Virtual power plant system scheduling method and device and computer equipment

Abstract

The invention relates to a virtual power plant system scheduling method and device and computer equipment. The method comprises the steps of obtaining a day-ahead energy price, a day-ahead energy load and a day-ahead power prediction value of renewable energy power generation power in a preset time period, and determining a day-ahead scheduling strategy of a virtual power plant system according to the day-ahead energy price, the day-ahead energy load and the day-ahead power prediction value, and based on the day-ahead planned output curve, predicting to obtain a time-ahead energy price and a time-ahead power prediction value of the renewable energy power generation power, adjusting a day-ahead scheduling strategy according to the time-ahead energy price and the time-ahead power prediction value to obtain a target scheduling strategy, executing the target scheduling strategy, and scheduling the virtual power plant system. By adopting the scheme, the accuracy of the target scheduling strategy can be improved.

Description

Technical Field

[0001] The present application relates to the field of electronic power technology, and in particular to a virtual power plant system scheduling method, apparatus, computer equipment, computer-readable storage medium and computer program product. Background Art

[0002] As the proportion of renewable energy generation in the power system gradually increases, the intermittent and volatile nature of renewable energy generation also brings many challenges to the power system. Therefore, virtual power plants come into being. Virtual power plants dispatch distributed renewable energy as a whole. However, how to quickly and efficiently determine the optimal dispatch strategy for the virtual power plant system has become one of the problems to be solved.

[0003] Traditional solutions usually rely too much on predicting the power generation of renewable energy, using the predicted power generation as the basis for scheduling and planning the output of each generator set in the virtual power plant system, so as to match the final power generation with the user's load demand as much as possible.

[0004] However, in traditional solutions, it is difficult to accurately estimate the power generation due to the frequent fluctuations in renewable energy power generation. Therefore, the scheduling strategy determined based on the predicted power generation of renewable energy is often difficult to meet the real-time electricity demand. That is, the scheduling strategy of the virtual power plant system determined by the traditional solution has low accuracy. Summary of the invention

[0005] Based on this, it is necessary to provide a virtual power plant system scheduling method, device, computer equipment, computer-readable storage medium and computer program product that can improve scheduling accuracy in response to the above-mentioned technical problems.

[0006] In a first aspect, the present application provides a virtual power plant system scheduling method, comprising:

[0007] Obtaining the day-ahead energy price, day-ahead energy load, and day-ahead power forecast value of renewable energy power generation within a preset time period;

[0008] Determine a day-ahead dispatch strategy for a virtual power plant system according to the day-ahead energy price, the day-ahead energy load, and the day-ahead power forecast value, wherein the day-ahead dispatch strategy includes a day-ahead planned output curve;

[0009] Based on the day-ahead planned output curve, predict the energy price before the hour and the power forecast value of the renewable energy power generation power before the hour;

[0010] According to the energy price before the hour and the power forecast value before the hour, the day-ahead scheduling strategy is adjusted to obtain a target scheduling strategy;

[0011] Execute the target scheduling strategy to schedule the virtual power plant system.

[0012] In one embodiment, the day-ahead dispatching strategy of the virtual power plant system is determined according to the day-ahead energy price, the day-ahead energy load and the day-ahead power forecast value, and the day-ahead dispatching strategy includes a day-ahead planned output curve, including:

[0013] According to the day-ahead energy price, the day-ahead energy load, the power forecast value, and the pre-constructed day-ahead collaborative optimization model, the day-ahead scheduling strategy is determined with the goal of maximizing a first day-ahead objective function in the day-ahead collaborative optimization model and maximizing a second day-ahead objective function in the day-ahead collaborative optimization model;

[0014] Among them, the first day-ahead objective function represents the net resource income of the virtual power plant system, and the second day-ahead objective function represents the sum of the interruptible load and the transferable load of the virtual power plant system.

[0015] In one of the embodiments, the day-ahead collaborative optimization model includes at least one of the following constraints: energy power balance constraint, energy storage operation constraint, cogeneration system operation constraint, energy network transmission constraint, and load demand response constraint.

[0016] In one embodiment, adjusting the day-ahead scheduling strategy according to the energy price before the hour and the power forecast value before the hour to obtain a target scheduling strategy includes:

[0017] According to the energy price before time, the power forecast value before time, and the pre-built collaborative optimization model before time, the first objective function before time of the collaborative optimization model before time and the second objective function before time of the collaborative optimization model before time are minimized as the goal, and the day-ahead scheduling strategy is adjusted to obtain a target scheduling strategy;

[0018] Among them, the first time-ahead objective function represents the output deviation between the actual output of the virtual power plant system and the planned output of the day-ahead scheduling strategy, and the second time-ahead objective function represents the waste amount of renewable energy power generation.

[0019] In one embodiment, obtaining a day-ahead power forecast value of renewable energy power generation power includes:

[0020] Acquiring climate data for a preset time period and operation data of the virtual power plant system;

[0021] Taking the climate data and the operation data as input, calling a preset day-ahead power prediction model to obtain the day-ahead power prediction value;

[0022] The day-ahead power prediction model is trained based on historical climate data, historical operation data, and historical power generation of renewable energy.

