A method for optimizing operation of an integrated energy system containing hybrid energy storage and a computing device

Abstract

The application discloses a kind of comprehensive energy system optimization operation methods and computing devices of mixed energy storage, method includes: using the historical power data corresponding to current time node generates predicted power parameter, constructs two-stage scheduling model, the predicted power parameter is input into the two-stage scheduling model, to minimize the objective function of comprehensive energy system operation cost, solve the model, output the equipment scheduling scheme of comprehensive energy system, equipment scheduling scheme is executed in preset time period, repeat the above process, until each preset time period and reach time threshold value.It can be known that the application constructs more detailed mixed energy storage system model, solves the problem of multi-time scale of heterogeneous energy.Through two layers of decision layer and objective function, fast response coordination is realized, and the operation cost of system is reduced.Through continuous rolling optimization, the influence of uncertainty on scheduling scheme is reduced.

Description

Technical Field

[0001] This invention relates to the field of power systems, and more particularly to a method for optimizing the operation of an integrated energy system including hybrid energy storage, a computing device, and a readable storage medium. Background Technology

[0002] An integrated energy system (IES) is a complex system involving multiple devices and energy conversion. It integrates various energy sources within a region, such as coal, oil, natural gas, electricity, and heat, to achieve coordinated planning, optimized operation, collaborative management, interactive response, and mutual support among multiple heterogeneous energy subsystems. It is a new type of integrated energy system that effectively improves energy utilization efficiency and promotes sustainable energy development while meeting the diverse energy needs within the system.

[0003] In recent years, with market development and technological advancements, the efficient operation of Energy Storage Systems (IES) faces new challenges. First, there are multiple uncertainties in internal and external conditions. Besides the uncertainties of renewable energy and various loads, with energy market reforms, the prices of energy sources such as electricity, natural gas, and heat will no longer be fixed but will dynamically change according to supply and demand, increasing the difficulty of economic operation for IES. Second, there are the multi-timescale characteristics of scheduling related equipment in IES, including electricity, heat, cooling, and gas. Electricity equipment often needs to change power at high frequencies to follow the load, while due to the inherent thermal inertia of heat and the application of building insulation materials, heat equipment can often change power at lower frequencies. This asynchronous scheduling of different equipment is crucial for high-quality energy management in IES. Third, there is the application of hybrid energy storage systems (HESS). Currently, there is no perfect energy storage form that simultaneously possesses the characteristics of low cost, high power, high capacity, and rapid response.

[0004] To address uncertainties in Systems for Energy (IES), methods such as prediction, random sampling, robust optimization, or rolling optimization are typically employed. For the multi-timescale scheduling problem in IES, a two-stage approach is often used. Two different two-stage approaches exist, differing primarily in that one focuses on developing the operational plan during the day-ahead phase and minimizing errors from the original plan during the intraday execution phase; the other focuses on the coordinated control of different devices. For the HESS (Heated System Execution System) coordinated operation problem in IES, two layers of control are typically involved: the upper layer primarily focuses on power allocation, charging state management, and system operational objectives, while the lower layer primarily focuses on node voltage and current stability.

[0005] Overall, existing solutions provide rich model references and theoretical support for energy management in energy systems (IES), but still have the following shortcomings: First, research on the uncertainties of IES needs further expansion; existing solutions all have certain limitations. Second, consideration of the multi-timescale characteristics of heterogeneous energy sources in IES needs to be further strengthened; as scheduling research gradually moves towards real-time, it will be essential to differentiate between different devices for different frequency scheduling. Third, research on the coordinated operation strategy of Heated Energy Systems (HESS) in IES needs further in-depth study; existing solutions typically do not reflect the coordinated operation problem in the model, and the multi-objective methods used in some solutions are not applicable. Summary of the Invention

[0006] Based on this, the present invention provides an optimized operation method for an integrated energy system including hybrid energy storage, in an attempt to solve or at least alleviate the problems mentioned above.

[0007] According to one aspect of the present invention, a method for optimizing the operation of an integrated energy system including hybrid energy storage is provided, suitable for execution in a computing device. The method includes: generating predicted power parameters using historical power data corresponding to the current time point; constructing a two-stage scheduling model, and dividing the predicted power parameters into fast-time-scale variables and slow-time-scale variables according to the time scale, the model including an objective function, constraints, and two decision layers; inputting the predicted power parameters into the two-stage scheduling model, solving the model with the objective of minimizing the operating cost of the integrated energy system, and outputting an equipment scheduling scheme for the integrated energy system; executing the equipment scheduling scheme within a preset time period; repeating the above generation, input, solving, output, and execution process until the sum of each preset time period reaches a time threshold; wherein the objective function includes:

[0008]

[0009] In the formula, t∈Ω T Represents slow-time-scale indices and sets, τ∈Ω Γ This represents fast timescale indexes and sets; Stage I represents the first decision level, and Stage II represents the second decision level. This indicates the cost of purchasing heat from the heat network for the integrated energy system. This indicates the cost of purchasing natural gas from the natural gas pipeline network by the integrated energy system. This indicates the operating cost of a proton exchange membrane electrolyzer. Indicates the operating cost of fuel cells, This indicates the cost of purchasing electricity from the main grid by the integrated energy system. This indicates the operating cost of the battery storage system.

[0010] Optionally, historical electricity data may include one or more of the following: historical electricity purchase price, historical electricity sales price, historical heat purchase price, historical gas purchase price, historical photovoltaic power generation, historical wind power generation, historical heat load, and historical electricity load.

