and operation.

[0195] Figure 4 The structural block diagram of the system configuration device based on probability prediction and credible adjustment potential quantification provided by the present invention is shown below. Figure 4 The system configuration device 400 based on probability prediction and credible adjustment potential quantification includes:

[0196] The data acquisition and preprocessing module 401 is used to acquire historical source load data and corresponding meteorological data, and to perform data preprocessing.

[0197] The model training module 402 is used to build a QRLSTM model that combines quantile regression and long short-term memory neural networks, and to train and test the model using preprocessed data.

[0198] The source-load probability prediction module 403 is used to generate typical light-load joint time series scenarios based on the DTW dynamic time warping algorithm. The source-load data of the typical scenarios are input into the trained QRLSTM model to obtain the source-load probability prediction results.

[0199] System modeling module 404 is used to determine the flexible resources in the integrated energy system and establish an integrated energy system network model that includes electricity, heat and cooling.

[0200] The scheduling decoupling module 405 is used for a comprehensive energy system network model based on electricity-heat-cooling. It adopts a robust optimization algorithm to aggregate the flexibility resources of the heating network and the cooling network, realize the scheduling decoupling of heating and power, heating and cooling, and cooling and power, and quantify the maximum adjustable potential and reliable adjustment potential of the heating and cooling network to the power grid.

[0201] The cost optimization module 406 is used to construct a two-layer, multi-scenario collaborative optimization configuration model with the goal of minimizing the cost of the integrated energy system.

[0202] The collaborative optimization configuration module 407 is used to solve the two-layer optimization configuration model based on system operating parameters, source load probability prediction results, the maximum power support range of the heat and cold network to the power grid, and preset constraints, and output the equipment configuration results of the integrated energy system.

[0203] The system configuration apparatus based on probability prediction and credible adjustment potential quantification provided by the present invention executes the system configuration method based on probability prediction and credible adjustment potential quantification provided in the above embodiments through the above modules. The system configuration method based on probability prediction and credible adjustment potential quantification has been described in detail in the above embodiments, and will not be repeated here.

[0204] Figure 5 The structural block diagram of the electronic device provided by the present invention is as follows: Figure 5 As shown, the present invention also provides an electronic device 500, which can be a mobile terminal, desktop computer, laptop, handheld computer, server, or other computing device. The electronic device 500 includes a processor 501 and a memory 502, wherein the memory 502 stores a system configuration program 503 based on probability prediction and quantification of reliable adjustment potential.

[0205] In some embodiments, memory 502 may be an internal storage unit of a computer device, such as a hard disk or memory. In other embodiments, memory 502 may be an external storage device of a computer device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc. Further, memory 502 may include both internal and external storage units of the computer device. Memory 502 is used to store application software and various types of data installed on the computer device, such as program code for installing the computer device. Memory 502 may also be used to temporarily store data that has been output or will be output. In one embodiment, when the system configuration program 503 based on probability prediction and credible adjustment potential quantification is executed by processor 501, the following steps are implemented:

[0206] Collect historical data of the load source and corresponding meteorological data, and perform data preprocessing;

[0207] A QRLSTM model combining quantile regression and long short-term memory neural networks was established, and the model was trained and tested using preprocessed data.

[0208] Based on the DTW dynamic time warping algorithm, typical light-load joint time series scenarios are generated. The source-load data of the typical scenarios are input into the trained QRLSTM model to obtain the source-load probability prediction results.

[0209] Identify the flexible resources in the integrated energy system and establish an integrated energy system network model that includes electricity, heat, and cooling;

[0210] Based on the integrated energy system network model of electricity-heat-cooling, a robust optimization algorithm is used to aggregate the flexible resources of heating and cooling networks, realize the decoupling of scheduling of heating and power, heating and cooling, and cooling and power, and quantify the maximum adjustable potential and reliable adjustment potential of heating and cooling networks to the power grid.

[0211] With the goal of minimizing the cost of integrated energy systems, a two-layer, multi-scenario collaborative optimization configuration model is constructed.

[0212] Based on system operating parameters, source-load probability prediction results, the maximum power support range of the heating and cooling network to the power grid, and preset constraints, the two-layer optimization configuration model is solved, and the equipment configuration results of the integrated energy system are output.

[0213] In some embodiments, processor 501 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 502 or process data, such as executing a system configuration program based on probability prediction and quantification of credible adjustment potential.

[0214] This embodiment also provides a computer-readable storage medium storing a system configuration program based on probability prediction and credible adjustment potential quantification. When the system configuration program 503 based on probability prediction and credible adjustment potential quantification is executed by a processor, it performs the following steps:

[0215] Collect historical data of the load source and corresponding meteorological data, and perform data preprocessing;

[0216] A QRLSTM model combining quantile regression and long short-term memory neural networks was established, and the model was trained and tested using preprocessed data.

