Intelligent scheduling method, device and system based on green electric driving

Abstract

The embodiment of the invention discloses an intelligent scheduling method, device and system based on green electric driving. The method is applied to a green power dispatching system, the system is used for dispatching a power grid system, a new energy power generation system, an energy storage system and a hydrogen production system, and the method comprises the following steps: obtaining a target dispatching mode at a prediction moment; obtaining a target system parameter at a prediction moment; on the basis of a preset target function and a preset scheduling constraint condition, a first target scheduling strategy at the prediction moment is determined according to the target scheduling mode and the target system parameters, and the target function indicates grid-connected income maximization, hydrogen production maximization and electricity abandonment rate minimization; and when the prediction time is reached, scheduling the power grid system, the new energy power generation system, the energy storage system and the hydrogen production system according to the first target scheduling strategy. According to the embodiment, the stability and scheduling efficiency of the green power scheduling system can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of electric power dispatching, and in particular to an intelligent dispatching method, device and system based on green electric power drive. Background Art

[0002] With the rapid development of renewable energy, the application of green electricity has become an important direction for future energy transformation. As an important means of energy storage and clean energy utilization, hydrogen production, especially in the context of obvious power fluctuations in new energy power generation such as wind power and photovoltaic power generation, how to effectively dispatch green electricity and optimize the hydrogen production process has become an important research issue.

[0003] However, traditional green power dispatching systems are highly dependent on real-time data for dynamic adjustments, but there may be problems with the transmission and synchronization of real-time data. If data cannot be transmitted in a timely manner, it will affect the stability of the system and the dispatching efficiency. Summary of the invention

[0004] The embodiments of the present application provide an intelligent dispatching method, device and system based on green power drive, which can improve the stability and dispatching efficiency of the green power dispatching system.

[0005] In a first aspect, an embodiment of the present application provides an intelligent dispatching method based on green power drive, the method is applied to a green power dispatching system, the green power dispatching system is used to dispatch a power grid system, a new energy power generation system, an energy storage system and a hydrogen production system, the method comprising:

[0006] Obtain a target scheduling mode at a predicted time, where the predicted time is a time after the current time;

[0007] Obtain target system parameters at the prediction time;

[0008] Based on the preset objective function and the preset scheduling constraints, the first target scheduling strategy at the prediction time is determined according to the target scheduling mode and the target system parameters, wherein the objective function indicates maximizing the grid connection revenue, maximizing the hydrogen production and minimizing the power abandonment rate, and the first target scheduling strategy includes the power grid scheduling strategy, the new energy scheduling strategy, the energy storage scheduling strategy and the hydrogen production scheduling strategy;

[0009] When the predicted time is reached, the power grid system, new energy power generation system, energy storage system and hydrogen production system are dispatched according to the first target dispatching strategy.

[0010] In a second aspect, the embodiment of the present application further provides an intelligent dispatching device based on green power drive, the device is configured in a green power dispatching system, the green power dispatching system is used to dispatch a power grid system, a new energy power generation system, an energy storage system and a hydrogen production system, and the device includes:

[0011] A transceiver unit, used to obtain a target scheduling mode at a predicted time, where the predicted time is a time after the current time; and also used to obtain a target system parameter at the predicted time;

[0012] A processing unit is used to determine a first target scheduling strategy at a prediction time based on a preset objective function and preset scheduling constraints, according to a target scheduling mode and target system parameters, wherein the objective function indicates maximizing grid-connected revenue, maximizing hydrogen production and minimizing power abandonment rate, and the first target scheduling strategy includes a power grid scheduling strategy, a new energy scheduling strategy, an energy storage scheduling strategy and a hydrogen production scheduling strategy; when the prediction time is reached, the power grid system, the new energy power generation system, the energy storage system and the hydrogen production system are scheduled according to the first target scheduling strategy.

[0013] In a third aspect, an embodiment of the present application further provides a green power dispatching system, which includes a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above method when executing the computer program.

[0014] The embodiment of the present application provides an intelligent dispatching method, device and system based on green power drive. Among them, the method is applied to a green power dispatching system, which is used to dispatch a power grid system, a new energy power generation system, an energy storage system and a hydrogen production system. The method includes: obtaining a target dispatching mode at a predicted moment, wherein the predicted moment is a moment after the current moment; obtaining target system parameters at the predicted moment; based on a preset objective function and preset dispatching constraints, determining a first target dispatching strategy at the predicted moment according to the target dispatching mode and the target system parameters, wherein the objective function indicates maximization of grid-connected revenue, maximization of hydrogen production and minimization of power abandonment rate, and the first target dispatching strategy includes a power grid dispatching strategy, a new energy dispatching strategy, an energy storage dispatching strategy and a hydrogen production dispatching strategy; when the predicted moment is reached, the power grid system, the new energy power generation system, the energy storage system and the hydrogen production system are dispatched according to the first target dispatching strategy. The green power dispatching system in the embodiment of the present application can predict the dispatching strategy of future moments in advance through preset optimization functions and dispatching constraints, so that the system dispatching does not need to be highly dependent on real-time data, thereby improving the stability and dispatching efficiency of the green power dispatching system. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1A schematic diagram of an application scenario of an intelligent scheduling method based on green power drive provided in an embodiment of the present application;

[0017] Figure 2 A schematic diagram of a flow chart of an intelligent dispatching method based on green power drive provided in an embodiment of the present application;

[0018] Figure 3 A simulation result of a grid-connected priority working mode in the intelligent dispatching method based on green power drive provided in an embodiment of the present application;

[0019] Figure 4 Another simulation result of the grid-connected priority working mode in the intelligent dispatching method based on green power drive provided in the embodiment of the present application;

[0020] Figure 5 Another simulation result of the grid-connected priority working mode in the intelligent dispatching method based on green power drive provided in the embodiment of the present application;

[0021] Figure 6 A simulation result of a hydrogen production priority working mode in the intelligent scheduling method based on green power drive provided in an embodiment of the present application;

[0022] Figure 7 Another simulation result of the hydrogen production priority working mode in the intelligent scheduling method based on green power drive provided in the embodiment of the present application;

[0023] Figure 8 Another simulation result of the hydrogen production priority working mode in the intelligent scheduling method based on green power drive provided in the embodiment of the present application;

[0024] Fig. 9 A simulation result of the automatic scheduling working mode in the intelligent scheduling method based on green power drive provided in the embodiment of the present application;

[0025] Fig.10 Another simulation result of the automatic scheduling working mode in the intelligent scheduling method based on green power drive provided in the embodiment of the present application;

[0026] Fig.11 A schematic block diagram of an intelligent dispatching device based on green power drive provided in an embodiment of the present application;

[0027] Fig.12 A schematic block diagram of a green power dispatching system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0029] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0030] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0031] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0032] The embodiments of the present application provide an intelligent scheduling method, device and system based on green power drive.

