Intraday dispatching method for energy storage power station based on rule base hybrid model predictive control

Abstract

The application relates to an energy storage power station intraday scheduling method based on a rule base hybrid model predictive control, wherein the method comprises the following steps: constructing a rule base considering actual operation of intraday optimization scheduling based on historical data of a target energy storage power station and scene application demand; constructing an improved particle swarm algorithm-model predictive control optimization model and generating an optimization prediction strategy fused with an adaptive mechanism; establishing an intraday scheduling hybrid optimization framework based on the rule base and the improved particle swarm algorithm-model predictive control optimization model; and generating an intraday scheduling optimization strategy based on the intraday scheduling hybrid optimization framework, the optimization prediction strategy, power deviation and operating conditions of the target energy storage power station. Thus, the problems in the prior art that the heuristic algorithm is highly dependent on initial parameter setting, is prone to falling into local optimization or divergence and non-convergence, and lacks an effective scheme for realizing rapid external feedback and internal rapid adjustment of an energy storage cluster without affecting a day-ahead planning curve are solved.

Description

Technical Field

[0001] This application relates to the field of new power system optimization operation technology, and in particular to an intraday scheduling method for energy storage power stations based on rule-based hybrid model predictive control. Background Technology

[0002] Currently, intraday optimized scheduling is based on continuously updating the output of each unit through shorter forecast periods of wind and solar power output and load demand, based on the unit combination obtained from the day-ahead optimized scheduling, to ensure stable and optimized system operation. However, while shorter-cycle renewable energy forecasts can improve the accuracy of wind power output, they place higher demands on the rapid response capabilities of energy storage.

[0003] In related technologies, dynamic programming algorithms are used for optimization scheduling calculations, while heuristic algorithms are widely used to solve optimization scheduling problems. By setting initial parameters and relying on iterative search for optimization, coordinated control of unit output and energy storage system can be achieved.

[0004] However, in related technologies, dynamic programming has a low computational speed when dealing with the large number of 0-1 variables introduced by energy storage clusters. Furthermore, with the continuous increase in the proportion of renewable energy, the dimensionality and nonlinearity of optimization scheduling are further aggravated, making it difficult for planning algorithms to correct constraint boundaries in a timely manner and meet the actual needs of system transformation. Heuristic algorithms rely heavily on initial parameter settings, which can easily lead to getting trapped in local optima or even diverging and not converging. At the same time, there is a lack of effective solutions to achieve rapid external feedback and rapid internal adjustment of energy storage clusters without affecting the day-ahead planning curve. These solutions cannot meet the high requirements of intraday rolling optimization for flexible and adjustable feedback of energy storage and urgently need to be improved. Summary of the Invention

[0005] This application provides a method for intraday scheduling of energy storage power stations based on rule-based hybrid model predictive control. This method addresses the problems in related technologies, such as the tendency of heuristic algorithms to rely heavily on initial parameter settings, leading to local optima or even divergence and non-convergence. Furthermore, it lacks an effective solution to achieve rapid external feedback and internal adjustment of the energy storage cluster without affecting the daily planning curve, thus failing to meet the high requirements of intraday rolling optimization for flexible and adjustable feedback of energy storage.

[0006] The first aspect of this application provides a method for intraday scheduling of an energy storage power station based on rule-based hybrid model predictive control, comprising the following steps: constructing a rule base that considers the actual operation of intraday optimized scheduling based on historical data and scenario application requirements of the target energy storage power station; constructing an improved particle swarm optimization algorithm-model predictive control optimization model, and generating an optimization prediction strategy with an integrated adaptive mechanism based on the improved particle swarm optimization algorithm-model predictive control optimization model; establishing an intraday scheduling hybrid optimization framework for the target energy storage power station based on the rule base and the improved particle swarm optimization algorithm-model predictive control optimization model, and generating an intraday scheduling optimization strategy for the target energy storage power station based on the intraday scheduling hybrid optimization framework, the optimization prediction strategy, the power deviation and operating status of the target energy storage power station.

[0007] Through the above-mentioned technical means, the embodiments of this application can construct a rule base that considers the actual operation of intraday optimized scheduling, and construct an improved particle swarm optimization algorithm and model predictive control optimization model to establish an intraday scheduling hybrid optimization framework. Based on the power deviation and operating status of the target energy storage power station, an optimization prediction strategy based on a fusion adaptive mechanism can be used to obtain an intraday scheduling optimization strategy, thereby achieving efficient optimization solution for intraday optimized scheduling, taking into account both second-level response capability and long-term optimization performance, effectively balancing the real-time performance and operating cost of system scheduling, reducing the frequency of complex model calls, and reducing computational load.

[0008] Optionally, in one embodiment of this application, generating an intraday scheduling optimization strategy for the target energy storage power station based on the intraday scheduling hybrid optimization framework, the optimization prediction strategy, the power deviation and operating status of the target energy storage power station includes: acquiring the load demand forecast curve, wind power output forecast, photovoltaic power output forecast, and operating data of the target energy storage power station; calculating the power deviation and operating status of the target energy storage power station based on the load demand forecast curve, the wind power output forecast, the photovoltaic power output forecast, and the operating data; determining the control rules of the target energy storage power station based on the rule base, the power deviation, and the operating status; generating the intraday scheduling optimization strategy based on the rule base in response to the control rules being emergency control rules; and generating the intraday scheduling optimization strategy based on the improved particle swarm optimization algorithm-model predictive control optimization model and the optimization prediction strategy in response to the control rules being steady-state control rules or minimum operating cost control rules.

[0009] Through the above-mentioned technical means, the embodiments of this application can calculate the power deviation and operating status based on load demand forecast, wind power output forecast, photovoltaic power output forecast and operating data, and flexibly select control rules based on the rule base and the degree of deviation, thereby realizing the differentiated formulation of scheduling strategies. This ensures both the rapid response capability of the system under emergency conditions and the stability and economic efficiency of steady-state operation. The two strategies serve as backups for each other, avoiding the global collapse caused by the failure of a single method and improving the feasibility of the project.

[0010] Optionally, in one embodiment of this application, determining the control rule for the target energy storage power station based on the rule base, combined with the power deviation and the operating status, includes: if the power deviation is greater than a first preset threshold, then determining the control rule as the emergency control rule; if the power deviation exceeds a second preset threshold, then determining the control rule as the steady-state control rule, wherein the first preset threshold is greater than the second preset threshold; if the control rule is neither the emergency control rule nor the steady-state control rule, then determining the control rule as the minimum operating cost control rule.

[0011] Through the above-mentioned technical means, the embodiments of this application can formulate different priority level rules based on power deviation, considering intraday optimization scheduling needs, and combining different actual operating conditions, thereby achieving rapid response to different operating states, ensuring safety and stability while minimizing operating costs.

[0012] Optionally, in one embodiment of this application, generating the intraday scheduling optimization strategy based on the improved particle swarm optimization algorithm-model predictive control optimization model and the optimization prediction strategy includes: generating a particle swarm for the intraday scheduling optimization strategy, and initializing the particle positions, particle velocities, and weight intervals of the particle swarm, wherein each particle in the particle swarm represents a control variable of the intraday scheduling optimization strategy, and the control variables include the thermal power unit output adjustment variable and the energy storage power adjustment variable of the target energy storage power station; calculating the fitness of the particle swarm, and updating the particle optimal and swarm optimal according to the fitness; calculating the weight interval at the current iteration number, generating an inertia weight for each particle swarm according to the weight interval, adjusting the particle velocity according to the inertia weight, and updating the particle position until a preset iteration termination condition is met, determining the globally optimal control variable; and obtaining the intraday scheduling optimization strategy based on the globally optimal control variable.