[0023] In a second aspect, the present application also provides a virtual power plant system scheduling device, including:

[0024] A data acquisition module is used to obtain the day-ahead energy price, the day-ahead energy load, and the day-ahead power forecast value of the renewable energy power generation power within a preset time period;

[0025] A day-ahead scheduling module, configured to determine a day-ahead scheduling strategy for a virtual power plant system according to the day-ahead energy price, the day-ahead energy load, and the day-ahead power forecast value, wherein the day-ahead scheduling strategy includes a day-ahead planned output curve;

[0026] A pre-hour scheduling module, used to predict the pre-hour energy price and the pre-hour power forecast value of the renewable energy power generation power based on the day-ahead planned output curve;

[0027] A strategy adjustment module, used to adjust the day-ahead scheduling strategy according to the energy price before the hour and the power forecast value before the hour to obtain a target scheduling strategy;

[0028] A strategy execution module is used to execute the target scheduling strategy and schedule the virtual power plant system.

[0029] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in any one of the above-mentioned virtual power plant system scheduling method embodiments when executing the computer program.

[0030] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in any one of the above-mentioned virtual power plant system scheduling method embodiments are implemented.

[0031] In a fifth aspect, the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps in any one of the above-mentioned virtual power plant system scheduling method embodiments.

[0032] The above-mentioned virtual power plant system scheduling method, device, computer equipment, computer-readable storage medium and computer program product adopt a two-stage optimization method, and analyze the day-ahead energy price, day-ahead energy load and day-ahead power forecast value of renewable energy power generation power, and formulate the day-ahead scheduling strategy of the virtual power plant based on this, and obtain the day-ahead output plan curve. Furthermore, since the day-ahead scheduling strategy may be difficult to cope with the frequent fluctuations in renewable energy power generation, this scheme adjusts the day-ahead scheduling strategy based on the day-ahead output plan curve and the hour-ahead power forecast value to obtain a target scheduling strategy that better matches the real-time load demand, and executes the target scheduling strategy to achieve the scheduling of the virtual power plant system. This two-stage scheduling strategy determination method can not only realize long-term strategic planning, but also cope with short-term real-time adjustments, and can significantly reduce the negative impact of the frequent volatility of renewable energy on the scheduling effect of the virtual power plant system, that is, it can obtain a more accurate target scheduling strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0034] FIG1 is an application environment diagram of a virtual power plant system scheduling method in one embodiment;

[0035] Figure 2 A schematic diagram of a flow chart of a virtual power plant system scheduling method in one embodiment;

[0036] Figure 3 A schematic diagram of a flow chart of a virtual power plant system scheduling method in another embodiment;

[0037] Figure 4 A schematic diagram of a flow chart of a virtual power plant system scheduling method in another embodiment;

[0038] Figure 5 A schematic diagram of a flow chart of a virtual power plant system scheduling method in a detailed embodiment;

[0039] Figure 6 It is a structural block diagram of a virtual power plant system dispatching device in one embodiment;

[0040] Figure 7 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0042] The virtual power plant system scheduling method provided in the embodiment of the present application can be applied in the application environment shown in FIG1. ​​The terminal 102 communicates with the server 104 through the network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers.

[0043] Specifically, the staff may upload the day-ahead energy price, day-ahead energy load, and day-ahead power forecast value of renewable energy power generation within a preset time period to the server 104 through the terminal 102, or the server 104 may directly obtain the above data from the data storage system. Then, the server 104 determines the day-ahead scheduling strategy of the virtual power plant system according to the day-ahead energy price, day-ahead energy load, and day-ahead power forecast value. The day-ahead scheduling strategy includes the day-ahead planned output curve. Then, based on the day-ahead planned output curve, the hour-ahead energy price and the hour-ahead power forecast value of renewable energy power generation are predicted. Furthermore, the server 104 adjusts the day-ahead scheduling strategy according to the hour-ahead energy price and the hour-ahead power forecast value to obtain the target scheduling strategy. Finally, the server 104 executes the target scheduling strategy to schedule the virtual power plant system.

[0044] The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. Head-mounted devices may be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 may be an independent physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0045] In an exemplary embodiment, Figure 2 As shown, a virtual power plant system scheduling method is provided, which is described by taking the method applied to the server 104 in FIG. 1 as an example, and includes the following steps:

[0046] S100, obtaining a day-ahead energy price, a day-ahead energy load, and a day-ahead power forecast value of renewable energy power generation within a preset time period.

[0047] The day-ahead energy price refers to the energy price of the day before the transaction in the electricity market, which is usually affected by factors such as weather, supply and demand, and season. The day-ahead energy load represents the user's demand for energy in the next day, such as the user's demand for electricity, which can be determined based on historical data using deep learning technology. Renewable energy includes but is not limited to wind energy, solar energy and other energy sources. Renewable energy has strong volatility uncertainty. The day-ahead power forecast value refers to the forecast value of the power generation power of renewable energy in the next day.