[0217] Based on the DTW dynamic time warping algorithm, typical light-load joint time series scenarios are generated. The source-load data of the typical scenarios are input into the trained QRLSTM model to obtain the source-load probability prediction results.

[0218] Identify the flexible resources in the integrated energy system and establish an integrated energy system network model that includes electricity, heat, and cooling;

[0219] Based on the integrated energy system network model of electricity-heat-cooling, a robust optimization algorithm is used to aggregate the flexible resources of heating and cooling networks, realize the decoupling of scheduling of heating and power, heating and cooling, and cooling and power, and quantify the maximum adjustable potential and reliable adjustment potential of heating and cooling networks to the power grid.

[0220] With the goal of minimizing the cost of integrated energy systems, a two-layer, multi-scenario collaborative optimization configuration model is constructed.

[0221] Based on system operating parameters, source-load probability prediction results, the maximum power support range of the heating and cooling network to the power grid, and preset constraints, the two-layer optimization configuration model is solved, and the equipment configuration results of the integrated energy system are output.

[0222] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0223] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; 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; and these 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 system configuration method based on probability prediction and credible adjustment potential quantification, characterized in that, include: Collect historical data of the load source and corresponding meteorological data, and perform data preprocessing; A QRLSTM model combining quantile regression and long short-term memory neural networks was established, and the model was trained and tested using preprocessed data. Based on the DTW dynamic time warping algorithm, typical light-load joint time series scenarios are generated. The source-load data of the typical scenarios are input into the trained QRLSTM model to obtain the source-load probability prediction results. Identify the flexible resources in the integrated energy system and establish an integrated energy system network model that includes electricity, heat, and cooling; Based on the integrated energy system network model of electricity-heat-cooling, a robust optimization algorithm is used to aggregate the flexible resources of heating and cooling networks, realize the decoupling of scheduling of heating and power, heating and cooling, and cooling and power, and quantify the maximum adjustable potential and reliable adjustment potential of heating and cooling networks to the power grid. With the goal of minimizing the cost of integrated energy systems, a two-layer, multi-scenario collaborative optimization configuration model is constructed. Based on system operating parameters, source-load probability prediction results, the maximum power support range of the heating and cooling network to the power grid, and preset constraints, the two-layer optimization configuration model is solved, and the equipment configuration results of the integrated energy system are output.

2. The system configuration method based on probability prediction and credible adjustment potential quantification according to claim 1, characterized in that, The data preprocessing includes: Data cleaning was performed on the historical source load data and corresponding meteorological data: the Z-score algorithm was used to detect outliers in the data and replace the detected outliers with zeros; linear interpolation was used to fill in missing values.

3. The system configuration method based on probability prediction and credible adjustment potential quantification according to claim 1, characterized in that, The establishment of a QRLSTM model combining quantile regression and long short-term memory neural networks, and the training and testing of the model using preprocessed data, specifically includes: In the Tensorflow framework, a QRLSTM model is constructed by combining quantile regression and long short-term memory neural networks; The preprocessed data samples are divided into training and test sets. A quantile loss function is defined, and the QRLSTM model is trained using the training set with the goal of minimizing the quantile loss function. Use the test set to verify whether the probability prediction accuracy of the trained QRLSTM model meets the preset accuracy requirements. If yes, the model training is complete; otherwise, repeat the above steps until the preset accuracy requirements are met.

4. The system configuration method based on probability prediction and credible adjustment potential quantification according to claim 1, characterized in that, The method of generating typical light-charge joint time series scenarios based on the DTW dynamic time warping algorithm, inputting the source-charge data of the typical scenarios into a trained QRLSTM model, and obtaining source-charge probability prediction results specifically includes: By characterizing the temporal correlation between the source and the load, a photovoltaic-load joint scenario is generated; The number of typical scenarios is determined based on the quadratic sum of intra-cluster errors and the contour coefficient method, and the typical scenarios and their corresponding probabilities are determined based on the DTW dynamic time warping algorithm. Input the source load data corresponding to typical scenarios into the trained QRLSTM model to obtain the source load probability prediction results.

