User side energy storage collaborative optimization method based on virtual power plant

Abstract

The invention relates to the technical field of energy storage adjustment, in particular to a user side energy storage collaborative optimization method based on a virtual power plant. Comprising the following steps: aggregating all user side energy storage resources based on a virtual power plant platform, and setting a plurality of energy storage nodes according to an aggregation result; establishing a plurality of scheduling cycles, and generating expected adjustable resource parameters of each energy storage node in the current scheduling cycle according to a preset response prediction model; obtaining an expected energy storage demand of the current scheduling period, and generating a first-level control strategy according to all the expected adjustable resource parameters and the expected energy storage demand; acquiring a feedback data packet according to a preset feedback time node, and judging whether a primary correction instruction is generated or not according to the feedback data packet; a plurality of node categories are established according to different user side energy storage equipment types, and a corresponding response sub-model is constructed according to characteristic parameters of each node category, so that accurate prediction of response capabilities of all energy storage nodes of a user side is realized, and collaborative energy storage efficiency and collaborative control of the user side are improved.

Description

Technical Field

[0001] The present application relates to the field of energy storage regulation technology, and in particular to a user-side energy storage collaborative optimization method based on a virtual power plant. Background Art

[0002] As the global energy mix accelerates toward cleaner, lower-carbon energy, the penetration of distributed renewable energy (DER), represented by photovoltaic and wind power, continues to increase in user-side locations (such as industrial parks, commercial buildings, and residential communities). Simultaneously, to improve energy self-sufficiency, reduce electricity costs, and participate in demand response, the installation scale of user-side electrochemical energy storage systems (ESS) has also seen explosive growth. These distributed resources are characterized by their dispersed locations, relatively small capacity, and diverse operating characteristics.

[0003] Currently, most behind-the-meter energy storage systems primarily serve local needs, such as arbitrage between peak and valley prices, increasing self-consumption of photovoltaic power, and ensuring power supply for critical loads. This single, independent operation model fails to fully realize the system-wide value of energy storage, resulting in suboptimal overall economic and social benefits. The capacity of individual user energy storage is limited, and its responsiveness to grid or power market signals is weak, making it difficult to meet the requirements of large-scale, highly reliable, and aggregated response. Summary of the Invention

[0004] The purpose of this application is: to solve the above technical problems, this application provides a user-side energy storage collaborative optimization method based on a virtual power plant, aiming to improve the collaborative energy storage efficiency and collaborative control on the user side.

[0005] In some embodiments of the present application, all user-side energy storage resources are aggregated based on virtual power plant technology, and multiple node categories are established according to different types of user-side energy storage equipment. Corresponding response sub-models are constructed according to the characteristic parameters of each node category to achieve accurate prediction of the response capabilities of all user-side energy storage nodes and improve the collaborative energy storage efficiency and collaborative control on the user side.

[0006] In some embodiments of the present application, by establishing multi-level regulation, the expected energy storage demand is first allocated according to the response characteristics of different node categories, and then a secondary allocation is performed according to the operating status of the energy storage nodes within each node category, thereby improving the control efficiency of the user-side energy storage nodes and improving the overall operating benefits.

[0007] In some embodiments of the present application, a method for collaborative optimization of user-side energy storage based on a virtual power plant is provided, comprising: Aggregate all user-side energy storage resources based on the virtual power plant platform and set multiple energy storage nodes based on the aggregation results; Establish multiple scheduling cycles and generate the expected adjustable resource parameters of each energy storage node in the current scheduling cycle based on the preset response prediction model; Obtain the expected energy storage demand for the current scheduling cycle and generate a primary control strategy based on all expected adjustable resource parameters and the expected energy storage demand; Obtaining a feedback data packet according to a preset feedback time node, and determining whether to generate a first-level correction instruction based on the feedback data packet; When setting multiple energy storage nodes, it includes: Establish energy storage node sequence A, A=(a1,a2…a i …a n ), where a i is the i-th energy storage node; n is the number of energy storage nodes.