[0033] The executor of the green power-driven intelligent dispatching method may be the green power-driven intelligent dispatching device provided in the embodiment of the present application, or a green power dispatching system integrating the green power-driven intelligent dispatching device, wherein the green power-driven intelligent dispatching device may be implemented in hardware or software, the green power dispatching system may be a terminal or a server, and the terminal may be a smart phone, a tablet computer, a PDA, or a laptop computer, etc.

[0034] See also Figure 1 , Figure 1 Schematic diagram of an application scenario of the intelligent dispatching method based on green power drive provided in the embodiment of the present application. The intelligent dispatching method based on green power drive is applied to Figure 1In the green power dispatching system in, the green power dispatching system is used to dispatch the power grid system, the new energy power generation system, the energy storage system and the hydrogen production system. Specifically, the green power dispatching system obtains a target dispatching mode at a predicted time, the target dispatching mode includes a target operation mode parameter and a target working mode parameter, and the predicted time is a time after the current time; obtains the target system parameters at the predicted time, the target system parameters include a maximum power prediction value of the new energy power generation system at the predicted time, and a predicted value of the energy storage charge state of the energy storage system at the predicted time; based on a preset objective function and preset dispatching constraints, a first target dispatching strategy at the predicted time is determined according to the target dispatching mode and the target system parameters, wherein the objective function indicates maximization of grid-connected benefits, maximization of hydrogen production and minimization of power abandonment rate, and the first target dispatching strategy includes a power grid dispatching strategy, a new energy dispatching strategy, an energy storage dispatching strategy and a hydrogen production dispatching strategy; when the predicted time is reached, the power grid system, the new energy power generation system, the energy storage system and the hydrogen production system are dispatched according to the first target dispatching strategy.

[0035] In this embodiment, the power grid system, the new energy power generation system, and the energy storage system are energy input modules of the system. The system realizes efficient power distribution and energy conversion through AC / DC converters to meet AC load requirements.

[0036] Among them, the grid dispatching strategy includes the grid predicted power, the new energy dispatching strategy includes the new energy predicted power, the energy storage dispatching strategy includes the energy storage predicted power, the hydrogen production dispatching strategy includes the hydrogen production predicted power, and the new energy power generation system includes at least one of a photovoltaic power generation system, a wind power generation system and a hydropower generation system.

[0037] Figure 2 is a flow chart of an intelligent dispatching method based on green power drive provided in an embodiment of the present application. Figure 2 As shown, the method includes the following steps S110-S140.

[0038] S110. Obtain a target scheduling mode at a predicted time, where the predicted time is a time after the current time.

[0039] In one embodiment, the target scheduling mode includes target operation mode parameters and target working mode parameters.

[0040] The target scheduling mode may be a scheduling mode currently input by the user, or a preset scheduling mode. In some embodiments, the user may set different scheduling modes for different time periods.

[0041] Specifically, the target operating mode parameters include off-grid operating mode parameters or grid-connected operating mode parameters, the target working mode parameters include grid-connected priority working mode parameters, hydrogen production priority working mode parameters or automatic scheduling working mode parameters, the grid-connected priority working mode parameters include a grid-connected weight sequence and a target grid-connected power, the hydrogen production priority working mode parameters include a hydrogen production weight sequence and a target hydrogen production power, and the automatic scheduling working mode parameters include an automatic scheduling weight sequence.

[0042] Among them, the weight sequence in the target working mode parameter includes the grid-connected weight, the hydrogen production weight and the power abandonment weight, and the sum of each weight is 1. When the target working mode parameter is the grid-connected priority working mode parameter, the corresponding weight sequence is the grid-connected weight sequence. In the grid-connected weight sequence, the grid-connected weight is the largest, and the hydrogen production weight and the power abandonment weight are smaller (in some cases, the hydrogen production weight and the power abandonment weight can be set to 0); when the target working mode parameter is the hydrogen production priority working mode parameter, the corresponding weight sequence is the hydrogen production weight sequence. In the hydrogen production weight sequence, the hydrogen production weight is the largest, and the grid-connected weight and the power abandonment weight are smaller (in some cases, the grid-connected weight and the power abandonment weight can be set to 0); when the target working mode parameter is the automatic scheduling working mode parameter, the corresponding weight sequence is the automatic scheduling weight sequence. In the automatic scheduling weight sequence, the grid-connected weight, hydrogen production weight and the power abandonment weight are relatively balanced.

[0043] S120: Obtain target system parameters at the prediction time.

[0044] In one embodiment, the target system parameters include a maximum power prediction value of the new energy power generation system at the prediction time, and a predicted energy storage charge state value of the energy storage system at the prediction time.

[0045] In some embodiments, the unit electricity purchase and sales cost, the upper and lower limits of grid-connected power, and the upper and lower limits of hydrogen production power of the power grid system in different time periods are relatively fixed, and the unit electricity purchase and sales cost, the upper and lower limits of grid-connected power, and the upper and lower limits of hydrogen production power can be set in the system in advance; in other embodiments, the unit electricity purchase and sales cost, the upper and lower limits of grid-connected power, and the upper and lower limits of hydrogen production power at a preset time can also be obtained in real time. At this time, the acquired target system parameters also include the unit electricity purchase and sales cost, the upper and lower limits of grid-connected power, and the upper and lower limits of hydrogen production power at the predicted time.

[0046] Among them, the maximum power prediction value of the new energy power generation system at the prediction time can be predicted by using an external machine learning model, and the energy storage charge state prediction value of the energy storage system at the prediction time can be determined based on the energy storage charge state value at the initial moment of the energy storage system and the energy storage scheduling power at each intermediate moment between the initial moment and the prediction moment.

[0047] S130. Based on a preset objective function and preset scheduling constraints, determine the first target scheduling strategy at the prediction moment according to the target scheduling mode and the target system parameters, wherein the objective function indicates maximizing the grid-connected revenue, maximizing the hydrogen production and minimizing the power abandonment rate, and the first target scheduling strategy includes a power grid scheduling strategy, a new energy scheduling strategy, an energy storage scheduling strategy and a hydrogen production scheduling strategy.

