Optimal scheduling method, device, computer equipment and program product of virtual power plant

Abstract

The application relates to a virtual power plant optimization scheduling method, device, computer equipment and program product. The method comprises the following steps: acquiring a next-day power generation power prediction curve, a next-day predicted state of charge of an energy storage system, a next-day electricity exchange value curve and a next-day electricity load prediction curve; determining a next-day power generation declaration curve, constructing an optimization scheduling model, and optimizing to obtain an optimal next-day power generation declaration curve; based on the next-day power generation power true value, the next-day electricity load true value and the optimal next-day power generation declaration curve, determining an actual power deviation; through the optimization scheduling model, optimizing the daily equipment output to obtain an optimized daily equipment output curve and an optimized daily electricity exchange curve; determining the cumulative net carbon emission amount in the carbon emission period, and adjusting the economic weight and the carbon emission weight based on the cumulative net carbon emission amount. The method can improve the optimization scheduling accuracy of the port.

Description

Technical Field

[0001] This application relates to the field of optimized scheduling technology, and in particular to an optimized scheduling method, apparatus, computer equipment, computer-readable storage medium, and computer program product for a virtual power plant. Background Technology

[0002] Against the backdrop of the national "dual-carbon" strategy and the trend of green and intelligent development of ports, ports can make full use of their natural resources by building their own photovoltaic and wind power systems. At the same time, by introducing equipment such as gas turbine generator sets and lithium battery energy storage systems, ports can further achieve organic integration with new energy power generation systems. While achieving self-sufficiency in electricity and heat during certain periods, ports can also participate in the "electricity-carbon" market as virtual power plants, thus realizing low-carbon and economical operation of ports.

[0003] In related technologies, the optimized operation and scheduling of virtual power plants are mostly aimed at non-port distributed new energy power generation systems such as industrial parks. However, the historical regularity of port electricity load data is poor and it is closely related to the ship entry and exit plans, making it difficult to accurately report the next day's power generation curve. On the other hand, conventional optimized scheduling is mostly based on objective functions (such as minimizing operating costs, maximizing operating revenue, minimizing carbon emissions, etc.) and fails to make dynamic adjustments based on the cumulative carbon quota of "green ports" over a period of time, resulting in inaccurate optimized scheduling of virtual power plants. Summary of the Invention

[0004] Therefore, it is necessary to provide a virtual power plant optimization scheduling method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can effectively improve the accuracy of virtual power plant optimization scheduling in response to the above-mentioned technical problems.

[0005] Firstly, this application provides an optimized scheduling method for a virtual power plant, comprising:

[0006] Obtain the next day's power generation forecast curve, the next day's predicted state of charge of the energy storage system, the next day's electricity exchange value curve, and the next day's electricity load forecast curve;

[0007] Based on the next day's power generation forecast curve and the next day's power load forecast curve, the next day's power generation declaration curve is determined under the constraint of power balance.

[0008] Based on the next day's power generation prediction curve, the next day's predicted state of charge, the next day's electricity load prediction curve, and the next day's electricity exchange value curve, an optimized scheduling model is constructed to optimize the next day's power generation declaration curve and obtain the optimal next day's power generation declaration curve.

[0009] The actual power deviation is determined based on the actual power generation value of the next day, the actual power load value of the next day, and the optimal power generation declaration curve for the next day.

[0010] Based on the actual power deviation, the intraday equipment output curve, the economic weight and carbon emission weight of the virtual power plant optimization scheduling, the intraday equipment output is optimized through the optimization scheduling model to obtain the optimized intraday equipment output curve and the optimized intraday power exchange curve.

[0011] Meteorological data and ship entry and exit data within the carbon emission cycle are acquired, and the cumulative net carbon emissions within the carbon emission cycle are determined. Based on the cumulative net carbon emissions, the economic weight and the carbon emission weight are adjusted.

[0012] In one embodiment, the process of obtaining the next day's electricity load forecast curve includes:

[0013] Obtain the port entry and exit times, vessel types, number of vessels, and tonnage for the following day;

[0014] Based on the ship type and the ship tonnage, determine the historical power consumption data of the corresponding ship;

[0015] Based on the historical power consumption data, the ship's arrival and departure times, and the ship's tonnage, the port's next-day power load at each moment of the next day is determined, and a next-day power load prediction curve is generated based on the port's next-day power load at each moment of the next day.

[0016] In one embodiment, the step of constructing an optimized scheduling model based on the next day's power generation prediction curve, the next day's predicted state of charge, the next day's electricity load prediction curve, and the next day's electricity exchange value curve includes:

[0017] Based on the next day's power generation prediction curve, the next day's predicted state of charge, the next day's power load prediction curve, and the next day's power exchange value curve, a first state space and a first action space are constructed.

[0018] Based on the first state space and the first action space, the scheduling model is adjusted and optimized until the next day's revenue, as represented by the reward function, is maximized.

[0019] In one embodiment, the optimization of intraday equipment output based on the actual power deviation, intraday equipment output curve, economic weights and carbon emission weights of virtual power plant optimized scheduling, through the optimized scheduling model, includes:

[0020] Based on the actual power deviation, the intraday equipment output curve, the economic weight and the carbon emission weight, the state space and action space are updated to obtain the second state space and the second action space.

[0021] Based on the second state space and the second action space, the optimized scheduling model is used to optimize the daily equipment output.

[0022] In one embodiment, acquiring meteorological data and ship arrival / departure data within the carbon emission cycle, and determining the cumulative net carbon emissions within the carbon emission cycle, includes:

[0023] Based on the meteorological data and the ship entry and exit data, determine the historical cumulative net carbon emissions from the first day of the carbon emission cycle to the current day;

[0024] The historical cumulative net carbon emissions are input into the net carbon emissions prediction model after training to obtain the predicted cumulative net carbon emissions for the remaining days in the carbon emission cycle.

[0025] The sum of the historical cumulative net carbon emissions and the predicted cumulative net carbon emissions is taken as the cumulative net carbon emissions within the carbon emission cycle.

[0026] In one embodiment, adjusting the economic weight and the carbon emission weight based on the cumulative net carbon emissions includes:

[0027] If the cumulative net carbon emissions exceed a preset benchmark value, the economic weight and carbon emission weight will be adjusted according to the following formula;

[0028] ;

[0029] =1- ;

[0030] in, For the adjusted carbon emission weights, The adjusted economic weights, For carbon emission weights, As an economic weight, T h For the duration of carbon emission cycles, Q represents the cumulative net carbon emissions over the carbon emission cycle. i0 The base amount for adjusting the carbon emission coefficient is M, where M is the length of the carbon emission cycle up to the current day;

[0031] If the cumulative net carbon emissions are less than a preset benchmark value, the economic weight and the carbon emission weight are adjusted according to the following formula;

[0032] ;

[0033] =1- ;

[0034] in, For the adjusted carbon emission weights, The adjusted economic weights, For carbon emission weights, As an economic weight, T h For the duration of carbon emission cycles, Q represents the cumulative net carbon emissions over the carbon emission cycle. d0 This is the baseline amount for adjusting the carbon emission coefficient, where M is the duration of the carbon emission cycle up to the current day.

