CN-122000923-A - Micro-grid carbon footprint scheduling method, micro-grid carbon footprint scheduling system, electronic equipment and medium of port exchange station

CN122000923ACN 122000923 ACN122000923 ACN 122000923ACN-122000923-A

Abstract

The invention relates to the technical field of power system automation, in particular to a micro-grid carbon footprint scheduling method, a micro-grid carbon footprint scheduling system, electronic equipment and a micro-grid carbon footprint scheduling medium for a port power exchange station. The method comprises the steps of firstly obtaining multisource operation data of a micro-grid of a port battery substation, sequentially executing physical consistency processing on the multisource operation data to obtain trusted data, executing photovoltaic output prediction and load power prediction based on the trusted data to obtain a predicted power value and an uncertainty parameter, calculating to obtain a dynamic carbon footprint parameter according to the predicted power value and the uncertainty parameter, and generating a multi-target cooperative scheduling instruction of the micro-grid of the port battery substation according to the predicted power value, the dynamic carbon footprint parameter and a set constraint condition. By the method, the problem that the existing scheduling strategy is easy to conflict with an environmental protection target in real-time application is solved, and scheduling accuracy and carbon economy of the port exchange station micro-grid under a complex operating environment are improved.

Inventors

YANG JUNJIA
ZHANG YIHONG
FENG HAO
ZHOU JINGYU
Zang Yizhi
ZHANG TAO

Assignees

国网浙江省电力有限公司经济技术研究院
国网浙江省电力有限公司

Dates

Publication Date: 20260508
Application Date: 20260410

Claims (13)

1. A micro-grid carbon footprint scheduling method of a port exchange station is characterized by comprising the following steps: acquiring multisource operation data of the port exchange station micro-grid; Performing physical consistency processing of time mark alignment, outlier rejection and data correction on the multi-source operation data in sequence to obtain trusted data; performing photovoltaic output prediction and load power prediction based on the trusted data to obtain a predicted power value and an uncertainty parameter; calculating to obtain a dynamic carbon footprint parameter according to the predicted power value and the uncertainty parameter; And generating a multi-target cooperative scheduling instruction of the port substation micro-grid according to the predicted power value, the dynamic carbon footprint parameter and a set constraint condition, wherein the set constraint condition comprises a power conservation constraint, a carbon risk constraint and an equipment health constraint.
2. The method of claim 1, wherein the obtaining multi-source operational data of the harbour substation micro grid comprises: Collecting environment monitoring data through an environment sensor network deployed at the port power exchange station; Collecting equipment operation state data through an equipment monitoring system of the port power exchange station; collecting electric quantity behavior data through an electric energy metering device; Collecting operation behavior data through an event recording device; And regularly storing the collected environment monitoring data, the equipment running state data, the electric quantity behavior data and the running behavior data according to a unified time scale format to form the multi-source running data.
3. The method according to claim 2, wherein the performing physical consistency processing of time-scale alignment, outlier rejection, and data correction on the multi-source operation data sequentially, to obtain trusted data, includes: Synchronizing and aligning the time stamps of all data channels in the multi-source operation data based on a preset reference event set; removing abnormal values in the aligned multi-source operation data by applying a preset abnormal detection rule, and performing interpolation processing on the missing data; performing sensor drift correction and data cross-correlation fusion on the multisource operation data with the outliers removed to correct measurement deviation; and performing energy conservation adjustment on the corrected multi-source operation data to obtain the trusted data.
4. A method according to claim 3, wherein said performing photovoltaic output prediction and load power prediction based on said trusted data results in predicted power values and uncertainty parameters, comprising: Extracting load tide cycle characteristics and photovoltaic output disturbance characteristics from the trusted data; Fusing the load tide cycle characteristic, the photovoltaic output disturbance characteristic with environment monitoring data, equipment running state data and running behavior data in the trusted data to construct a multi-dimensional characteristic vector, and carrying out standardized processing on the multi-dimensional characteristic vector; carrying out joint prediction on the photovoltaic output and the load power of the normalized multidimensional feature vector through a preset time sequence prediction model, and outputting the predicted power value; Calculating a prediction residual error based on a comparison result between the prediction power value and a true value in the trusted data; And generating the uncertainty parameter according to the prediction residual.
5. The method of claim 4, wherein the calculating a dynamic carbon footprint parameter from the predicted power value and the uncertainty parameter comprises: Decomposing a source load energy supply path in the predicted power value according to a preset energy conservation relation, and calculating to obtain energy supply share of each energy source; according to the energy supply share and a preset marginal carbon factor, calculating to obtain an initial carbon footprint parameter; Performing sensitivity correction on the initial carbon footprint parameters according to the uncertainty parameters to obtain corrected carbon footprint point values; converting the uncertainty parameters into carbon footprint confidence intervals by a statistical conduction method; And carrying out engineering constraint projection processing on the corrected carbon footprint point value and the carbon footprint confidence interval to obtain the dynamic carbon footprint parameter.
6. The method of claim 5, wherein the generating the multi-objective co-scheduling instructions for the harbour substation micro grid based on the predicted power values, the dynamic carbon footprint parameters, and the set constraints comprises: constructing a decision vector comprising energy storage charge-discharge power, power grid interaction power and load control parameters; Based on the decision vector, the predicted power value and the dynamic carbon footprint parameter, aiming at electric energy balance, carbon bank control and equipment operation, constructing a multi-objective optimization function; establishing a constraint condition set according to the set constraint conditions; Solving the multi-objective optimization function under the constraint condition set by adopting a preset optimization algorithm to obtain an optimized scheduling solution; and generating an executable scheduling instruction at the current moment according to the optimized scheduling solution, and transmitting the scheduling instruction to corresponding execution equipment in the port substation micro-grid.
7. The method of claim 6, wherein prior to generating the multi-objective co-scheduling instructions for the port substation micro grid, the method further comprises: Setting the power conservation constraint according to the power balance relation between the energy supply side and the energy utilization side of the micro-grid; setting the carbon risk constraint according to the dynamic carbon footprint parameter and a preset carbon risk upper limit value; Setting the equipment health constraint according to the state of charge boundary of the energy storage system, the battery temperature rise limit and the equipment health degradation requirement; And constructing the constraint condition by the set power conservation constraint, the carbon risk constraint and the equipment health constraint.
8. A micro-grid carbon footprint scheduling system of a port replacement station, comprising: The multi-source operation data acquisition module is used for acquiring multi-source operation data of the port exchange station micro-grid; the trusted data generation module is used for sequentially executing physical consistency processing of time mark alignment, outlier rejection and data correction on the multi-source operation data to obtain trusted data; The power and uncertainty prediction module is used for performing photovoltaic output prediction and load power prediction based on the trusted data to obtain a predicted power value and uncertainty parameters; the dynamic carbon footprint parameter generation module is used for calculating and obtaining dynamic carbon footprint parameters according to the predicted power value and the uncertainty parameter; And the collaborative scheduling instruction generation module is used for generating a multi-target collaborative scheduling instruction of the port exchange station micro-grid according to the predicted power value, the dynamic carbon footprint parameter and a set constraint condition, wherein the set constraint condition comprises a power conservation constraint, a carbon risk constraint and an equipment health constraint.
9. The micro-grid carbon footprint scheduling system of a port substation of claim 8, wherein the power and uncertainty prediction module is further configured to extract load tidal cycle characteristics and photovoltaic output disturbance characteristics from the trusted data; Fusing the load tide cycle characteristic, the photovoltaic output disturbance characteristic with environment monitoring data, equipment running state data and running behavior data in the trusted data to construct a multi-dimensional characteristic vector, and carrying out standardized processing on the multi-dimensional characteristic vector; carrying out joint prediction on the photovoltaic output and the load power of the normalized multidimensional feature vector through a preset time sequence prediction model, and outputting the predicted power value; Calculating a prediction residual error based on a comparison result between the prediction power value and a true value in the trusted data; And generating the uncertainty parameter according to the prediction residual.
10. The micro-grid carbon footprint scheduling system of a port substation according to claim 9, wherein the dynamic carbon footprint parameter generating module is further configured to decompose a source load energy supply path in the predicted power value according to a preset energy conservation relationship, and calculate energy supply shares of each energy source; according to the energy supply share and a preset marginal carbon factor, calculating to obtain an initial carbon footprint parameter; Performing sensitivity correction on the initial carbon footprint parameters according to the uncertainty parameters to obtain corrected carbon footprint point values; converting the uncertainty parameters into carbon footprint confidence intervals by a statistical conduction method; And carrying out engineering constraint projection processing on the corrected carbon footprint point value and the carbon footprint confidence interval to obtain the dynamic carbon footprint parameter.
11. The micro-grid carbon footprint scheduling system of a port substation according to claim 9, wherein the co-scheduling instruction generating module is further configured to construct a decision vector including energy storage charging and discharging power, grid interaction power and load control parameters; Based on the decision vector, the predicted power value and the dynamic carbon footprint parameter, aiming at electric energy balance, carbon bank control and equipment operation, constructing a multi-objective optimization function; establishing a constraint condition set according to the set constraint conditions; Solving the multi-objective optimization function under the constraint condition set by adopting a preset optimization algorithm to obtain an optimized scheduling solution; and generating an executable scheduling instruction at the current moment according to the optimized scheduling solution, and transmitting the scheduling instruction to corresponding execution equipment in the port substation micro-grid.
12. An electronic device, comprising: and a memory communicatively coupled to the at least one processor; Wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.
13. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1-7.