[0008] In some embodiments of the present application, when a response prediction model is preset, it includes: Generate multiple equipment characteristic indicators based on all energy storage node parameters; Generate multiple node categories based on all device characteristic indicators; Establish a node category sequence B, B=(b1, b2…b i …b m ), where b i is the i-th node category; m is the number of node categories; Construct the response sub-model of each node category in turn; Establish the response sub-model series P, P=(p1, p2…p i …p m ), where p i is the response submodel of the i-th node category; A response prediction model is constructed based on the response sub-model sequence P.

[0009] In some embodiments of the present application, the sequential construction of the response sub-models for each node category includes: Set b in sequence based on the node category sequence B i is the target node category; Generate multiple perturbation feature indicators of the target node category; Construct an initial evaluation model for the target node category; Get all associated energy storage nodes of the target node category; Establishing a sequence A1 of associated energy storage nodes of the target node category; A1=(a 11 ,a 12 …a 1i …a 1n1 ), where a 1i is the i-th associated energy storage node; n1 is the number of associated energy storage nodes of the target node category; According to the number of associated energy storage nodes A1, set a1i Associate energy storage nodes with the target; Obtain a historical operation package of the target associated energy storage node, and generate a disturbance deviation value c of the target associated energy storage node based on the historical operation package; Preset disturbance deviation threshold C1; If c>C1, generate the compensation sub-strategy of the target associated energy storage node; Determine in turn whether each associated energy storage node generates a compensation sub-strategy; A response sub-model of the target program category is generated according to all compensation sub-strategies and the initial evaluation model.

[0010] In some embodiments of the present application, generating a disturbance deviation value c of a target associated energy storage node includes: c=[ η i *(v i -v' i )]; Among them, θ1 is the number of disturbance feature indicators of the target node category; η i is the influencing factor of the i-th disturbance characteristic index in the target node category; v i is the reference value of the i-th disturbance characteristic index generated based on the historical operation package; v' i is the standard reference value of the i-th disturbance characteristic index in the target node category.

[0011] In some embodiments of the present application, generating the expected adjustable resource parameters of each energy storage node in the current scheduling period includes: Set the first prediction time node of the current scheduling period; The response prediction model generates response capability parameters of each energy storage node at the first prediction time node; Generate a responsiveness sub-table for each node category based on all responsiveness parameters; Generate an expected adjustable resource table for the current scheduling period based on all response capability sub-tables.

[0012] In some embodiments of the present application, generating a primary control strategy includes: Generate expected energy storage demand based on expected grid fluctuation parameters; Generate a first-level allocation strategy based on the expected energy storage demand and the response capability sub-table of each node category; Generate energy storage sub-demands for each node category based on the first-level allocation strategy; Generate the secondary allocation strategy for each node category in turn; Generate a first-level control strategy based on all second-level allocation strategies.

[0013] In some embodiments of the present application, generating a secondary allocation strategy for each node category includes: Set b in sequence according to the node category sequence B i is the node category to be assigned; Establish the associated energy storage node sequence A2 of the node category to be allocated; A2=(a 21 ,a 22 …a 2i …a 2n2 ), where a 2i is the i-th associated energy storage node of the node category to be allocated; n2 is the number of associated energy storage nodes of the node category to be allocated; Generate a response evaluation value of each associated energy storage node in the associated energy storage node sequence A2; Generate a response scheduling order for the node categories to be assigned based on all response evaluation values; Obtain the energy storage sub-demand of the node category to be allocated; A secondary allocation strategy for the node category to be allocated is generated based on the response scheduling order and energy storage sub-demand.