[0011] Optionally, the predicted power parameters include one or more of the following: predicted electricity purchase price, predicted electricity sales price, predicted heat purchase price, predicted gas purchase price, predicted photovoltaic power generation capacity, predicted wind power generation capacity, predicted heat load, and predicted electrical load.

[0012] Optionally, generating predicted power parameters using historical power data corresponding to the current time point includes: inputting historical power data corresponding to the current time point into a prediction model to generate predicted power parameters, wherein the prediction model is an LSTM neural network model.

[0013] Optionally, the two-stage scheduling model includes two decision layers: a first decision layer, which decides all slow timescale variables and the fast timescale variables for the first period in each second time period; and a second decision layer, which, based on the first decision layer, decides the fast timescale variables for the remaining periods in each second time period.

[0014] Optionally, slow time-scale variables include: combined heat and power (CHP) power output, CHP heat output, air source heat pump power output, air source heat pump heat output, proton exchange membrane electrolyzer power consumption, proton exchange membrane electrolyzer hydrogen production efficiency, fuel cell power output, fuel cell hydrogen production-to-consumption ratio, hydrogen input loss ratio of hydrogen storage tank, hydrogen release loss ratio of hydrogen storage tank, and hydrogen content of hydrogen storage tank; fast time-scale variables include: battery energy storage system charging power, battery energy storage system discharging power, battery energy storage system charging efficiency, purchased electricity, and sold electricity.

[0015] Optionally, the objective function of the two-stage scheduling model includes the integrated energy system's cost of purchasing electricity from the main grid: In the formula, Indicates the electricity purchase price. Indicates the amount of electricity purchased. Indicates the electricity price. Δτ represents the electricity sold, and Δτ represents the first time period.

[0016] Optionally, the objective function of the two-stage scheduling model includes the operating cost of the battery storage system:

[0017]

[0018] In the formula, This indicates the cost of the battery storage system equipment. Indicates the charging power of the battery storage system equipment. Cycles indicates the charging efficiency of a battery storage system. BSS Indicates the number of charge-discharge cycles of the battery storage system. This indicates the maximum energy consumption of the battery storage system. Indicates the discharge power of the battery storage system. Battery storage system discharge efficiency Battery storage system charging aging cost, This indicates the discharge aging cost of the battery storage system.

[0019] Optionally, the objective function of the two-stage scheduling model includes the integrated energy system's cost of purchasing heat from the heat grid: In the formula, Indicates the purchase price of heat. Δt represents the purchased heat, and Δt represents the second time period.

[0020] Optionally, the objective function of the two-stage scheduling model includes the integrated energy system's cost of purchasing natural gas from the pipeline network: In the formula, Indicates the gas purchase price. This indicates the amount of gas purchased.

[0021] Optionally, the objective function of the two-stage scheduling model includes the operating cost of the proton exchange membrane electrolyzer:

[0022]

[0023] In the formula, Indicates the cost of a proton exchange membrane electrolyzer, in Hours PEME This indicates the lifespan of the proton exchange membrane electrolyzer equipment. This indicates the operating and maintenance costs of a proton exchange membrane electrolyzer. This indicates the time that the proton exchange membrane electrolyzer equipment has been in use. This indicates the start-up cost of a proton exchange membrane electrolyzer. This indicates the number of times the proton exchange membrane electrolyzer equipment has been turned on. This indicates the shutdown loss cost of the proton exchange membrane electrolyzer equipment. This indicates the number of times the proton exchange membrane electrolyzer equipment has been shut down.

[0024] Optionally, the objective function of the two-stage scheduling model includes the fuel cell operating cost:

[0025]

[0026] In the formula, Indicates the cost of fuel cell equipment, Hours FC Indicates fuel cell lifespan. This indicates the operating and maintenance costs of fuel cells. Indicates the time that the fuel cell has been used. This indicates the start-up loss cost of a fuel cell. Indicates the number of times the fuel cell has been turned on. This indicates the cost of fuel cell shutdown losses. This indicates the number of times the fuel cell has been shut down.

[0027] Optionally, the constraints of the staged scheduling model include power balance, thermal balance, and constraints related to market interaction:

[0028] The power balance constraints include:

[0029]

[0030] The thermodynamic balance constraints include:

[0031]

[0032] The constraints on market interaction include:

[0033]

[0034]

[0035]

[0036] In the formula, Indicates photovoltaic power generation capacity. Indicates wind power generation capacity. Indicates the power output of combined heat and power (CHP). Indicates the power generation capacity of the fuel cell. This indicates the power consumption of the air heat pump. This indicates the power consumption of the proton exchange membrane electrolyzer. Indicates electrical load. Indicates the heat production capacity of combined heat and power (CHP). This indicates the heat production capacity of the air heat source pump. Indicates heat load, Indicates the maximum power of the power grid. Indicates the maximum power of the heating network. This indicates the maximum power of the natural gas pipeline network.

[0037] Optionally, the equipment scheduling scheme executed within the preset time period includes: executing the scheduling scheme for the equipment corresponding to the fast time scale variable within the first time period; and executing the scheduling scheme for the equipment corresponding to the slow time scale variable within the second time period.

[0038] According to another aspect of the present invention, a computing device is provided, comprising: at least one processor; and a memory storing program instructions, wherein the program instructions are configured to be executed by the at least one processor, the program instructions including instructions for performing the methods described above.

[0039] According to another aspect of the present invention, a readable storage medium storing program instructions is provided, which, when read and executed by a computing device, causes the computing device to perform the method described above.