[0013] Through the aforementioned technical means, the embodiments of this application can utilize the adaptive mechanism of the improved particle swarm optimization algorithm to optimize control variables, effectively improving the algorithm's global optimization capability and convergence speed, avoiding getting trapped in local optima, accurately determining the optimal control variables for thermal power units and energy storage power, meeting the real-time requirements of intraday scheduling optimization, and fully considering the 0-1 variable solution problem brought about by the large number of distributed energy storage systems in the current power system. This improves the efficiency of optimization solution.

[0014] Optionally, in one embodiment of this application, the step of generating the intraday scheduling optimization strategy based on the improved particle swarm optimization algorithm-model predictive control optimization model and the optimization prediction strategy further includes: collecting the load demand prediction curve, wind power output prediction, and photovoltaic power output prediction for the next prediction period; and updating the rule base and the improved particle swarm optimization algorithm-model predictive control optimization model based on the load demand prediction curve, wind power output prediction, and photovoltaic power output prediction for the next prediction period until a preset optimization termination condition is met.

[0015] Through the above-mentioned technical means, the embodiments of this application can collect the actual operating data at the current moment and the renewable energy output forecast and load demand forecast for the next forecast period, update the rule base parameters and optimization model, thereby realizing the closed-loop rolling optimization of intraday scheduling, which can adapt to the fluctuations of wind and solar power output and load demand in real time, continuously correct the optimization scheme, and improve the dynamic adaptability of the scheduling strategy to the real-time operating scenario.

[0016] Optionally, in one embodiment of this application, the step of generating an intraday scheduling optimization strategy for the target energy storage power station based on the intraday scheduling hybrid optimization framework, the power deviation and operating status data of the target energy storage power station, further includes: generating charging and discharging instructions for the target energy storage power station based on the intraday scheduling optimization strategy; transmitting the charging and discharging instructions to each energy storage unit of the target energy storage power station; and determining the output of the thermal power units of the target energy storage power station at the next moment according to the intraday scheduling optimization strategy.

[0017] Through the above-mentioned technical means, the embodiments of this application can generate energy storage charging and discharging instructions and thermal power unit output instructions based on intraday scheduling optimization strategies, and send them to each energy storage unit and thermal power unit, so as to realize the implementation of scheduling optimization strategies, ensure that the optimization scheme directly affects the actual operation of the energy storage power station, and improve the overall operational reliability.

[0018] The second aspect of this application provides a daytime scheduling device for an energy storage power station based on a rule-based hybrid model predictive control, comprising: a first construction module, used to construct a rule base that considers the actual operation of daytime optimized scheduling based on historical data and scenario application requirements of the target energy storage power station; a second construction module, used to construct an improved particle swarm optimization algorithm-model predictive control optimization model, and generate an optimization prediction strategy with an integrated adaptive mechanism based on the improved particle swarm optimization algorithm-model predictive control optimization model; and a scheduling module, used to establish a daytime scheduling hybrid optimization framework for the target energy storage power station based on the rule base and the improved particle swarm optimization algorithm-model predictive control optimization model, and to generate a daytime scheduling optimization strategy for the target energy storage power station based on the daytime scheduling hybrid optimization framework, the optimization prediction strategy, the power deviation and operating status of the target energy storage power station.

[0019] Through the above-mentioned technical means, the embodiments of this application can construct a rule base that considers the actual operation of intraday optimized scheduling, and construct an improved particle swarm optimization algorithm and model predictive control optimization model to establish an intraday scheduling hybrid optimization framework. Based on the power deviation and operating status of the target energy storage power station, an optimization prediction strategy based on a fusion adaptive mechanism can be used to obtain an intraday scheduling optimization strategy, thereby achieving efficient optimization solution for intraday optimized scheduling, taking into account both second-level response capability and long-term optimization performance, effectively balancing the real-time performance and operating cost of system scheduling, reducing the frequency of complex model calls, and reducing computational load.

[0020] Optionally, in one embodiment of this application, the scheduling module includes: an acquisition unit, configured to acquire the load demand forecast curve, wind power output forecast, photovoltaic power output forecast, and operating data of the target energy storage power station; a calculation unit, configured to calculate the power deviation and operating status of the target energy storage power station based on the load demand forecast curve, the wind power output forecast, the photovoltaic power output forecast, and the operating data; a first determination unit, configured to determine the control rules of the target energy storage power station based on the rule base, the power deviation, and the operating status; a first generation unit, configured to generate the intraday scheduling optimization strategy based on the rule base in response to the control rules being emergency control rules; and a second generation unit, configured to generate the intraday scheduling optimization strategy based on the improved particle swarm optimization algorithm-model predictive control optimization model and the optimization prediction strategy in response to the control rules being steady-state control rules or minimum operating cost control rules.

[0021] Through the above-mentioned technical means, the embodiments of this application can calculate the power deviation and operating status based on load demand forecast, wind power output forecast, photovoltaic power output forecast and operating data, and flexibly select control rules based on the rule base and the degree of deviation, thereby realizing the differentiated formulation of scheduling strategies. This ensures both the rapid response capability of the system under emergency conditions and the stability and economic efficiency of steady-state operation. The two strategies serve as backups for each other, avoiding the global collapse caused by the failure of a single method and improving the feasibility of the project.

[0022] Optionally, in one embodiment of this application, the determining unit includes: a first determining subunit, configured to determine the control rule as the emergency control rule if the power deviation is greater than a first preset threshold; a second determining subunit, configured to determine the control rule as the steady-state control rule if the power deviation exceeds a second preset threshold, wherein the first preset threshold is greater than the second preset threshold; and a third determining subunit, configured to determine the control rule as the minimum operating cost control rule if the control rule is neither the emergency control rule nor the steady-state control rule.

[0023] Through the above-mentioned technical means, the embodiments of this application can formulate different priority level rules based on power deviation, considering intraday optimization scheduling needs, and combining different actual operating conditions, thereby achieving rapid response to different operating states, ensuring safety and stability while minimizing operating costs.

[0024] Optionally, in one embodiment of this application, the second generation unit includes: an initialization subunit, used to generate a particle swarm of the intraday scheduling optimization strategy, and initialize the particle positions, particle velocities, and weight intervals of the particle swarm, wherein each particle in the particle swarm represents a control variable of the intraday scheduling optimization strategy, and the control variables include the thermal power unit output adjustment variable and the energy storage power adjustment variable of the target energy storage power station; a first calculation subunit, used to calculate the fitness of the particle swarm, and update the particle optimum and the swarm optimum according to the fitness; a second calculation subunit, used to calculate the weight interval under the current iteration number, generate the inertia weight of each particle swarm according to the weight interval, adjust the particle velocity according to the inertia weight, and update the particle position until a preset iteration termination condition is met, and determine the globally optimal control variable; and a generation subunit, used to obtain the intraday scheduling optimization strategy based on the globally optimal control variable.