[0048] Among them, the formula corresponding to the objective function is:

[0049] obj=min[w1*(C grid +C segrid )]+max[w2*M hy ]+min[w3*W pv ];

[0050] Where obj is the objective function, C grid is the electricity purchase cost, C segrid is the electricity sales cost, M hy is the hydrogen production load, W pv The amount of electricity wasted by new energy sources, w 1 is the grid connection weight in the weight sequence of the target working mode parameters, w 2 is the hydrogen production weight in the weight sequence, w 3 is the power abandonment weight in the weight sequence;

[0051] in:

[0052]

[0053]

[0054] In the formula, c g,t is the unit electricity purchase cost at time t, c sg,t is the unit electricity sales cost at time t, P grid,t is the purchased power at time t, P segrid,t is the electricity sales power at time t, P load,t is the hydrogen production power at time t, η hy is the hydrogen production efficiency, qlhv is the calorific value, P pv,max,t is the maximum power prediction value of the new energy power generation system at time t, P v,t is the power dispatch value of the new energy power generation system at time t.

[0055] Among them, the dispatch constraints include power balance constraints, grid-connected power constraints, new energy station output constraints, hydrogen production load constraints, energy storage power station operation constraints and energy storage safety threshold constraints.

[0056] The formula corresponding to the power balance constraint is:

[0057]

[0058] Where P grid,t is the purchased power at time t, P segrid,t is the electricity sales power at time t, P v,i,t is the output of the i-th renewable energy power station at time t, N v is the number of renewable energy power stations, P ess,dis,t is the discharge power of the energy storage system at time t, P ess,ch,t is the charging power of the energy storage system at time t, P load,t is the hydrogen production power of the hydrogen production system at time t. When the target operation mode parameter is the off-grid operation mode parameter, P grid,t and P segrid,t are all 0. When the target operation mode parameter is the grid-connected operation mode parameter, P grid,t and P segrid,t All are non-zero values;

[0059] The formula corresponding to the grid-connected power constraint is:

[0060]

[0061] In the formula, is the maximum power purchase power of the power grid system, is the maximum power sold by the power grid system;

[0062] The formula corresponding to the output constraint of the new energy station is:

[0063] 0≤P v,t ≤P pv,max,t ;

[0064] Where P v,t is the power dispatch value of the new energy power generation system at time t, P pv,max,t is the maximum power prediction value of the new energy power generation system at time t; wherein, since the power generation power of new energy changes over time, the future power generation (maximum power prediction value) can be predicted by analyzing historical data and meteorological conditions and using a machine learning model.

[0065] The formula corresponding to the hydrogen production load constraint is:

[0066] P load,t+k =L(P loadh,t ,P loadh,t-1 ,…,P loadh,t-m );

[0067] λ min P load,e ≤Pload,t ≤λ max P load,e ;

[0068] Where L is the time series load forecasting model, m is the historical time window of the training model, k is the forecast time window of the training model, and λ min is the lower limit ratio of the electrolyzer in the hydrogen production system, λ max is the upper limit ratio of the operation of the electrolytic cell, P load,e is the rated power of the electrolyzer; wherein, accurate load forecasting can help the energy storage system store energy during low periods and release energy during peak periods, thereby maintaining a balance between grid load and power generation and preventing grid load overload.

[0069] The formula corresponding to the energy storage power station operation constraint is:

[0070] 0≤P ess,dis,t ≤U ess,dis,t P n ;

[0071] 0≤P ess,ch,t ≤U ess,ch,t P n ;

[0072] U ess,dis,t +U ess,ch,t ≤1;

[0073]

[0074] E 0 =soc 0 ·E n ;

[0075]

[0076] Where U ess,dis,t is the energy storage and discharge state variable of the energy storage system, U ess,ch,t is the energy storage charging state variable of the energy storage system, P n is the maximum charge and discharge power of the energy storage system, E ess,t is the energy storage capacity of the energy storage system at time t; η ch is the energy storage charging efficiency of the energy storage system, E 0 is the initial energy storage capacity of the energy storage system, is the minimum energy storage capacity of the energy storage system, E n is the maximum energy storage capacity of the energy storage system, soc 0 is the initial charge state of the energy storage system;

[0077] The formula corresponding to the energy storage safety threshold constraint is:

[0078]

[0079] Where, f(SOC i ) is the protection factor of the energy storage system, the f(SOC i ) is used to limit the energy storage power, SOC min is the lower limit of the energy storage state of charge of the energy storage system (e.g. 0.1), SOC max is the upper limit of the energy storage state of charge of the energy storage system (for example, 0.9), SOC safeh is the upper limit of the safety threshold of the energy storage system (e.g. 0.6), SOC safes is the lower limit of the safety threshold of the energy storage system (e.g. 0.3), SOC i is the charge state of the energy storage system.

[0080] It can be seen from the above formula that when the state of charge reaches the safety threshold, the energy storage power gradually decreases linearly, and finally stops charging and discharging when the operating limit is reached. In order to achieve the above function, a linear function is introduced in the energy storage safety threshold constraint to control the attenuation of power output. When the energy storage unit reaches the safety threshold, the power output will gradually decrease, and completely stop charging and discharging when the state of charge reaches the operating limit.

[0081] In this embodiment, the algorithm corresponding to the objective function and the scheduling constraints is used to solve the large-scale optimization problem through the HiGHS solver, so as to calculate the optimal target scheduling strategy.

[0082] Among them, step S130 includes day-ahead scheduling and / or intraday scheduling. The objective functions and constraints of day-ahead scheduling and intraday scheduling are the same. The target scheduling mode and target system parameters may be the same or different. The prediction error of day-ahead scheduling can be corrected through intraday scheduling.

[0083] Furthermore, the system also provides a dynamic adjustment function for the user. The system can make real-time adjustments to the day-ahead scheduling and the intra-day scheduling based on the dynamic adjustment instructions input by the user. At this time, after the first target scheduling strategy at the predicted time is determined according to the target scheduling mode and the target system parameters based on the preset objective function and the preset scheduling constraints, and before reaching the predicted time, the method further includes:

[0084] S1301. Obtain dynamic adjustment instructions, wherein the dynamic adjustment instructions include scheduling mode adjustment instructions and / or system parameter adjustment instructions, wherein the scheduling mode adjustment instructions carry the adjusted target scheduling mode, and the system parameter adjustment instructions carry at least one of the energy storage state of charge correction value at the prediction moment, the maximum power correction value of the new energy power generation system, the upper and lower limits of the grid-connected power, and the upper and lower limits of the hydrogen production power; based on the objective function and the scheduling constraints, determine the second target scheduling strategy at the prediction moment according to the dynamic adjustment instructions; and update the first target scheduling strategy according to the second target scheduling strategy.

[0085] It can be seen that the green power dispatching system provided by the present application can switch the target dispatching mode and modify the system parameters in real time, thereby improving the accuracy of system prediction and the stability of mode switching.