[0014] In some embodiments of the present application, generating a response evaluation value of each associated energy storage node in the associated energy storage node sequence A2 includes: According to the number of associated energy storage nodes A2, set a 2i is the associated energy storage node to be evaluated; Generate a response evaluation value f of the associated energy storage node to be evaluated; f=e1*Q1*c'+e2*Q2*[ β i *s i ]; Among them, e1 is the preset first fixed coefficient; e2 is the preset second fixed coefficient; Q1 is the preset first weight coefficient; Q2 is the preset second fixed coefficient; c' is the disturbance deviation value of the associated energy storage node to be evaluated; θ2 is the number of response resource indicators; β i is the impact factor of the i-th response resource indicator; s i is the reference value of the i-th response resource indicator of the associated energy storage node to be evaluated.

[0015] In some embodiments of the present application, determining whether to generate a first-level correction instruction based on a feedback data packet includes: Preset multiple feedback time nodes; Get the feedback data packet of the current feedback time node; Generates a revised evaluation value d of the current feedback time node based on the feedback data packet; d=e3*Q3*[ λ i *ki ]+e4*Q4*[ r i *j i ]; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; is the energy storage demand indicator quantity; i is the influencing factor of the i-th energy storage demand index; k i is the fluctuation value of the i-th energy storage demand; r i is the impact factor of the i-th energy storage node in the energy storage node array A; j i is the response capability change value of the i-th energy storage node; Preset correction evaluation value threshold D1; If d>D1, the current feedback time node generates a first-level correction instruction.

[0016] In some embodiments of the present application, the first-level correction instruction includes: Obtain real-time status parameters of each energy storage node; The response prediction model updates the expected adjustable resource table based on all real-time status parameters; Obtain the actual energy storage demand at the current feedback time node; A secondary control strategy is generated based on the updated expected adjustable resource table and actual energy storage demand.

[0017] Compared with the prior art, the user-side energy storage collaborative optimization method based on a virtual power plant in the embodiment of the present application has the following advantages: Based on virtual power plant technology, all user-side energy storage resources are aggregated, and multiple node categories are established according to different types of user-side energy storage equipment. Corresponding response sub-models are constructed based on the characteristic parameters of each node category to achieve accurate prediction of the response capabilities of all user-side energy storage nodes and improve the collaborative energy storage efficiency and collaborative control on the user side.

[0018] By establishing multi-level regulation, the expected energy storage demand is initially allocated based on the response characteristics of different node categories, and then a secondary allocation is made based on the operating status of the energy storage nodes within each node category, thereby improving the control efficiency of the user-side energy storage nodes and increasing the overall operating benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flow chart of a user-side energy storage collaborative optimization method based on a virtual power plant in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0020] The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0021] In the description of this application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application.

[0022] 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 the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this application, unless otherwise specified, "plurality" means two or more.

[0023] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0024] like Figure 1 As shown, a user-side energy storage collaborative optimization method based on a virtual power plant in a preferred embodiment of the present application includes: S101: Aggregate all user-side energy storage resources based on the virtual power plant platform and set multiple energy storage nodes based on the aggregation results; S102: Establish multiple scheduling cycles and generate expected adjustable resource parameters for each energy storage node in the current scheduling cycle based on a preset response prediction model; S103: Obtain the expected energy storage demand in the current scheduling period, and generate a primary control strategy based on all expected adjustable resource parameters and the expected energy storage demand; S104: Obtain a feedback data packet according to a preset feedback time node, and determine whether to generate a first-level correction instruction based on the feedback data packet; When setting multiple energy storage nodes, it includes: Establish energy storage node sequence A, A=(a1,a2…a i …a n), where a i is the i-th energy storage node; n is the number of energy storage nodes.

[0025] Specifically, based on virtual power plant technology, all user-side energy storage resources are aggregated to establish multiple energy storage nodes, where a single energy storage node represents a user-side energy storage device.

[0026] Specifically, the duration of the scheduling cycle is preferably 1 day.

[0027] Specifically, when presetting the response prediction model, it includes: Generate multiple equipment characteristic indicators based on all energy storage node parameters; Generate multiple node categories based on all device characteristic indicators; Establish a node category sequence B, B=(b1, b2…b i …b m ), where b i is the i-th node category; m is the number of node categories; Construct the response sub-model of each node category in turn; Establish the response sub-model series P, P=(p1, p2…p i …p m ), where p i is the response submodel of the i-th node category; A response prediction model is constructed based on the response sub-model sequence P.