[0040] According to the technical solution of the present invention, an optimized operation method for an integrated energy system including hybrid energy storage is proposed. The method generates predicted power data using historical power data corresponding to the current time node; a two-stage scheduling model is constructed, and the predicted power parameters are input into the model. The model is solved with the goal of minimizing the operating cost of the integrated energy system, and the equipment scheduling scheme of the integrated energy system is output; the above operation is repeated after a certain period of time for rolling optimization.

[0041] As can be seen from the above, the two-stage approach can simultaneously solve the IES heterogeneous energy multi-timescale scheduling problem and the HESS coordinated operation problem. In the heterogeneous energy multi-timescale problem, equipment such as heat, natural gas, and helium can be scheduled on a slow timescale, while power-related equipment can be scheduled on a fast timescale, thus satisfying the supply and demand balance of various energy sources.

[0042] Furthermore, the system schedules both the HSS and BSS at the first decision level, and only the BSS at the second decision level. Considering the start-up delay characteristics of the PEME, and through various constraints, the HSS and BSS can cooperate to absorb surplus or supplement deficits, thus better coordinating power density and energy density. Moreover, due to the properties of the objective function, the resulting equipment scheduling scheme can minimize the overall energy system operating cost, achieve more rational power allocation, extend equipment life, and reduce the overall HESS cost. Furthermore, through continuous rolling prediction, solution, and execution of MPC, the impact of uncertainty on the scheduling scheme is minimized. Attached Figure Description

[0043] Figure 1 A structural block diagram of a computing device 100 according to an embodiment of the present invention is shown;

[0044] Figure 2 A schematic diagram of the basic framework of IES including HESS is shown;

[0045] Figure 3 A flowchart of an optimized operation method 300 for an integrated energy system including hybrid energy storage according to an embodiment of the present invention is shown;

[0046] Figure 4A schematic diagram of a two-stage method according to an embodiment of the present invention is shown;

[0047] Figure 5 A schematic diagram of a model predictive control process according to an embodiment of the present invention is shown. Detailed Implementation

[0048] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0049] Figure 1 A structural block diagram of a computing device 100 according to an embodiment of the present invention is shown. It should be noted that... Figure 1 The computing device 100 shown is merely an example. In practice, the computing device used to implement the screenshot processing method of the present invention can be any type of device, and its hardware configuration can be similar to... Figure 1 The computing device 100 shown is the same as, and can also be the same as, the computing device 100 shown. Figure 1 The computing device 100 shown is different. In practice, the computing device used to implement the method for constructing the virtual power plant cost allocation model of the present invention can be... Figure 1 The hardware components of the computing device 100 shown may be added or removed. This invention does not limit the specific hardware configuration of the computing device.

[0050] like Figure 1 As shown, in the basic configuration 102, the computing device 100 typically includes a system memory 106 and one or more processors 104. A memory bus 108 can be used for communication between the processors 104 and the system memory 106.

[0051] Depending on the desired configuration, processor 104 can be any type of processor, including but not limited to: microprocessor (μP), microcontroller (μC), digital information processor (DSP), or any combination thereof. Processor 104 may include one or more levels of cache such as L1 cache 110 and L2 cache 112, processor core 114, and registers 116. Example processor core 114 may include an arithmetic logic unit (ALU), floating-point unit (FPU), digital signal processing core (DSP core), or any combination thereof. Example memory controller 118 may be used with processor 104, or in some implementations, memory controller 118 may be an internal part of processor 104.

[0052] Depending on the desired configuration, system memory 106 can be any type of memory, including but not limited to volatile memory (such as RAM), non-volatile memory (such as ROM, flash memory, etc.), or any combination thereof. System memory 106 may include operating system 120, one or more applications 122, and program data 124. In some embodiments, application 122 may be configured to operate on the operating system using program data 124. Application 122 is used to execute instructions of method 300.

[0053] The computing device 100 also includes a storage device 132, which includes a removable memory 136 and a non-removable memory 138, both of which are connected to a storage interface bus 134. In this invention, relevant data of events occurring during program execution and time information indicating the occurrence of each event can be stored in the storage device 132, and the operating system 120 is adapted to manage the storage device 132. The storage device 132 can be a disk.

[0054] The computing device 100 may also include an interface bus 140 that facilitates communication from various interface devices (e.g., output devices 142, peripheral interfaces 144, and communication devices 146) to the basic configuration 102 via a bus / interface controller 130. Example output devices 142 include an image processing unit 148 and an audio processing unit 150. They may be configured to facilitate communication with various external devices such as displays or speakers via one or more A / V ports 152. Example peripheral interfaces 144 may include a serial interface controller 154 and a parallel interface controller 156, which may be configured to facilitate communication with external devices such as input devices (e.g., keyboards, mice, pens, voice input devices, touch input devices) or other peripherals (e.g., printers, scanners, etc.) via one or more I / O ports 158. Example communication devices 146 may include a network controller 160, which may be arranged to facilitate communication with one or more other computing devices 162 via a network communication link through one or more communication ports 164.

[0055] A network communication link can be an example of a communication medium. A communication medium can typically be embodied in a modulated data signal, such as a carrier wave or other transmission mechanism, and can include any information delivery medium. A “modulated data signal” can be a signal whose data set, or whose modifications, can be encoded with information within the signal. As a non-limiting example, a communication medium can include wired media such as wired networks or leased lines, and various wireless media including sound, radio frequency (RF), microwave, infrared (IR), or other wireless media. The term “computer-readable medium” as used herein can include both storage media and communication media.