[0086] S140. When the predicted time is reached, the power grid system, the new energy power generation system, the energy storage system and the hydrogen production system are dispatched according to a first target dispatching strategy.

[0087] In this embodiment, when the predicted time is reached, the system dispatches the power grid system, the new energy power generation system, the energy storage system and the hydrogen production system according to the first target scheduling strategy calculated in advance. Specifically, the power grid system is dispatched according to the power grid scheduling strategy, the new energy power generation system is dispatched according to the new energy scheduling strategy, the energy storage system is dispatched according to the energy storage scheduling strategy, and the hydrogen production system is dispatched according to the hydrogen production scheduling strategy.

[0088] Furthermore, in order to verify the system performance, the green power dispatching system provided in this application will also verify the feasibility of the case through simulation verification tests on the system's operating performance in grid-connected priority, hydrogen production priority and automatic dispatching working modes.

[0089] The following is a detailed description of the green power dispatching system strategy method provided by the embodiment of the present application:

[0090] First, the green power dispatching system of this application provides a phased dispatching optimization algorithm:

[0091] At this time, the dispatch process is divided into the day-ahead phase (day-ahead optimization algorithm) and the intraday phase (intraday rolling optimization algorithm), and the energy storage system and load power are dynamically adjusted in combination with real-time data. The operation is carried out through the following mechanisms:

[0092] Day-ahead optimization algorithm: Formulate reasonable scheduling strategies by predicting load demand, renewable energy generation capacity and energy storage system status in the future.

[0093] Intraday rolling optimization algorithm: Based on the day-ahead optimization, combined with real-time grid data and load fluctuations, the system operation is dynamically adjusted to reduce the operating power error, ensuring that the system can cope with complex situations such as new energy forecasts and load fluctuations in actual operation. When switching modes, the day-ahead stage can be skipped and rapid adjustments can be made directly within the day to improve dispatch efficiency and response speed.

[0094] Second, the green power dispatching system of this application provides a dynamic adjustment mechanism:

[0095] This application has the ability to correct the energy storage charge state, load target power, grid power upper and lower limits, and hydrogen production power upper and lower limits in real time. Through this mechanism, the system can: timely adjust the charge and discharge state of the energy storage system according to the real-time load and green power production fluctuations to ensure the adequacy and stability of the energy storage system. Dynamically correct the upper and lower limits of the load grid connection to adapt to complex grid conditions and load fluctuations, and ensure the stability and flexibility of system operation.

[0096] In some embodiments, the electrolyzer is set to a minimum technical output of 380kW, a rated power of 5000kW, a photovoltaic rated power of 6000kW, an energy storage setting of 1800kW / 1800kWh, and a maximum grid power of 6000kW.

[0097] The following is a detailed description of the working mode of the green power dispatching system provided in the embodiment of the present application:

[0098] First, grid-connected priority working mode:

[0099] In this mode, renewable energy generation is prioritized to meet grid demand. When renewable energy power is insufficient, energy storage systems are used to supplement the power required by the grid. If there is surplus power from renewable energy generation, it is prioritized for hydrogen production or charging energy storage. Through these logics and constraints, the use of renewable energy and energy storage is optimized to balance the power demand of the grid.

[0100] 1. Definition of new energy power: P renew,i =P v,t ;

[0101] 2. If the power of new energy is sufficient to meet the needs of the power grid, new energy shall be used first: if P renew,t ≥P segrid,t , then U renew,t =1,U renew,t is an indicator variable, which is 1 if the renewable energy meets the grid demand, and 0 otherwise.

[0102] 3. When the power of new energy is not enough to meet the grid demand, use energy storage: If P renew,t <P segrid,t , then U es,t =1,Ues,t is an indicator variable, which is 1 if energy storage power is used and 0 otherwise.

[0103] 5. Energy storage power supplements the remaining power required by the grid: If U es,t =1, then P ess,dis,t ≥P segrid,t -P renew,t .

[0104] 6. If the renewable energy is more than the grid-connected power, the remaining renewable energy power is used as follows: P excess,t =P renew,t -P segrid,t , if P excess,t ≥0, then P load,t +P ess,ch,t ≤P excess,t .

[0105] Figure 3 , Figure 4 as well as Figure 5 It is the simulation result under the grid-connected priority working mode, where the following simulation takes the photovoltaic power generation system as an example;

[0106] Figure 3 It is a comparison between the dynamically changing grid control target and the renewable energy power generation under the grid priority working mode. The orange curve represents the hydrogen production control target under the grid priority condition, and the blue curve represents the grid power control target. The grid power remains stable during the entire time period. The green curve represents the dispatching power and predicted power of photovoltaic power generation, which increases in a step-by-step manner, showing that the photovoltaic power generation gradually increases over time. It can be seen from the figure that the abandoned power under the grid priority condition does not exceed 5%.

[0107] Figure 4 is the predicted value of system power in the grid-connected priority working mode. The blue curve represents the overall grid-connected power of the system, and the green curve represents the output power of photovoltaic power generation. The photovoltaic power generation power gradually approaches and eventually exceeds the grid-connected power demand in the later stage. The change in the grid-connected curve shows that in the stage of insufficient photovoltaic power generation, the system supplemented electricity through energy storage or the grid to meet the grid-connected demand. As the photovoltaic power generation increases, the grid-connected power is completely met by photovoltaic power generation, and the remaining photovoltaic power generation in the later stage is used to charge energy storage. This is basically consistent with the logic of the strategy, that is, "giving priority to meeting the grid demand."

[0108] Figure 5 In the grid-connected priority working mode, Figure 3The target value is constantly solved under dynamic changing conditions. In the early stage of the simulation, the photovoltaic output is close to zero from 0 to 300 seconds, which is not enough to meet the grid demand. The energy storage takes on the output and meets the hydrogen production demand. At this time, the hydrogen production and electricity purchase costs remain stable. In the middle and late stages of the simulation, the photovoltaic power generation gradually increases, the grid demand is met first, and part of the remaining electricity is used to charge the energy storage. The electricity sales revenue also increases significantly with the grid-connected power, showing the efficient use of photovoltaic power generation. The strategy logic optimizes its distribution well, so that the grid demand, hydrogen production demand and energy storage charging demand are balanced.

[0109] Second, hydrogen production priority working mode:

[0110] In this mode, photovoltaic power generation is used first for hydrogen production. When photovoltaic power generation is not enough to meet the demand for hydrogen production, the energy storage system is used to provide the remaining electricity. If the energy storage system cannot meet the demand, electricity is purchased from the power grid. The remaining new energy electricity will be used to supply power to the grid first, and if there is still electricity left, it will be used to charge the energy storage system. Through these constraints, the power dispatch between new energy, energy storage and the power grid is optimized, making the use of electricity more efficient.