[0025] Through the aforementioned technical means, the embodiments of this application can utilize the adaptive mechanism of the improved particle swarm optimization algorithm to optimize control variables, effectively improving the algorithm's global optimization capability and convergence speed, avoiding getting trapped in local optima, accurately determining the optimal control variables for thermal power units and energy storage power, meeting the real-time requirements of intraday scheduling optimization, and fully considering the 0-1 variable solution problem brought about by the large number of distributed energy storage systems in the current power system. This improves the efficiency of optimization solution.

[0026] Optionally, in one embodiment of this application, the second generation unit further includes: a collection subunit, used to collect the load demand forecast curve, the wind power output forecast, and the photovoltaic output forecast for the next forecast period; and an update subunit, used to update the rule base and the improved particle swarm optimization algorithm-model predictive control optimization model based on the load demand forecast curve, the wind power output forecast, and the photovoltaic output forecast for the next forecast period, until a preset optimization termination condition is met.

[0027] Through the above-mentioned technical means, the embodiments of this application can collect the actual operating data at the current moment and the renewable energy output forecast and load demand forecast for the next forecast period, update the rule base parameters and optimization model, thereby realizing the closed-loop rolling optimization of intraday scheduling, which can adapt to the fluctuations of wind and solar power output and load demand in real time, continuously correct the optimization scheme, and improve the dynamic adaptability of the scheduling strategy to the real-time operating scenario.

[0028] Optionally, in one embodiment of this application, the scheduling module further includes: a third generation unit, configured to generate charging and discharging instructions for the target energy storage power station based on the intraday scheduling optimization strategy; and a second determination unit, configured to transmit the charging and discharging instructions to each energy storage unit of the target energy storage power station, and determine the output of the thermal power unit of the target energy storage power station at the next moment according to the intraday scheduling optimization strategy.

[0029] Through the above-mentioned technical means, the embodiments of this application can generate energy storage charging and discharging instructions and thermal power unit output instructions based on intraday scheduling optimization strategies, and send them to each energy storage unit and thermal power unit, so as to realize the implementation of scheduling optimization strategies, ensure that the optimization scheme directly affects the actual operation of the energy storage power station, and improve the overall operational reliability.

[0030] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement the intraday scheduling method for an energy storage power station based on rule-based hybrid model predictive control as described in the above embodiments.

[0031] A fourth aspect of this application provides a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described intraday scheduling method for an energy storage power station based on a rule-based hybrid model predictive control.

[0032] A fifth aspect of this application provides a computer program product that stores a computer program that, when executed by a processor, implements the above-described intraday scheduling method for energy storage power stations based on rule-based hybrid model predictive control.

[0033] This application's embodiments can construct a rule base that considers the actual operation of intraday optimized scheduling, and construct an improved particle swarm optimization algorithm and model predictive control optimization model to establish an intraday scheduling hybrid optimization framework. Based on the power deviation and operating status of the target energy storage power station, it can obtain intraday scheduling optimization strategies based on an optimization prediction strategy using a fusion adaptive mechanism, thereby achieving efficient optimization solutions for intraday optimized scheduling, balancing second-level response capability with long-term optimization performance, effectively balancing the real-time performance and operating cost of system scheduling, reducing the frequency of complex model calls, and lowering the computational load. This solves the problems in related technologies, such as the heuristic algorithm's reliance on initial parameter settings, which easily leads to local optima or even divergence and non-convergence, and the lack of an effective solution for rapid external feedback and rapid internal adjustment of the energy storage cluster without affecting the day-ahead planning curve, thus failing to meet the high requirements of intraday rolling optimization for flexible and adjustable energy storage feedback.

[0034] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0035] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of an intraday scheduling method for an energy storage power station based on a rule-based hybrid model predictive control, according to an embodiment of this application. Figure 2 This is a flowchart illustrating the solution process for a rule-based hybrid model predictive control according to an embodiment of this application. Figure 3 This is a flowchart of an improved particle swarm optimization algorithm with a fusion adaptive mechanism according to an embodiment of this application; Figure 4 This is a graph showing wind power, photovoltaic power, and load under different scenarios in conventional and emergency situations, according to one embodiment of this application; Figure 5 The diagram shows the operating results of various types of generator sets under normal scenarios according to an embodiment of this application; Figure 6 The figures show the operating results of various types of generator sets under extreme scenarios according to one embodiment of this application; Figure 7 This is a comparison chart of the computation time and optimization results of different algorithms provided according to an embodiment of this application; Figure 8 This is a schematic diagram of the structure of an intraday dispatching device for an energy storage power station based on rule-based hybrid model predictive control, according to an embodiment of this application. Figure 9 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application.

[0036] Figure label: 10-Daily dispatching device for energy storage power station based on rule-based hybrid model predictive control; 100-First building module, 200-Second building module, 300-Dispatch module; 901-Memory, 902-Processor, 903-Communication interface. Detailed Implementation

[0037] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0038] The following describes, with reference to the accompanying drawings, an intraday scheduling method for energy storage power stations based on rule-based hybrid model predictive control, according to embodiments of this application. Addressing the issues raised in the background section regarding related technologies, heuristic algorithms, heavily reliant on initial parameter settings, are prone to getting stuck in local optima or even diverging and failing to converge. Furthermore, they lack effective solutions for achieving rapid external feedback and internal adjustment of the energy storage cluster without affecting the day-ahead planning curve, thus failing to meet the high requirements of intraday rolling optimization for flexible and adjustable energy storage feedback. This application provides an intraday scheduling method for energy storage power stations based on rule-based hybrid model predictive control. This method constructs a rule base that considers the actual operation of intraday optimized scheduling and builds an improved particle swarm optimization algorithm and a model predictive control optimization model, establishing a hybrid optimization framework for intraday scheduling. Based on the power deviation and operating status of the target energy storage power station, an optimization prediction strategy based on a fusion adaptive mechanism is used to obtain an intraday scheduling optimization strategy, thereby achieving efficient optimization and solution for intraday optimized scheduling, balancing second-level response capability with long-term optimization performance, effectively balancing the real-time performance and operating cost of system scheduling, reducing the frequency of complex model calls, and lowering the computational load. This solves the problems in related technologies, such as the fact that heuristic algorithms rely heavily on initial parameter settings, which can easily lead to local optima or even divergence and non-convergence, and the lack of an effective solution to achieve rapid external feedback and internal adjustment of energy storage clusters without affecting the day-ahead planning curve, thus failing to meet the high requirements of intraday rolling optimization for flexible and adjustable feedback of energy storage.

[0039] Specifically, Figure 1 This is a flowchart illustrating an intraday scheduling method for an energy storage power station based on a rule-based hybrid model predictive control, provided as an embodiment of this application.

[0040] like Figure 1 As shown, the intraday scheduling method for energy storage power stations based on rule-based hybrid model predictive control includes the following steps: In step S101, a rule base is constructed based on the historical data and application requirements of the target energy storage power station, taking into account the actual operation of intraday optimized scheduling.

[0041] It is understood that the rule base in this application embodiment can be understood as a set of rules extracted from the historical operating data of energy storage power stations and different application scenarios, used to guide the actual operation of intraday optimization scheduling.

[0042] In practical implementation, this application embodiment can combine historical data with actual application scenario requirements, consider different situations in the actual operation of intraday optimized scheduling, and construct a rule base to achieve rapid response. Specifically, the construction of the rule base needs to combine historical data with actual application scenario requirements. This application embodiment can ensure its completeness, efficiency, and maintainability through systematic design. This application embodiment can consider intraday optimized scheduling requirements and formulate different priority level rules based on different actual operating conditions to achieve rapid response to different operating states.