[0048] S200, determining a day-ahead dispatching strategy for the virtual power plant system according to the day-ahead energy price, the day-ahead energy load, and the day-ahead power forecast value, wherein the day-ahead dispatching strategy includes a day-ahead planned output curve.

[0049] The day-ahead dispatch strategy refers to the dispatch strategy formulated one day before the operation of the virtual power plant system, including but not limited to the power generation plan of the power generation equipment in the virtual power plant system, the charging and discharging plan of the energy storage equipment, etc. The day-ahead planned output curve is used to characterize the output power changes of the power generation equipment in the virtual power plant system in different time periods, and is closely related to the day-ahead energy load and the day-ahead power forecast value.

[0050] For example, in a virtual power plant system, an optimization goal can be set, such as maximizing resource returns, maximizing user satisfaction, and maximizing resource utilization, and based on this optimization goal, the power generation equipment in the virtual power plant system should be started, the charging and discharging time of the energy storage equipment, the time to participate in the power trading market, etc., to obtain the day-ahead scheduling strategy.

[0051] S300, based on the day-ahead planned output curve, predict and obtain the hour-ahead energy price and the hour-ahead power forecast value of the renewable energy power generation power.

[0052] Among them, the day-ahead planned output curve refers to the output plan of the power generation equipment in the virtual power system on the next day, and the energy price before the hour refers to the energy price one hour before the transaction in the energy market. For example, in the power market, the power price of the virtual power plant system one hour before the power transaction is different from the day-ahead energy price. The energy price before the hour is closer to the energy price at the time of the actual transaction, so it is more accurate. The power forecast value before the hour refers to the predicted value of the power generation of renewable energy one hour before the actual power generation. Compared with the power forecast value before the day, the power forecast value before the hour is more accurate because it is closer to the actual power generation time and is less affected by the uncertainty of the volatility of renewable energy.

[0053] For example, since the energy price and power forecast value before the hour are affected by the power generation power of the power generation equipment in the virtual power system, the energy price and power forecast value before the hour can be further predicted based on the day-ahead output plan. Climate data may also be used in the prediction process to improve the prediction accuracy.

[0054] S400, adjusting the day-ahead dispatching strategy according to the energy price before the hour and the power forecast value before the hour to obtain a target dispatching strategy.

[0055] Among them, the target scheduling strategy refers to the final strategy obtained by correcting the original day-ahead scheduling strategy in the pre-hour stage in combination with the pre-hour energy price and the pre-hour power forecast value, which serves as the scheduling strategy actually implemented by the virtual power plant system.

[0056] Exemplarily, in the pre-hour optimization stage, pre-hour optimization goals can be formulated, including but not limited to maximizing resource returns, maximizing user satisfaction, and maximizing resource utilization, and based on the pre-hour optimization goals, as well as the pre-hour energy prices and pre-hour power forecast values, the day-ahead scheduling strategy can be adjusted to obtain the target scheduling strategy.

[0057] S500, executing the target scheduling strategy to schedule the virtual power plant system.

[0058] Exemplarily, the target scheduling strategy includes, but is not limited to, the output planning curve of power generation equipment in the virtual power plant system, the charging and discharging planning curve of energy storage equipment, the time of participating in the energy trading market, etc. The virtual power plant system executes the above-mentioned target scheduling strategy so that the virtual power plant system can achieve the best possible state in terms of energy utilization, resource return rate, etc.

[0059] The above virtual power plant system scheduling method adopts a two-stage optimization method. The day-ahead energy price, day-ahead energy load and day-ahead power forecast of renewable energy power generation are obtained by analyzing the day-ahead energy price, day-ahead energy load and day-ahead power forecast of renewable energy power generation, and the day-ahead scheduling strategy of the virtual power plant is formulated based on this to obtain the day-ahead output plan curve. Furthermore, since the day-ahead scheduling strategy may be difficult to cope with the frequent fluctuations in renewable energy power generation, this scheme adjusts the day-ahead scheduling strategy based on the day-ahead output plan curve and the day-ahead power forecast value to obtain a target scheduling strategy that better matches the real-time load demand, and executes the target scheduling strategy to achieve the scheduling of the virtual power plant system. This two-stage scheduling strategy determination method can not only realize long-term strategic planning, but also cope with short-term real-time adjustments. It can significantly reduce the negative impact of the frequent volatility of renewable energy on the scheduling effect of the virtual power plant system, that is, it can obtain a more accurate target scheduling strategy.

[0060] In an exemplary embodiment, Figure 3 As shown, S200 includes:

[0061] S210, according to the day-ahead energy price, the day-ahead energy load, the power forecast value, and the pre-built day-ahead collaborative optimization model, the day-ahead scheduling strategy is determined with the goal of maximizing the first day-ahead objective function in the day-ahead collaborative optimization model and maximizing the second day-ahead objective function in the day-ahead collaborative optimization model.