[0056] Before introducing method 300, it should be noted that the integrated energy system studied in this invention is composed of multiple electrical devices, such as... Figure 2 As shown, Figure 2 It also includes energy plants and energy loads. Power plants include heat plants, natural gas plants and the main power grid, which provide heat, natural gas and electricity to the IES system, respectively. Energy loads include heat loads and electrical loads.

[0057] Figure 3 A flowchart of an optimized operation method 300 for an integrated energy system including hybrid energy storage according to an embodiment of the present invention is shown. This method is suitable for residing in... Figure 1 Executed in the computing device 100 shown. For example... Figure 3 As shown, method 300 begins with step S310. In step S310, predicted power parameters are generated using historical power data corresponding to the current time point.

[0058] According to one embodiment of the present invention, predicted power parameters can be generated in the following manner: specifically, historical power data corresponding to the current time node is input into the prediction model, and the predicted power parameters are generated through the prediction model.

[0059] In this embodiment, historical electricity data serves as input data for the prediction model, which is an LSTM neural network model. The historical electricity data includes one or more of the following: historical electricity purchase price, historical electricity sales price, historical heat purchase price, historical gas purchase price, historical photovoltaic power generation, historical wind power generation, historical heat load, and historical electrical load. The predicted electricity parameters are the output of the prediction model and include one or more of the following: measured electricity purchase price, predicted electricity sales price, predicted heat purchase price, predicted gas purchase price, predicted photovoltaic power generation, predicted wind power generation, predicted heat load, and predicted electrical load.

[0060] The energy data in the historical power data changes in real time. The equipment scheduling plan is obtained based on the historical power data corresponding to the current time node and executed within a preset time period. After the preset time period, the energy data will change. At this time, the changed energy data is integrated into the historical power data to update the historical power data.

[0061] The time period during which various energy data change after the preset time period can be set according to the actual application scenario, and this invention does not impose any restrictions.

[0062] Taking the prediction of power parameters for the next 24 hours as an example, the current historical power data is first input into the LSTM neural network model, and the power parameters for the next 24 hours are obtained through the LSTM neural network model. After the power parameters are predicted, step S320 is entered to construct a two-stage scheduling model, and the predicted power parameters are divided into fast time-scale variables and slow time-scale variables according to the time scale. The model includes an objective function, constraints, and two decision layers.

[0063] According to one embodiment of the present invention, the model includes an objective function, constraints, and two decision layers.

[0064] The objective function includes the operating cost of the integrated energy system, the cost of purchasing electricity from the main grid, the operating cost of the battery storage system, the cost of purchasing heat from the heating network, the cost of purchasing gas from the natural gas pipeline network, the operating cost of the proton exchange membrane electrolyzer, and the operating cost of the fuel cell.

[0065] The integrated energy system operating cost function is:

[0066]

[0067] In the formula, t∈Ω T Represents slow-time-scale indices and sets, τ∈Ω Γ This represents fast timescale indexes and sets; Stage I represents the first stage, and Stage II represents the second stage. This indicates the cost of purchasing heat from the heat network for the integrated energy system. This indicates the cost of purchasing natural gas from the natural gas pipeline network by the integrated energy system. This indicates the operating cost of a proton exchange membrane electrolyzer. Indicates the operating cost of fuel cells, This indicates the cost of purchasing electricity from the main grid by the integrated energy system. This represents the operating cost of the battery storage system. Another equivalent form of the integrated energy system operating cost function is... To facilitate understanding of the two-stage approach, this invention divides it into two parts: a first stage and a second stage. In the first stage, decisions are made on slow-timescale variables such as heat, natural gas, and hydrogen for all time periods, as well as fast-timescale variables related to electricity for the first time period in each second time cycle.

[0068] The integrated energy system's cost function for purchasing electricity from the main grid is:

[0069]

[0070] In the formula, Indicates the electricity purchase price. Indicates the amount of electricity purchased. Indicates the electricity price. Let Δτ represent the electricity sold, and Δτ represent the first time period. It can be seen that IES can both purchase electricity from the main grid and sell excess electricity back to the main grid to generate revenue.

[0071] Battery storage system (BSS) manufacturers typically use the number of charge-discharge cycles to represent the lifespan of a BSS. In addition, the BSS incurs a certain degradation cost during the charging and discharging process based on the operating power. Taking all these factors into account, the operating cost function of a battery storage system is as follows:

[0072]

[0073] In the formula, This indicates the cost of the battery storage system equipment. Indicates the charging power of the battery storage system equipment. Cycles indicates the charging efficiency of a battery storage system. BSS Indicates the number of charge-discharge cycles of the battery storage system. This indicates the maximum energy consumption of the battery storage system. Indicates the discharge power of the battery storage system. Battery storage system discharge efficiency Battery storage system charging aging cost, This indicates the discharge aging cost of the battery storage system.

[0074] The integrated energy system's cost function for purchasing heat from the heat grid is:

[0075]

[0076] In the formula, Indicates the purchase price of heat. Δt represents the purchased heat, and Δt represents the second time period.

[0077] The cost function for the integrated energy system to purchase natural gas from the pipeline network is:

[0078]

[0079] In the formula, Indicates the gas purchase price. This indicates the amount of gas purchased.

[0080] In the calculation of the hydrogen storage system (HSS), the operating costs of the proton exchange membrane electrolyzer (HESS) and fuel cell (FC) are mainly calculated, while the operating costs of the hydrogen storage tank (HST) are negligible. PEME and FC manufacturers typically use service hours to represent equipment lifespan. Furthermore, both PEME and FC incur wear and tear during startup and shutdown. Operating cost functions for the proton exchange membrane electrolyzer and fuel cell are constructed separately.