[0043] Among them, the emergency control rule is the highest priority response mechanism, designed to address emergency situations such as sudden drops in renewable energy power generation, equipment overload failures, and communication link interruptions under extreme weather conditions. This rule forces the energy storage system to charge and discharge at its rated power extremes, minimizing the duration of transient processes and ensuring the system quickly returns to its steady-state operating range.

[0044] The emergency control rule is triggered when the power deviation between the intraday wind and solar power output and load demand monitoring data and the day-ahead forecast data exceeds a threshold. As shown in equation (1).

[0045] (1) In the formula, , and These represent the changes in energy storage, wind power, and photovoltaic power during the day, respectively. This represents the number of time granularities within a day, where the threshold is... Depends on the current moment t The ability of thermal power plants to climb slopes and the ability of energy storage to regulate are jointly determined, as shown in equation (2).

[0046] (2) In the formula, Indicates the power of the thermal power unit. and These represent the rated power and real-time discharge power of the energy storage cluster, respectively. and These represent the minimum energy value and real-time energy value of the energy storage cluster, respectively. When this abnormal operating condition is detected, the control algorithm will instantly release the power constraint condition of the energy storage system, activate the maximum discharge power command, and suspend the execution of other optimization processes through a priority preemption mechanism.

[0047] Furthermore, the steady-state control rule is designed to address scenarios with significant deviations in renewable energy power generation forecasts. Through a pre-set power adjustment mechanism, it mitigates the risk of energy storage units exceeding their state-of-charge limits due to uncertainties in wind and solar power output. When the relative error between short-term forecast power and real-time monitoring data exceeds a pre-set tolerance range... When the system is in use, the rule will activate the dynamic power compensation function of the energy storage system and correct the energy storage output command in real time, thereby strictly constraining the SOC (State of Charge) within the technical specification range and effectively avoiding battery life degradation and system stability deterioration caused by exceeding the SOC limit.

[0048] The steady-state regulation rule is shown in equation (3).

[0049] (3) Where the threshold It depends on the adjustability of all energy storage units under the condition that the SOC does not exceed the limit at the current moment, as shown in Equation (4).

[0050] (4) This indicates the rated charging power of the energy storage cluster. By adjusting the power of all energy storage units, a safety boundary is ensured.

[0051] The triggering mechanism of the minimum operating cost control rule is based on the dynamic update process of the renewable energy output forecast. It has the lowest priority and will default to the minimum operating cost control if the emergency control rule and the steady-state control rule are not triggered. In this case, only some energy storage units need to participate in the power adjustment to achieve power balance.

[0052] The embodiments of this application can take into account the intraday optimization scheduling needs, and formulate different priority level rules in combination with different actual operating conditions to achieve rapid response to different operating states, thereby improving the efficiency and reliability of intraday scheduling decisions.

[0053] In step S102, an improved particle swarm optimization algorithm-model predictive control optimization model is constructed, and an optimization prediction strategy with an integrated adaptive mechanism is generated based on the improved particle swarm optimization algorithm-model predictive control optimization model.

[0054] It is understood that the optimization prediction strategy that integrates the adaptive mechanism in the embodiments of this application can be an improved stochastic weighted particle swarm optimization algorithm; the improved particle swarm optimization algorithm-model predictive control optimization model can be understood as embedding the improved stochastic particle swarm optimization algorithm into model predictive control.

[0055] In practical implementation, this application's embodiments propose an improved stochastic weighted particle swarm optimization algorithm-model predictive control optimization prediction model to adapt to intraday optimization scheduling scenarios with high nonlinearity and multiple constraints. It also proposes an improved particle swarm optimization algorithm that integrates an adaptive mechanism, dynamically adjusting the stochastic weight interval through rolling optimization to ensure solution efficiency.

[0056] Specifically, embodiments of this application can use the difference between the system's energy output and the active power demand. Thermal power unit output Energy storage cluster charging and discharging power And the energy stored in the energy storage cluster constitutes the state variables. As shown in equation (5).

[0057] (5) The control variables consist of the output adjustment variables of thermal power units and the energy storage power adjustment variables. As shown in equation (6).

[0058] (6) The deviation between the intraday wind-solar-load forecast and the day-ahead forecast is used as the disturbance input. As shown in equation (7).

[0059] (7) The output variable is the difference between the system's energy output and load demand, as well as the energy stored in the energy storage system. As shown in equation (8).

[0060] (8) Based on the above, state-space equations are established.

[0061] (9) (10) In the formula A , B , C , D These are the coefficients of the corresponding vectors. In the current... k At this moment, by iterating through the system's state-space equations, we can obtain the equations from... k Time to k+M System state sequence at time 1 And a series of predicted outputs are shown in Equation (11): (11) Based on the current state of the system and the prediction in the time domain using formula (11), and combined with the constraints and optimization objectives in the intraday optimization model, a model to be optimized is formed.

[0062] Specifically, the goal of intraday optimized scheduling in this application embodiment is to achieve adjustable resource power output adjustment with minimal operating costs based on the determination of thermal power start-up and shutdown during the day-ahead optimized scheduling phase. This includes thermal power unit operating costs, renewable energy operating costs, energy storage operating costs, wind and solar curtailment penalties, load shedding penalties, and inter-regional power exchange costs. Constraints include physical constraints for various types of generating units, grid topology, and line constraints.

[0063] The embodiments of this application can compensate for the difficulty of model predictive control in solving high-dimensional complex constraint problems by integrating improved particle swarm optimization algorithm and model predictive control, thereby improving the solution efficiency and providing a precise and efficient optimization calculation basis for intraday scheduling.

[0064] In step S103, a hybrid optimization framework for intraday scheduling of the target energy storage power station is established based on the rule base and the improved particle swarm optimization algorithm-model predictive control optimization model. Based on the hybrid optimization framework for intraday scheduling, the optimization prediction strategy, the power deviation and operating status of the target energy storage power station, an intraday scheduling optimization strategy for the target energy storage power station is generated.

[0065] It is understood that the intraday scheduling hybrid optimization framework in this application embodiment can be understood as a two-layer scheduling architecture that integrates rule-based qualitative decision-making and model-based quantitative calculation; power deviation can be understood as the difference between the actual output and planned output of the energy storage power station; the operating status can include operating parameters such as energy storage charge status, unit operating status, and equipment safety status.

[0066] In actual implementation, the embodiments of this application can update the state space based on the real-time operating status of the system and the updated short-term wind and solar predictions, and combine the rule base with the improved particle swarm algorithm-model predictive control to form a hybrid optimization framework.

[0067] The improved particle swarm optimization (PSO) algorithm-model predictive control (MVC) optimization model and the rule base are computed in parallel. The PSO algorithm-model predictive control model thread continuously solves the MVC problem and generates backup strategies, while the rule engine thread monitors the system status in real time and preemptively executes emergency rules. Simultaneously, the rule base and the improved PSO algorithm-model predictive control model are synergistically coupled, embedding the rule base's constraints into the optimization model to avoid strategy conflicts. Furthermore, the rule base's thresholds are updated based on the optimization output, improving engineering feasibility. This dual-strategy approach acts as a backup for each other, preventing a single method failure from causing a global crash.