[0035] Secondly, this application also provides an optimized scheduling device for a virtual power plant, comprising:

[0036] The acquisition module is used to acquire the next day's power generation forecast curve, the next day's predicted state of charge of the energy storage system, the next day's power exchange value curve, and the next day's power load forecast curve.

[0037] The determination module is used to determine the next day's power generation forecast curve based on the next day's power generation forecast curve and the next day's power load forecast curve, under the constraint of power balance.

[0038] The optimization module is used to construct an optimized scheduling model based on the next day's power generation prediction curve, the next day's predicted state of charge, the next day's electricity load prediction curve, and the next day's electricity exchange value curve, and to optimize the next day's power generation declaration curve to obtain the optimal next day's power generation declaration curve.

[0039] The determining module is also used to determine the actual power deviation based on the actual value of the next day's power generation, the actual value of the next day's electricity load, and the optimal next day's power generation declaration curve;

[0040] The optimization module is also used to optimize the daily equipment output based on the actual power deviation, the daily equipment output curve, the economic weight and carbon emission weight of the virtual power plant optimization scheduling, through the optimization scheduling model, to obtain the optimized daily equipment output curve and the optimized daily power exchange curve.

[0041] The acquisition module is also used to acquire meteorological data and ship entry and exit data during the carbon emission cycle, determine the cumulative net carbon emissions during the carbon emission cycle, and adjust the economic weight and the carbon emission weight based on the cumulative net carbon emissions.

[0042] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0043] Obtain the next day's power generation forecast curve, the next day's predicted state of charge of the energy storage system, the next day's electricity exchange value curve, and the next day's electricity load forecast curve;

[0044] Based on the next day's power generation forecast curve and the next day's power load forecast curve, the next day's power generation declaration curve is determined under the constraint of power balance.

[0045] Based on the next day's power generation prediction curve, the next day's predicted state of charge, the next day's electricity load prediction curve, and the next day's electricity exchange value curve, an optimized scheduling model is constructed to optimize the next day's power generation declaration curve and obtain the optimal next day's power generation declaration curve.

[0046] The actual power deviation is determined based on the actual power generation value of the next day, the actual power load value of the next day, and the optimal power generation declaration curve for the next day.

[0047] Based on the actual power deviation, the intraday equipment output curve, the economic weight and carbon emission weight of the virtual power plant optimization scheduling, the intraday equipment output is optimized through the optimization scheduling model to obtain the optimized intraday equipment output curve and the optimized intraday power exchange curve.

[0048] Meteorological data and ship entry and exit data within the carbon emission cycle are acquired, and the cumulative net carbon emissions within the carbon emission cycle are determined. Based on the cumulative net carbon emissions, the economic weight and the carbon emission weight are adjusted.

[0049] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0050] Obtain the next day's power generation forecast curve, the next day's predicted state of charge of the energy storage system, the next day's electricity exchange value curve, and the next day's electricity load forecast curve;

[0051] Based on the next day's power generation forecast curve and the next day's power load forecast curve, the next day's power generation declaration curve is determined under the constraint of power balance.

[0052] Based on the next day's power generation prediction curve, the next day's predicted state of charge, the next day's electricity load prediction curve, and the next day's electricity exchange value curve, an optimized scheduling model is constructed to optimize the next day's power generation declaration curve and obtain the optimal next day's power generation declaration curve.

[0053] The actual power deviation is determined based on the actual power generation value of the next day, the actual power load value of the next day, and the optimal power generation declaration curve for the next day.

[0054] Based on the actual power deviation, the intraday equipment output curve, the economic weight and carbon emission weight of the virtual power plant optimization scheduling, the intraday equipment output is optimized through the optimization scheduling model to obtain the optimized intraday equipment output curve and the optimized intraday power exchange curve.

[0055] Meteorological data and ship entry and exit data within the carbon emission cycle are acquired, and the cumulative net carbon emissions within the carbon emission cycle are determined. Based on the cumulative net carbon emissions, the economic weight and the carbon emission weight are adjusted.

[0056] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0057] Obtain the next day's power generation forecast curve, the next day's predicted state of charge of the energy storage system, the next day's electricity exchange value curve, and the next day's electricity load forecast curve;

[0058] Based on the next day's power generation forecast curve and the next day's power load forecast curve, the next day's power generation declaration curve is determined under the constraint of power balance.

[0059] Based on the next day's power generation prediction curve, the next day's predicted state of charge, the next day's electricity load prediction curve, and the next day's electricity exchange value curve, an optimized scheduling model is constructed to optimize the next day's power generation declaration curve and obtain the optimal next day's power generation declaration curve.

[0060] The actual power deviation is determined based on the actual power generation value of the next day, the actual power load value of the next day, and the optimal power generation declaration curve for the next day.

[0061] Based on the actual power deviation, the intraday equipment output curve, the economic weight and carbon emission weight of the virtual power plant optimization scheduling, the intraday equipment output is optimized through the optimization scheduling model to obtain the optimized intraday equipment output curve and the optimized intraday power exchange curve.

[0062] Meteorological data and ship entry and exit data within the carbon emission cycle are acquired, and the cumulative net carbon emissions within the carbon emission cycle are determined. Based on the cumulative net carbon emissions, the economic weight and the carbon emission weight are adjusted.

[0063] The aforementioned virtual power plant's optimized scheduling method, apparatus, computer equipment, computer-readable storage medium, and computer program product first acquire the next day's power generation forecast curve, the next day's predicted state of charge of the energy storage system, the next day's electricity exchange value curve, and the next day's electricity load forecast curve. Based on the next day's power generation forecast curve and the next day's electricity load forecast curve, under the constraint of power balance, the next day's power generation declaration curve is determined. Based on the next day's power generation forecast curve, the next day's predicted state of charge, the next day's electricity load forecast curve, and the next day's electricity exchange value curve, an optimized scheduling model is constructed to optimize the next day's power generation declaration curve, resulting in... The optimal next-day power generation reporting curve is obtained. Based on the actual next-day power generation, actual next-day electricity load, and the optimal next-day power generation reporting curve, the actual power deviation is determined. Based on the actual power deviation, intraday equipment output curves, and the economic and carbon emission weights of the virtual power plant's optimized scheduling, the intraday equipment output is optimized using an optimized scheduling model, resulting in optimized intraday equipment output curves and optimized intraday electricity exchange curves. Meteorological data and ship entry / exit data within the carbon emission cycle are acquired, and the cumulative net carbon emissions within the carbon emission cycle are determined. Based on the cumulative net carbon emissions, the economic and carbon emission weights are adjusted. Thus, by fully considering the unique characteristics of port electricity load forecasting, accurate reporting of the next-day power generation curve is achieved, and the weights are dynamically adjusted based on the cumulative carbon emissions over a period of time, further improving the accuracy of the virtual power plant's optimized scheduling. Attached Figure Description

[0064] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0065] Figure 1 This is a diagram illustrating the application environment of an optimized scheduling method for a virtual power plant in one embodiment.