5. The system configuration method based on probability prediction and credible adjustment potential quantification according to claim 1, characterized in that, The determination of flexible resources in the integrated energy system and the establishment of an integrated energy system network model including electricity, heat, and cooling specifically include: The flexible resources in the integrated energy system include combined cooling, heating and power (CCHP) units, gas-fired boiler equipment (GB), thermal energy storage equipment (HS), electric chiller equipment (EC), cold energy storage equipment (CS), photovoltaic units (PV), and electric energy storage equipment (ES). A heat network and cold network model is established using a quality regulation method. In the model, the water supply flow rate is constant, and the inflow flow rate at each node equals the outflow flow rate at each node. For the heat network, the heat provided by the heating equipment enters the thermal system through a heat exchange station. The expression for this process is: In the formula, and Let be the heating power of CCHP and GB at time t, respectively. and The exothermic and charge-heating power of HS at time t are respectively, and c w The specific heat capacity of water, The traffic injected into node k at time t. and These are the heat source supply temperature and return water network temperature at node k at time t, respectively. The expression for the dynamic change of water supply network temperature is: In the formula, and Let be the average temperatures of the water supply pipe and the return pipe p at time t, respectively. and Let be the outlet temperature and inlet temperature of water supply pipe p at time t, respectively. and These are the outlet and inlet temperatures of the return water pipe p at time t, respectively, where Δt is the time interval, and S is the inlet temperature. p L p and λ p These represent the cross-sectional area, length, and heat transfer coefficient of pipe p, respectively, and T. t W The ambient temperature around the pipeline, m p,t Let be the flow rate of pipe p at time t; When hot water flows from multiple pipes to a node or from a node to multiple pipes, the mixing temperature at the node should satisfy the node temperature constraint. The expression for the node mixing temperature is: In the formula, Let t be the mixed water temperature at node k in the water supply network. and Each represents a set of pipes in the water supply / return network with node k as both the endpoint and the starting point. The expression for the heat exchange process on the load side is: In the formula, H k,t Let be the heat load of node k at time t. Let be the regeneration temperature of node k at time t; For a cold network, the cooled air supplied by the cooling equipment enters the cooling system through a cooling exchange station. The expression for this process is: In the formula, and Let be the cooling power of CCHP and EC at time t, respectively. and Let be the cooling discharge and charging power of CS at time t, respectively. and These are the cooling source supply temperature and the return water network temperature of node k at time t, respectively. The expression for the cooling capacity exchange process of the load-side cooling network is: In the formula, C k,t Let be the cooling load of node k at time t. Let be the recooling temperature of node k at time t.