[0068] The embodiments of this application can establish an intraday scheduling hybrid optimization framework. Through the synergistic effect of the rule base and the improved particle swarm optimization algorithm-model predictive control optimization model, the advantages of rapid response and global optimization are complemented, thereby generating efficient and reliable intraday scheduling optimization strategies under different operating conditions, enhancing the adaptability and stability of energy storage power stations in the face of renewable energy fluctuations.

[0069] Optionally, in one embodiment of this application, an intraday scheduling optimization strategy for the target energy storage power station is generated based on the intraday scheduling hybrid optimization framework, the optimization prediction strategy, the power deviation and operating status of the target energy storage power station, including: acquiring the load demand forecast curve, wind power output forecast, photovoltaic power output forecast and operating data of the target energy storage power station; calculating the power deviation and operating status of the target energy storage power station based on the load demand forecast curve, wind power output forecast, photovoltaic power output forecast and operating data; determining the control rules of the target energy storage power station based on the rule base, power deviation and operating status; generating an intraday scheduling optimization strategy based on the rule base in response to the control rule being an emergency control rule; and generating an intraday scheduling optimization strategy based on the improved particle swarm optimization algorithm-model predictive control optimization model and the optimization prediction strategy in response to the control rule being a steady-state control rule or a control rule with minimum operating cost.

[0070] For example, the embodiments of this application can acquire data such as the load demand forecast curve for the next 4 hours, wind power output forecast, photovoltaic output forecast, and the current operating status of each energy storage unit every 15 minutes. Based on the load demand forecast curve, wind power output forecast, photovoltaic output forecast, and operating data, the system power deviation and equipment operating status are calculated. Combined with the real-time operating status, the control rules corresponding to the current state are quickly matched through the early warning threshold.

[0071] The appropriate strategy is selected based on the rules. The specific operation is as follows: If an emergency rule is triggered, the rule base control is executed immediately, skipping the solution of complex models and achieving a millisecond-level response to quickly alleviate the impact of abnormal operating conditions on the normal operation of the system; otherwise, the improved particle swarm algorithm-model predictive control model generation optimization strategy is called to generate an intraday scheduling optimization strategy to optimize operating costs.

[0072] The embodiments of this application can calculate power deviation and operating status based on load demand forecast, wind power output forecast, photovoltaic power output forecast and operating data, and flexibly select control rules based on rule base and deviation degree, thereby realizing differentiated formulation of scheduling strategy. This ensures the rapid response capability of the system under emergency conditions, while also taking into account the stability and economic efficiency of steady-state operation. The two strategies serve as backups for each other, avoiding the global collapse caused by the failure of a single method, and improving the feasibility of the project.

[0073] Optionally, in one embodiment of this application, based on a rule base and in combination with power deviation and operating status, the control rules for the target energy storage power station are determined, including: if the power deviation is greater than a first preset threshold, the control rule is determined to be an emergency control rule; if the power deviation exceeds a second preset threshold, the control rule is determined to be a steady-state control rule, wherein the first preset threshold is greater than the second preset threshold; if the control rule is neither an emergency control rule nor a steady-state control rule, the control rule is determined to be a control rule with minimum operating cost.

[0074] It is understood that the first preset threshold in the embodiments of this application can be determined by the climbing ability of thermal power and the regulation capability of energy storage at the current time t. The first preset threshold can be set by those skilled in the art according to the actual situation, and no specific restrictions are imposed here. The second preset threshold can be determined by the adjustable capability of all energy storage units under the condition that the SOC does not exceed the limit at the current time. The second preset threshold can be set by those skilled in the art according to the actual situation, and no specific restrictions are imposed here.

[0075] For example, in this embodiment of the application, the power deviation between the intraday wind and solar power output and load demand detection data and the day-ahead forecast data exceeds a first preset threshold. Triggering emergency control rules, first preset threshold Depends on the current moment t The power grid's ramp-up capability and energy storage regulation capability are jointly determined. When this abnormal operating condition is detected, the control algorithm will instantly release the power constraint condition of the energy storage system, activate the maximum discharge power command, and stop the execution of other optimization processes through the priority preemption mechanism.

[0076] Furthermore, when the relative error between the short-term predicted power and the real-time monitoring data exceeds a second preset threshold... At this time, the rule will activate the dynamic power compensation function of the energy storage system, correcting the energy storage output command in real time, thereby strictly constraining the SOC within the technical specification range and effectively avoiding battery life degradation and system stability deterioration caused by exceeding the SOC limit. The second preset threshold... It depends on the adjustability of all energy storage units under the condition that their SOC does not exceed the limit at the current moment.

[0077] The triggering mechanism of the minimum operating cost control rule is based on the dynamic update process of the renewable energy output forecast. It has the lowest priority and will default to the minimum operating cost control if the emergency control rule and the steady-state control rule are not triggered. In this case, only some energy storage units need to participate in the power adjustment to achieve power balance.

[0078] The embodiments of this application can formulate different priority level rules based on power deviation, taking into account intraday optimization scheduling needs, and combining different actual operating conditions, so as to achieve rapid response to different operating states, ensuring safety and stability while minimizing operating costs.

[0079] Optionally, in one embodiment of this application, an intraday scheduling optimization strategy is generated based on an improved particle swarm optimization algorithm-model predictive control optimization model and an optimization prediction strategy. This includes: generating a particle swarm for the intraday scheduling optimization strategy and initializing the particle positions, particle velocities, and weight intervals of the particle swarm. Each particle in the particle swarm represents a control variable of the intraday scheduling optimization strategy, and the control variables include the thermal power unit output adjustment variable and the energy storage power adjustment variable of the target energy storage power station; calculating the fitness of the particle swarm and updating the particle optimal and swarm optimal values ​​based on the fitness; calculating the weight interval at the current iteration number, generating an inertial weight for each particle swarm based on the weight interval, adjusting the particle velocity based on the inertial weight, and updating the particle position until a preset iteration termination condition is met, determining the globally optimal control variable; and obtaining the intraday scheduling optimization strategy based on the globally optimal control variable.

[0080] It is understood that in the embodiments of this application, the particle swarm can be understood as the set of search individuals of the optimization algorithm; the inertia weight can be understood as the core parameter affecting the local and global search capabilities of the particles; the fitness can be understood as a quantitative index used to evaluate the quality of the scheduling control variable; the preset iteration termination condition can be that the result meets the calculation accuracy or the number of iterations reaches the upper limit. The preset iteration termination condition can be set by those skilled in the art according to the actual situation, and no specific restrictions are made here.

[0081] In actual implementation, the embodiments of this application can randomly generate a particle swarm, with each particle representing a control sequence, i.e., time. k+1 to k+M Adjustment variables of thermal power unit output and energy storage power at any time Assign initial position and velocity, and set initial weight range. and shrinkage coefficient .

[0082] Furthermore, embodiments of this application can calculate the fitness of the particle swarm for each generation, i.e., the objective function value, and update the optimal particle swarm based on the calculation results. with group optimal Calculate the current iteration The weight intervals under each number are shown in equations (12) and (13).

[0083] (12) (13) Furthermore, embodiments of this application can generate new random inertial weights for each particle swarm within a weight interval. The speed is adjusted according to random weights, and the position is updated. It is then judged whether the result meets the calculation accuracy or whether the number of iterations has reached the upper limit. If the termination requirement is not met, the calculation of the fitness of each generation of particle swarm is returned; otherwise, the result is output.