[0111] 1. Definition of new energy power: P renew,t =P v,t

[0112] 2. If the power of new energy is sufficient to meet the demand for hydrogen production, new energy should be used first: if P renew,t ≥P load,t , then U renew,t =1,U renew,t is an indicator variable, which is 1 if the renewable energy meets the grid demand, and 0 otherwise.

[0113] 3. When the power of new energy is not enough to meet the demand for hydrogen production, use energy storage: such as P renew,t <P load,t , then U es,t =1,U es,t is an indicator variable, which is 1 if energy storage power is used and 0 otherwise.

[0114] 4. When new energy and energy storage are insufficient, purchase electricity from the grid: es,dis,t ≤P load,t -P renew,t , then U grid,t =1,U grid,t is an indicator variable, which is 1 if purchased electricity is used and 0 otherwise.

[0115] 5. If the power of new energy is sufficient to produce hydrogen, the remaining power of new energy shall be connected to the grid first: P excess,i =P renew,t -P load,t , if P excess,i≥0, then P segrid,t ≤P excess,t .

[0116] 6. After the remaining power is online, there is still some power left, which can be used to charge the energy storage: P recess,i =P excess,i -P segrid,t , if P recess,i ≥0, then P ess,ch,t ≤P recess,i .

[0117] Figure 6 , Figure 7 as well as Figure 8 This is the simulation result under the hydrogen production priority working mode, where the following simulation takes the photovoltaic power generation system as an example;

[0118] Figure 6 The orange curve in the figure represents the hydrogen production control target, which is simulated and updated every 60 seconds, reflecting the dynamic control strategy. The photovoltaic power generation curve is stepped and closely matches the forecast curve. When photovoltaic power is insufficient, energy storage or grid power will be called to supplement demand.

[0119] Figure 7 is the system power forecast value. The figure shows the distribution of system power, including photovoltaic power generation, energy storage system power, grid input and output. The green curve represents photovoltaic power generation, which rises steadily; from 0 to 300 seconds, photovoltaic power is not enough to support the hydrogen production power, and energy storage and grid are dynamically adjusted to meet demand when necessary. After meeting the hydrogen production demand, the remaining renewable energy flows to the grid or energy storage system according to priority. Considering the income from electricity sales, the excess electricity is mainly connected to the grid. The prediction model can dynamically adapt to demand and efficiently coordinate the energy distribution between photovoltaics, energy storage and the grid.

[0120] Figure 8It is an economic and operational indicator that shows the optimization target of the system. Considering that the rolling optimization only outputs the value of one point each time, it is calculated once every 60 seconds, so this figure will test each solution and the dynamic parameter changes given by the outside world. The amount of hydrogen produced shows a segmented change trend according to the target power of hydrogen production, which reflects the dynamic adjustment mechanism of the hydrogen production target in the strategy. Each rising step closely follows the increase of photovoltaic power generation, which verifies the principle of giving priority to photovoltaic power generation for hydrogen production. When photovoltaic and energy storage power cannot meet the demand, the system purchases electricity from the power grid, resulting in a jump in the cost of purchasing electricity during a specific period of time. Between 300 and 400 seconds of simulation time, the cost of purchasing electricity increased slightly due to insufficient photovoltaic power and incomplete coverage of energy storage. During 600 to 700 seconds, because purchasing electricity from the power grid is the last choice, the strategy successfully reduced the frequency of power grid use. When photovoltaic power generation is in excess, the remaining electricity is sent to the power grid for sale first, and the revenue from electricity sales increases accordingly. The photovoltaic power generation remains stable. As the main input energy of the system, its utilization rate directly affects the economy and operation efficiency of the system.

[0121] Third, automatic scheduling working mode:

[0122] This mode automatically switches the operating mode according to the real-time data and the changes in the demand of the power grid, and flexibly dispatches between the grid connection priority and the hydrogen production priority to maximize the economy and stability of the system. This flexible working mode can be switched according to actual needs, making the system have a wider range of application scenarios, while improving user friendliness and ease of operation.

[0123] Fig. 9 as well as Fig.10 It is the simulation result under the automatic scheduling working mode, in which the following simulation takes the photovoltaic power generation system as an example for the new energy power generation system;

[0124] Fig. 9 The power prediction value of the system in the automatic scheduling working mode is shown. As can be seen from the figure, the power prediction value changes with time, which reflects the real-time changes in grid demand. It shows that the optimization strategy can quickly and accurately predict the system power according to the real-time demand of the grid and the actual situation of green electricity hydrogen production, thereby realizing flexible scheduling between grid connection priority and hydrogen production priority.

[0125] Fig.10 The target values ​​of the system in the automatic scheduling mode are shown. These target values ​​may be the power, efficiency or other key indicators that the system needs to achieve during operation. Fig. 9 By comparing the power forecast values ​​with the actual power forecast values, we can see how well the optimization strategy performs in achieving these target values. As can be seen from the figure, the optimization strategy can flexibly adjust the system's operating mode according to actual demand and real-time changes in the power grid to maximize or minimize the target values.

[0126] To sum up, the green power dispatching system in the embodiment of the present application can predict the dispatching strategy at future times in advance through preset optimization functions and dispatching constraints, so that system dispatching does not need to be highly dependent on real-time data, thereby improving the stability and dispatching efficiency of the green power dispatching system.

[0127] In addition, the embodiments of the present application also have the following beneficial effects:

[0128] 1. Enhance system flexibility: This application takes into account multiple working modes such as grid connection priority, hydrogen production priority and automatic scheduling. Users can flexibly switch according to actual needs, which improves the user-friendliness of the system and the breadth of application scenarios.

[0129] 2. Optimize scheduling in stages: The scheduling process is divided into two stages: day-ahead and intraday, and the energy storage system and load power limits are adjusted dynamically in combination with real-time data. When switching modes, it can quickly transition from the day-ahead stage to the intraday stage, while supporting real-time dynamic adjustment of the working mode or target value during operation to ensure the continuity and flexibility of the solution process.

[0130] 3. Dynamic adjustment mechanism: This application takes into account the protection factor of the energy storage system by correcting the state of charge, hydrogen production power and upper and lower power limits of grid-connected operation in real time. When the state of charge is close to the upper and lower limits, the energy storage charging and discharging power rate will slow down to adapt to more complex load fluctuations and grid conditions, thereby improving operating efficiency and system stability.

