A device scheduling management method and system of an integrated energy system

Abstract

The application provides a kind of equipment scheduling management method and system of integrated energy system, comprising: obtaining the current predicted value of the load demand quantity and energy supply time length of various energy equipment of integrated energy system;The current predicted value is input into the device scheduling management digital twin model DT3 constructed in advance, to obtain the energy inflow, outflow and equipment capacity of various energy equipment;Based on the energy inflow, outflow and equipment capacity of various energy equipment, the start-stop and output of various energy equipment of integrated energy system are controlled;The device scheduling management digital twin model DT3 is constructed considering the coupling relationship between various energy flows of integrated energy system, input constraint and power flow constraint and equipment operation scheduling cost constraint, the coupling relationship between various energy flows is considered in the construction, the collaborative management between various energy subsystems in the operation process of integrated energy system is realized, and the flexibility of integrated and energy scheduling management is improved.

Description

Technical Field

[0001] This invention belongs to the field of integrated energy system control technology, specifically relating to a method and system for equipment scheduling and management of integrated energy systems. Background Technology

[0002] With the development of society and economy and the progress of technology, energy transformation characterized by energy interconnection is poised to take off. Integrated energy systems have become one of the important development trends in the future energy field. Among them, the core backbone of the power grid and the coupling, complementarity and interconnection of multiple energy sources have become one of the main manifestations of integrated energy systems.

[0003] Currently, due to the complexity of equipment in integrated energy systems, the equipment scheduling and management of integrated energy systems face the following problems: First, only individual scheduling and management of various energy devices within the integrated energy system is possible, rather than centralized scheduling and management, resulting in low flexibility in system energy scheduling; Second, existing integrated energy system scheduling and management mainly rely on dispatchers' prediction of the integrated energy system's load and the issuance of actual operation instructions to major energy subsystems based on experience. This operation is affected by human factors, lacks stability, and cannot achieve real-time scheduling and management of integrated energy devices. Therefore, how to solve the above problems is an urgent issue for those skilled in the art. Summary of the Invention

[0004] To overcome the shortcomings of the prior art, the present invention provides a method for equipment scheduling and management of an integrated energy system, comprising:

[0005] Obtain current forecasts of load demand and energy supply duration for various energy devices in the integrated energy system;

[0006] The current predicted value is input into the pre-built digital twin model DT3 for equipment scheduling and management to obtain the energy inflow, outflow and equipment capacity of various energy equipment;

[0007] Based on the energy inflow, outflow, and equipment capacity of the various energy devices, the start-up, shutdown, and output of the various energy devices in the integrated energy system are controlled;

[0008] The aforementioned digital twin model for equipment scheduling and management, DT3, is constructed by considering the coupling relationships between various energy flows in the integrated energy system, input constraints, power flow constraints, and equipment operation and scheduling cost constraints.

[0009] Preferably, the current forecast values ​​of load demand and energy supply duration for various energy devices in the integrated energy system are obtained, including:

[0010] Obtain current historical load data for various energy devices in the integrated energy system;

[0011] The current historical load data is input into a pre-built neural network model to obtain the current predicted values ​​of load demand and energy supply duration for various energy devices in the integrated energy system.

[0012] Preferably, the construction of the equipment scheduling management digital twin model DT3 includes:

[0013] With the goal of minimizing the operating cost of the integrated energy system, and considering the coupling relationship between various energy flows in the integrated energy system, a digital twin model DT1 for equipment scheduling and management during the commissioning phase is constructed.

[0014] Based on the digital twin model DT1 for equipment scheduling and management during the commissioning phase, a digital twin model DT2 for equipment scheduling and management during the operation phase is constructed, taking into account the input constraints and power flow constraints of the integrated energy system.

[0015] Based on the digital twin model DT2 for equipment scheduling management in the operation phase, a digital twin model DT3 for equipment scheduling management is constructed considering the constraints of equipment operation and scheduling costs in the integrated energy system; the constraints of equipment operation and scheduling costs in the integrated energy system are constructed considering the scheduling response of various types of equipment.

[0016] Preferably, based on the digital twin model DT1 for equipment scheduling and management during the commissioning phase, a digital twin model DT2 for equipment scheduling and management during the operation phase is constructed, considering the input constraints and power flow constraints of the integrated energy system, including:

[0017] Based on the digital twin model DT1 for equipment scheduling and management during the commissioning phase, a digital twin model DT1' for equipment scheduling and management during the commissioning phase is constructed, taking into account the input constraints of the integrated energy system.

[0018] Based on the digital twin model DT1' of equipment scheduling and management during the commissioning phase, a digital twin model DT2 of equipment scheduling and management during the operation phase is constructed, taking into account the power flow constraints of the integrated energy system.

[0019] Preferably, the construction of input constraints for the integrated energy system includes:

[0020] Based on historical load data of various energy equipment in the integrated energy system during the commissioning phase, calculate the predicted values ​​of load demand and energy supply duration of various energy equipment in the integrated energy system during the commissioning phase.

[0021] The predicted values ​​during the commissioning phase are input into the digital twin model DT1 for equipment scheduling and management during the commissioning phase to obtain the energy inflow, outflow, and equipment capacity of various energy equipment during a single commissioning phase.

[0022] Based on the energy inflow, outflow and equipment capacity of various energy devices after a single commissioning, the output and start / stop of various energy devices in the integrated energy system are commissioned and controlled.

[0023] Based on the operational data from multiple debugging sessions, the maximum and minimum values ​​of energy input for the integrated energy system are determined.