[0081] The operating cost function for a proton exchange membrane electrolyzer is:

[0082]

[0083] In the formula, Indicates the cost of a proton exchange membrane electrolyzer, in Hours PEME This indicates the lifespan of the proton exchange membrane electrolyzer equipment. This indicates the operating and maintenance costs of a proton exchange membrane electrolyzer. This indicates the time that the proton exchange membrane electrolyzer equipment has been in use. This indicates the start-up cost of a proton exchange membrane electrolyzer. This indicates the number of times the proton exchange membrane electrolyzer equipment has been turned on. This indicates the shutdown loss cost of the proton exchange membrane electrolyzer equipment. This indicates the number of times the proton exchange membrane electrolyzer equipment has been shut down.

[0084] Fuel cell operating cost function:

[0085]

[0086] In the formula, Indicates the cost of fuel cell equipment, Hours FC Indicates fuel cell lifespan. This indicates the operating and maintenance costs of fuel cells. Indicates the time that the fuel cell has been used. This indicates the start-up loss cost of a fuel cell. Indicates the number of times the fuel cell has been turned on. This indicates the cost of fuel cell shutdown losses. This indicates the number of times the fuel cell has been shut down.

[0087] This two-stage scheduling model comprises two decision layers: a first decision layer, which decides on all slow-timescale variables and the fast-timescale variables for the first period of each second time period; and a second decision layer, which, based on the first decision layer, decides on the fast-timescale variables for the remaining periods of each second time period. Slow-timescale variables include: combined heat and power (CHP) power output, CHP heat output, air source heat pump power output, air source heat pump heat output, proton exchange membrane electrolyzer power consumption, proton exchange membrane electrolyzer hydrogen production efficiency, fuel cell power output, fuel cell hydrogen production-to-consumption ratio, hydrogen input loss ratio of hydrogen storage tank, hydrogen release loss ratio of hydrogen storage tank, and hydrogen content in hydrogen storage tank. Fast-timescale variables include: battery energy storage system charging power, battery energy storage system discharging power, battery energy storage system charging efficiency, purchased electricity volume, and sold electricity volume.

[0088] When scheduling equipment, in addition to meeting physical characteristic constraints at the equipment level, constraints related to power balance, thermal balance, and interaction with the market must also be met at the system level. This can be described as follows:

[0089] The power balance constraints are:

[0090]

[0091] The formula contains decision variables with both fast and slow time scales. For the index of the decision variable with a slow time scale, it is easier to calculate by using 4|τ instead of t. 4|τ means τ divided by 4 and rounded down.

[0092] The thermal equilibrium constraint is:

[0093]

[0094] The constraints on interaction with the market are:

[0095]

[0096]

[0097]

[0098] The three formulas above represent the interaction power between electricity, heat, natural gas, and the market, respectively, not exceeding the upper limit. In the formulas, Indicates photovoltaic power generation capacity. Indicates wind power generation capacity. Indicates the power output of combined heat and power (CHP). Indicates the power generation capacity of the fuel cell. This indicates the power consumption of the air heat pump. This indicates the power consumption of the proton exchange membrane electrolyzer. Indicates electrical load. Indicates the heat production capacity of combined heat and power (CHP). This indicates the heat production capacity of the air heat source pump. Indicates heat load, Indicates the maximum power of the power grid. Indicates the maximum power of the heating network. This indicates the maximum power of the natural gas pipeline network.

[0099] After constructing the two-stage scheduling model, step S330 is executed, where predicted power parameters are input into the two-stage scheduling model. The model is then solved with the objective of minimizing the operating cost of the integrated energy system, outputting a scheduling scheme for the integrated energy system's equipment. This scheduling scheme includes scheduling plans for multiple devices, each corresponding to different time-scale variables.

[0100] In this invention, the problem of solving the two-stage scheduling model is a mixed integer linear programming (MILP) problem. MILP problems can be solved by cutting planes, score bounding, and other methods. These methods have been integrated into commercial solvers such as Cplex and Gurobi and can be directly called. This invention will not elaborate on these methods.

[0101] After obtaining the equipment scheduling plan for the integrated energy system, proceed to step S340 and execute the equipment scheduling plan within a preset time period.

[0102] Specifically, for devices with fast time-scale variables, their corresponding device scheduling scheme will be executed within the first time period, and for devices with slow time-scale variables, their corresponding device scheduling scheme will be executed within the second time period. The length of the first time period is less than the length of the second time period, and the second time period is an integer multiple of the first time period.

[0103] According to one embodiment of the present invention, after obtaining the equipment scheduling scheme of the integrated energy system, the scheduling scheme of the equipment corresponding to the fast time-scale variable is executed in the first time period. Simultaneously with the execution of the scheduling scheme of the equipment corresponding to the fast time-scale variable, the scheduling scheme of the equipment corresponding to the slow time-scale variable is executed in the second time period.

[0104] Then, the rolling optimization process begins. In step S350, the processes of generation, input, solution, output, and execution are repeated until the sum of each preset time period reaches a time threshold. The rolling optimization in this invention is a rolling optimization based on model predictive control (MPC).