[0084] This application's embodiments can utilize the adaptive mechanism of an improved particle swarm optimization algorithm to optimize control variables, effectively enhancing the algorithm's global optimization capability and convergence speed, avoiding getting trapped in local optima, accurately determining the optimal control variables for thermal power units and energy storage power, meeting the real-time requirements of intraday scheduling optimization, and fully considering the 0-1 variable solution challenges brought about by the large number of distributed energy storage systems in the current power system. This improves the efficiency of optimization solutions.

[0085] Optionally, in one embodiment of this application, generating an intraday scheduling optimization strategy based on an improved particle swarm optimization algorithm-model predictive control optimization model and an optimization prediction strategy further includes: collecting the load demand forecast curve, wind power output forecast, and photovoltaic power output forecast for the next forecast period; updating the rule base and the improved particle swarm optimization algorithm-model predictive control optimization model based on the load demand forecast curve, wind power output forecast, and photovoltaic power output forecast for the next forecast period, until a preset optimization termination condition is met.

[0086] It is understood that the preset optimization termination condition in the embodiments of this application can be 96 optimization completion times. The preset optimization termination condition can be set by those skilled in the art according to the actual situation, and no specific restrictions are imposed here.

[0087] In actual implementation, this application embodiment can collect the current operating data and the renewable energy output forecast and load demand forecast for the next forecast period, and update the rule base parameters and optimization model. It requires selecting the first globally optimal control variable calculated by the improved stochastic weighted particle swarm optimization algorithm and applying it to the intraday scheduling control system. At time k+1, based on the system's real-time operating status and the updated short-term wind and solar forecasts, the state space is updated. The forecast data for the next window is adjusted according to the actual wind and solar power output and load demand, and the relevant rolling optimization data is updated. This process is repeated until 96 time points have been rolled over for optimization.

[0088] Specifically, intraday optimization scheduling is a rolling optimization process. If the current time is t, the data that the system has actually run (optimized from the previous time) will be imported into formulas (5)-(11) and combined with the intraday optimization scheduling model to perform a new round of optimization calculations at time t+1. The actual running data at time t+1 (actually optimized at time t) will continue to be put into formulas (5)-(11) and then optimized at time t+2. At the same time, the rule base is continuously updated.

[0089] The embodiments of this application can collect the actual operating data at the current moment and the renewable energy output forecast and load demand forecast for the next forecast period, update the rule base parameters and optimization model, thereby realizing the closed-loop rolling optimization of intraday scheduling, which can adapt to the fluctuations of wind and solar power output and load demand in real time, continuously correct the optimization scheme, and improve the dynamic adaptability of the scheduling strategy to the real-time operating scenario.

[0090] Optionally, in one embodiment of this application, based on the intraday scheduling hybrid optimization framework, the power deviation and operating status data of the target energy storage power station, an intraday scheduling optimization strategy for the target energy storage power station is generated, which further includes: generating charging and discharging instructions for the target energy storage power station based on the intraday scheduling optimization strategy; transmitting the charging and discharging instructions to each energy storage unit of the target energy storage power station; and determining the output of the thermal power unit of the target energy storage power station at the next moment according to the intraday scheduling optimization strategy.

[0091] It is understood that the charging and discharging instructions in the embodiments of this application can be understood as specific power setting values ​​or operating modes issued for each energy storage unit, and the output of the thermal power unit at the next moment can be understood as the power generation plan adjusted according to the intraday scheduling optimization strategy.

[0092] In actual implementation, the embodiments of this application can transmit the charging and discharging commands obtained by the improved particle swarm optimization algorithm-model predictive control model to each energy storage unit, and adjust the output of the thermal power unit at the next moment.

[0093] For example, in this embodiment of the application, the optimized total energy storage power adjustment can be decomposed into individual energy storage units. Considering constraints such as the SOC and maximum charge / discharge power of each unit, charge / discharge commands for each unit are generated. Simultaneously, based on the thermal power unit output adjustment variables in the optimization strategy, the target output value of the thermal power units for the next moment is determined.

[0094] The embodiments of this application can generate energy storage charging and discharging commands and thermal power unit output commands based on intraday scheduling optimization strategies, and send them to each energy storage unit and thermal power unit to realize the implementation of scheduling optimization strategies, ensure that the optimization scheme directly affects the actual operation of the energy storage power station, and improve the overall operational reliability.

[0095] Specifically, it can be combined with Figures 2 to 7 As shown, a specific embodiment is used to elaborate in detail on the working principle of the intraday scheduling method for energy storage power stations based on rule-based hybrid model predictive control in this application.

[0096] like Figure 2 As shown, embodiments of this application may include the following steps: Step S201: Data acquisition.

[0097] The embodiments of this application can obtain the fluctuations in wind and solar power and load rolling forecasts, as well as the current operating status of various types of units, at a certain point in time during the daily optimization rolling process.

[0098] Step S202: Status assessment.

[0099] Using formulas (5) to (11), the embodiments of this application can "predict" the power difference and energy storage status at the next rolling point.

[0100] Step S203: Rule matching, determine whether it is an emergency control rule. If yes, proceed to step S204; otherwise, proceed to step S205.

[0101] The embodiments of this application can perform matching in a rule base based on power difference and energy storage status.

[0102] Step S204: Rule base control.

[0103] Step S205: Improved Particle Swarm Optimization Algorithm - Model Predictive Control Optimization Model.

[0104] This application embodiment can call an improved particle swarm optimization algorithm-model predictive control optimization model to generate optimization strategies, thereby optimizing operating costs. It collects actual operating data at the current moment and renewable energy output and load demand forecasts for the next forecast period, updating rule base parameters and the optimization model. It requires selecting the first globally optimal control variable calculated by the improved stochastic weighted particle swarm optimization algorithm and applying it to the intraday scheduling control system. At time k+1, based on the system's real-time operating status and the updated short-term wind and solar forecasts, the state space is updated. The forecast data for the next window is adjusted according to the actual wind and solar power output and load demand, and the relevant rolling optimization data is updated. This process is repeated until 96 time points have been completed for rolling optimization.

[0105] Step S206: Determine whether the termination condition is met. If yes, end the process. If no, execute step S202 and update the rule judgment threshold in step S203.

[0106] The embodiments of this application can determine whether the result meets the calculation accuracy or whether the number of iterations has reached the upper limit. If the termination requirement is not met, the process returns to step S202; otherwise, the result is output.

[0107] like Figure 3 As shown, embodiments of this application may include the following steps: Step S301: Initialize the particle swarm, particle positions, velocities, and initial weight range.

[0108] Step S302: Calculate fitness updates for individuals and the global optimum.

[0109] Step S303: Calculate the range of random weight values.

[0110] Step S304: Randomly generate inertia weights.

[0111] Step S305: Update particle swarm velocity and position.

[0112] Step S306: Determine whether the termination condition is met. If yes, proceed to step S307; otherwise, proceed to step S302.

[0113] Step S307: Output the result.

[0114] For example, the curves for wind power, solar power, and load in different scenarios, such as conventional and emergency scenarios, are as follows: Figure 4 As shown. Intraday optimized scheduling is based on the day-ahead thermal power dispatch plan, with adjustments made to establish a rolling optimization cycle of 4 hours, using 15-minute units. The initial maximum and minimum weights of the improved stochastic weighted particle swarm optimization algorithm are set to 0.4 and 0.9 respectively, with a shrinkage coefficient... Set them to 0.2 and 0.1 respectively.