[0028] Specifically, multiple device characteristic indicators are established based on different user-side energy storage device parameters, thereby constructing multiple node categories. The device characteristic indicators include but are not limited to; device category, device response time, device operation randomness and other parameters. Its single node category represents the same type of energy storage device, such as electric vehicle charging pile equipment, distributed energy storage equipment, central air-conditioning equipment, industrial and commercial load control equipment, etc.

[0029] Specifically, corresponding response submodels are established based on the characteristics of different node types. For example, a single model of a distributed energy storage device is established based on distributed energy storage parameters and PCS parameters, generating the corresponding response submodel. A single model of a charging pile is established based on its device parameters, generating the corresponding response submodel. These response submodels can perform both day-ahead and real-time assessments of the node type's responsiveness based on its characteristics.

[0030] In a preferred embodiment of the present application, when constructing the response sub-model of each node category in sequence, it includes: Set b in sequence based on the node category sequence B i is the target node category; Generate multiple perturbation feature indicators of the target node category; Construct an initial evaluation model for the target node category; Get all associated energy storage nodes of the target node category; Establishing a sequence A1 of associated energy storage nodes of the target node category; A1=(a 11 ,a 12 …a 1i …a 1n1 ), where a 1i is the i-th associated energy storage node; n1 is the number of associated energy storage nodes of the target node category; According to the number of associated energy storage nodes A1, set a 1i Associate energy storage nodes with the target; Obtain a historical operation package of the target associated energy storage node, and generate a disturbance deviation value c of the target associated energy storage node based on the historical operation package; Preset disturbance deviation threshold C1; If c>C1, generate the compensation sub-strategy of the target associated energy storage node; Determine in turn whether each associated energy storage node generates a compensation sub-strategy; A response sub-model of the target program category is generated according to all compensation sub-strategies and the initial evaluation model.

[0031] Specifically, the LightGBM ensemble algorithm is used to build the initial evaluation model for each node category.

[0032] Specifically, the initial evaluation model of the target node category is to obtain the corresponding operating curve of historical similar days based on the operating characteristics of the target node category, build a prediction baseline, and calculate the expected operating status at each moment in the current cycle through the prediction algorithm.

[0033] Specifically, the prediction baseline in the initial evaluation model is calculated as:

[0034] in, is the baseline load value of the kth period on the jth day; is the load value for the k-hour period d days before the j-th day; N is the total number of typical days. The number of typical days should be set based on the characteristics of the target node type. Typical days should be selected from several consecutive operating days before the current cycle and should be of the same type as the current cycle (weekdays or holidays). If a day is already under energy storage optimization scheduling, the previous day of the same type is selected as the typical day.

[0035] Specifically, the initial evaluation model of the target node category can also generate the response capability at each moment of the remaining time of the current cycle based on the real-time operating status and prediction baseline of the energy storage node.

[0036] Specifically, when generating the disturbance deviation value c of the target associated energy storage node, it includes: c=[ η i *(v i -v' i )]; Among them, θ1 is the number of disturbance feature indicators of the target node category; η i is the influencing factor of the i-th disturbance characteristic index in the target node category; v i is the reference value of the i-th disturbance characteristic index generated based on the historical operation package; v' i is the standard reference value of the i-th disturbance characteristic index in the target node category.

[0037] Specifically, the disturbance characteristic indicators include but are not limited to parameters such as the cumulative operating time of the equipment, the equipment failure rate, and the remaining life of the equipment. The standard reference values ​​of each disturbance characteristic value are set according to the corresponding equipment parameters (optimal operating state) when establishing a single model according to the target node category. The larger the disturbance deviation value, the greater the probability that the initial evaluation model of the current target node category will deviate when predicting the response capability of the target associated energy storage node.