[0062] The day-ahead coordinated optimization model is used to coordinate different resources in the virtual power plant system during the day-ahead stage, including but not limited to power generation equipment, energy storage equipment, etc. The day-ahead dispatch strategy determined based on the day-ahead coordinated optimization model can determine the output plan, charging and discharging plan, etc. of the virtual power plant system for the next day, thereby maximizing the net resource income and user satisfaction of the virtual power plant system.

[0063] The first-day-ahead objective function represents the net resource income of the virtual power plant system. Net resource income refers to the profit of the virtual power plant system in the power trading market, minus the operating costs of power generation equipment and energy storage equipment. Maximizing the first-day-ahead objective function means that the virtual power plant system can obtain the best economic benefits. The second-day-ahead objective function represents the sum of the interruptible load and the transferable load of the virtual power plant system. The interruptible load is the load that can be temporarily suspended, such as suspending the operation of certain non-critical power equipment when the power price is high or the power is in short supply. The transferable load is the power demand that can be transferred between different time periods, such as performing power consumption activities when the power price is low. Through the interruptible load and transferable load, the user satisfaction of the virtual power plant system can be quantified.

[0064] For example, taking resources as economic resources, the net resource income of the virtual power plant system can be expressed by the difference between the operating income and operating cost of the virtual power plant system. The operating income includes but is not limited to the income obtained by the virtual power plant system from participating in the energy trading of the power grid, heat grid and gas grid, the economic compensation obtained by the virtual power plant system from supplying electricity and heat to users, and participating in other demand responses. The operating cost includes but is not limited to fuel cost, operation and maintenance cost and environmental emission cost. Therefore, the objective function before the first day can be expressed by formula (1):

[0065] (1)

[0066] In formula (1), It is the net resource income of the virtual power plant system; The operating income of the virtual power plant system; is the operating cost of the virtual power plant system. The operating income of the virtual power plant system can be expressed by formula (2):

[0067] (2)

[0068] In formula (2), The revenue from electricity sales for the virtual power plant system; The revenue from heat sales for the virtual power plant system; Profits from power and heat supply for the virtual power plant system; The benefits obtained by the virtual power plant system participating in the grid demand response dispatch; is the interactive power between the virtual power plant system and the power grid; is the interactive power between the virtual power plant system and the heat network; The price for electricity trading between the virtual power plant system and the grid; To establish a heat trading price between the virtual power plant system and the heat network; It is the heat load of users in the virtual power plant system after demand response; It is the user's electric load in the virtual power plant system after demand response; It is the interruptible load capacity in the virtual power plant system; Demand response compensation price for interruptible load capacity in virtual power plant systems.

[0069] The operating cost of the virtual power plant system can be expressed by formula (3):

[0070] (3)

[0071] In formula (3), The cost of natural gas for the operation of the virtual power plant system; The operation and maintenance costs of the virtual power plant system; The operating environment cost of the virtual power plant system; is the price of natural gas; is the output power of the CHP virtual power plant system; is the output power of the gas boiler; is the low calorific value power of natural gas; The rated power of the energy supply equipment in the virtual power plant system; The unit power operation and maintenance cost of energy supply equipment in the virtual power plant system; The output power of the pollutant emission source of the virtual power plant system; The virtual power plant system The unit power emission of each pollutant; For the virtual power plant system Basic emission charges for various pollutants; For the virtual power plant system Fees for pollutants emitted in excess of the basic emission quota.

[0072] When participating in the comprehensive demand response of the power grid and the heat network, the virtual power plant system will guide the users of the virtual power plant system to adjust their loads. The change of load directly affects the user's electricity consumption experience, which can be quantified as user satisfaction through interruptible load and transferable load. Therefore, the objective function before the second day represents the sum of the interruptible load and transferable load of the virtual power plant system, which is used to quantify user satisfaction. Among them, user satisfaction can be expressed by formula (4):

[0073] (4)

[0074] In formula (4), For user satisfaction; is the ratio of interruptible load and transferable load to total load; Calling state variables for interruptible loads and transferable loads; The maximum call amount for interruptible load and transferable load.

[0075] The above equations (1) to (4) adjust the operating status of the power generation equipment and energy storage equipment in the virtual power plant system by maximizing the objective function on the first day before the deadline, for example, reducing power generation or energy storage operations when the electricity price is high, or increasing power generation and energy storage when the electricity price is low, so that the net resource income of the virtual power plant system is improved. By minimizing the objective function on the second day before the deadline, flexibly adjusting the interruptible load and transferable load of the virtual power plant system, and maximizing the sum of the interruptible and transferable loads, the energy consumption of the virtual power plant system during peak hours can be reduced, and at the same time, low-priced energy can be fully utilized when the electricity price is low, thereby optimizing energy utilization efficiency and improving user satisfaction.

[0076] In this embodiment, by maximizing the first day-ahead objective function and the second day-ahead objective function, the virtual power plant system can not only increase the net resource income but also improve user satisfaction, thereby enabling the virtual power plant system to flexibly respond to market fluctuations and energy load changes, obtain accurate day-ahead scheduling strategies, and provide an accurate basis for subsequent time-ahead optimization.