[0131] 4. Engineering application value: This application takes into account multiple optimization goals, such as maximizing grid-connected benefits, maximizing hydrogen production, and minimizing the rate of abandoned power from new energy sources, by optimizing green electricity and hydrogen production processes under different working modes. These optimization strategies improve energy utilization, increase system benefits, and are more in line with actual application scenarios, with high engineering application value.

[0132] Fig.11 is a schematic block diagram of an intelligent dispatching device 200 based on green power drive provided in an embodiment of the present application. Fig.11 As shown, corresponding to the above intelligent dispatching method based on green power drive, the present application also provides an intelligent dispatching device 200 based on green power drive. The intelligent dispatching device 200 based on green power drive is configured in a green power dispatching system, which is used to dispatch power grid systems, new energy power generation systems, energy storage systems and hydrogen production systems. The intelligent dispatching device 200 based on green power drive includes: a transceiver unit 210 and a processing unit 220, wherein:

[0133] The transceiver unit 210 is used to obtain a target scheduling mode at a predicted time, where the predicted time is a time after the current time; and is also used to obtain a target system parameter at the predicted time;

[0134] In one embodiment, the target scheduling mode includes target operation mode parameters and target working mode parameters.

[0135] In one embodiment, the target system parameters include a maximum power prediction value of the new energy power generation system at the prediction time, and a predicted energy storage charge state value of the energy storage system at the prediction time.

[0136] The processing unit 220 is used to determine the first target scheduling strategy at the predicted time based on a preset objective function and preset scheduling constraints, according to the target scheduling mode and the target system parameters, wherein the objective function indicates maximizing the grid-connected revenue, maximizing the hydrogen production and minimizing the power abandonment rate, and the first target scheduling strategy includes a power grid scheduling strategy, a new energy scheduling strategy, an energy storage scheduling strategy and a hydrogen production scheduling strategy; when the predicted time is reached, the power grid system, the new energy power generation system, the energy storage system and the hydrogen production system are scheduled according to the first target scheduling strategy.

[0137] In some embodiments, the target operating mode parameters include off-grid operating mode parameters or grid-connected operating mode parameters, the target working mode parameters include grid-connected priority working mode parameters, hydrogen production priority working mode parameters or automatic scheduling working mode parameters, the grid-connected priority working mode parameters include a grid-connected weight sequence and a target grid-connected power, the hydrogen production priority working mode parameters include a hydrogen production weight sequence and a target hydrogen production power, and the automatic scheduling working mode parameters include an automatic scheduling weight sequence.

[0138] In some embodiments, the transceiver unit 210 is further used to obtain a dynamic adjustment instruction, the dynamic adjustment instruction includes a dispatch mode adjustment instruction and / or a system parameter adjustment instruction, the dispatch mode adjustment instruction carries the adjusted target dispatch mode, and the system parameter adjustment instruction carries at least one of the energy storage charge state correction value at the predicted time, the maximum power correction value of the new energy power generation system, the upper and lower limits of the grid-connected power, and the upper and lower limits of the hydrogen production power;

[0139] The processing unit 220 is further used to determine a second target scheduling strategy at the prediction moment based on the objective function and the scheduling constraints according to the dynamic adjustment instruction; and update the first target scheduling strategy according to the second target scheduling strategy.

[0140] In some embodiments, the formula corresponding to the objective function is:

[0141] obj=min[w1*(C grid +C segrid )]+max[w2*M hy]+min[w3*W pv ];

[0142] Where obj is the objective function, C grid is the electricity purchase cost, C segrid is the electricity sales cost, M hy is the hydrogen production load, W pv The amount of electricity wasted by new energy sources, w 1 is the grid connection weight in the weight sequence of the target working mode parameters, w 2 is the hydrogen production weight in the weight sequence, w 3 is the power abandonment weight in the weight sequence;

[0143] in:

[0144]

[0145] In the formula, c g,t is the unit electricity purchase cost at time t, c sg,t is the unit electricity sales cost at time t, P grid,t is the purchased power at time t, P segrid,t is the electricity sales power at time t, P load,t is the hydrogen production power at time t, η hy is the hydrogen production efficiency, qlhv is the calorific value, P pv,max,t is the maximum power prediction value of the new energy power generation system at time t, P v,t is the power dispatch value of the new energy power generation system at time t.

[0146] In some embodiments, the dispatch constraints include power balance constraints, grid-connected power constraints, new energy station output constraints, hydrogen production load constraints, energy storage power station operation constraints, and energy storage safety threshold constraints.

[0147] In some embodiments, the formula corresponding to the power balance constraint is:

[0148]

[0149] Where P grid,t is the purchased power at time t, P segrid,t is the electricity sales power at time t, P v,i,t is the output of the i-th renewable energy power station at time t, N v is the number of renewable energy power stations, P ess,dis,t is the discharge power of the energy storage system at time t, P ess,ch,t is the charging power of the energy storage system at time t, P load,t is the hydrogen production power of the hydrogen production system at time t. When the target operation mode parameter is the off-grid operation mode parameter, P grid,t and Psegrid,t are all 0. When the target operation mode parameter is the grid-connected operation mode parameter, P grid,t and P segrid,t All are non-zero values;

[0150] The formula corresponding to the grid-connected power constraint is:

[0151]

[0152] In the formula, is the maximum power purchase power of the power grid system, is the maximum power sold by the power grid system;

[0153] The formula corresponding to the output constraint of the new energy station is:

[0154] 0≤P v,t ≤P pv,max,t ;

[0155] Where P v,t is the power dispatch value of the new energy power generation system at time t, P pv,max,t is the maximum power prediction value of the new energy power generation system at time t;

[0156] The formula corresponding to the hydrogen production load constraint is:

[0157] P load,t+k =L(P loadh,t ,P loadh,t-1 ,…,P loadh,t-m );

[0158] λ min P load,e ≤P load,t ≤λ max P load,e ;

[0159] Where L is the time series load forecasting model, m is the historical time window of the training model, k is the forecast time window of the training model, and λ min is the lower limit ratio of the electrolyzer in the hydrogen production system, λ max is the upper limit ratio of the operation of the electrolytic cell, P load,e is the rated power of the electrolytic cell;

[0160] The formula corresponding to the energy storage power station operation constraint is:

[0161] 0≤P ess,dis,t ≤U ess,dis,t P n ;

[0162] 0≤P ess,ch,t ≤U ess,ch,tP n ;

[0163] U ess,dis,t +U ess,ch,t ≤1;

[0164]

[0165] E 0 =soc 0 ·E n ;

[0166]

[0167] Where U ess,dis,t is the energy storage and discharge state variable of the energy storage system, U ess,ch,t is the energy storage charging state variable of the energy storage system, P n is the maximum charge and discharge power of the energy storage system, E ess,t is the energy storage capacity of the energy storage system at time t; η ch is the energy storage charging efficiency of the energy storage system, E 0 is the initial energy storage capacity of the energy storage system, is the minimum energy storage capacity of the energy storage system, E n is the maximum energy storage capacity of the energy storage system, soc 0 is the initial charge state of the energy storage system;

[0168] The formula corresponding to the energy storage safety threshold constraint is:

[0169]

[0170] Where, f(SOC i ) is the protection factor of the energy storage system, SOC min is the lower limit of the energy storage state of charge of the energy storage system, SOC max is the upper limit of the energy storage state of charge of the energy storage system, SOC safeh is the upper limit of the safety threshold of the energy storage system, SOC safes is the lower limit of the safety threshold of the energy storage system, SOC i is the charge state of the energy storage system.