[0038] Specifically, the larger the reference value of each disturbance characteristic index is, the worse the operating status of the energy storage device corresponding to the current target associated energy storage node is, and the worse the ability to coordinate energy storage response is.

[0039] Specifically, the impact factor of each disturbance deviation indicator can be set according to the degree of interference it has on the response capability prediction. The greater the interference degree, the greater the corresponding impact factor.

[0040] Specifically, the compensation sub-strategy refers to generating corresponding compensation values ​​by analyzing the evaluation differences of the target associated energy storage nodes by the initial evaluation model, and correcting the original prediction results by using the compensation values.

[0041] It can be understood that in the above embodiment, all user-side energy storage resources are aggregated based on virtual power plant technology, and multiple node categories are established according to different types of user-side energy storage equipment. Corresponding response sub-models are constructed based on the characteristic parameters of each node category to achieve accurate prediction of the response capabilities of all user-side energy storage nodes, thereby improving the collaborative energy storage efficiency and collaborative control on the user side.

[0042] In a preferred embodiment of the present application, when generating the expected adjustable resource parameters of each energy storage node in the current scheduling period, it includes: Set the first prediction time node of the current scheduling period; The response prediction model generates response capability parameters of each energy storage node at the first prediction time node; Generate a responsiveness sub-table for each node category based on all responsiveness parameters; Generate an expected adjustable resource table for the current scheduling period based on all response capability sub-tables.

[0043] Specifically, the first prediction time node is set based on the day-ahead prediction principle, generally within the first 24 to 72 hours of the start of the current regulation cycle. The status of each energy storage node within the current regulation cycle is predicted in advance.

[0044] Specifically, the response prediction model estimates the expected operating status of a single energy storage node at each moment in the current scheduling cycle, generating the node's response capability parameters. These parameters include the energy storage's day-ahead peak shaving response capability, the energy storage's day-ahead valley filling response capability, and the energy storage's real-time peak shaving and valley filling capabilities. Each capability includes dispatchable duration and dispatchable power.

[0045] Specifically, when generating a first-level control strategy, it includes: Generate expected energy storage demand based on expected grid fluctuation parameters; Generate a first-level allocation strategy based on the expected energy storage demand and the response capability sub-table of each node category; Generate energy storage sub-demands for each node category based on the first-level allocation strategy; Generate the secondary allocation strategy for each node category in turn; Generate a first-level control strategy based on all second-level allocation strategies.

[0046] Specifically, by integrating all resources within a single node category, a corresponding response capability sub-table is generated. Based on optimization principles and the actual response characteristics of each node category, an initial allocation of expected energy storage demand is performed, generating a corresponding primary allocation strategy. Secondary allocation is then performed based on the operating status of the energy storage nodes within each node category, improving the control efficiency of user-side energy storage nodes and increasing overall operational benefits.

[0047] Specifically, the operating parameters of each energy storage node are set according to the allocation results, and a first-level control strategy is generated based on all the operating parameters.

[0048] In a preferred embodiment of the present application, generating a secondary allocation strategy for each node category includes: Set b in sequence according to the node category sequence B i is the node category to be assigned; Establish the associated energy storage node sequence A2 of the node category to be allocated; A2=(a21 ,a 22 …a 2i …a 2n2 ), where a 2i is the i-th associated energy storage node of the node category to be allocated; n2 is the number of associated energy storage nodes of the node category to be allocated; Generate a response evaluation value of each associated energy storage node in the associated energy storage node sequence A2; Generate a response scheduling order for the node categories to be assigned based on all response evaluation values; Obtain the energy storage sub-demand of the node category to be allocated; A secondary allocation strategy for the node category to be allocated is generated based on the response scheduling order and energy storage sub-demand.

[0049] Specifically, the larger the response evaluation value, the higher the collaborative energy storage efficiency of the corresponding associated energy storage node, and it should be selected first to share the energy storage sub-demand required by the node category to be assigned. This improves the collaborative energy storage scheduling efficiency within a single node category.