[0115] In typical scenarios, the scheduling results under different solution algorithms are shown in Table 1 and... Figure 5 As shown, Table 1 is the daily scheduling result table under normal operating conditions.

[0116] Table 1

[0117] In emergency scenarios, the scheduling results under different solution algorithms are shown in Table 2. Figure 6 As shown, Table 2 is the intraday scheduling result table for emergency scenarios.

[0118] Table 2

[0119] Comparison results of different algorithms considering the number of energy storage clusters under different models and algorithms are as follows: Figure 7 As shown.

[0120] The intraday scheduling method for energy storage power stations based on rule-based hybrid model predictive control proposed in this application can construct a rule base that considers the actual operation of intraday optimized scheduling, and build an improved particle swarm optimization algorithm and model predictive control optimization model to establish an intraday scheduling hybrid optimization framework. This framework can obtain intraday scheduling optimization strategies based on the power deviation and operating status of the target energy storage power station and an optimization prediction strategy using a fusion adaptive mechanism. This achieves efficient optimization solutions for intraday optimized scheduling, balancing second-level response capability with long-term optimization performance, effectively balancing the real-time performance and operating cost of system scheduling, reducing the frequency of complex model calls, and lowering the computational load. Therefore, it solves the problems in related technologies where heuristic algorithms rely heavily on initial parameter settings, leading to a tendency to get trapped in local optima or even diverge and fail to converge. Furthermore, it lacks an effective solution for achieving rapid external feedback and internal adjustment of the energy storage cluster without affecting the daily planning curve, thus failing to meet the high requirements of intraday rolling optimization for flexible and adjustable feedback capabilities of energy storage.

[0121] Next, referring to the accompanying drawings, we describe the intraday scheduling device for an energy storage power station based on a rule-based hybrid model predictive control according to an embodiment of this application.

[0122] Figure 8 This is a schematic diagram of the intraday scheduling device for an energy storage power station based on rule-based hybrid model predictive control, according to an embodiment of this application.

[0123] like Figure 8 As shown, the intraday scheduling device 10 of the energy storage power station based on rule-based hybrid model predictive control includes: a first construction module 100, a second construction module 200, and a scheduling module 300.

[0124] The first construction module 100 is used to build a rule base that takes into account the actual operation of intraday optimized scheduling based on the historical data and scenario application requirements of the target energy storage power station.

[0125] The second building module 200 is used to build an improved particle swarm optimization algorithm-model predictive control optimization model, and based on the improved particle swarm optimization algorithm-model predictive control optimization model, generate an optimization prediction strategy that integrates adaptive mechanisms.

[0126] The scheduling module 300 is used to establish a hybrid optimization framework for intraday scheduling of the target energy storage power station based on a rule base and an improved particle swarm optimization algorithm-model predictive control optimization model. Based on the intraday scheduling hybrid optimization framework, optimization prediction strategy, power deviation and operating status of the target energy storage power station, it generates an intraday scheduling optimization strategy for the target energy storage power station.

[0127] Optionally, in one embodiment of this application, the scheduling module 300 includes: an acquisition unit, a calculation unit, a first determination unit, a first generation unit, and a second generation unit.

[0128] The acquisition unit is used to acquire the load demand forecast curve, wind power output forecast, photovoltaic power output forecast, and operation data of the target energy storage power station.

[0129] The calculation unit is used to calculate the power deviation and operating status of the target energy storage power station based on load demand forecast curves, wind power output forecasts, photovoltaic power output forecasts, and operating data.

[0130] The first determining unit is used to determine the control rules of the target energy storage power station based on the rule base, power deviation, and operating conditions.

[0131] The first generation unit is used to generate intraday scheduling optimization strategies based on the rule base, in response to the control rules being emergency control rules.

[0132] The second generation unit is used to generate intraday scheduling optimization strategies based on the improved particle swarm optimization algorithm-model predictive control optimization model and optimization prediction strategy, in response to the control rule being a steady-state control rule or a control rule with minimum operating cost.

[0133] Optionally, in one embodiment of this application, the determining unit includes: a first determining subunit, a second determining subunit, and a third determining subunit.

[0134] The first determining subunit is used to determine the control rule as an emergency control rule if the power deviation is greater than the first preset threshold.

[0135] The second determining subunit is used to determine the control rule as a steady-state control rule if the power deviation exceeds the second preset threshold, wherein the first preset threshold is greater than the second preset threshold.

[0136] The third determining subunit is used to determine the control rule as the minimum operating cost control rule if the control rule is not an emergency control rule or a steady-state control rule.

[0137] Optionally, in one embodiment of this application, the second generation unit includes: an initialization subunit, a first calculation subunit, a second calculation subunit, and a generation subunit.

[0138] The initialization sub-unit is used to generate a particle swarm for the intraday scheduling optimization strategy and to initialize the particle position, particle velocity and weight range of the particle swarm. Each particle in the particle swarm represents a control variable of the intraday scheduling optimization strategy. The control variables include the output adjustment variable of the thermal power unit and the energy storage power adjustment variable of the target energy storage power station.

[0139] The first computational subunit is used to calculate the fitness of the particle swarm and update the particle optimality and swarm optimality based on the fitness.

[0140] The second calculation subunit is used to calculate the weight interval under the current iteration number, generate the inertia weight of each particle group according to the weight interval, adjust the particle velocity according to the inertia weight, and update the particle position until the preset iteration termination condition is met, and determine the globally optimal control variable.

[0141] Generate sub-units to obtain intraday scheduling optimization strategies based on globally optimal control variables.

[0142] Optionally, in one embodiment of this application, the second generation unit further includes: a collection subunit and an update subunit.

[0143] The data acquisition subunit is used to collect the load demand forecast curve, wind power output forecast, and photovoltaic power output forecast for the next forecast period.

[0144] The updated sub-unit is used to update the rule base and the improved particle swarm optimization algorithm-model predictive control optimization model based on the load demand forecast curve, wind power output forecast and photovoltaic output forecast for the next forecast period, until the preset optimization termination condition is met.

[0145] Optionally, in one embodiment of this application, the scheduling module 300 further includes: a third generation unit and a second determination unit.

[0146] The third generation unit is used to generate charging and discharging instructions for the target energy storage power station based on the intraday scheduling optimization strategy.

[0147] The second determining unit is used to transmit charging and discharging commands to each energy storage unit of the target energy storage power station, and to determine the output of the thermal power units of the target energy storage power station at the next moment according to the intraday scheduling optimization strategy.

[0148] It should be noted that the foregoing explanation of the intraday scheduling method for energy storage power stations based on rule-based hybrid model predictive control also applies to the intraday scheduling device for energy storage power stations based on rule-based hybrid model predictive control in this embodiment, and will not be repeated here.