[0171] In some embodiments, the new energy power generation system includes at least one of a photovoltaic power generation system, a wind power generation system, and a hydropower generation system.

[0172] In summary, the green power-driven intelligent dispatching device 200 in the embodiment of the present application can predict the dispatching strategy at future times in advance through preset optimization functions and dispatching constraints, so that system dispatching does not need to be highly dependent on real-time data, thereby improving the stability and dispatching efficiency of the green power dispatching system.

[0173] It should be noted that technical personnel in the relevant field can clearly understand that the specific implementation process of the above-mentioned green power-driven intelligent scheduling device and each unit can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and conciseness of the description, it will not be repeated here.

[0174] The above-mentioned intelligent dispatching device based on green power drive can be implemented in the form of a computer program, which can be used in Fig.12 The green power dispatch system shown is running.

[0175] See also Fig.12 , Fig.12 3 is a schematic block diagram of a green power dispatching system provided in an embodiment of the present application. The green power dispatching system 300 can be a terminal or a server, and the green power dispatching system is used to dispatch a power grid system, a new energy power generation system, an energy storage system, and a hydrogen production system.

[0176] See also Fig.12 The green power dispatching system 300 includes a processor 302 , a memory and a network interface 305 connected via a system bus 301 , wherein the memory may include a non-volatile storage medium 303 and an internal memory 304 .

[0177] The non-volatile storage medium 303 can store an operating system 3031 and a computer program 3032. The computer program 3032 includes program instructions, and when the program instructions are executed, the processor 302 can execute an intelligent scheduling method based on green power drive.

[0178] The processor 302 is used to provide computing and control capabilities to support the operation of the entire green power dispatching system 300 .

[0179] The internal memory 304 provides an environment for the operation of the computer program 3032 in the non-volatile storage medium 303. When the computer program 3032 is executed by the processor 302, the processor 302 can execute an intelligent scheduling method based on green power drive.

[0180] The network interface 305 is used to communicate with other devices over the network. Fig.12The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present application, and does not constitute a limitation on the green power dispatching system 300 to which the scheme of the present application is applied. The specific green power dispatching system 300 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0181] The processor 302 is used to run a computer program 3032 stored in the memory to implement the following steps:

[0182] Obtaining a target scheduling mode at a predicted time, the target scheduling mode including a target operation mode parameter and a target working mode parameter, the predicted time being a time after the current time;

[0183] Acquire target system parameters at the prediction time, wherein the target system parameters include a maximum power prediction value of the new energy power generation system at the prediction time, and a predicted energy storage charge state value of the energy storage system at the prediction time;

[0184] Based on a preset objective function and preset scheduling constraints, a first target scheduling strategy at the prediction time is determined according to the target scheduling mode and the target system parameters, wherein the objective function indicates maximizing the grid connection revenue, maximizing the hydrogen production, and minimizing the power abandonment rate, and the first target scheduling strategy includes a power grid scheduling strategy, a new energy scheduling strategy, an energy storage scheduling strategy, and a hydrogen production scheduling strategy;

[0185] When the predicted time is reached, the power grid system, the new energy power generation system, the energy storage system and the hydrogen production system are scheduled according to a first target scheduling strategy.

[0186] It should be understood that in the embodiment of the present application, the processor 302 may be a central processing unit (CPU), and the processor 302 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0187] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0188] Therefore, the present application also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the following steps:

[0189] Obtaining a target scheduling mode at a predicted time, the target scheduling mode including a target operation mode parameter and a target working mode parameter, the predicted time being a time after the current time;

[0190] Acquire target system parameters at the prediction time, wherein the target system parameters include a maximum power prediction value of the new energy power generation system at the prediction time, and a predicted energy storage charge state value of the energy storage system at the prediction time;

[0191] Based on a preset objective function and preset scheduling constraints, a first target scheduling strategy at the prediction time is determined according to the target scheduling mode and the target system parameters, wherein the objective function indicates maximizing the grid connection revenue, maximizing the hydrogen production, and minimizing the power abandonment rate, and the first target scheduling strategy includes a power grid scheduling strategy, a new energy scheduling strategy, an energy storage scheduling strategy, and a hydrogen production scheduling strategy;

[0192] When the predicted time is reached, the power grid system, the new energy power generation system, the energy storage system and the hydrogen production system are scheduled according to a first target scheduling strategy.

[0193] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.

[0194] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0195] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0196] The steps in the method of the embodiment of the present application can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present application can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0197] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application.

[0198] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. An intelligent dispatching method based on green power drive, characterized in that: The method is applied to a green power dispatching system, which is used to dispatch a power grid system, a new energy power generation system, an energy storage system, and a hydrogen production system. The method includes: Obtain a target scheduling mode at a predicted time, where the predicted time is a time after the current time; Obtain target system parameters at the prediction time; Based on a preset objective function and preset scheduling constraints, a first target scheduling strategy at the prediction time is determined according to the target scheduling mode and the target system parameters, wherein the objective function indicates maximizing the grid connection revenue, maximizing the hydrogen production, and minimizing the power abandonment rate, and the first target scheduling strategy includes a power grid scheduling strategy, a new energy scheduling strategy, an energy storage scheduling strategy, and a hydrogen production scheduling strategy; When the predicted time is reached, the power grid system, the new energy power generation system, the energy storage system and the hydrogen production system are scheduled according to a first target scheduling strategy.

2. The method according to claim 1, characterized in that The target scheduling mode includes target operation mode parameters and target working mode parameters; The target operation mode parameters include off-grid operation mode parameters or grid-connected operation mode parameters; The target operating mode parameters include grid-connected priority operating mode parameters, hydrogen production priority operating mode parameters or automatic scheduling operating mode parameters. The grid-connected priority operating mode parameters include a grid-connected weight sequence and a target grid-connected power. The hydrogen production priority operating mode parameters include a hydrogen production weight sequence and a target hydrogen production power. The automatic scheduling operating mode parameters include an automatic scheduling weight sequence.