[0050] Specifically, when generating the response evaluation value of each associated energy storage node in the associated energy storage node sequence A2, it includes: According to the number of associated energy storage nodes A2, set a 2i is the associated energy storage node to be evaluated; Generate a response evaluation value f of the associated energy storage node to be evaluated; f=e1*Q1*c'+e2*Q2*[ β i *s i ]; Among them, e1 is the preset first fixed coefficient; e2 is the preset second fixed coefficient; Q1 is the preset first weight coefficient; Q2 is the preset second fixed coefficient; c' is the disturbance deviation value of the associated energy storage node to be evaluated; θ2 is the number of response resource indicators; β i is the impact factor of the i-th response resource indicator; s i is the reference value of the i-th response resource indicator of the associated energy storage node to be evaluated.

[0051] Specifically, the response resource indicators include but are not limited to parameters such as the callable duration and the dispatchable power. The larger the reference value of each response resource indicator, the stronger the response capability of the current associated energy storage node to be evaluated and the higher the operating efficiency of the equipment.

[0052] Specifically, by presetting a first fixed coefficient, the disturbance deviation value c' of the associated energy storage node to be evaluated is processed so that the larger the value of c' is, the larger the corresponding response evaluation value f is.

[0053] Specifically, all parameters in the model are processed by presetting the first fixed coefficient and the second fixed coefficient, so that each parameter in the model is in the same value range.

[0054] In a preferred embodiment of the present application, when determining whether to generate a first-level correction instruction based on a feedback data packet, the method includes: Preset multiple feedback time nodes; Get the feedback data packet of the current feedback time node; Generates a revised evaluation value d of the current feedback time node based on the feedback data packet; d=e3*Q3*[ λ i *k i ]+e4*Q4*[ r i *j i ]; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; is the energy storage demand indicator quantity; i is the influencing factor of the i-th energy storage demand index; k i is the fluctuation value of the i-th energy storage demand; r i is the impact factor of the i-th energy storage node in the energy storage node array A; j i is the response capability change value of the i-th energy storage node; Preset correction evaluation value threshold D1; If d>D1, the current feedback time node generates a first-level correction instruction.

[0055] Specifically, the energy storage demand indicators include but are not limited to various parameters that affect power generation efficiency, such as changes in light intensity that affect photovoltaic power generation, temperature, and changes in wind speed that affect wind power. The change value of each energy storage demand indicator is set based on the difference between the reference value when generating the expected energy storage demand and the real-time reference value at the current feedback time node. The larger the difference, the greater the corresponding fluctuation value.

[0056] Specifically, the change value of the response capability of each energy storage node is set according to the difference between its real-time response capability and the parameters in the expected adjustable resource table. The greater the difference, the greater the corresponding change value.

[0057] Specifically, the correction evaluation value threshold can be set according to historical parameters. When the real-time correction evaluation value is greater than the preset correction evaluation value threshold, it means that the current first-level control strategy cannot complete the current energy storage coordination and scheduling task, and needs to be corrected in time to ensure the collaborative energy storage efficiency and collaborative control efficiency on the user side.

[0058] Specifically, all parameters in the model are normalized by presetting the third fixed coefficient and the fourth fixed coefficient, so that each parameter in the model is in the same value range.

[0059] Specifically, the first-level correction instructions include: Obtain real-time status parameters of each energy storage node; The response prediction model updates the expected adjustable resource table based on all real-time status parameters; Obtain the actual energy storage demand at the current feedback time node; A secondary control strategy is generated based on the updated expected adjustable resource table and actual energy storage demand.

[0060] Specifically, the response prediction model generates the response capacity at each moment of the remaining time of the current cycle based on the real-time operating status of the energy storage node and the prediction baseline. The updated expected adjustable resource table includes the response capacity parameters of each energy storage node in the remaining time of the current scheduling cycle.

[0061] Specifically, the generation method of the secondary control strategy is the same as that of the primary control strategy, which is a secondary allocation method.