[0024] Based on the maximum and minimum values ​​of the energy input of the integrated energy system, an input constraint for the integrated energy system is constructed.

[0025] The commissioning operation data includes the energy inflow, outflow and capacity of various energy equipment during the commissioning period, as well as the actual load demand and energy supply duration of various energy equipment in the integrated energy system.

[0026] Preferably, the construction of integrated energy system power flow constraints includes:

[0027] Input the predicted values ​​of the commissioning phase into the digital twin model DT1' of the equipment scheduling and management during the commissioning phase to obtain the energy inflow, outflow and equipment capacity of various energy equipment during the secondary commissioning phase;

[0028] Based on the energy inflow, outflow and equipment capacity of various energy equipment after secondary commissioning, the output and start-up / stop of various energy equipment in the integrated energy system are commissioned and controlled.

[0029] Based on the operational data from multiple secondary debugging sessions, the maximum and minimum values ​​of the power flow in the integrated energy system were determined.

[0030] Based on the maximum and minimum values ​​of the power flow in the integrated energy system, power flow constraints for the integrated energy system are constructed.

[0031] Preferably, based on the digital twin model DT2 for equipment scheduling management during the operation phase, a digital twin model DT3 for equipment scheduling management is constructed considering the constraints of equipment operation and scheduling costs in the integrated energy system, including:

[0032] A1 calculates the predicted values ​​of load demand and energy supply duration for various energy equipment in the integrated energy system based on historical load data of the operation phases of various energy equipment in the integrated energy system.

[0033] A2 inputs the predicted values ​​of the operation phase into the digital twin model DT2 for equipment scheduling and management in the operation phase to obtain the energy inflow, outflow and equipment capacity of various energy equipment in the operation phase.

[0034] A3 controls the output and start / stop of various energy devices in the integrated energy system based on the energy inflow, outflow and equipment capacity of various energy devices after operation;

[0035] Based on the operation data after multiple operations, A4 determines the operation and scheduling cost constraints of the integrated energy system equipment, and adds the operation and scheduling cost constraints of the integrated energy system equipment to the operation phase equipment scheduling management digital twin model DT2 to obtain the operation phase equipment scheduling management digital twin model DT2'.

[0036] A5 determines whether the control result of the equipment scheduling and management digital twin model DT2' meets the operational stage prediction values ​​of the load demand and energy supply duration of various energy equipment in the integrated energy system. If it does, then the equipment scheduling and management digital twin model DT2' is the equipment scheduling and management digital twin model DT3. If it does not meet, execute steps A1-A5 until the control result of the equipment scheduling and management digital twin model DT2' meets the operational stage prediction values ​​of the load demand and energy supply duration of various energy equipment in the integrated energy system.

[0037] The operational data includes the energy inflow, outflow, and capacity of various energy devices during the operation period, the scheduling response of each type of device, and the actual load demand and energy supply duration of various energy devices in the integrated energy system.

[0038] The preferred digital twin model DT1 for equipment scheduling and management during the commissioning phase is as follows:

[0039]

[0040] In the formula, This represents the optimal function for commissioning and operation of the integrated energy system considering energy intercoupling, where P δ For δ-type energy flow input, L δ For the energy flow output of type δ, R vδ Let f2(P) represent the equipment capacity for energy type δ, N represent the total energy types, L represent the output matrix of the integrated energy system, P represent the input matrix of the integrated energy system, and C represent the coupling coefficient matrix of the integrated energy system, characterizing the coupling relationship between different energy forms. δ ,R vδ E(δ) ≤ c represents the constraint on the operation and maintenance costs of integrated energy system equipment, where c is the upper limit of the operation and maintenance costs of various types of integrated energy equipment; inα E(δ) represents the power injected into node α of the δ-type energy network. outα For the power flowing out of node α in the δ-type energy network, n e This represents the total number of nodes in the δ-class energy network.

[0041] The preferred digital twin model DT1' for equipment scheduling and management during the commissioning phase is as follows:

[0042]

[0043] In the formula, Pmax ≤P≤P min To constrain the total energy input of the integrated energy system during its operation, let P be the total energy input of the integrated energy system. max P represents the upper limit of the total energy input of the integrated energy system. min This represents the lower limit of the total energy input for the integrated energy system.

[0044] The preferred digital twin model DT2 for equipment scheduling and management during the operation phase is as follows:

[0045]

[0046] In the formula, F min ≤F≤F max For the integrated energy system network power flow constraints, F represents the integrated energy system network power flow. max F is the upper limit of network power flow in the integrated energy system. min This represents the lower limit of network power flow in an integrated energy system.

[0047] The preferred digital twin model DT2' for equipment scheduling and management during the operation phase is as follows:

[0048]

[0049] In the formula, f3(E trδ E tpδ E stδ )≤c represents the overall energy system equipment operation and scheduling cost constraint considering the scheduling response of various types of equipment, where E trδ E represents the equipment operation and scheduling costs of transmission equipment under different energy execution conditions in class δ energy. tpδ The equipment operation and scheduling costs of energy conversion equipment in δ-type energy under different energy execution conditions, E stδ This refers to the equipment operation and scheduling costs of energy storage devices in δ-type energy sources under different energy execution conditions.