[0066] Figure 2 This is a flowchart illustrating the optimized scheduling method for a virtual power plant in one embodiment;

[0067] Figure 3 This is a flowchart illustrating the optimized scheduling method for a virtual power plant in another embodiment;

[0068] Figure 4 Here is a structural diagram of a BP neural network model in one embodiment;

[0069] Figure 5 This is a structural block diagram of the optimized scheduling device for a virtual power plant in one embodiment;

[0070] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0071] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0072] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0073] The virtual power plant optimization scheduling method provided in this application embodiment can be applied to, for example, Figure 1 The application environment is shown. In this environment, the virtual power plant is a power coordination and management system that participates in the electricity market and grid operation as a special power plant through information and communication technology and software. Terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated on server 104 or placed in the cloud or on other network servers. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart vehicle devices, projection devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0074] In one exemplary embodiment, such as Figure 2 As shown, an optimized scheduling method for a virtual power plant is provided, which can be applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps 202 to 212. Wherein:

[0075] Step 202: Obtain the next day's power generation forecast curve, the next day's predicted state of charge of the energy storage system, the next day's power exchange value curve, and the next day's power load forecast curve.

[0076] The power generation capacity includes photovoltaic power generation capacity and wind power generation capacity.

[0077] For example, a power generation forecast curve for the next day is predicted using a preset power generation forecast model. The power generation includes both photovoltaic power generation and wind power generation; therefore, the power generation forecast curve for the next day includes the photovoltaic power generation forecast curve for the next day. Wind power generation forecast curve for the next day ,in, This represents the photovoltaic power generation at time t on the following day. The wind power generation is the wind power output at the corresponding time point t on the next day. The power generation prediction model can be a data-driven prediction algorithm based on a neural network, or other models with prediction capabilities; this application does not limit this.

[0078] The pre-set load forecasting model is used to predict the electricity load curve for the next day. ,in, Given the electricity load at time t the following day, the predicted state of charge of the energy storage system is obtained, specifically: Where SOC(t) is the state of charge of the energy storage system at time t on the next day.

[0079] Step 204: Based on the next day's power generation forecast curve and the next day's electricity load forecast curve, determine the next day's power generation declaration curve under the constraint of power balance.

[0080] Optionally, under the constraint of power balance, the power generation declaration curve for the next day is determined. The specific formula is shown in (1).

[0081] (1)

[0082] in, This is the curve for the next day's power generation declaration. This represents the predicted photovoltaic power generation at time t on the following day. This represents the predicted wind power generation at the corresponding time point t on the following day. This represents the predicted electricity load for the corresponding time point t on the next day.

[0083] Step 206: Based on the next day's power generation prediction curve, the next day's predicted state of charge, the next day's electricity load prediction curve, the next day's power generation declaration curve, and the next day's electricity exchange value curve, construct an optimized scheduling model, optimize the next day's power generation declaration curve, and obtain the optimal next day's power generation declaration curve.

[0084] For example, using the next day's power generation forecast curve, the next day's predicted state of charge, the next day's electricity load forecast curve, the next day's power generation declaration curve, and the next day's electricity exchange value curve as inputs, an optimized scheduling model is constructed based on the DQN algorithm to optimize the next day's power generation declaration curve, thereby obtaining the optimal next day's power generation declaration curve and the planned optimal output curve.

[0085] Among them, the DQN algorithm is an algorithm that combines deep learning and reinforcement learning. It approximates the Q-value function through a neural network to solve the reinforcement learning problem in a high-dimensional state space. The optimal next-day power generation reporting curve is... The next day's electricity exchange value curve is ,in, This represents the optimal power generation declaration value for the corresponding time t on the next day. This represents the exchange value (price of electricity) of the electricity at the corresponding time t on the next day.

[0086] The Q-value function in the DQN algorithm is approximated using a deep neural network. Model training was conducted to analyze the power generation reporting curve for the following day. By selecting actions for each time period, the optimized power generation reporting curve for the next day is obtained. The specific formula is shown in (2).

[0087]

[0088] (2)

[0089] Among them, P SOC_in_best (t) represents the charging power of the energy storage system at time t; P SOC_out_best (t) represents the discharge power of the energy storage system at time t.

[0090] Step 208: Determine the actual power deviation based on the actual power generation value of the next day, the actual power load value of the next day, and the optimal power generation declaration curve for the next day.

[0091] For example, obtain the actual power generation value and the actual electricity load value for the next day. The actual power generation value for the next day includes the actual photovoltaic power generation value for the next day. and the actual wind power generation value the next day .

[0092] The actual power deviation is calculated using the formula shown in (3).

[0093] (3)

[0094] in, This represents the actual photovoltaic power generation at time t the following day. This represents the actual wind power generation value on the following day at time t. This represents the actual electricity load at time t on the following day. This represents the optimal power generation declaration value for the corresponding time t on the next day.

[0095] Step 210: Based on the actual power deviation, the intraday equipment output curve, the economic weight and carbon emission weight of the virtual power plant optimization scheduling, the intraday equipment output is optimized through the optimization scheduling model to obtain the optimized intraday equipment output curve and the optimized intraday power exchange curve.

[0096] Optionally, based on the actual power deviation, intraday equipment output curve, economic weights and carbon emission weights of the virtual power plant's optimized dispatch, the intraday equipment output is optimized using an optimized dispatch model to obtain the optimized intraday equipment output curve and the optimized intraday power exchange curve. The specific calculation formula is shown in (4).

[0097] (4)

[0098] in, The daily charging power of the energy storage system at time t. Let be the daily discharge power of the energy storage system at time t. This represents the daily power generation of the gas turbine unit at time t.

[0099] Step 212: Obtain meteorological data and ship entry and exit data within the carbon emission cycle, determine the cumulative net carbon emissions within the carbon emission cycle, and adjust the economic weight and carbon emission weight based on the cumulative net carbon emissions.

[0100] For example, the net daily carbon emissions Q(m) are calculated using the formula shown in (5).

[0101] (5)

[0102] in, For equipment intraday processing The corresponding carbon emission factor, This represents the output data of the equipment at time t within the day, where i represents photovoltaic, wind power, energy storage systems, and gas turbine units.

[0103] Meteorological data and ship entry and exit data within the carbon emission cycle are used to determine the net carbon emissions for each day within the carbon emission cycle, and to calculate the cumulative net carbon emissions within the carbon emission cycle. Based on the relationship between the cumulative net carbon emissions and the preset benchmark value, the economic weight and carbon emission weight are adjusted.

[0104] In one embodiment, the implementation of this application can be continuously applied to the port's operation process, constantly adjusting the economic weight and carbon emission weight, and applying it to the optimized scheduling of the next day.

[0105] In another embodiment, the unit of measurement for the specific implementation of the scheme can be a day, week, year, etc., and this application does not limit this.