[0062] It is understandable that in the above embodiment, by establishing multiple feedback time nodes, timely warnings are issued for energy storage fluctuations within the current scheduling cycle, and corresponding control strategies are adjusted to ensure collaborative energy storage efficiency and collaborative control efficiency on the user side.

[0063] According to the first concept of the present application, all user-side energy storage resources are aggregated based on virtual power plant technology, and multiple node categories are established according to different types of user-side energy storage equipment. Corresponding response sub-models are constructed according to the characteristic parameters of each node category to achieve accurate prediction of the response capabilities of all energy storage nodes on the user side, thereby improving the collaborative energy storage efficiency and collaborative control on the user side.

[0064] According to the second concept of the present application, by establishing multi-level regulation, the expected energy storage demand is first allocated according to the response characteristics of different node categories, and then a secondary allocation is made according to the operating status of the energy storage nodes within each node category, thereby improving the control efficiency of the user-side energy storage nodes and improving the overall operating benefits.

[0065] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and replacements can be made without departing from the technical principles of the present application. These improvements and replacements should also be regarded as the scope of protection of the present application.

Claims

1. A user-side energy storage collaborative optimization method based on a virtual power plant, characterized in that: include: Aggregate all user-side energy storage resources based on the virtual power plant platform and set multiple energy storage nodes based on the aggregation results; Establish multiple scheduling cycles and generate the expected adjustable resource parameters of each energy storage node in the current scheduling cycle based on the preset response prediction model; Obtain the expected energy storage demand for the current scheduling cycle and generate a primary control strategy based on all expected adjustable resource parameters and the expected energy storage demand; Obtaining a feedback data packet according to a preset feedback time node, and determining whether to generate a first-level correction instruction based on the feedback data packet; When setting multiple energy storage nodes, it includes: Establish energy storage node sequence A, A=(a1,a2…a i …a n ), where a i is the i-th energy storage node; n is the number of energy storage nodes.

2. The user-side energy storage collaborative optimization method based on a virtual power plant according to claim 1, characterized in that: When pre-setting the response prediction model, include: Generate multiple equipment characteristic indicators based on all energy storage node parameters; Generate multiple node categories based on all device characteristic indicators; Establish a node category sequence B, B=(b1, b2…b i …b m ), where b i is the i-th node category; m is the number of node categories; Construct the response sub-model of each node category in turn; Establish the response sub-model series P, P=(p1, p2…p i …p m ), where p i is the response submodel of the i-th node category; A response prediction model is constructed based on the response sub-model sequence P.

3. The user-side energy storage collaborative optimization method based on a virtual power plant according to claim 2, characterized in that: The step of sequentially constructing the response sub-models for each node category includes: Set b in sequence based on the node category sequence B i is the target node category; Generate multiple perturbation feature indicators of the target node category; Construct an initial evaluation model for the target node category; Get all associated energy storage nodes of the target node category; Establishing a sequence A1 of associated energy storage nodes of the target node category; A1=(a 11 ,a 12 …a 1i …a 1n1 ), where a 1i is the i-th associated energy storage node; n1 is the number of associated energy storage nodes of the target node category; According to the number of associated energy storage nodes A1, set a 1i Associate energy storage nodes with the target; Obtain a historical operation package of the target associated energy storage node, and generate a disturbance deviation value c of the target associated energy storage node based on the historical operation package; Preset disturbance deviation threshold C1; If c>C1, generate the compensation sub-strategy of the target associated energy storage node; Determine in turn whether each associated energy storage node generates a compensation sub-strategy; A response sub-model of the target program category is generated according to all compensation sub-strategies and the initial evaluation model.

4. The user-side energy storage collaborative optimization method based on a virtual power plant according to claim 3, characterized in that: When generating the disturbance deviation value c of the target associated energy storage node, it includes: c=[ η i *(v i -v' i )]; Among them, θ1 is the number of disturbance feature indicators of the target node category; η i is the influencing factor of the i-th disturbance characteristic index in the target node category; v i is the reference value of the i-th disturbance characteristic index generated based on the historical operation package; v' i is the standard reference value of the i-th disturbance characteristic index in the target node category.