[0105] According to one embodiment of the present invention, firstly, historical power data of IES is collected at time τ. The historical power data includes renewable energy generation data, load data, and price data. Power parameters in the future PH period are predicted using the LSTM method, and the current state of charge (SOC) and level of hydrogen (LOH) of HESS are read. The above data are input into a two-stage scheduling model for solution to obtain the equipment scheduling plan in the future prediction horizon (PH) period. At this time, the equipment scheduling plan in the control horizon (CH) period is executed. The calculation results of other periods are only used as reference.

[0106] Then, at time τ+1, the SOC in the HESS has been updated. The values ​​of the slow-timescale decision variables at t=0 are fixed. The LSTM learns the latest historical data and provides predicted values ​​for the fast-timescale parameters in the future PH period. This data is then input into the two-stage scheduling model to solve for the scheduling plan for the future PH period. At this point, only the scheduling plan for the fast-timescale decision variables in the previous CH period is executed. In this invention, the duration of the slow timescale is four times that of the fast timescale, so the process is the same for times τ+2 and τ+3.

[0107] Finally, at time τ+4, both the SOC and LOH in the HESS have been updated. The LSTM predicts the status of all parameters in the future PH period based on the latest historical data. This data is then input into the two-stage scheduling model for solution, and the scheduling plan for all decision variables in the previous CH period is executed. By repeating the above process, IES rolling scheduling optimization considering different time scales can be achieved.

[0108] It should be noted that τ is the index of the fast time scale and t is the index of the slow time scale. The durations of PH and CH can be adjusted according to actual needs, and this invention does not impose any restrictions on this.

[0109] Figure 4 A schematic diagram of the two-stage method in this invention is shown, as follows: Figure 4As shown, t is the index of the slow-time-scale variable, and τ is the index of the fast-time-scale variable. The model is divided into two layers. The first decision layer decides all slow-time-scale variables and the fast-time-scale variables for the first time period in each Δt. The second decision layer, based on the first decision layer, decides the fast-time-scale variables for the remaining time periods in each Δt. Using this method, devices with different flexibility can operate in a coordinated manner.

[0110] According to the optimization operation method of integrated energy systems with hybrid energy storage of the present invention, a more refined model of HESS is provided, considering the charge-discharge cycle cost and decay cost of BSS, and the start-up cost and service time cost of PEME and FC, making the model more accurate and closer to real-world usage scenarios. This model can effectively handle the multi-timescale problem of heterogeneous energy in IES, scheduling equipment such as heat, natural gas, and hydrogen on a slow timescale, and power-related equipment on a fast timescale, ensuring the supply and demand balance of various energy sources is met. Furthermore, the model's first decision layer schedules both HSS and BSS, while the second decision layer schedules only BSS, and considers the start-up delay characteristics of PEME, achieving rapid response coordination. Through various constraints, HSS and BSS can cooperate to absorb surplus or supplement deficits, coordinating power density and energy density. The objective function in the model minimizes the overall cost of HESS, reducing the overall system operating expenses. This method enables more rational power allocation, significantly reduces the start-up and shutdown frequency of PEME and FC, and extends equipment lifespan. Furthermore, through continuous rolling prediction, solution, and execution by MPC, the impact of uncertainty on the scheduling scheme is reduced as much as possible, and multiple uncertainties are handled.

[0111] The various techniques described herein can be implemented in combination with hardware or software, or a combination thereof. Thus, the methods and apparatus of the present invention, or certain aspects or portions thereof, can take the form of program code (i.e., instructions) embedded in a tangible medium, such as a removable hard disk, USB flash drive, floppy disk, CD-ROM, or any other machine-readable storage medium, wherein when the program is loaded into and executed by a machine such as a computer, the machine becomes an apparatus for practicing the present invention.

[0112] A8. As described in A1, wherein the objective function of the two-stage scheduling model includes the integrated energy system's electricity purchase cost from the main grid:

[0113]

[0114] In the formula, Indicates the electricity purchase price. Indicates the amount of electricity purchased. Indicates the electricity price. Δτ represents the electricity sold, and Δτ represents the first time period.

[0115] A9. The method described in A1, wherein the objective function of the two-stage scheduling model includes the operating cost of the battery storage system:

[0116]

[0117] In the formula, This indicates the cost of the battery storage system equipment. Indicates the charging power of the battery storage system equipment. Cycles indicates the charging efficiency of a battery storage system. BSS Indicates the number of charge-discharge cycles of the battery storage system. This indicates the maximum energy consumption of the battery storage system. Indicates the discharge power of the battery storage system. Battery storage system discharge efficiency Battery storage system charging aging cost, This indicates the discharge aging cost of the battery storage system.

[0118] A10. As described in A5, wherein the objective function of the two-stage scheduling model includes the integrated energy system's cost of purchasing heat from the heat grid:

[0119]

[0120] In the formula, Indicates the purchase price of heat. Δt represents the purchased heat, and Δt represents the second time period.

[0121] A11. As described in A5, wherein the objective function of the two-stage scheduling model includes the integrated energy system's gas purchase cost from the natural gas pipeline network:

[0122]

[0123] In the formula, Indicates the gas purchase price. This indicates the amount of gas purchased.

[0124] A12. The method as described in A1, wherein the objective function of the two-stage scheduling model includes the proton exchange membrane electrolyzer operating cost:

[0125]

[0126] In the formula, Indicates the cost of a proton exchange membrane electrolyzer, in Hours PEME This indicates the lifespan of the proton exchange membrane electrolyzer equipment. This indicates the operating and maintenance costs of a proton exchange membrane electrolyzer. This indicates the time that the proton exchange membrane electrolyzer equipment has been in use. This indicates the start-up cost of a proton exchange membrane electrolyzer. This indicates the number of times the proton exchange membrane electrolyzer equipment has been turned on. This indicates the shutdown loss cost of the proton exchange membrane electrolyzer equipment. This indicates the number of times the proton exchange membrane electrolyzer equipment has been shut down.