[0106] In the aforementioned optimized scheduling method for virtual power plants, the following steps are taken: obtaining the next-day power generation forecast curve, the next-day predicted state of charge of the energy storage system, the next-day electricity exchange value curve, and the next-day electricity load forecast curve; based on the next-day power generation forecast curve and the next-day electricity load forecast curve, the next-day power generation declaration curve is determined under power balance constraints; based on the next-day power generation forecast curve, the next-day predicted state of charge, the next-day electricity load forecast curve, and the next-day electricity exchange value curve, an optimized scheduling model is constructed to optimize the next-day power generation declaration curve, obtaining the optimal next-day power generation declaration curve ... power generation declaration curve is determined; and based on the next-day power generation forecast curve, the next-day power generation declaration curve is determined. The actual power generation deviation is determined by using the actual daily power generation value, the actual next-day electricity load value, and the optimal next-day power generation reporting curve. Based on the actual power deviation, the intraday equipment output curve, and the economic and carbon emission weights of the virtual power plant's optimized scheduling, the intraday equipment output is optimized using an optimized scheduling model, resulting in optimized intraday equipment output curves and optimized intraday electricity exchange curves. Meteorological data and ship entry / exit data for the carbon emission cycle are acquired, and the cumulative net carbon emissions for the carbon emission cycle are determined. Based on the cumulative net carbon emissions, the economic and carbon emission weights are adjusted. Thus, by fully considering the unique characteristics of port electricity load forecasting, accurate reporting of the next-day power generation curve is achieved, and the weights are dynamically adjusted based on the cumulative carbon emissions over a period of time, further improving the accuracy of the virtual power plant's optimized scheduling.

[0107] In an exemplary embodiment, the process of obtaining the next day's electricity load forecast curve includes: obtaining the next day's ship arrival and departure times, ship type, number of ships, and ship tonnage; determining the historical power consumption data of the corresponding ships based on the ship type and ship tonnage; determining the next day's electricity load of the port at each moment on the next day based on the historical power consumption data, ship arrival and departure times, and ship tonnage; and generating the next day's electricity load forecast curve based on the next day's electricity load of the port at each moment on the next day.

[0108] In practice, for time t of the next day, the type, number, and tonnage of the ships that are at the berth and carrying out normal loading and unloading at time t of the next day are determined.

[0109] In one embodiment, container ship N J(t) Ships, with tonnages of T J-1 T J-2 ... T J-NJ(t) Bulk carrier N S(t) Ships, with tonnages of T S-1 T S-2 ... T S-NS(t) LNG ship N L(t) Ships, with tonnages of T L-1 T L-2 ... T L-NL(t) Ro-Ro ship N G(t) Ships, with tonnages of T G-1 T G-2 ... T G-NG(t) Based on the preset power consumption statistics table, as shown in Table 1, determine the corresponding historical power consumption data for the operation.

[0110] Table 1. Preset Power Consumption Statistics

[0111] container ship bulk carriers LNG ship Ro-Ro ship Small tonnage <![CDATA[P J-S ]]> <![CDATA[P S-S ]]> <![CDATA[P L-S ]]> <![CDATA[P G-S ]]> Small and medium tonnage <![CDATA[P J-MS ]]> <![CDATA[P S-MS ]]> <![CDATA[P L-MS ]]> <![CDATA[P G-MS <!-- 8 -->]]> medium tonnage <![CDATA[P J-M ]]> <![CDATA[P S-M ]]> <![CDATA[P L-M ]]> <![CDATA[P G-M ]]> medium and large tonnage <![CDATA[P J-ML ]]> <![CDATA[P S-ML ]]> <![CDATA[P L-ML ]]> <![CDATA[P G-ML ]]> large tonnage <![CDATA[P J-L ]]> <![CDATA[P S-L ]]> <![CDATA[P L-L ]]> <![CDATA[P G-L ]]>

[0112] The total electrical power P of all ships at time t on the next day was calculated. task(t) The specific calculation formula is shown in (6).

[0113] (6)

[0114] Among them, P J-i(t) This indicates that the i-th container ship is based on its tonnage T. J-i Historical power consumption data for the operation matched in Table 1; P S-j(t) This indicates that the j-th bulk carrier is based on its tonnage T. S-j Historical power consumption data for the operation matched in Table 1; P L-k(t) This indicates that the k-th LNG ship is based on its tonnage T. L-k Historical power consumption data for the operation matched in Table 1; P G-n(t) This indicates that the nth roll-on / roll-off ship is based on its tonnage T. G-n The historical power consumption data of the operation matched by Table 1.

[0115] The total power load P of the port at time t on the next day is calculated. load(t) The specific calculation formula is shown in (7).

[0116]

[0117] (7)

[0118] Among them, P shorepower (t) represents the port shore power load at time t on the next day. P is the conversion factor from port machinery power load to shore power load. light (t) represents the port lighting load power at time t on the next day. P is the conversion factor from port machinery electrical load to lighting load. other (t) represents the power consumption of other electrical loads such as port living and office use at time t on the next day. This is the conversion factor from the electrical load of the port machinery to other loads.

[0119] Repeat the above steps until the electricity load for all times of the next day is obtained, and generate the electricity load forecast curve for the next day. .

[0120] In the above embodiments, by combining the actual ship conditions at the port, the electricity load curve for the next day is predicted, making the prediction results more accurate.

[0121] In an exemplary embodiment, an optimized scheduling model is constructed based on the next day's power generation forecast curve, the next day's predicted state of charge, the next day's electricity load forecast curve, and the next day's electricity exchange value curve. The model includes: constructing a first state space and a first action space based on the next day's power generation forecast curve, the next day's predicted state of charge, the next day's electricity load forecast curve, and the next day's electricity exchange value curve; and adjusting the optimized scheduling model based on the first state space and the first action space until the next day's revenue, as represented by the reward function, is maximized.

[0122] In actual implementation, the first state space s is constructed based on the DQN algorithm, and the specific formula is shown in (8). The first action space a is constructed based on the specific formula shown in (9).

[0123] (8)

[0124] (9)

[0125] in, Adjust the step size for the number of applications submitted.

[0126] With the goal of maximizing the next day's revenue, a reward function is constructed by combining the value of electricity exchange and the operating cost of equipment. The specific formula is shown in (10).

[0127] (10)

[0128] in, The virtual battery device operating cost is given at time t on the next day.

[0129] In the above embodiments, setting a reward function optimizes the scheduling effect and improves accuracy.

[0130] In an exemplary embodiment, based on the actual power deviation, the intraday equipment output curve, the economic weight, and the carbon emission weight, the intraday equipment output is optimized by an optimized scheduling model, including: updating the state space and action space based on the actual power deviation, the intraday equipment output curve, the economic weight, and the carbon emission weight to obtain a second state space and a second action space; and using the optimized scheduling model to optimize the intraday equipment output based on the second state space and the second action space.

[0131] In practical implementation, a second state space is constructed based on the DQN algorithm. The specific formula is shown in (11), the second action space The specific formula is shown in (12).

[0132] (11)

[0133] (12)

[0134] in, As an economic weight, For carbon emission weights, P represents the actual electricity load for the next day. pv_real P represents the actual photovoltaic power generation capacity for the next day. wind_real This represents the actual wind power generation capacity for the following day.

[0135] With the goal of minimizing intraday costs and maximizing intraday stage revenue, a reward function is constructed by combining electricity trading revenue and costs with equipment operating costs. The specific formula is shown in (13).