[0077] In an exemplary embodiment, the day-ahead collaborative optimization model includes at least one of the following constraints: energy power balance constraint, energy storage operation constraint, cogeneration system operation constraint, energy network transmission constraint, and load demand response constraint.

[0078] Following the above embodiments, in order to enable the virtual power plant system to operate safely and efficiently, the relevant boundaries of the virtual power plant system operation are used as constraints. In the day-ahead optimization stage, in addition to satisfying constraints such as power balance and energy network, it is also necessary to satisfy the maximum power constraints of the equipment and the operation constraints of the energy storage system.

[0079] Specifically, the energy power balance constraint can be expressed as:

[0080] (5)

[0081] In formula (5), is the electric load power in the virtual power plant system; is the thermal load power in the virtual power plant system; The charging power for the electric energy storage; is the thermal storage power of thermal energy storage; is the power generation capacity of wind turbines in the virtual power plant system; is the thermal efficiency of CHP in the virtual power plant system; The electrical efficiency of the CHP (Combined Heat and Power) unit in the virtual power plant system; The operating efficiency of GB (Gas Boiler) in the virtual power plant system; is the discharge power of the electric energy storage; is the heat release power of thermal energy storage; For residential natural gas loads; The natural gas load consumed by the CHP system; The natural gas load consumed by the gas boiler; Natural gas input into the virtual power plant system from the external natural gas grid.

[0082] In the virtual power plant system, electric thermal energy storage units can realize load peak shaving and valley filling, reducing operating costs. The capacity of energy storage equipment at a certain moment is closely related to the remaining capacity and its own discharge (heat) depth at the previous moment. Energy storage equipment should not be overcharged and discharged (heated) during use. Its storage energy must have upper and lower limits. Therefore, the capacity and power of electric energy storage and thermal energy storage must meet the energy storage operation constraints. Among them, the energy storage operation constraints include electric energy storage operation constraints and thermal energy storage operation constraints. The electric energy storage operation constraints are shown in equations (6) and (7):

[0083] (6)

[0084] (7)

[0085] In formula (6) and formula (7), is the maximum charging power of the electric energy storage (kW); Charging efficiency for electric energy storage; is the maximum discharge power of the electric energy storage (kW); is the discharge efficiency of electrical energy storage; is the maximum charging and discharging current of the energy storage (A); The maximum value of the state of charge of the electric energy storage; It is the state of charge of the energy storage.

[0086] The operating constraints of thermal energy storage are shown in formula (8):

[0087] (8)

[0088] In formula (8), is the maximum charging power of thermal energy storage (kW); Charging efficiency for thermal energy storage; is the maximum heat release power of thermal energy storage (kW); It is the heat storage and heat release efficiency.

[0089] In the virtual power plant system, during the operation of the cogeneration unit (or cogeneration system), considering the characteristics of the equipment and the safety and reliability requirements of the system, the power of the equipment must be maintained within a certain output power range, that is, the operating constraints of the cogeneration system, as shown in equations (9) and (10):

[0090] (9)

[0091] (10)

[0092] In formula (9) and formula (10), is the rated power of the CHP unit; is the minimum climbing power of the CHP unit; is the maximum climbing power of the CHP unit.

[0093] In the virtual power plant system, the virtual power plant exchanges power with the power grid, heat grid, and natural gas grid through interconnection lines. Energy transmission must meet the energy network transmission constraints, as shown in equations (11)-(13):

[0094] (11)

[0095] (12)

[0096] (13)

[0097] In formulas (11)-(13), is the maximum transmission power of the power grid; is the minimum transmission power of the power grid; is the maximum transmission power of the heating network; is the minimum transmission power of the heating network; is the maximum transmission power of the natural gas grid; is the minimum transmission power of the natural gas grid.

[0098] When energy prices fluctuate or the reliability of the virtual power plant system is threatened, users can respond to energy price signals based on the information released by the integrated energy service provider and change their inherent energy consumption patterns to reduce and shift loads. Therefore, when guiding users to participate in demand response, the interruptible loads and transferable loads in the virtual power plant system must meet the load demand response constraints, as shown in equations (14)-(15):

[0099] (14)

[0100] (15)

[0101] In the formula, The maximum transfer-in and transfer-out amounts of the transferable load; is the maximum transfer amount of the transferable load; A set of adjustable time periods for transferable loads.

[0102] In this embodiment, a series of constraints are introduced in the day-ahead optimization stage, so that the day-ahead scheduling strategy obtained by maximizing the first day-ahead objective function and the second day-ahead objective function is feasible, meets various constraints of the virtual power plant system, and improves the reliability of the day-ahead scheduling strategy.