[0149] The intraday scheduling device for energy storage power stations based on rule-based hybrid model predictive control proposed in this application can construct a rule base that considers the actual operation of intraday optimized scheduling, and construct an improved particle swarm optimization algorithm and model predictive control optimization model to establish an intraday scheduling hybrid optimization framework. Based on the power deviation and operating status of the target energy storage power station, an optimization prediction strategy based on a fusion adaptive mechanism can be used to obtain an intraday scheduling optimization strategy, thereby achieving efficient optimization and solution for intraday optimized scheduling, balancing second-level response capability and long-term optimization performance, effectively balancing the real-time performance and operating cost of system scheduling, reducing the frequency of complex model calls, and lowering the computational load. This solves the problems in related technologies, where heuristic algorithms rely heavily on initial parameter settings, leading to a tendency to get trapped in local optima or even diverge and fail to converge, and lacking an effective solution for rapid external feedback and internal adjustment of the energy storage cluster without affecting the daily planning curve, thus failing to meet the high requirements of intraday rolling optimization for flexible and adjustable feedback capabilities of energy storage.

[0150] Figure 9 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 901, the processor 902, and the computer program stored on the memory 901 and capable of running on the processor 902.

[0151] When the processor 902 executes the program, it implements the intraday scheduling method for energy storage power stations based on rule-based hybrid model predictive control provided in the above embodiments.

[0152] Furthermore, electronic devices also include: Communication interface 903 is used for communication between memory 901 and processor 902.

[0153] The memory 901 is used to store computer programs that can run on the processor 902.

[0154] The memory 901 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0155] If the memory 901, processor 902, and communication interface 903 are implemented independently, then the communication interface 903, memory 901, and processor 902 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 9 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0156] Optionally, in a specific implementation, if the memory 901, processor 902, and communication interface 903 are integrated on a single chip, then the memory 901, processor 902, and communication interface 903 can communicate with each other through an internal interface.

[0157] The processor 902 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0158] This application also provides a non-volatile computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described intraday scheduling method for energy storage power stations based on rule-based hybrid model predictive control.

[0159] This application also provides a computer program product storing a computer program that, when executed by a processor, implements the above-described intraday scheduling method for energy storage power stations based on rule-based hybrid model predictive control.

[0160] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0161] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0162] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0163] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0164] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0165] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0166] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0167] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for intraday scheduling of energy storage power stations based on rule-based hybrid model predictive control, characterized in that, Includes the following steps: Based on the historical data and application requirements of the target energy storage power station, a rule base is constructed that takes into account the actual operation of intraday optimized scheduling. An improved particle swarm optimization algorithm-model predictive control optimization model is constructed, and an optimization prediction strategy with an adaptive mechanism is generated based on the improved particle swarm optimization algorithm-model predictive control optimization model. Based on the rule base and the improved particle swarm optimization algorithm-model predictive control optimization model, a hybrid optimization framework for intraday scheduling of the target energy storage power station is established. Based on the hybrid optimization framework for intraday scheduling, the optimization prediction strategy, the power deviation and operating status of the target energy storage power station, an intraday scheduling optimization strategy for the target energy storage power station is generated.

2. The method according to claim 1, characterized in that, The process of generating an intraday scheduling optimization strategy for the target energy storage power station based on the intraday scheduling hybrid optimization framework, the optimization prediction strategy, and the power deviation and operating status of the target energy storage power station includes: Obtain the load demand forecast curve, wind power output forecast, photovoltaic power output forecast, and operation data of the target energy storage power station; Based on the load demand forecast curve, the wind power output forecast, the photovoltaic power output forecast, and the operating data, the power deviation and operating status of the target energy storage power station are calculated. Based on the rule base, the power deviation, and the operating status, the control rules for the target energy storage power station are determined; In response to the fact that the control rule is an emergency control rule, the intraday scheduling optimization strategy is generated based on the rule base; In response to the control rule being a steady-state control rule or a control rule with minimum operating cost, the intraday scheduling optimization strategy is generated based on the improved particle swarm optimization algorithm-model predictive control optimization model and the optimization prediction strategy.

3. The method according to claim 2, characterized in that, The process of determining the control rules for the target energy storage power station based on the rule base, combined with the power deviation and the operating status, includes: If the power deviation is greater than the first preset threshold, then the control rule is determined to be the emergency control rule; If the power deviation exceeds the second preset threshold, the control rule is determined to be the steady-state control rule, wherein the first preset threshold is greater than the second preset threshold; If the control rule is neither the emergency control rule nor the steady-state control rule, then the control rule is determined to be the minimum operating cost control rule.

4. The method according to claim 2, characterized in that, The process of generating the intraday scheduling optimization strategy based on the improved particle swarm optimization algorithm-model predictive control optimization model and the optimization prediction strategy includes: A particle swarm of the intraday scheduling optimization strategy is generated, and the particle position, particle velocity and weight range of the particle swarm are initialized. Each particle in the particle swarm represents a control variable of the intraday scheduling optimization strategy. The control variables include the thermal power unit output adjustment variable and the energy storage power adjustment variable of the target energy storage power station. Calculate the fitness of the particle swarm, and update the particle optimum and swarm optimum based on the fitness; Calculate the weight interval for the current iteration number, generate the inertia weight for each particle swarm based on the weight interval, adjust the particle velocity according to the inertia weight, and update the particle position until the preset iteration termination condition is met, and determine the globally optimal control variable. The intraday scheduling optimization strategy is obtained based on the globally optimal control variables.

5. The method according to claim 2, characterized in that, The step of generating the intraday scheduling optimization strategy based on the improved particle swarm optimization algorithm-model predictive control optimization model and the optimization prediction strategy further includes: Collect the load demand forecast curve, wind power output forecast, and photovoltaic power output forecast for the next forecast period; Based on the load demand forecast curve, wind power output forecast, and photovoltaic power output forecast for the next forecast period, update the rule base and the improved particle swarm optimization algorithm-model predictive control optimization model until the preset optimization termination condition is met.

6. The method according to claim 1, characterized in that, The step of generating an intraday scheduling optimization strategy for the target energy storage power station based on the intraday scheduling hybrid optimization framework, the power deviation and operating status data of the target energy storage power station, further includes: Based on the intraday scheduling optimization strategy, charge and discharge instructions for the target energy storage power station are generated. The charging and discharging commands are transmitted to each energy storage unit of the target energy storage power station, and the output of the thermal power unit of the target energy storage power station at the next moment is determined according to the intraday scheduling optimization strategy.

7. A daily dispatching device for an energy storage power station based on rule-based hybrid model predictive control, characterized in that, Including the following: The first construction module is used to build a rule base that takes into account the actual operation of intraday optimized scheduling based on the historical data and scenario application requirements of the target energy storage power station. The second construction module is used to construct an improved particle swarm optimization algorithm-model predictive control optimization model, and based on the improved particle swarm optimization algorithm-model predictive control optimization model, generate an optimization prediction strategy that integrates adaptive mechanisms. The scheduling module is used to establish a daytime scheduling hybrid optimization framework for the target energy storage power station based on the rule base and the improved particle swarm optimization algorithm-model predictive control optimization model, and to generate a daytime scheduling optimization strategy for the target energy storage power station based on the daytime scheduling hybrid optimization framework, the optimization prediction strategy, the power deviation and operating status of the target energy storage power station.

8. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and capable of running on the processor, wherein the processor executes the program to implement the intraday scheduling method for energy storage power stations based on rule-based hybrid model predictive control as described in any one of claims 1-6.

9. A non-volatile computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the intraday scheduling method for energy storage power plants based on rule-based hybrid model predictive control as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, The computer program is executed to implement the intraday scheduling method for energy storage power stations based on rule-based hybrid model predictive control as described in any one of claims 1-6.

Images