[0127] A13. The method as described in A1, wherein the objective function of the two-stage scheduling model includes the fuel cell operating cost:

[0128]

[0129] In the formula, Indicates the cost of fuel cell equipment, Hours FC Indicates fuel cell lifespan. This indicates the operating and maintenance costs of fuel cells. Indicates the time that the fuel cell has been used. This indicates the start-up loss cost of a fuel cell. Indicates the number of times the fuel cell has been turned on. This indicates the cost of fuel cell shutdown losses. This indicates the number of times the fuel cell has been shut down.

[0130] A14. The method as described in A1, wherein the constraints of the two-stage scheduling model include constraints on power balance, thermal balance, and interaction with the market:

[0131] The power balance constraints include:

[0132]

[0133] The thermodynamic balance constraints include:

[0134]

[0135] The constraints on market interaction include:

[0136]

[0137]

[0138]

[0139] In the formula, Indicates photovoltaic power generation capacity. Indicates wind power generation capacity. Indicates the power output of combined heat and power (CHP). Indicates the power generation capacity of the fuel cell. This indicates the power consumption of the air heat pump. This indicates the power consumption of the proton exchange membrane electrolyzer. Indicates electrical load. Indicates the heat production capacity of combined heat and power (CHP). This indicates the heat production capacity of the air heat source pump. Indicates heat load, Indicates the maximum power of the power grid. Indicates the maximum power of the heating network. This indicates the maximum power of the natural gas pipeline network.

[0140] When the program code is executed on a programmable computer, the computing device generally includes a processor, a processor-readable storage medium (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device. The memory is configured to store program code; the processor is configured to execute the method for constructing the virtual power plant cost allocation model of the present invention according to instructions in the program code stored in the memory.

[0141] By way of example, and not limitation, readable media include readable storage media and communication media. Readable storage media stores information such as computer-readable instructions, data structures, program modules, or other data. Communication media generally embodies computer-readable instructions, data structures, program modules, or other data in the form of modulated data signals such as carrier waves or other transmission mechanisms, and includes any information delivery medium. Any combination of the above is also included within the scope of readable media.

[0142] In the specification provided herein, the algorithms and displays are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used with the examples of this invention. The required structure for constructing such systems is apparent from the above description. Furthermore, this invention is not directed to any particular programming language. It should be understood that the contents of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the invention.

[0143] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0144] Similarly, it should be understood that, in order to streamline this disclosure and aid in understanding one or more of the various aspects of the invention, features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the above description of exemplary embodiments of the invention. However, this method of disclosure should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim.

[0145] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments can be used in any combination.

[0146] Furthermore, some of the embodiments described herein are methods or combinations of method elements that can be implemented by a processor of a computer system or by other means of performing the functions. Therefore, a processor having the necessary instructions for implementing the methods or method elements forms means for implementing the methods or method elements. Furthermore, the elements described herein in the apparatus embodiments are examples of means for implementing the functions performed by elements for the purposes of carrying out the invention.

[0147] As used herein, unless otherwise specified, the use of ordinal numbers such as “first,” “second,” “third,” etc., to describe ordinary objects merely indicates different instances of similar objects and is not intended to imply that the objects being described must have a given order in time, space, ordering, or any other manner.

[0148] Although the invention has been described with reference to a limited number of embodiments, those skilled in the art will understand from the foregoing description that other embodiments are conceivable within the scope of the invention described herein. Furthermore, it should be noted that the language used in this specification has been chosen primarily for readability and instructional purposes, and not for the purpose of interpreting or limiting the subject matter of the invention. Therefore, many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the appended claims. The disclosure of the invention is illustrative and not restrictive, and the scope of the invention is defined by the appended claims.

Claims

1. A method for optimizing the operation of an integrated energy system including hybrid energy storage, suitable for execution in a computing device, the method comprising: Generate predicted power parameters using historical power data corresponding to the current time point; A two-stage scheduling model is constructed, and the predicted power parameters are divided into fast time-scale variables and slow time-scale variables according to the time scale. The model includes an objective function, constraints, and two decision layers. The predicted power parameters are input into the two-stage scheduling model. With the goal of minimizing the operating cost of the integrated energy system, the model is solved to output the equipment scheduling scheme of the integrated energy system. The equipment scheduling scheme is executed within a preset time period, wherein the preset time period includes a first time period corresponding to a fast time scale variable and a second time period corresponding to a slow time scale variable. Repeat the above process of generation, input, solution, output and execution until the sum of each preset time period reaches the time threshold; The two-stage scheduling model includes two decision layers: The first decision-making layer decides on all slow-timescale variables, as well as the fast-timescale variables for the first period in each second time cycle; The second decision-making layer builds upon the first decision-making layer, making decisions on fast-timescale variables for the remaining periods within each second time period; The objective function includes: ； In the formula, Represents slow-time-scale indexes and sets. Represents fast timescale indexes and sets. Indicates the first stage. This indicates the second stage. This indicates the cost of purchasing heat from the heat network for the integrated energy system. This indicates the cost of purchasing natural gas from the natural gas pipeline network by the integrated energy system. This indicates the operating cost of a proton exchange membrane electrolyzer. Indicates the operating cost of fuel cells, This indicates the cost of purchasing electricity from the main grid by the integrated energy system. PH represents the operating cost of the battery storage system, and PH represents the future forecast domain.