[0050] Based on the same concept, the present invention also provides an equipment scheduling and management system for an integrated energy system, comprising:

[0051] The execution scenario prediction module is used to obtain the current predicted values ​​of the load demand and energy supply duration of various energy equipment in the integrated energy system;

[0052] The digital twin simulation module is used to input the current predicted value into the pre-built equipment scheduling and management digital twin model DT3 to obtain the energy inflow, outflow and equipment capacity of various energy equipment;

[0053] The equipment scheduling module is used to control the start-up, shutdown, and output of various energy equipment in the integrated energy system based on the energy inflow, outflow, and equipment capacity of the various types of energy equipment.

[0054] The aforementioned digital twin model for equipment scheduling and management, DT3, is constructed by considering the coupling relationships between various energy flows in the integrated energy system, input constraints, power flow constraints, and equipment operation and scheduling cost constraints.

[0055] Preferably, the execution scenario prediction module includes:

[0056] The data acquisition unit is used to acquire the current historical load data of various energy equipment in the integrated energy system;

[0057] The neural network computing unit is used to input the current historical load data into a pre-built neural network model to obtain the current predicted values ​​of the load demand and energy supply duration of various energy devices in the integrated energy system.

[0058] Preferably, the system further includes a model building module, the model building module comprising:

[0059] The commissioning model construction unit is used to construct a digital twin model DT1 for equipment scheduling and management during the commissioning phase, taking the minimum operating cost of the integrated energy system as the objective function and considering the coupling relationship between various energy flows in the integrated energy system.

[0060] The operation model construction unit is used to construct the operation phase equipment scheduling and management digital twin model DT2 based on the commissioning phase equipment scheduling and management digital twin model DT1, taking into account the input constraints and power flow constraints of the integrated energy system.

[0061] The operation model revision unit is used to construct an equipment scheduling management digital twin model DT3 based on the operation phase equipment scheduling management digital twin model DT2, taking into account the integrated energy system equipment operation scheduling cost constraints; the integrated energy system equipment operation scheduling cost constraints are constructed by considering the scheduling response of various types of equipment.

[0062] Preferably, the operation model revision unit includes:

[0063] The revised subunit 1 is used to calculate the predicted values ​​of the load demand and energy supply duration of various energy equipment in the integrated energy system based on the historical load data of the operation phase of various energy equipment in the integrated energy system.

[0064] The revised subunit 2 is used to input the predicted values ​​of the operation phase into the digital twin model DT2 for equipment scheduling and management of the operation phase, so as to obtain the energy inflow, outflow and equipment capacity of various energy equipment in the operation phase.

[0065] Sub-unit 3 is revised to be used for debugging the sub-unit to control the output and start / stop of various energy equipment in the integrated energy system based on the energy inflow, outflow and equipment capacity of various energy equipment after operation.

[0066] The revised subunit 4 is used to determine the integrated energy system equipment operation and scheduling cost constraint based on the operation data after multiple operations, and add the integrated energy system equipment operation and scheduling cost constraint to the operation phase equipment scheduling management digital twin model DT2 to obtain the operation phase equipment scheduling management digital twin model DT2'.

[0067] Revision subunit 5 is used to determine whether the control result of the equipment scheduling management digital twin model DT2' meets the operational stage prediction values ​​of load demand and energy supply duration of various energy equipment in the integrated energy system. If it meets the requirements, then the equipment scheduling management digital twin model DT2' is the equipment scheduling management digital twin model DT3. If it does not meet the requirements, the functions of steps revision subunit 1 to revision subunit 5 are executed until the control result of the equipment scheduling management digital twin model DT2' meets the operational stage prediction values ​​of load demand and energy supply duration of various energy equipment in the integrated energy system.

[0068] The operational data includes the energy inflow, outflow, and capacity of various energy devices during the operation period, the scheduling response of each type of device, and the actual load demand and energy supply duration of various energy devices in the integrated energy system.

[0069] Compared with the closest existing technology, the present invention has the following beneficial effects:

[0070] This invention provides a method and system for equipment scheduling and management of an integrated energy system, comprising: acquiring current predicted values ​​of load demand and energy supply duration for various types of energy equipment in the integrated energy system; inputting the current predicted values ​​into a pre-constructed digital twin model DT3 for equipment scheduling and management to obtain the energy inflow, outflow, and equipment capacity of various types of energy equipment; and controlling the start-up, shutdown, and output of various types of energy equipment in the integrated energy system based on the energy inflow, outflow, and equipment capacity of the various types of energy equipment. The digital twin model DT3 for equipment scheduling and management is constructed considering the coupling relationship between various energy flows in the integrated energy system, input constraints, power flow constraints, and equipment operation and scheduling cost constraints. This invention considers the coupling relationship between various energy flows, realizes the collaborative management of various energy subsystems during the operation of the integrated energy system, and improves the flexibility of integrated energy scheduling and management.

[0071] Meanwhile, this invention models the scheduling and management process, and the model self-corrects based on the actual operating results, thereby realizing automated scheduling and management of the integrated energy system, improving the real-time performance and accuracy of the integrated energy system's scheduling and management, and ensuring the safe and reliable operation of the integrated energy system. Attached Figure Description

[0072] Figure 1 A schematic diagram of an equipment scheduling and management method for an integrated energy system provided by the present invention;

[0073] Figure 2 A schematic diagram of an equipment scheduling and management system for an integrated energy system provided by the present invention;

[0074] Figure 3 This is a flowchart illustrating the construction process of the digital twin model for equipment scheduling and management provided in this embodiment of the invention. Detailed Implementation

[0075] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0076] Example 1:

[0077] This invention discloses a method for equipment scheduling and management of an integrated energy system, such as... Figure 1 As shown, it includes:

[0078] S1 obtains the current forecast values ​​of the load demand and energy supply duration of various energy devices in the integrated energy system;

[0079] S2 inputs the current predicted value into the pre-built digital twin model DT3 for equipment scheduling and management to obtain the energy inflow, outflow and equipment capacity of various energy equipment;

[0080] S3 controls the start-up, shutdown, and output of various energy devices in the integrated energy system based on the energy inflow, outflow, and device capacity of the various energy devices.