[0136] (13)

[0137] in, To optimize the value curve for intraday market participation, Intraday costs include intraday operating costs of energy storage systems and gas turbine units, as well as intraday penalty costs.

[0138] In the above embodiments, the daily equipment output is optimized based on the error and intraday equipment output curve, economic weight and carbon emission weight, so that the optimized scheduling of the port virtual factory is more accurate.

[0139] In an exemplary embodiment, acquiring meteorological data and ship entry / exit data within a carbon emission cycle, and determining the cumulative net carbon emissions within the carbon emission cycle, includes: determining the historical cumulative net carbon emissions from the first day of the carbon emission cycle to the current day based on the meteorological data and ship entry / exit data; inputting the historical cumulative net carbon emissions into a net carbon emissions prediction model after training to obtain the predicted cumulative net carbon emissions for the remaining days of the carbon emission cycle; and using the sum of the historical cumulative net carbon emissions and the predicted cumulative net carbon emissions as the cumulative net carbon emissions within the carbon emission cycle.

[0140] In practice, the daily net carbon emissions Q(m) are calculated as follows: The daily net carbon emissions from the first day to the current day are: Q(m), m = 1, 2, …, M. Here, M represents the current day as part of the carbon emission accounting cycle T. h The daily meteorological data from the first day to the current day are as follows: total irradiance S (m) on day m, average temperature T (m) on day m, and average wind speed V (m) on day m.

[0141] The daily ship arrival and departure data from the first day to the current day is as follows: Total number of container ships arriving on day m, K J (m), Total tonnage of container ships entering port on day m U J (m), Total number of bulk carriers entering port on day m K S (m), Total tonnage of bulk carriers entering port on day m U S (m), Total number of LNG vessels entering port on day m K L (m), Total tonnage of LNG vessels entering port on day m U L (m), Total number of roll-on / roll-off vessels entering the port on day m (K) G (m), Total tonnage of roll-on / roll-off vessels entering port on day m U G (m).

[0142] A BP neural network was used to construct a daily net carbon emission prediction model, with the total irradiance S(m) on day m, the average temperature T(m) on day m, the average wind speed V(m) on day m, and the total number of container ships entering the port K on day m as the parameters. J (m), Total tonnage of container ships entering port on day m U J (m), Total number of bulk carriers entering port on day m K S (m), Total tonnage of bulk carriers entering port on day m U S (m), Total number of LNG vessels entering port on day m K L (m), Total tonnage of LNG vessels entering port on day m U L (m), Total number of roll-on / roll-off vessels entering the port on day m (K) GThe BP neural network model is constructed using the total tonnage of roll-on / roll-off vessels entering the port on day m as input and the net carbon emissions Q(m) on day m as output.

[0143] Based on carbon emission accounting cycle T h Within the period, statistical data from day 1 to the current day is used to train a constructed BP neural network model to calculate the remaining days within the carbon emission cycle, specifically day (T). h -M) day, (T) h -M+1) day, ..., Tth h On that day, a daily net carbon emission prediction model was constructed using meteorological forecast data and ship entry and exit plan data for the remaining days, yielding the predicted net carbon emissions for the remaining days: Q*(T h -M), Q*(T) h -M+1), ..., Q*(T) h ), calculate the cumulative net carbon emissions Q during the carbon emission cycle. c The specific calculation formula is shown in (14).

[0144] (14)

[0145] Where m is the number of days from the first day to the current day, and n is the number of days from the current day to the last day of the carbon emission cycle.

[0146] In the above embodiments, the net carbon emissions for the remaining days are predicted using a predictive model, making the calculation of the cumulative net carbon emissions within the carbon emission cycle more accurate.

[0147] In one exemplary embodiment, the economic weight and carbon emission weight are adjusted based on cumulative net carbon emissions, including:

[0148] If the cumulative net carbon emissions exceed the preset benchmark value, the economic weight and carbon emission weight shall be adjusted according to formulas (15) and (16).

[0149] (15)

[0150] =1- (16)

[0151] in, For the adjusted carbon emission weights, The adjusted economic weights, For carbon emission weights, As an economic weight, T h For the duration of carbon emission cycles, Q represents the cumulative net carbon emissions over the carbon emission cycle. i0The base amount for adjusting the carbon emission coefficient is M, where M is the length of the carbon emission cycle up to the current day;

[0152] If the cumulative net carbon emissions are less than the preset benchmark value, the economic weight and carbon emission weight shall be adjusted according to formula (17) and formula (18).

[0153] (17)

[0154] =1- (18)

[0155] in, For the adjusted carbon emission weights, The adjusted economic weights, For carbon emission weights, As an economic weight, T h For the duration of carbon emission cycles, Q represents the cumulative net carbon emissions over the carbon emission cycle. d0 This is the baseline amount for adjusting the carbon emission coefficient, where M is the duration of the carbon emission cycle up to the current day.

[0156] In the above embodiments, the weights are dynamically adjusted based on the cumulative carbon emissions of the port over a period of time, which further improves the accuracy of the optimal operation and scheduling of the virtual power plant.

[0157] To illustrate the optimized scheduling method of the virtual power plant in this application in detail, an embodiment is described below, and the specific flowchart is as follows. Figure 3 As illustrated, this application provides an example of an optimized scheduling method for a virtual power plant in a specific scenario.

[0158] First, a neural network algorithm is used to predict the photovoltaic power generation curve for the next day, resulting in the predicted photovoltaic power generation curve for the next day:

[0159] ;

[0160] The wind power generation curve for the next day is predicted, resulting in the predicted wind power generation curve for the next day:

[0161] ;

[0162] Based on the confirmed vessel entry and exit schedule for the next day, the port's electricity load curve for the next day is predicted, resulting in the port's predicted electricity load curve for the next day. Taking the 10th hour of the next day as an example, according to the confirmed vessel entry and exit schedule for the next day, the following data are obtained regarding the type, number, and tonnage of vessels that are at berths and carrying out normal loading and unloading at the 10th hour of the next day: 5 container ships with tonnages of 40,000 tons, 180,000 tons, 80,000 tons, 150,000 tons, and 120,000 tons; 7 bulk carriers with tonnages of 20,000 tons, 110,000 tons, 70,000 tons, 120,000 tons, 90,000 tons, 170,000 tons, and 130,000 tons; 0 LNG carriers; and 1 roll-on / roll-off ship with 5,000 vehicle berths.

[0163] Based on the preset power consumption statistics table, as shown in Table 2, the corresponding historical power consumption data for the operation is determined.