3. The method according to claim 1, characterized in that The target system parameters include a maximum power prediction value of the new energy power generation system at the prediction time, and a predicted energy storage charge state value of the energy storage system at the prediction time.

4. The method according to claim 1, characterized in that: After determining the first target scheduling strategy at the prediction time based on the preset objective function and the preset scheduling constraint conditions, according to the target scheduling mode and the target system parameters, and before reaching the prediction time, the method further includes: Acquire a dynamic adjustment instruction, wherein the dynamic adjustment instruction includes a dispatch mode adjustment instruction and / or a system parameter adjustment instruction, wherein the dispatch mode adjustment instruction carries an adjusted target dispatch mode, and the system parameter adjustment instruction carries at least one of a correction value of the energy storage state of charge at the predicted time, a maximum power correction value of the new energy power generation system, upper and lower limits of the grid-connected power, and upper and lower limits of the hydrogen production power; Based on the objective function and the scheduling constraint, determining a second target scheduling strategy at the prediction time according to the dynamic adjustment instruction; The first target scheduling strategy is updated according to the second target scheduling strategy.

5. The method according to claim 1, characterized in that The formula corresponding to the objective function is: obj=min[w1*(C grid +C segrid )]+max[w2*M hy ]+min[w3*W pv ]; Where obj is the objective function, C grid is the electricity purchase cost, C segrid is the electricity sales cost, M hy is the hydrogen production load, W pv is the amount of abandoned electricity from new energy sources, w1 is the grid connection weight in the weight sequence of the target working mode parameters, w2 is the hydrogen production weight in the weight sequence, and w3 is the abandoned electricity weight in the weight sequence; in: In the formula, c g,t is the unit electricity purchase cost at time t, c sg,t is the unit electricity sales cost at time t, P grid,t is the purchased power at time t, P segrid,t is the electricity sales power at time t, P load,t is the hydrogen production power at time t, η hy is the hydrogen production efficiency, qlhv is the calorific value, P pv,max,t is the maximum power prediction value of the new energy power generation system at time t, P v,t is the power dispatch value of the new energy power generation system at time t.

6. The method according to claim 1, characterized in that The dispatch constraints include power balance constraints, grid-connected power constraints, new energy station output constraints, hydrogen production load constraints, energy storage power station operation constraints, and energy storage safety threshold constraints.

7. The method according to claim 6, characterized in that The formula corresponding to the power balance constraint is: Where P grid,t is the purchased power at time t, P segrid,t is the electricity sales power at time t, P v,i,t is the output of the i-th renewable energy power station at time t, N v is the number of renewable energy power stations, P ess,dis,t is the discharge power of the energy storage system at time t, P ess,ch,t is the charging power of the energy storage system at time t, P load,t is the hydrogen production power of the hydrogen production system at time t. When the target operation mode parameter is the off-grid operation mode parameter, P grid,t and P segrid,t are all 0. When the target operation mode parameter is the grid-connected operation mode parameter, P grid,t and P segrid,t All are non-zero values; The formula corresponding to the grid-connected power constraint is: In the formula, is the maximum power purchase power of the power grid system, is the maximum power sold by the power grid system; The formula corresponding to the output constraint of the new energy station is: 0≤P v,t ≤P pv,max,t ; Where P v,t is the power dispatch value of the new energy power generation system at time t, P pv,max,t is the maximum power prediction value of the new energy power generation system at time t; The formula corresponding to the hydrogen production load constraint is: P load,t+k =L(P loadh,t ,P loadh,t-1 ,…,P loadh,t-m ); l min P load,e ≤P load,t ≤λ max P load,e ; Where L is the time series load forecasting model, m is the historical time window of the training model, k is the forecast time window of the training model, and λ min is the lower limit ratio of the electrolyzer in the hydrogen production system, λ max is the upper limit ratio of the operation of the electrolytic cell, P load,e is the rated power of the electrolytic cell; The formula corresponding to the energy storage power station operation constraint is: 0≤P ess,dis,t ≤U ess,dis,t P n ; 0≤P ess,ch,t ≤U ess,ch,t P n ; IN ess,dis,t +U ess,ch,t ≤1; E0=soc0·E n ; Where U ess,dis,t is the energy storage and discharge state variable of the energy storage system, U ess,ch,t is the energy storage charging state variable of the energy storage system, P n is the maximum charge and discharge power of the energy storage system, E ess,t is the energy storage capacity of the energy storage system at time t; η ch is the energy storage charging efficiency of the energy storage system, E0 is the initial energy storage capacity of the energy storage system, is the minimum energy storage capacity of the energy storage system, E n is the maximum energy storage capacity of the energy storage system, soc0 is the initial energy storage charge state of the energy storage system; The formula corresponding to the energy storage safety threshold constraint is: Where, f(SOC i ) is the protection factor of the energy storage system, SOC min is the lower limit of the energy storage state of charge of the energy storage system, SOC max is the upper limit of the energy storage state of charge of the energy storage system, SOC safeh is the upper limit of the safety threshold of the energy storage system, SOC safes is the lower limit of the safety threshold of the energy storage system, SOC i is the charge state of the energy storage system.

8. The method according to any one of claims 1 to 7, characterized in that The new energy power generation system includes at least one of a photovoltaic power generation system, a wind power generation system and a hydropower generation system.

9. An intelligent dispatching device based on green power drive, characterized in that: The device is configured in a green power dispatching system, which is used to dispatch a power grid system, a new energy power generation system, an energy storage system, and a hydrogen production system. The device includes: A transceiver unit, used to obtain a target scheduling mode at a predicted time, where the predicted time is a time after the current time; and also used to obtain a target system parameter at the predicted time; A processing unit is used to determine a first target scheduling strategy at the prediction time based on a preset objective function and preset scheduling constraints, according to the target scheduling mode and the target system parameters, wherein the objective function indicates maximization of grid-connected revenue, maximization of hydrogen production and minimization of power abandonment rate, and the first target scheduling strategy includes a power grid scheduling strategy, a new energy scheduling strategy, an energy storage scheduling strategy and a hydrogen production scheduling strategy; when the prediction time is reached, the power grid system, the new energy power generation system, the energy storage system and the hydrogen production system are scheduled according to the first target scheduling strategy.

10. A green power dispatching system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the intelligent scheduling method based on green power drive as described in any one of claims 1 to 8 is implemented.

Images