[0081] The equipment scheduling and management digital twin model DT3 is constructed by considering the coupling relationship between various energy flows in the integrated energy system, input constraints and power flow constraints, as well as equipment operation and scheduling cost constraints.

[0082] Before conducting integrated energy equipment scheduling and management, it is necessary to pre-build a digital twin model (DT3) for equipment scheduling and management, and to construct specific processes such as... Figure 3 As shown, it specifically includes:

[0083] Step A1 collects relevant energy equipment data for each energy form in the integrated energy system. This data includes: data related to electrical energy equipment (e.g., voltage U, current I, line impedance Z); and data related to natural gas (e.g., upstream and downstream pressure P of the gas pipeline network). g Gas temperature T in the gas pipeline g Data such as the friction coefficient f of gas pipelines; data on heating and cooling related equipment, such as heat medium flow rate q and heat medium temperature T. q wait.

[0084] Step A2 takes the minimum operating cost of the integrated energy system as the objective function, considers the coupling relationship between the various energy flows in the integrated energy system, and constructs a digital twin virtual model DT1 that matches the integrated energy system during the commissioning phase.

[0085] Specifically, the digital twin virtual model DT1 during the debugging phase is shown below:

[0086]

[0087] In the formula, This represents the input P of each energy flow considering energy intercoupling. δ Output L δ and the capacity R of various types of energy equipment vδ The optimal function for the commissioning and operation cost of the integrated energy system is given, where δ represents each energy type and N represents the total energy types; in the constraints, f2(P) δ ,R vδ )≤c represents the equipment operation and maintenance cost constraint in the integrated energy system. This cost constraint is constructed by considering various factors such as equipment capacity demand and energy input. c represents the allowable value of equipment operation and maintenance cost in the integrated energy system.

[0088] The coupling relationship between the various energy flows in an integrated energy system can be expressed as:

[0089] L=CP

[0090]

[0091] In the formula,

[0092] L represents the output matrix of the integrated energy system, L1, L2…L… N For the output of various types of energy in a comprehensive energy system;

[0093] P is the input matrix of the integrated energy system, P1, P2…P g For the input of various types of energy in the integrated energy system;

[0094] C is the coupling coefficient matrix, representing the coupling relationship between various energy forms, and η is the conversion efficiency of the energy conversion device between various energy forms.mn This represents the conversion efficiency between the m-th energy source and the n-th energy source.

[0095] ρ is the allocation coefficient that proportionally distributes each energy source to different energy transmission or conversion methods. mn This represents the ratio coefficient by which the m-th energy source is allocated to the n-th energy source.

[0096] The energy exchange constraint under the δ-th type of energy is:

[0097]

[0098] In the formula,

[0099] E(δ) inα This represents the energy injected into the α node of this δ-type energy network;

[0100] E(δ) outα This represents the energy flowing out of node α in this type of energy network;

[0101] n δ This represents the total number of nodes in the δ-type energy network.

[0102] Step A3: Construct a neural network model. Using a backpropagation (BP) neural network, input historical load data of the integrated energy system (including energy consumption periods and load magnitude during those periods) to predict the future final demand for different types of energy loads under various energy execution scenarios. xδ and energy supply duration t gδ Energy execution scenarios include various forms such as energy transfer between different energy sources and load reduction;

[0103] The future final demand for different types of energy loads under various energy execution scenarios, f xδ and energy supply duration t gδ Input the digital twin virtual model DT1 of the integrated energy system commissioning phase to obtain the energy inflow, outflow and equipment capacity of various energy equipment during the first commissioning phase;

[0104] Based on the energy inflow, outflow, and capacity of various energy devices during the initial commissioning phase, the start-up, shutdown, and output of the relevant energy devices are adjusted to meet the predicted energy execution scenarios.

[0105] Specifically, the construction of a neural network model includes:

[0106] (1) Initialize the parameters in the BP neural network and initialize the number of learning samples N in the BP neural network. test Number of predicted samples N pred Number of nodes N in input layer, hidden layer, and output layer in N hiN out The weights ω from the input layer to the hidden layer and from the hidden layer to the output layer. ih ω ho The threshold b between the input layer and the hidden layer, and between the output layer and the hidden layer. h b o Input historical load data from the integrated energy system, normalize the data, and set the maximum number of network training iterations E. max Learning rate p lr The target error is E0.

[0107] (2) Perform BP neural network sample training and calculate the output of each hidden layer and output layer forward;

[0108] The hidden layer output is:

[0109]

[0110] In the formula,

[0111] logsig is the activation function of the neural network;

[0112] x represents the historical load data matrix of the integrated energy system;

[0113] ω ih b h , where i represents the weights and thresholds from each node in the input layer to each node in the hidden layer, and h represents the h-th node in the hidden layer.

[0114] The output layer outputs:

[0115]

[0116] In the formula,

[0117] ω ho b o These are the weights and thresholds between each node in the output layer and each node in the hidden layer, respectively.

[0118] h represents the h-th node in the hidden layer, and o represents the o-th node in the output layer.