5. The user-side energy storage collaborative optimization method based on a virtual power plant according to claim 3 is characterized in that: When generating the expected adjustable resource parameters of each energy storage node in the current scheduling cycle, it includes: Set the first prediction time node of the current scheduling period; The response prediction model generates response capability parameters of each energy storage node at the first prediction time node; Generate a responsiveness sub-table for each node category based on all responsiveness parameters; Generate an expected adjustable resource table for the current scheduling period based on all response capability sub-tables.

6. The user-side energy storage collaborative optimization method based on a virtual power plant according to claim 5, characterized in that: When generating a primary control strategy, include: Generate expected energy storage demand based on expected grid fluctuation parameters; Generate a first-level allocation strategy based on the expected energy storage demand and the response capability sub-table of each node category; Generate energy storage sub-demands for each node category based on the first-level allocation strategy; Generate the secondary allocation strategy for each node category in turn; Generate a first-level control strategy based on all second-level allocation strategies.

7. The user-side energy storage collaborative optimization method based on a virtual power plant according to claim 6, characterized in that: When generating the secondary allocation strategy for each node category, it includes: Set b in sequence according to the node category sequence B i is the node category to be assigned; Establish the associated energy storage node sequence A2 of the node category to be allocated; A2=(a 21 ,a 22 …a 2i …a 2n2 ), where a 2i is the i-th associated energy storage node of the node category to be allocated; n2 is the number of associated energy storage nodes of the node category to be allocated; Generate a response evaluation value of each associated energy storage node in the associated energy storage node sequence A2; Generate a response scheduling order for the node categories to be assigned based on all response evaluation values; Obtain the energy storage sub-demand of the node category to be allocated; A secondary allocation strategy for the node category to be allocated is generated based on the response scheduling order and energy storage sub-demand.

8. The user-side energy storage collaborative optimization method based on a virtual power plant according to claim 7, characterized in that: When generating the response evaluation value of each associated energy storage node in the associated energy storage node sequence A2, it includes: According to the number of associated energy storage nodes A2, set a 2i is the associated energy storage node to be evaluated; Generate a response evaluation value f of the associated energy storage node to be evaluated; f=e1*Q1*c'+e2*Q2*[ β i *s i ]; Among them, e1 is the preset first fixed coefficient; e2 is the preset second fixed coefficient; Q1 is the preset first weight coefficient; Q2 is the preset second fixed coefficient; c' is the disturbance deviation value of the associated energy storage node to be evaluated; θ2 is the number of response resource indicators; β i is the impact factor of the i-th response resource indicator; s i is the reference value of the i-th response resource indicator of the associated energy storage node to be evaluated.

9. The user-side energy storage collaborative optimization method based on a virtual power plant according to claim 7, characterized in that: When determining whether to generate a first-level correction instruction based on the feedback data packet, it includes: Preset multiple feedback time nodes; Get the feedback data packet of the current feedback time node; Generates a revised evaluation value d of the current feedback time node based on the feedback data packet; d=e3*Q3*[ λ i *k i ]+e4*Q4*[ r i *j i ]; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; is the energy storage demand indicator quantity; i is the influencing factor of the i-th energy storage demand index; k i is the fluctuation value of the i-th energy storage demand; r i is the impact factor of the i-th energy storage node in the energy storage node array A; j i is the response capability change value of the i-th energy storage node; Preset correction evaluation value threshold D1; If d>D1, the current feedback time node generates a first-level correction instruction.

10. The user-side energy storage collaborative optimization method based on a virtual power plant according to claim 9, characterized in that: The first-level correction instructions include: Obtain real-time status parameters of each energy storage node; The response prediction model updates the expected adjustable resource table based on all real-time status parameters; Obtain the actual energy storage demand at the current feedback time node; A secondary control strategy is generated based on the updated expected adjustable resource table and actual energy storage demand.

Images