[0164] Table 2 Preset Power Consumption Statistics Table

[0165] container ship bulk carriers LNG ship Ro-Ro ship Small tonnage 60.5kw 35.6kW 17.5kW 26.6kW Small and medium tonnage 72.5kw 42.6kW 19.5kW 33.6kW medium tonnage 82.8kW 52.5kW 26.9kW 39.5kW medium and large tonnage 91.9kW 59.5kW 29.5kW 43.2kW large tonnage 105.6kW 71.2kW 33.6kW 49.8kW

[0166] The total power consumption P of all vessels in port at 10 o'clock the following day during loading and unloading operations was obtained. task (10):

[0167] ;

[0168] The total power load data P of the port at time 10 the next day was obtained by conversion. load (10):

[0169] ;

[0170] ;

[0171] Among them, P shorepower (10) indicates the port shore power load at time 10 the next day. The conversion factor from port machinery power load to shore power load is used in this embodiment. ;P light (10) indicates the port lighting load power at the 10th hour of the next day. The conversion factor from port machinery electrical load to lighting load is used in this embodiment. ;P other (10) indicates the power consumption of other electrical loads such as port living and office use at the 10th time of the next day. The conversion factor from port machinery electrical load to other loads is used in this embodiment. In summary, P can be calculated. load (10) = 1882kW.

[0172] Repeat the above steps until the total port power load data from time 1 to time 24 of the next day is obtained, thus obtaining the port's power load curve for the next day:

[0173] ;

[0174] Based on the next day's photovoltaic and wind power generation forecast curves and the next day's electricity load forecast curves, the next day's power generation declaration curve is obtained from the power balance, namely:

[0175] ;

[0176] The following day's power generation reporting curve was obtained as follows:

[0177] ;

[0178] The state of charge of the energy storage system, in this embodiment, is taken as:

[0179] ;

[0180] In this embodiment, the next day's electricity exchange value curve is as follows:

[0181] ;

[0182] In this embodiment, the optimal charge-discharge curve for the energy storage day-ahead plan is... , They are respectively:

[0183] ;

[0184] ;

[0185] In this embodiment, the optimized next-day power generation reporting curve is as follows:

[0186] ;

[0187] The actual value of wind power generation in the actual power generation value on the next day is The actual value of photovoltaic power generation The actual power load at the port the following day The actual power deviation is calculated based on the optimal next-day power generation reporting curve. In this embodiment, the calculated actual power deviation is:

[0188] ;

[0189] Constructing a second state space based on the DQN algorithm The specific formula is shown in (11), the second action space The specific formula is shown in (12). With the goal of minimizing intraday costs and maximizing intraday stage revenue, a reward function is constructed by combining electricity trading revenue and costs with equipment operating costs. The specific formula is shown in (13).

[0190] In this embodiment, the economic weight is: Carbon emission weighting is The cost of energy storage is calculated at 0.11 yuan / kWh; the cost of gas turbine units is calculated at 0.55 yuan / kWh.

[0191] ;

[0192] The daily net carbon emissions data Q(m) is calculated, taking day 5 as an example, as follows:

[0193] ;

[0194] In this embodiment, the net carbon emissions data Q(5) on day 5 can be calculated to be 1592.7 tons.

[0195] Based on daily net carbon emissions data from the first day to the current day within the carbon emission accounting cycle, meteorological data, and ship entry and exit data, a daily net carbon emissions prediction model was constructed using a BP neural network, and the model training was completed.

[0196] In this embodiment, the carbon emission accounting period is T. h It is the 30th;

[0197] In this embodiment, the current day is the 5th day, and the net carbon emissions data for each day from the 1st day to the current day (i.e. the 5th day) are: Q(1) = 1562.2 tons, Q(2) = 1365.9 tons, Q(3) = 1026.5 tons, Q(4) = 998.5 tons, Q(5) = 1592.7 tons;

[0198] The daily meteorological data from day 1 to the present day (i.e. day 5) are as follows: total irradiance S (m) on day m, average temperature T (m) on day m, and average wind speed V (m) on day m.

[0199] The daily ship entry and exit data from day 1 to the current day (i.e., day 5) is as follows: Total number of container ships entering the port on day m, K J (m), Total tonnage of container ships entering port on day m U J (m), Total number of bulk carriers entering port on day m K S (m), Total tonnage of bulk carriers entering port on day m U S (m), Total number of LNG vessels entering port on day m K L (m), Total tonnage of LNG vessels entering port on day m U L(m), Total number of roll-on / roll-off vessels entering the port on day m (K) G (m), Total tonnage of roll-on / roll-off vessels entering port on day m U G (m);

[0200] A BP neural network is used to construct a daily net carbon emission prediction model, specifically: the total irradiance S(m) on day m, the average temperature T(m) on day m, the average wind speed V(m) on day m, and the total number of container ships entering the port K on day m. J (m), Total tonnage of container ships entering port on day m U J (m), Total number of bulk carriers entering port on day m K S (m), Total tonnage of bulk carriers entering port on day m U S (m), Total number of LNG vessels entering port on day m K L (m), Total tonnage of LNG vessels entering port on day m U L (m), Total number of roll-on / roll-off vessels entering the port on day m (K) G (m), Total tonnage of roll-on / roll-off vessels entering port on day m U G (m) is the input to the BP neural network model; the net carbon emissions Q(m) on day m are used as the output of the BP neural network model to construct the BP neural network model, and the model structure is as follows. Figure 4 As shown;

[0201] Based on carbon emission accounting cycle T h =Within 30 days, the statistical data from the 1st day to the current day (i.e. the 5th day) are used to train the constructed BP neural network model. The remaining days in the carbon emission accounting cycle are: the 6th day, the 7th day, ..., the 30th day.

[0202] In this embodiment, the net carbon emissions for the remaining days of the carbon emission cycle are predicted as follows: the meteorological forecast data and ship entry and exit plan data for the remaining days are input into the constructed daily net carbon emission prediction model to obtain the predicted net carbon emissions for the remaining days: Q*(6)=1526.5 tons, Q*(7)=1332.2, ..., Q*(30)=1916.2. The cumulative net carbon emissions Q for the entire carbon emission cycle are then calculated. c =38,085 tons.

[0203] In this embodiment, the reference value Q is taken. baseline If the volume is 30,000 tons, then the economic weight and carbon emission weight of the port virtual power plant's optimized scheduling will be adjusted the following day, specifically as follows:

[0204] Because Qc is greater than Q baseline If the amount is 30,000 tons, then the carbon emission weight will be adjusted:

[0205] ;

[0206] in, The adjusted carbon emission weights; Q i0 To adjust the carbon emission coefficient to a baseline amount, in this embodiment, Q is taken as... i0 =1000 tons. Subsequently, the economic weighting was adjusted. =1- =0.2343.

[0207] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0208] Based on the same inventive concept, this application also provides an optimized scheduling apparatus for virtual power plants to implement the optimized scheduling method for virtual power plants described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more embodiments of the optimized scheduling apparatus for virtual power plants provided below can be found in the limitations of the optimized scheduling method for virtual power plants described above, and will not be repeated here.

[0209] In one exemplary embodiment, such as Figure 5 As shown, an optimized scheduling device for a virtual power plant is provided, comprising: an acquisition module 501, a determination module 502, and an optimization module 503, wherein:

[0210] The acquisition module 501 is used to acquire the next day's power generation prediction curve, the next day's predicted state of charge of the energy storage system, the next day's electricity exchange value curve, and the next day's electricity load prediction curve.

[0211] The determination module 502 is used to determine the next day's power generation forecast curve based on the next day's power generation forecast curve and the next day's power load forecast curve, under the constraint of power balance.