[0119] (3) Calculate the deviation between the output of the output layer and the expected output, specifically expressed as:

[0120]

[0121] In the formula, O net For the desired output, O out This is the output result for the output layer.

[0122] When the error is greater than the target error, the weights ω between the output layer and the hidden layer are adjusted. hoand threshold b o Make corrections:

[0123] ω ho t+1 =ω ho t +p lr O hi (O net -O out )

[0124]

[0125] In the formula, t and t+1 represent the number of iterations; ω ho t b o t ω represents the weights and thresholds between the output layer and the hidden layer at the t-th iteration. ho t+1 b o t+1 This represents the result after correcting the weights and thresholds between the output layer and the hidden layer after the (t+1)th iteration;

[0126] The weights ω between the input layer and the hidden layer ih and threshold b h Make corrections:

[0127]

[0128] b h t+1 =b h t +p lr (O net -O out )

[0129] In the formula, t and t+1 represent the number of iterations, and ω ih t b h t ω represents the weights and thresholds between the input layer and the hidden layer at the t-th iteration. ih t+1 b h t+1 This represents the result after correcting the weights and thresholds between the input layer and the hidden layer after the (t+1)th iteration.

[0130] (4) Repeat steps 2-3 to iteratively update the threshold and weights to find the optimal weights and thresholds; the weights are adjusted between neurons in different layers, and the thresholds are adjusted within neurons.

[0131] (5) Determine whether the algorithm iteration has ended. When the error E is less than the target error, the BP neural network training is complete, and the energy execution data, i.e., the predicted energy load demand for different categories, is obtained. xδ and energy supply duration t gδ Predicted values.

[0132] Step A4, based on operational data from multiple initial commissioning runs (including energy inflow, outflow, and capacity of various energy devices during the initial commissioning phase, as well as the actual load demand and energy supply duration of various energy devices in the integrated energy system), determines the input constraints of the integrated energy system, and then modifies the digital twin virtual model DT1 from the commissioning phase to obtain DT1'. Specifically, the expression for DT1' is as follows:

[0133]

[0134] In the formula, P min ≤P≤P max This represents the system input constraints during the commissioning and operation of the integrated energy system, mainly derived from data related to network constraints and equipment operation constraints of the integrated energy system during the commissioning phase.

[0135] Step A5 inputs the predicted values ​​of the commissioning phase into the digital twin model DT1' of the equipment scheduling and management during the commissioning phase to obtain the energy inflow, outflow and equipment capacity of various energy equipment during the secondary commissioning phase;

[0136] Based on the energy inflow, outflow and equipment capacity of various energy equipment after secondary commissioning, the output and start-up / stop of various energy equipment in the integrated energy system are commissioned and controlled.

[0137] Based on operational data from multiple secondary commissioning cycles, the power flow constraints of the integrated energy system are determined. Then, based on the digital twin virtual model DT1' of the integrated energy system commissioning phase, a digital twin virtual model DT2 for equipment scheduling and management during the integrated energy system operation phase is constructed. The expression for DT2 is as follows:

[0138]

[0139] In the formula, F min ≤F≤F max This represents the system network power flow constraints during the operation of an integrated energy system.

[0140] Step A6: Based on the digital twin virtual model DT2 for equipment scheduling management during the operation phase, input relevant data on the energy execution prediction results during the operation phase, and control the output and start / stop of relevant energy equipment in the integrated energy system during the operation phase.

[0141] Step A7, based on the energy execution data, start-up / shutdown and output status data generated during the operation phase, determines the integrated energy system equipment operation and scheduling cost constraints (constructed considering the scheduling response of various types of equipment), updates the equipment scheduling management digital twin virtual model DT2 for the operation phase, and obtains the equipment scheduling management digital twin virtual model DT2' for the operation phase. Specifically, the expression for DT2' is as follows:

[0142]

[0143] In the formula, f3(E tr E tp E st )≤c represents the integrated energy system equipment scheduling and operation cost considering the scheduling response of various types of equipment. This includes various factors such as the proportion of equipment participating in each category of integrated energy scheduling and the required costs. The equipment types in the integrated energy system include: energy transmission equipment, energy conversion equipment, and energy storage equipment.

[0144] The overall energy system equipment scheduling and operation cost, considering the scheduling response of various types of equipment, can be expressed as:

[0145]

[0146] In the formula, E trδ E tpδ E stδ These represent the start-up and shutdown scheduling costs for different energy transmission equipment, energy conversion equipment, and energy storage equipment under different energy execution conditions; I etrδ I etpδ I estδ These respectively represent the equipment response levels of energy transmission, energy conversion, and energy storage devices under different energy execution conditions; sgn δ (Δx) is a signal function that characterizes the scheduling execution category of the device, where Δx = f xδ -f gδ This represents the difference between the demand and supply of a certain type of energy.

[0147] sgn δ The value of the (Δx) function is

[0148]

[0149] sgn δ When (Δx) = 0, the device does not participate in scheduling;

[0150] sgn δ When (Δx) = +1, the device participates in energy transfer;

[0151] sgn δWhen (Δx) = -1, the equipment participates in load reduction.

[0152] Step A8 determines whether the integrated energy iterative scheduling digital twin virtual model DT2' meets the requirements of the predicted integrated energy execution scenario. If it meets the requirements of the predicted integrated energy execution scenario, the final integrated energy equipment scheduling model DT3 is constructed based on DT2'. If it does not meet the requirements of the predicted integrated energy execution scenario, step A7 is repeated until DT2' meets the expression requirements, and the final integrated energy scheduling model DT3 is output.