6. The system configuration method based on probability prediction and credible adjustment potential quantification according to claim 5, characterized in that, The integrated energy system network model based on electricity, heat, and cooling employs a robust optimization algorithm to aggregate the flexibility resources of the heating and cooling networks, achieving decoupling of the scheduling of heat and power, heating and cooling, and cooling and power. Specifically, the quantification of the maximum adjustable potential and reliable adjustment potential of the heating and cooling networks to the power grid includes: A robust optimization algorithm is employed to establish a flexible aggregation model for the heating network, aiming to maximize the difference between the feasible upper and lower bounds of the aggregated CCHP output under the worst-case scenario. In the formula, and Let ξ be the vector consisting of the feasible upper and lower bounds of CCHP output at each time step. t Let x(ξ) represent the uncertainty of CCHP output at time t, and U be the set of uncertainties of CCHP output at all times; t ) is a vector consisting of decision variables other than CCHP output at time t, including GB output, HS charging power, heat release power and HS charging and heat release state; Solving the aforementioned heat network flexibility aggregation model yields the optimized results after heat network power aggregation. Utilizing the electro-thermal coupling relationship of CCHP Decoupling yields the regulation potential range provided by the heating network to the power grid. Utilizing the thermal-cold coupling relationship of CCHP Decoupling provides the heating network with a flexible power support range for the cooling network. A robust optimization algorithm is used to establish a cold network flexibility aggregation model, aiming to maximize the difference between the feasible upper and lower bounds of the aggregated EC output under the worst-case scenario. In the formula, and C EC Let ζ be the vector consisting of the feasible upper and lower bounds of EC output at each time step. t Let x(ζ) represent the uncertainty of EC output at time t, and D be the set of uncertainties of EC output at all times; t ) is a vector consisting of decision variables other than EC output at time t, including CCHP output after thermal-cold decoupling, CS charging and cooling power, cooling power, and CS charging and cooling states; Solving the aforementioned cold network flexibility aggregation model yields the optimized results after cold network power aggregation. Utilizing EC electrical-cold coupling relationship Decoupling yields the power regulation range of the cold network. In an integrated energy system, flexibility resources can provide upward / downward flexibility, expressed as: In the formula, and F represents the upward flexible adjustment capability of CCHP, ES, EC, and PV at time t. t CCHP,dn F t ES,dn F t EC,dn and F t PV,dn The downward flexible adjustment capabilities of CCHP, ES, EC, and PV at time t are respectively, r CCHP and r EC The gradeability rates for CCHP and EC are respectively. and These are the charging efficiency and discharging efficiency of the ES, respectively. and These are the maximum charging power and maximum discharging power of ES, respectively. ES For the capacity of ES, SOC t Let be the energy storage state of ES at time t. and SOC ES These represent the maximum and minimum energy storage states of an energy storage system (ES), P. t PV For the output of PV at time t, The maximum output of PV at time t. Let be the minimum output of PV at time t; Flexibility resources in an integrated energy system can provide the maximum upside potential F t m,up The expression is: F t m,up =F t CCHP,up +F t ES,up +F t PV,up +F t EC,up Flexibility resources in an integrated energy system can provide the maximum downside adjustability potential F t m,dn The expression is: F t m,dn =F t CCHP,dn +F t ES,dn +F t PV,dn +F t EC,dn Because photovoltaic power is an uncontrollable source, its output fluctuates and is uncontrollable. Flexible resources within an integrated energy system can provide reliable upward adjustment potential. t b,up The expression is: F t b,up =F t CCHP,up +F t ES,up -F t PV,dn +F t EC,up Flexible resources in an integrated energy system can provide reliable downside regulation potential F t b,dn The expression is: F t b,dn =F t CCHP,dn +F t ES,dn -F t PV,up +F t EC,dn 。 7. The system configuration method based on probability prediction and credible adjustment potential quantification according to claim 6, characterized in that, The dual-layer, multi-scenario collaborative optimization configuration model includes an upper-layer model and a lower-layer model; The upper-level model aims to minimize the total system investment cost and annual operating cost. The objective function of the upper-level model is: min(C inv +C ope ) In the formula, C inv C represents the total investment cost. ope The annual operating cost of the system; The lower-level model aims to minimize the annual operating cost of the system, and its objective function is: minC ope The two-layer, multi-scenario collaborative optimization configuration model, consisting of an upper-layer model and a lower-layer model, is as follows: In the formula, s represents a typical scenario, S represents the set of typical scenarios, and π represents the total number of scenarios. s Let be the dual variable of scenario s; Total investment cost C of integrated energy system inv The expression is: In the formula, j is the j-th type of device among CCHP, GB, EC, ES, HS, CS, and PV, and k j Let M be the discount period for the j-th type of equipment. j Let j be the installation capacity of the j-th type of equipment. Let $\frac{j}{\frac ... System annual operating cost C ope The expression is: In the formula, ρ s Let be the probability of a typical scenario s. and These represent the system's electricity purchase cost, gas purchase cost, and operation and maintenance cost of flexible resources under scenario s. Let be the penalty cost for insufficient system flexibility in scenario s, and let a and b be the weighting coefficients of economic cost and penalty cost for insufficient flexibility, respectively. The expression for the penalty cost of insufficient system flexibility is: In the formula, F t def,up F t def,dn and F t def F represents the system's insufficient upward, downward, and overall flexibility at time t. t load,up and F t load,dn c represents the upward and downward adjustment demand of the electrical load at time t. def This is the penalty cost coefficient.

8. A system configuration device based on probability prediction and credible adjustment potential quantification, characterized in that, include: The data acquisition and preprocessing module is used to collect historical source load data and corresponding meteorological data, and to perform data preprocessing. The model training module is used to build a QRLSTM model that combines quantile regression and long short-term memory neural networks, and to train and test the model using preprocessed data. The source-load probability prediction module is used to generate typical light-load joint time series scenarios based on the DTW dynamic time warping algorithm. The source-load data of the typical scenarios are input into the trained QRLSTM model to obtain the source-load probability prediction results. The system modeling module is used to identify flexible resources in an integrated energy system and establish an integrated energy system network model that includes electricity, heat, and cooling. The scheduling decoupling module is used for the integrated energy system network model based on electricity-heat-cooling. It adopts a robust optimization algorithm to aggregate the flexibility resources of the heating network and the cooling network, realize the scheduling decoupling of heat and power, heat and cooling, and cooling and power, and quantify the maximum adjustable potential and reliable adjustment potential of the heating and cooling network to the power grid. The cost optimization module is used to construct a two-layer, multi-scenario collaborative optimization configuration model with the goal of minimizing the cost of the integrated energy system. The collaborative optimization configuration module is used to solve the two-layer optimization configuration model based on system operating parameters, source load probability prediction results, the maximum power support range of the heating and cooling network to the power grid, and preset constraints, and output the equipment configuration results of the integrated energy system.

9. An electronic device, Its features are, Including memory and processor, among which, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the system configuration method based on probability prediction and credible adjustment potential quantification as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store computer-readable programs or instructions, which, when executed by a processor, enable the implementation of the steps in the system configuration method based on probability prediction and credible adjustment potential quantification as described in any one of claims 1 to 7.

Images