[0103] In an exemplary embodiment, Figure 4 As shown, S400 includes:

[0104] S410, according to the pre-time energy price, the pre-time power forecast value, and the pre-time collaborative optimization model, minimize the first pre-time objective function of the pre-time collaborative optimization model, and minimize the second pre-time objective function of the pre-time collaborative optimization model as the goal, adjust the day-ahead scheduling strategy, and obtain the target scheduling strategy.

[0105] Among them, the first objective function before time represents the output deviation between the actual output of the virtual power plant system and the planned output of the day-ahead scheduling strategy, and the second objective function before time represents the waste of renewable energy power generation. Minimizing the first objective function before time is equivalent to minimizing the output deviation between the actual output of the virtual power plant system and the planned output of the day-ahead scheduling strategy, because the output deviation is difficult to completely avoid in the virtual power plant system, especially when there are fluctuating renewable energy sources involved. Therefore, minimizing the output deviation can make the output of the virtual power plant system more in line with expectations and reduce the instability of the virtual power plant system caused by excessive output deviation. Minimizing the second objective function before time is equivalent to reducing the waste of renewable energy power generation. This is because renewable energy is volatile. If it is not used in time when there is excess power generation, it may lead to wind and solar abandonment, resulting in energy waste. By minimizing the second objective function before time, the virtual power plant system can dispatch resources more flexibly and try to absorb renewable energy power generation.

[0106] For example, the first time-ahead objective function can be expressed by the penalty cost of the deviation between the actual interactive power of the virtual power plant participating in energy dispatch in the virtual power plant system and the planned interactive power in the day-ahead dispatch strategy. Taking wind energy as an example of renewable energy in the virtual power plant system, the second time-ahead objective function can be expressed by the penalty cost of wind abandonment. Specifically, the first time-ahead objective function can be expressed by equation (16), and the second time-ahead objective function can be expressed by equations (17)-(18):

[0107] (16)

[0108] (17)

[0109] (18)

[0110] In the above formula, Penalty costs for virtual power plants to participate in power and heat dispatch; Penalize costs for system abandonment of wind; The penalty cost caused by output deviation when the virtual power plant participates in grid dispatch; is the basic penalty coefficient for system wind abandonment; The system abandoned air volume; The output deviation of the system compared with the previous day's dispatch plan; is the penalty coefficient when the output deviation is greater than zero; is the step penalty coefficient when the output deviation is less than zero; Contribute to the system's planning for participating in day-ahead dispatch optimization of power grid dispatch.

[0111] It should be noted that the virtual power plant system participates in the optimization process of coordinated operation of the power grid, heat network, and gas network. The adjustable active output unit is a controllable unit and energy storage device that is reserved for backup in real-time optimization. In addition, the virtual power plant system exchanges power with the power grid, heat network, and gas network through interconnection lines. Therefore, the interconnection line power of the actual virtual power plant system is also adjustable. However, in the actual operation process, it will face the output deviation assessment penalty of the power grid, heat network, and gas network. In the day-ahead optimization stage, the planned interactive power of the virtual power plant system participating in the power grid and heat network scheduling can be obtained. In the process of minimizing the first time-ahead objective function and the second time-ahead objective function, the constraints expressed by equations (19)-(20) must also be satisfied:

[0112] (19)

[0113] (20)

[0114] In the above formula, It is the positive value of the ratio of the virtual power plant system output deviation to the actual output; It is the positive value of the actual output deviation of the system; It is the negative value of the actual output deviation of the virtual power plant system.

[0115] In this embodiment, through pre-time optimization, the virtual power plant system can respond to market and load changes more flexibly, achieve optimal scheduling of resources, and reduce output deviations and economic losses caused by prediction errors. Moreover, in the pre-time optimization stage, by minimizing output deviations, the virtual power plant system can better control its power generation behavior and reduce unnecessary adjustment costs. By minimizing the amount of energy waste, the virtual power plant system can maximize the use of renewable energy, improve the environmental benefits and resource utilization of the virtual power plant system, and improve the accuracy and reliability of the target scheduling strategy.

[0116] In an exemplary embodiment, obtaining a day-ahead power forecast value of renewable energy power generation power includes: obtaining climate data for a preset time period and operating data of a virtual power plant system, using the climate data and operating data as input, calling a preset day-ahead power forecast model, and obtaining a day-ahead power forecast value.

[0117] The preset time period can be real-time. Climate data refers to weather-related information, including but not limited to wind speed, temperature, humidity, solar radiation, etc. Climate data is an important basis in the power prediction stage of renewable energy generation, especially wind power and photovoltaic power generation, which are renewable energy sources that are highly sensitive to climate conditions. Operation data refers to the historical operation information of each power generation equipment in the virtual power plant system, including but not limited to power generation, equipment efficiency, load rate, etc. The power prediction model is a deep learning model that can predict the power generation of the virtual power plant system in the future by inputting climate data and operation data.