[0153] The digital twin virtual models iterate and update each other to improve the expression accuracy of the digital twin, ultimately realizing the scheduling and management of integrated energy system equipment.

[0154] Example 2:

[0155] This invention discloses an equipment scheduling and management system for an integrated energy system, such as... Figure 2 As shown, it includes:

[0156] The execution scenario prediction module is used to obtain the current predicted values ​​of the load demand and energy supply duration of various energy equipment in the integrated energy system;

[0157] The digital twin simulation module is used to input the current predicted value into the pre-built equipment scheduling and management digital twin model DT3 to obtain the energy inflow, outflow and equipment capacity of various energy equipment;

[0158] The equipment scheduling module is used to control the start-up, shutdown, and output of various energy devices in the integrated energy system based on the energy inflow, outflow, and equipment capacity of the various energy devices.

[0159] The equipment scheduling and management digital twin model DT3 is constructed by considering the coupling relationship between various energy flows in the integrated energy system, input constraints and power flow constraints, as well as equipment operation and scheduling cost constraints.

[0160] Preferably, the execution scenario prediction module includes:

[0161] The data acquisition unit is used to acquire the current historical load data of various energy equipment in the integrated energy system;

[0162] The neural network computing unit is used to input the current historical load data into a pre-built neural network model to obtain the current predicted values ​​of the load demand and energy supply duration of various energy devices in the integrated energy system.

[0163] Preferably, the system further includes a model building module, the model building module comprising:

[0164] The commissioning model construction unit is used to construct a digital twin model DT1 for equipment scheduling and management during the commissioning phase, taking the minimum operating cost of the integrated energy system as the objective function and considering the coupling relationship between various energy flows in the integrated energy system.

[0165] The operation model construction unit is used to construct the operation phase equipment scheduling and management digital twin model DT2 based on the commissioning phase equipment scheduling and management digital twin model DT1, taking into account the input constraints and power flow constraints of the integrated energy system.

[0166] The operation model revision unit is used to construct an equipment scheduling management digital twin model DT3 based on the operation phase equipment scheduling management digital twin model DT2, taking into account the integrated energy system equipment operation scheduling cost constraints; the integrated energy system equipment operation scheduling cost constraints are constructed by considering the scheduling response of various types of equipment.

[0167] Preferably, the operation model revision unit includes:

[0168] The revised subunit 1 is used to calculate the predicted values ​​of the load demand and energy supply duration of various energy equipment in the integrated energy system based on the historical load data of the operation phase of various energy equipment in the integrated energy system.

[0169] The revised subunit 2 is used to input the predicted values ​​of the operation phase into the digital twin model DT2 for equipment scheduling and management of the operation phase, so as to obtain the energy inflow, outflow and equipment capacity of various energy equipment in the operation phase.

[0170] Sub-unit 3 is revised to be used for debugging the sub-unit to control the output and start / stop of various energy equipment in the integrated energy system based on the energy inflow, outflow and equipment capacity of various energy equipment after operation.

[0171] The revised subunit 4 is used to determine the integrated energy system equipment operation and scheduling cost constraint based on the operation data after multiple operations, and add the integrated energy system equipment operation and scheduling cost constraint to the operation phase equipment scheduling management digital twin model DT2 to obtain the operation phase equipment scheduling management digital twin model DT2'.

[0172] Revision subunit 5 is used to determine whether the control result of the equipment scheduling management digital twin model DT2' meets the operational stage prediction values ​​of load demand and energy supply duration of various energy equipment in the integrated energy system. If it meets the requirements, then the equipment scheduling management digital twin model DT2' is the equipment scheduling management digital twin model DT3. If it does not meet the requirements, the functions of steps revision subunit 1 to revision subunit 5 are executed until the control result of the equipment scheduling management digital twin model DT2' meets the operational stage prediction values ​​of load demand and energy supply duration of various energy equipment in the integrated energy system.

[0173] The operational data includes the energy inflow, outflow, and capacity of various energy devices during the operation period, the scheduling response of each type of device, and the actual load demand and energy supply duration of various energy devices in the integrated energy system.

[0174] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0175] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0176] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0177] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0178] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and not to limit its protection scope. Although this application has been described in detail with reference to the above embodiments, those skilled in the art should understand that after reading this application, they can still make various changes, modifications or equivalent substitutions to the specific implementation of the application, but these changes, modifications or equivalent substitutions are all within the protection scope of the claims pending approval.

Claims

1. A method for equipment scheduling and management of an integrated energy system, characterized in that, include: Obtain current forecasts of load demand and energy supply duration for various energy devices in the integrated energy system; The current predicted value is input into the pre-built digital twin model DT3 for equipment scheduling and management to obtain the energy inflow, outflow and equipment capacity of various energy equipment; Based on the energy inflow, outflow, and equipment capacity of the various energy devices, the start-up, shutdown, and output of the various energy devices in the integrated energy system are controlled; The aforementioned digital twin model for equipment scheduling and management, DT3, is constructed by considering the coupling relationships between various energy flows in the integrated energy system, input constraints, power flow constraints, and equipment operation and scheduling cost constraints. The construction of the device scheduling and management digital twin model DT3 includes: With the goal of minimizing the operating cost of the integrated energy system, and considering the coupling relationship between various energy flows in the integrated energy system, a digital twin model DT1 for equipment scheduling and management during the commissioning phase is constructed. Based on the digital twin model DT1 for equipment scheduling and management during the commissioning phase, a digital twin model DT2 for equipment scheduling and management during the operation phase is constructed, taking into account the input constraints and power flow constraints of the integrated energy system. Based on the digital twin model DT2 for equipment scheduling management in the operation phase, a digital twin model DT3 for equipment scheduling management is constructed considering the constraints of equipment operation and scheduling costs in the integrated energy system; the constraints of equipment operation and scheduling costs in the integrated energy system are constructed considering the scheduling response of various types of equipment.