[0212] The optimization module 503 is used to construct an optimized scheduling model based on the next day's power generation prediction curve, the next day's predicted state of charge, the next day's power load prediction curve, and the next day's power exchange value curve, and to optimize the next day's power generation declaration curve to obtain the optimal next day's power generation declaration curve.

[0213] The determining module 502 is also used to determine the actual power deviation based on the actual value of the next day's power generation, the actual value of the next day's electricity load, and the optimal next day's power generation declaration curve.

[0214] The optimization module 503 is further used to optimize the intraday equipment output based on the actual power deviation, intraday equipment output curve, economic weight of virtual power plant optimization scheduling and carbon emission weight, through the optimization scheduling model, to obtain the optimized intraday equipment output curve and the optimized intraday power exchange curve.

[0215] The acquisition module 501 is also used to acquire meteorological data and ship entry and exit data during the carbon emission cycle, determine the cumulative net carbon emissions during the carbon emission cycle, and adjust the economic weight and the carbon emission weight based on the cumulative net carbon emissions.

[0216] In one exemplary embodiment, the acquisition module 501 is further configured to acquire the ship's arrival and departure times, ship type, number of ships, and ship tonnage for the next day.

[0217] Based on the ship type and the ship tonnage, determine the historical power consumption data of the corresponding ship;

[0218] Based on the historical power consumption data, the ship's arrival and departure times, and the ship's tonnage, the port's next-day power load at each moment of the next day is determined, and a next-day power load prediction curve is generated based on the port's next-day power load at each moment of the next day.

[0219] In one exemplary embodiment, the device further includes a construction module for constructing a first state space and a first action space based on the next day's power generation prediction curve, the next day's predicted state of charge, the next day's electricity load prediction curve, and the next day's electricity exchange value curve.

[0220] Based on the first state space and the first action space, the scheduling model is adjusted and optimized until the next day's revenue, as represented by the reward function, is maximized.

[0221] In one exemplary embodiment, the optimization module 503 is further configured to update the state space and action space based on the actual power deviation, the intraday equipment output curve, the economic weight and the carbon emission weight, to obtain a second state space and a second action space.

[0222] Based on the second state space and the second action space, the optimized scheduling model is used to optimize the daily equipment output.

[0223] In one exemplary embodiment, the determining module 502 is further configured to determine the historical cumulative net carbon emissions from the first day of the carbon emission cycle to the current day based on the meteorological data and the ship entry and exit data.

[0224] The historical cumulative net carbon emissions are input into the net carbon emissions prediction model after training to obtain the predicted cumulative net carbon emissions for the remaining days in the carbon emission cycle.

[0225] The sum of the historical cumulative net carbon emissions and the predicted cumulative net carbon emissions is taken as the cumulative net carbon emissions within the carbon emission cycle.

[0226] In one exemplary embodiment, the device further includes an adjustment module for adjusting the economic weight and carbon emission weight according to the following formula if the cumulative net carbon emissions are greater than a preset benchmark value.

[0227] ;

[0228] =1- ;

[0229] in, For the adjusted carbon emission weights, The adjusted economic weights, For carbon emission weights, As an economic weight, T h For the duration of carbon emission cycles, Q represents the cumulative net carbon emissions over the carbon emission cycle. i0 The base amount for adjusting the carbon emission coefficient is M, where M is the length of the carbon emission cycle up to the current day;

[0230] If the cumulative net carbon emissions are less than a preset benchmark value, the economic weight and the carbon emission weight are adjusted according to the following formula;

[0231] ;

[0232] =1- ;

[0233] in, For the adjusted carbon emission weights, The adjusted economic weights, For carbon emission weights, As an economic weight, Th For the duration of carbon emission cycles, Q represents the cumulative net carbon emissions over the carbon emission cycle. d0 This is the baseline amount for adjusting the carbon emission coefficient, where M is the duration of the carbon emission cycle up to the current day.

[0234] The various modules in the aforementioned virtual power plant's optimized dispatching device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can invoke and execute the corresponding operations of each module.

[0235] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6 As shown, this computer device includes a processor, memory, input / output interfaces (I / O), communication interfaces, a display unit, and input devices. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface, display unit, and input devices are also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores the output data of the virtual power plant. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements an optimized scheduling method for a virtual power plant.

[0236] The display unit of this computer device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of this computer device can be a touch layer covering the display screen, or buttons, a trackball, or a touchpad set on the casing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0237] Those skilled in the art will understand that Figure 6The structures shown are merely block diagrams of some structures related to the present application and do not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the following steps:

[0238] Obtain the next day's power generation forecast curve, the next day's predicted state of charge of the energy storage system, the next day's electricity exchange value curve, and the next day's electricity load forecast curve;

[0239] Based on the next day's power generation forecast curve and the next day's power load forecast curve, the next day's power generation declaration curve is determined under the constraint of power balance.

[0240] Based on the next day's power generation prediction curve, the next day's predicted state of charge, the next day's electricity load prediction curve, and the next day's electricity exchange value curve, an optimized scheduling model is constructed to optimize the next day's power generation declaration curve and obtain the optimal next day's power generation declaration curve.

[0241] The actual power deviation is determined based on the actual power generation value of the next day, the actual power load value of the next day, and the optimal power generation declaration curve for the next day.

[0242] Based on the actual power deviation, the intraday equipment output curve, the economic weight and carbon emission weight of the virtual power plant optimization scheduling, the intraday equipment output is optimized through the optimization scheduling model to obtain the optimized intraday equipment output curve and the optimized intraday power exchange curve.

[0243] Meteorological data and ship entry and exit data within the carbon emission cycle are acquired, and the cumulative net carbon emissions within the carbon emission cycle are determined. Based on the cumulative net carbon emissions, the economic weight and the carbon emission weight are adjusted.

[0244] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0245] Obtain the next day's power generation forecast curve, the next day's predicted state of charge of the energy storage system, the next day's electricity exchange value curve, and the next day's electricity load forecast curve;

[0246] Based on the next day's power generation forecast curve and the next day's power load forecast curve, the next day's power generation declaration curve is determined under the constraint of power balance.

[0247] Based on the next day's power generation prediction curve, the next day's predicted state of charge, the next day's electricity load prediction curve, and the next day's electricity exchange value curve, an optimized scheduling model is constructed to optimize the next day's power generation declaration curve and obtain the optimal next day's power generation declaration curve.

[0248] The actual power deviation is determined based on the actual power generation value of the next day, the actual power load value of the next day, and the optimal power generation declaration curve for the next day.

[0249] Based on the actual power deviation, the intraday equipment output curve, the economic weight and carbon emission weight of the virtual power plant optimization scheduling, the intraday equipment output is optimized through the optimization scheduling model to obtain the optimized intraday equipment output curve and the optimized intraday power exchange curve.

[0250] Meteorological data and ship entry and exit data within the carbon emission cycle are acquired, and the cumulative net carbon emissions within the carbon emission cycle are determined. Based on the cumulative net carbon emissions, the economic weight and the carbon emission weight are adjusted.