2. The method as described in claim 1, wherein, The historical power data includes one or more of the following: historical electricity purchase price, historical electricity sales price, historical heat purchase price, historical gas purchase price, historical photovoltaic power generation, historical wind power generation, historical heat load, and historical electricity load.

3. The method as described in claim 2, wherein, The predicted power parameters include one or more of the following: predicted electricity purchase price, predicted electricity sales price, predicted heat purchase price, predicted gas purchase price, predicted photovoltaic power generation, predicted wind power generation, predicted heat load, and predicted electrical load.

4. The method according to any one of claims 1-3, wherein, The process of generating predicted power parameters using historical power data corresponding to the current time point includes: Historical power data corresponding to the current time point is input into the prediction model to generate predicted power parameters. The prediction model is an LSTM neural network model.

5. The method of claim 1, wherein, The slow timescale variables include: combined heat and power (CHP) power output, CHP heat output, air heat pump power output, air heat pump heat output, proton exchange membrane electrolyzer power consumption, proton exchange membrane electrolyzer hydrogen production efficiency, fuel cell power output, fuel cell hydrogen production-to-consumption ratio, hydrogen storage tank hydrogen input loss ratio, hydrogen storage tank hydrogen release loss ratio, and hydrogen content in the hydrogen storage tank. The fast timescale variables include: battery energy storage system charging power, battery energy storage system discharging power, battery energy storage system charging efficiency, purchased electricity, and sold electricity.

6. The method of claim 1, wherein, The objective function of the two-stage scheduling model includes the integrated energy system's electricity purchase cost from the main grid: ； In the formula, Indicates the electricity purchase price. Indicates the amount of electricity purchased. Indicates the electricity price. Indicates the amount of electricity sold. This represents the first time period.

7. The method of claim 6, wherein, The objective function of the two-stage scheduling model includes the operating cost of the battery storage system. ； In the formula, This indicates the cost of the battery storage system equipment. Indicates the charging power of the battery storage system equipment. This indicates the charging efficiency of the battery storage system. Indicates the number of charge-discharge cycles of the battery storage system. This indicates the maximum energy consumption of the battery storage system. Indicates the discharge power of the battery storage system. Battery storage system discharge efficiency Battery storage system charging aging cost, This indicates the discharge aging cost of the battery storage system.

8. The method of claim 7, wherein, The objective function of the two-stage scheduling model includes the integrated energy system's cost of purchasing heat from the heat grid: ； In the formula, Indicates the purchase price of heat. Indicates the purchase of calories. This indicates the second time period.

9. The method of claim 8, wherein, The objective function of the two-stage scheduling model includes the integrated energy system's gas purchase cost from the natural gas pipeline network: ； In the formula, Indicates the gas purchase price. This indicates the amount of gas purchased.

10. The method of claim 9, wherein, The objective function of the two-stage scheduling model includes the operating cost of the proton exchange membrane electrolyzer: ； In the formula, This indicates the cost of a proton exchange membrane electrolyzer. This indicates the lifespan of the proton exchange membrane electrolyzer equipment. This indicates the operating and maintenance costs of a proton exchange membrane electrolyzer. This indicates the time that the proton exchange membrane electrolyzer equipment has been in use. This indicates the start-up cost of a proton exchange membrane electrolyzer. This indicates the number of times the proton exchange membrane electrolyzer equipment has been turned on. This indicates the shutdown loss cost of the proton exchange membrane electrolyzer equipment. This indicates the number of times the proton exchange membrane electrolyzer equipment has been shut down.

11. The method of claim 10, wherein, The objective function of the two-stage scheduling model includes fuel cell operating costs: ； In the formula, Indicates the cost of fuel cell equipment. Indicates fuel cell lifespan. This indicates the operating and maintenance costs of fuel cells. Indicates the time that the fuel cell has been used. This indicates the start-up loss cost of a fuel cell. Indicates the number of times the fuel cell has been turned on. This indicates the cost of fuel cell shutdown losses. This indicates the number of times the fuel cell has been shut down.

12. The method of claim 11, wherein, The constraints of the two-stage scheduling model include power balance, thermal balance, and market interaction constraints: The power balance constraints include: ； The thermodynamic balance constraints include: ； The constraints on market interaction include: ； ； ； In the formula, Indicates photovoltaic power generation capacity. Indicates wind power generation capacity. Indicates the power output of combined heat and power (CHP). Indicates the power generation capacity of the fuel cell. This indicates the power consumption of the air heat pump. This indicates the power consumption of the proton exchange membrane electrolyzer. Indicates electrical load. Indicates the heat production capacity of combined heat and power (CHP). This indicates the heat production capacity of the air heat source pump. Indicates heat load, Indicates the maximum power of the power grid. Indicates the maximum power of the heating network. This indicates the maximum power of the natural gas pipeline network.

13. The method of claim 1, wherein, The equipment scheduling scheme executed within the preset time period includes: Within the first time period, execute the scheduling scheme for the equipment corresponding to the fast time-scale variable; During the second time period, the scheduling scheme for the devices corresponding to the slow time scale variables is executed.

14. A computing device, comprising: At least one processor; and A memory storing program instructions, wherein the program instructions are configured to be executed by the at least one processor, the program instructions including instructions for performing the method as described in any one of claims 1-13.

15. A readable storage medium storing program instructions that, when read and executed by a computing device, cause the computing device to perform the method as described in any one of claims 1-13.

Images