2. The method as described in claim 1, characterized in that, The acquisition of current predicted values ​​for the load demand and energy supply duration of various energy devices in the integrated energy system includes: Obtain current historical load data for various energy devices in the integrated energy system; The current historical load data is input into a pre-built neural network model to obtain the current predicted values ​​of load demand and energy supply duration for various energy devices in the integrated energy system.

3. The method as described in claim 1, characterized in that, The construction of the operational phase digital twin model DT2, based on the commissioning phase equipment scheduling management digital twin model DT1 and considering the input constraints and power flow constraints of the integrated energy system, includes: Based on the aforementioned digital twin model DT1 for equipment scheduling and management during the commissioning phase, and considering the input constraints of the integrated energy system, a new digital twin model DT1 for equipment scheduling and management during the commissioning phase is constructed. ’ ; Based on the digital twin model DT1 for equipment scheduling and management during the commissioning phase ’ Considering the power flow constraints of the integrated energy system, a digital twin model DT2 is constructed for equipment scheduling and management during the operation phase.

4. The method as described in claim 3, characterized in that, The construction of the input constraints for the integrated energy system includes: Based on historical load data of various energy equipment in the integrated energy system during the commissioning phase, calculate the predicted values ​​of load demand and energy supply duration of various energy equipment in the integrated energy system during the commissioning phase. The predicted values ​​during the commissioning phase are input into the digital twin model DT1 for equipment scheduling and management during the commissioning phase to obtain the energy inflow, outflow, and equipment capacity of various energy equipment during a single commissioning phase. Based on the energy inflow, outflow and equipment capacity of various energy devices after a single commissioning, the output and start / stop of various energy devices in the integrated energy system are commissioned and controlled. Based on the operational data from multiple debugging sessions, the maximum and minimum values ​​of energy input for the integrated energy system are determined. Based on the maximum and minimum values ​​of the energy input of the integrated energy system, an input constraint for the integrated energy system is constructed. The commissioning operation data includes the energy inflow, outflow and capacity of various energy equipment during the commissioning period, as well as the actual load demand and energy supply duration of various energy equipment in the integrated energy system.

5. The method as described in claim 4, characterized in that, The construction of the power flow constraints of the integrated energy system includes: The predicted values ​​during the commissioning phase are input into the DT1 digital twin model for equipment scheduling and management during the commissioning phase. ’ This allows us to obtain the energy inflow, outflow, and equipment capacity of various energy devices during the secondary commissioning phase. Based on the energy inflow, outflow and equipment capacity of various energy equipment after secondary commissioning, the output and start-up / stop of various energy equipment in the integrated energy system are commissioned and controlled. Based on the operational data from multiple secondary debugging sessions, the maximum and minimum values ​​of the power flow in the integrated energy system were determined. Based on the maximum and minimum values ​​of the power flow in the integrated energy system, power flow constraints for the integrated energy system are constructed.

6. The method as described in claim 3, characterized in that, The digital twin model DT3 for equipment scheduling management, based on the operational phase equipment scheduling management digital twin model DT2, and considering the constraints of integrated energy system equipment operation and scheduling costs, includes: A1 calculates the predicted values ​​of load demand and energy supply duration for various energy equipment in the integrated energy system based on historical load data of the operation phases of various energy equipment in the integrated energy system. A2 inputs the predicted values ​​of the operation phase into the digital twin model DT2 for equipment scheduling and management in the operation phase to obtain the energy inflow, outflow and equipment capacity of various energy equipment in the operation phase. A3 controls the output and start / stop of various energy devices in the integrated energy system based on the energy inflow, outflow and equipment capacity of various energy devices after operation; Based on operational data from multiple operations, A4 determines the integrated energy system equipment operation and scheduling cost constraints, and adds these constraints to the operational phase equipment scheduling management digital twin model DT2, thus obtaining the operational phase equipment scheduling management digital twin model DT2. ’ ; A5 determines the equipment scheduling management digital twin model DT2. ’ Whether the regulation results meet the predicted values ​​of load demand and energy supply duration for various energy devices in the integrated energy system during the operational phase: If they do, then the equipment scheduling and management digital twin model DT2... ’ This is the equipment scheduling management digital twin model DT3; if it does not meet the requirements, proceed with steps A1-A5 until the equipment scheduling management digital twin model DT2 is reached. ’ The regulation results meet the predicted values ​​for the load demand and energy supply duration of various energy equipment in the integrated energy system during the operation phase. The operational data includes the energy inflow, outflow, and capacity of various energy devices during the operation period, the scheduling response of each type of device, and the actual load demand and energy supply duration of various energy devices in the integrated energy system.