[0118] Exemplarily, the virtual power plant system can obtain climate data for a preset time period through a weather station or weather service, including but not limited to wind speed, wind direction, solar radiation intensity, temperature, humidity and other data. In addition, it is also necessary to integrate the operating data of each power generation equipment and generator set in the virtual power plant, including but not limited to power generation, equipment efficiency, downtime, etc. Since the day-ahead power prediction model is trained based on historical climate data, historical operating data, and historical power generation of renewable energy, the day-ahead power prediction model has learned the impact characteristics of climate data on power generation. Therefore, the climate data and operating data obtained in real time are input into the day-ahead power prediction model to generate a day-ahead power prediction value with higher accuracy.

[0119] In this embodiment, by combining climate data, operating data of the virtual power plant system, and deep learning technology, the day-ahead power prediction model can significantly improve the accuracy of the day-ahead power prediction value, and further improve the accuracy of the subsequent virtual power plant system in formulating and optimizing scheduling strategies.

[0120] In order to make a clearer description of the virtual power plant system scheduling method provided by the present application, the following is a specific embodiment and the attached Figure 5 To illustrate, this specific embodiment includes the following steps:

[0121] S501, obtaining climate data for a preset time period and operating data of the virtual power plant system, using the climate data and operating data as input, calling a preset day-ahead power prediction model, and obtaining a day-ahead power prediction value for the preset time period.

[0122] S502: Obtain the day-ahead energy price and the day-ahead energy load within a preset time period.

[0123] S503, based on the day-ahead energy price, the day-ahead energy load, the power forecast value, and the pre-built day-ahead collaborative optimization model, with the goal of maximizing the first day-ahead objective function in the day-ahead collaborative optimization model and maximizing the second day-ahead objective function in the day-ahead collaborative optimization model, determine the day-ahead scheduling strategy. The day-ahead scheduling strategy includes the day-ahead planned output curve.

[0124] S504: Based on the day-ahead planned output curve, the energy price and the power forecast value of the renewable energy power generation power are predicted.

[0125] S505, according to the pre-time energy price, the pre-time power forecast value, and the pre-time collaborative optimization model, minimize the first pre-time objective function of the pre-time collaborative optimization model, and minimize the second pre-time objective function of the pre-time collaborative optimization model as the goal, adjust the day-ahead scheduling strategy, and obtain the target scheduling strategy.

[0126] S506, executing the target scheduling strategy to schedule the virtual power plant system.

[0127] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0128] Based on the same inventive concept, the embodiment of the present application also provides a virtual power plant system scheduling device for implementing the virtual power plant system scheduling method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more virtual power plant system scheduling device embodiments provided below can refer to the limitations of the virtual power plant system scheduling method above, and will not be repeated here.

[0129] In an exemplary embodiment, Figure 6 As shown, a virtual power plant system scheduling device 600 is provided, including: a data acquisition module 610, a day-ahead scheduling module 620, a pre-hour scheduling module 630, a strategy adjustment module 640 and a strategy execution module 650, wherein:

[0130] The data acquisition module 610 is used to acquire the day-ahead energy price, the day-ahead energy load, and the day-ahead power forecast value of the renewable energy power generation power within a preset time period.

[0131] The day-ahead scheduling module 620 is used to determine the day-ahead scheduling strategy of the virtual power plant system according to the day-ahead energy price, the day-ahead energy load and the day-ahead power forecast value. The day-ahead scheduling strategy includes the day-ahead planned output curve.

[0132] The pre-hour scheduling module 630 is used to predict the pre-hour energy price and the pre-hour power forecast value of the renewable energy power generation power based on the day-ahead planned output curve.

[0133] The strategy adjustment module 640 is used to adjust the day-ahead scheduling strategy according to the energy price before the hour and the power forecast value before the hour to obtain the target scheduling strategy.

[0134] The strategy execution module 650 is used to execute the target scheduling strategy and schedule the virtual power plant system.

[0135] In an exemplary embodiment, the day-ahead scheduling module 620 is specifically used to determine the day-ahead scheduling strategy based on the day-ahead energy price, the day-ahead energy load, the power forecast value, and the pre-built day-ahead collaborative optimization model, with the goal of maximizing the first day-ahead objective function in the day-ahead collaborative optimization model and maximizing the second day-ahead objective function in the day-ahead collaborative optimization model. The first day-ahead objective function represents the net resource income of the virtual power plant system, and the second day-ahead objective function represents the sum of the interruptible load and the transferable load of the virtual power plant system.

[0136] In an exemplary embodiment, the day-ahead collaborative optimization model includes at least one of the following constraints: energy power balance constraint, energy storage operation constraint, cogeneration system operation constraint, energy network transmission constraint, and load demand response constraint.

[0137] In an exemplary embodiment, the strategy adjustment module 640 is specifically used to adjust the day-ahead scheduling strategy based on the day-ahead energy price, the day-ahead power forecast value, and the pre-built day-ahead collaborative optimization model, with the goal of minimizing the first day-ahead objective function of the day-ahead collaborative optimization model and minimizing the second day-ahead objective function of the day-ahead collaborative optimization model to obtain a target scheduling strategy, wherein the first day-ahead objective function represents the output deviation between the actual output of the virtual power plant system and the planned output of the day-ahead scheduling strategy, and the second day-ahead objective function represents the waste amount of renewable energy power generation.