[0251] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0252] Obtain the next day's power generation forecast curve, the next day's predicted state of charge of the energy storage system, the next day's electricity exchange value curve, and the next day's electricity load forecast curve;

[0253] Based on the next day's power generation forecast curve and the next day's power load forecast curve, the next day's power generation declaration curve is determined under the constraint of power balance.

[0254] Based on the next day's power generation prediction curve, the next day's predicted state of charge, the next day's electricity load prediction curve, and the next day's electricity exchange value curve, an optimized scheduling model is constructed to optimize the next day's power generation declaration curve and obtain the optimal next day's power generation declaration curve.

[0255] The actual power deviation is determined based on the actual power generation value of the next day, the actual power load value of the next day, and the optimal power generation declaration curve for the next day.

[0256] Based on the actual power deviation, the intraday equipment output curve, the economic weight and carbon emission weight of the virtual power plant optimization scheduling, the intraday equipment output is optimized through the optimization scheduling model to obtain the optimized intraday equipment output curve and the optimized intraday power exchange curve.

[0257] Meteorological data and ship entry and exit data within the carbon emission cycle are acquired, and the cumulative net carbon emissions within the carbon emission cycle are determined. Based on the cumulative net carbon emissions, the economic weight and the carbon emission weight are adjusted.

[0258] 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, data stored, data displayed, 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 the relevant data must comply with relevant regulations.

[0259] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this 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. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0260] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0261] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An optimized scheduling method for a virtual power plant, characterized in that, The method includes: The system acquires the next-day power generation forecast curve, the next-day predicted state of charge of the energy storage system, the next-day power exchange value curve, and the next-day power load forecast curve. The process of acquiring the next-day power load forecast curve includes: acquiring the next-day ship arrival and departure times, ship type, number of ships, and ship tonnage; determining the historical power consumption data of the corresponding ships based on the ship type and tonnage; determining the next-day power load of the port at each moment on the next day based on the historical power consumption data, the ship arrival and departure times, and the ship tonnage; and generating the next-day power load forecast curve based on the next-day power load of the port at each moment on the next day. Based on the next day's power generation forecast curve and the next day's power load forecast curve, the next day's power generation declaration curve is determined under the constraint of power balance. Based on the next day's power generation prediction curve, the next day's predicted state of charge, the next day's electricity load prediction curve, and the next day's electricity exchange value curve, a first state space and a first action space are constructed. On the basis of the first state space and the first action space, the scheduling model is adjusted and optimized until the next day's revenue represented by the reward function is maximized. The next day's power generation declaration curve is then optimized to obtain the optimal next day's power generation declaration curve. The actual power deviation is determined based on the actual power generation value of the next day, the actual power load value of the next day, and the optimal power generation declaration curve for the next day. Based on the actual power deviation, the intraday equipment output curve, the economic weight and carbon emission weight of the virtual power plant optimization scheduling, the intraday equipment output is optimized through the optimization scheduling model to obtain the optimized intraday equipment output curve and the optimized intraday power exchange curve. Based on meteorological data and ship arrival and departure data, the historical cumulative net carbon emissions from the first day of the carbon emission cycle to the current day are determined. The historical cumulative net carbon emissions are input into the net carbon emission prediction model after training to obtain the predicted cumulative net carbon emissions for the remaining days in the carbon emission cycle. The sum of the historical cumulative net carbon emissions and the predicted cumulative net carbon emissions is taken as the cumulative net carbon emissions in the carbon emission cycle. Based on the cumulative net carbon emissions, the economic weight and the carbon emission weight are adjusted.

2. The method according to claim 1, characterized in that, The optimization of intraday equipment output based on the actual power deviation, intraday equipment output curve, economic weights and carbon emission weights of virtual power plant optimized scheduling, through the optimized scheduling model, includes: Based on the actual power deviation, the intraday equipment output curve, the economic weight and the carbon emission weight, the state space and action space are updated to obtain the second state space and the second action space. Based on the second state space and the second action space, the optimized scheduling model is used to optimize the daily equipment output.

3. The method according to claim 1, characterized in that, The adjustment of the economic weight and the carbon emission weight based on the cumulative net carbon emissions includes: If the cumulative net carbon emissions exceed a preset benchmark value, the economic weight and carbon emission weight will be adjusted according to the following formula; ； =1- ； in, For the adjusted carbon emission weights, The adjusted economic weights, For carbon emission weights, T h For the duration of carbon emission cycles, Q represents the cumulative net carbon emissions over the carbon emission cycle. i0 The base amount for adjusting the carbon emission coefficient is M, where M is the length of the carbon emission cycle up to the current day; If the cumulative net carbon emissions are less than a preset benchmark value, the economic weight and the carbon emission weight are adjusted according to the following formula; ； =1- ； in, For the adjusted carbon emission weights, The adjusted economic weights, For carbon emission weights, T h For the duration of carbon emission cycles, Q represents the cumulative net carbon emissions over the carbon emission cycle. d0 This is the baseline amount for adjusting the carbon emission coefficient, where M is the duration of the carbon emission cycle up to the current day.

4. An optimized scheduling device for a virtual power plant, characterized in that, The device includes: The acquisition module is used to acquire the next day's power generation forecast curve, the next day's predicted state of charge of the energy storage system, the next day's power exchange value curve, and the next day's power load forecast curve. The acquisition process of the next day's power load forecast curve includes: acquiring the next day's ship arrival and departure times, ship type, number of ships, and ship tonnage; determining the historical power consumption data of the corresponding ships based on the ship type and ship tonnage; determining the next day's power load of the port at each moment on the next day based on the historical power consumption data, the ship arrival and departure times, and the ship tonnage; and generating the next day's power load forecast curve based on the next day's power load of the port at each moment on the next day. The determination module is used to determine the next day's power generation forecast curve based on the next day's power generation forecast curve and the next day's power load forecast curve, under the constraint of power balance. The optimization module is used to construct a first state space and a first action space based on the next day's power generation prediction curve, the next day's predicted state of charge, the next day's electricity load prediction curve, and the next day's electricity exchange value curve; and to adjust and optimize the scheduling model based on the first state space and the first action space until the next day's revenue represented by the reward function is maximized, thereby optimizing the next day's power generation declaration curve to obtain the optimal next day's power generation declaration curve. The determining module is also used to determine the actual power deviation based on the actual value of the next day's power generation, the actual value of the next day's electricity load, and the optimal next day's power generation declaration curve; The optimization module is also used to optimize the daily equipment output based on the actual power deviation, the daily equipment output curve, the economic weight and carbon emission weight of the virtual power plant optimization scheduling, through the optimization scheduling model, to obtain the optimized daily equipment output curve and the optimized daily power exchange curve. The acquisition module is further configured to determine the historical cumulative net carbon emissions from the first day of the carbon emission cycle to the current day based on meteorological data and ship entry and exit data; input the historical cumulative net carbon emissions into the net carbon emissions prediction model after training to obtain the predicted cumulative net carbon emissions for the remaining days in the carbon emission cycle; use the sum of the historical cumulative net carbon emissions and the predicted cumulative net carbon emissions as the cumulative net carbon emissions in the carbon emission cycle, and adjust the economic weight and the carbon emission weight based on the cumulative net carbon emissions.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 3.

7. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 3.

Images