7. The method as described in claim 6, characterized in that, The digital twin model DT1 for equipment scheduling and management during the commissioning phase is as follows: In the formula, This represents the optimal function for commissioning and operating the integrated energy system considering energy intercoupling, where... P δ for δ Energy flow input, L δ for δ Energy flow output, R vδ for δ Energy-type equipment capacity, N L represents the total energy type; P represents the output matrix of the integrated energy system; C represents the input matrix of the integrated energy system; and C represents the coupling coefficient matrix of the integrated energy system, which characterizes the coupling relationship between various energy forms. To constrain the operation and maintenance costs of integrated energy system equipment, c This represents the upper limit for the operation and maintenance costs of various integrated energy equipment. For injection δ Energy-like network nodes α power, For outflow δ Energy-like network nodes α power, n e for δ The total number of nodes in the energy network.

8. The method as described in claim 7, characterized in that, The digital twin model DT1 for equipment scheduling and management during the commissioning phase ’ as follows: In the formula, P min ≤P≤P max To constrain the total energy input of the integrated energy system during its operation, let P be the total energy input of the integrated energy system. max P represents the upper limit of the total energy input of the integrated energy system. min This represents the lower limit of the total energy input for the integrated energy system.

9. The method as described in claim 8, characterized in that, The digital twin model DT2 for equipment scheduling and management during the operation phase is as follows: In the formula, For the integrated energy system network power flow constraints, F represents the integrated energy system network power flow. max F is the upper limit of network power flow in the integrated energy system. min This represents the lower limit of network power flow in an integrated energy system.

10. The method as described in claim 9, characterized in that, The digital twin model DT2 for equipment scheduling and management during the operation phase. ’ as follows: In the formula, To account for the integrated energy system equipment operation and scheduling cost constraints considering the scheduling response of various types of equipment, among which E trδ for δ The cost of equipment operation and scheduling for energy transmission equipment under different energy execution conditions. E tpδ for δ The equipment operation and scheduling costs of energy conversion equipment in different energy execution conditions in energy-type energy sources E stδ for δ The cost of equipment operation and scheduling for energy storage devices in different energy scenarios.

11. An equipment scheduling and management system for an integrated energy system, characterized in that, include: The execution scenario prediction module is used to obtain the current predicted values ​​of the load demand and energy supply duration of various energy equipment in the integrated energy system; The digital twin simulation module is used to input the current predicted value into the pre-built equipment scheduling and management digital twin model DT3 to obtain the energy inflow, outflow and equipment capacity of various energy equipment; The equipment scheduling module is used to control the start-up, shutdown, and output of various energy devices in the integrated energy system based on the energy inflow, outflow, and equipment capacity of the various energy devices. The aforementioned digital twin model for equipment scheduling and management, DT3, is constructed by considering the coupling relationships between various energy flows in the integrated energy system, input constraints, power flow constraints, and equipment operation and scheduling cost constraints. The system also includes a model building module, which includes: The commissioning model construction unit is used to construct a digital twin model DT1 for equipment scheduling and management during the commissioning phase, taking the minimum operating cost of the integrated energy system as the objective function and considering the coupling relationship between various energy flows in the integrated energy system. The operation model construction unit is used to construct the operation phase equipment scheduling and management digital twin model DT2 based on the commissioning phase equipment scheduling and management digital twin model DT1, taking into account the input constraints and power flow constraints of the integrated energy system. The operation model revision unit is used to construct an equipment scheduling management digital twin model DT3 based on the operation phase equipment scheduling management digital twin model DT2, taking into account the integrated energy system equipment operation scheduling cost constraints; the integrated energy system equipment operation scheduling cost constraints are constructed by considering the scheduling response of various types of equipment.

12. The system as claimed in claim 11, characterized in that, The execution scenario prediction module includes: The data acquisition unit is used to acquire the current historical load data of various energy equipment in the integrated energy system; The neural network computing unit is used to input the current historical load data into a pre-built neural network model to obtain the current predicted values ​​of the load demand and energy supply duration of various energy devices in the integrated energy system.

13. The system as described in claim 11, characterized in that, The operation model revision unit includes: The revised subunit 1 is used to calculate the predicted values ​​of the load demand and energy supply duration of various energy equipment in the integrated energy system based on the historical load data of the operation phase of various energy equipment in the integrated energy system. The revised subunit 2 is used to input the predicted values ​​of the operation phase into the digital twin model DT2 for equipment scheduling and management of the operation phase, so as to obtain the energy inflow, outflow and equipment capacity of various energy equipment in the operation phase. Sub-unit 3 is revised to be used for debugging the sub-unit to control the output and start / stop of various energy equipment in the integrated energy system based on the energy inflow, outflow and equipment capacity of various energy equipment after operation. Revision subunit 4 is used to determine the integrated energy system equipment operation and scheduling cost constraints based on operation data after multiple operations, and add the integrated energy system equipment operation and scheduling cost constraints to the operation phase equipment scheduling management digital twin model DT2 to obtain the operation phase equipment scheduling management digital twin model DT2. ’ ; Revision subunit 5 is used to determine the equipment scheduling management digital twin model DT2. ’ Whether the regulation results meet the predicted values ​​of load demand and energy supply duration for various energy devices in the integrated energy system during the operational phase: If they do, then the equipment scheduling and management digital twin model DT2... ’ This is the equipment scheduling management digital twin model DT3; if it does not meet the requirements, execute steps 1-5 of the revision sub-units until the equipment scheduling management digital twin model DT2 is reached. ’ The regulation results meet the predicted values ​​for the load demand and energy supply duration of various energy equipment in the integrated energy system during the operation phase. The operational data includes the energy inflow, outflow, and capacity of various energy devices during the operation period, the scheduling response of each type of device, and the actual load demand and energy supply duration of various energy devices in the integrated energy system.

Images