[0138] In an exemplary embodiment, the data acquisition module 610 is also used to obtain climate data for a preset time period and operating data of the virtual power plant system. With the climate data and operating data as input, the preset day-ahead power prediction model is called to obtain a day-ahead power prediction value, wherein the day-ahead power prediction model is trained based on historical climate data, historical operating data, and historical power generation of renewable energy.

[0139] Each module in the above virtual power plant system dispatching device can be implemented in whole or in part by software, hardware and their combination. Each module can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0140] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 7 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as the day-ahead energy price, the day-ahead energy load, and the day-ahead power forecast value of renewable energy power generation. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a virtual power plant system scheduling method is implemented.

[0141] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0142] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps in any one of the above-mentioned virtual power plant system scheduling method embodiments are implemented.

[0143] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in any one of the above-mentioned virtual power plant system scheduling method embodiments are implemented.

[0144] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps in any one of the above-mentioned virtual power plant system scheduling method embodiments.

[0145] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0146] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0147] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0148] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A virtual power plant system scheduling method, characterized in that: The method comprises: Obtaining the day-ahead energy price, day-ahead energy load, and day-ahead power forecast value of renewable energy power generation within a preset time period; Determine a day-ahead dispatch strategy for a virtual power plant system according to the day-ahead energy price, the day-ahead energy load, and the day-ahead power forecast value, wherein the day-ahead dispatch strategy includes a day-ahead planned output curve; Based on the day-ahead planned output curve, predict the energy price before the hour and the power forecast value of the renewable energy power generation power before the hour; According to the energy price before the hour and the power forecast value before the hour, the day-ahead scheduling strategy is adjusted to obtain a target scheduling strategy; Execute the target scheduling strategy to schedule the virtual power plant system.

2. The method according to claim 1, characterized in that: The determining, according to the day-ahead energy price, the day-ahead energy load and the day-ahead power forecast value, a day-ahead dispatching strategy of the virtual power plant system includes: According to the day-ahead energy price, the day-ahead energy load, the power forecast value, and the pre-constructed day-ahead collaborative optimization model, the day-ahead scheduling strategy is determined with the goal of maximizing a first day-ahead objective function in the day-ahead collaborative optimization model and maximizing a second day-ahead objective function in the day-ahead collaborative optimization model; Among them, the first day-ahead objective function represents the net resource income of the virtual power plant system, and the second day-ahead objective function represents the sum of the interruptible load and the transferable load of the virtual power plant system.

3. The method according to claim 2, characterized in that The day-ahead collaborative optimization model includes at least one of the following constraints: energy power balance constraint, energy storage operation constraint, cogeneration system operation constraint, energy network transmission constraint, and load demand response constraint.

4. According to claim 1, it is characterized in that: The step of adjusting the day-ahead scheduling strategy according to the energy price before the hour and the power forecast value before the hour to obtain a target scheduling strategy includes: According to the energy price before time, the power forecast value before time, and the pre-built collaborative optimization model before time, the first objective function before time of the collaborative optimization model before time and the second objective function before time of the collaborative optimization model before time are minimized as the goal, and the day-ahead scheduling strategy is adjusted to obtain a target scheduling strategy; Among them, the first time-ahead objective function represents the output deviation between the actual output of the virtual power plant system and the planned output of the day-ahead scheduling strategy, and the second time-ahead objective function represents the waste amount of renewable energy power generation.

5. The method according to claim 1, characterized in that Obtain the day-ahead power forecast of renewable energy power generation, including: Acquiring climate data for a preset time period and operation data of the virtual power plant system; Taking the climate data and the operation data as input, calling a preset day-ahead power prediction model to obtain the day-ahead power prediction value; The day-ahead power prediction model is trained based on historical climate data, historical operation data, and historical power generation of renewable energy.

6. A virtual power plant system dispatching device, characterized in that: The device comprises: A data acquisition module is used to obtain the day-ahead energy price, day-ahead energy load, and day-ahead power forecast value of renewable energy power generation within a preset time period; A day-ahead scheduling module, configured to determine a day-ahead scheduling strategy for a virtual power plant system according to the day-ahead energy price, the day-ahead energy load, and the day-ahead power forecast value, wherein the day-ahead scheduling strategy includes a day-ahead planned output curve; A pre-hour scheduling module, used to predict the pre-hour energy price and the pre-hour power forecast value of the renewable energy power generation power based on the day-ahead planned output curve; A strategy adjustment module, used to adjust the day-ahead scheduling strategy according to the energy price before the hour and the power forecast value before the hour to obtain a target scheduling strategy; A strategy execution module is used to execute the target scheduling strategy and schedule the virtual power plant system.

7. The device according to claim 6, characterized in that The day-ahead collaborative optimization model includes at least one of the following constraints: energy power balance constraint, energy storage operation constraint, cogeneration system operation constraint, energy network transmission constraint, and load demand response constraint.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images