Description

Micro-grid carbon footprint scheduling method, micro-grid carbon footprint scheduling system, electronic equipment and medium of port exchange station Technical Field The invention relates to the technical field of power system automation, in particular to a micro-grid carbon footprint scheduling method, a micro-grid carbon footprint scheduling system, electronic equipment and a micro-grid carbon footprint scheduling medium for a port power exchange station. Background Along with the rapid development of new energy automobile industry, the micro-grid of the charging and replacing station is used as an important component part of the optical storage, charging and replacing integrated system, and plays a key role in improving the energy utilization efficiency and reducing the operation cost. The micro-grid of the charging and replacing station is usually connected with a power distribution network through a distribution transformer and is integrated into a distributed photovoltaic device, an energy storage device and a replacing load, and the dispatching optimization of the micro-grid directly affects the economical efficiency and the stability of the system. However, the source load resource of the micro-grid of the charging and replacing station has high uncertainty (such as that the photovoltaic output is influenced by weather fluctuation, the replacing load changes along with the arrival law of a vehicle), the dispatching process needs to take account of the constraint of the grid, the service life of equipment and the environmental protection requirement, and the traditional economic dispatching method is difficult to realize dynamic optimization under multiple targets. In the prior art, resource aggregation and scheduling optimization focuses on an economic target, and power distribution is performed through a fixed strategy or a static model. For example, the prior art (application publication number CN118966720 a) discloses a method and a system for optimizing economic dispatch of a micro-grid of a charging and replacing station, which aims at minimizing charging cost and photovoltaic reverse delivery punishment cost, constructs operation constraint conditions of a grid-connected transformer, an energy storage and replacing station, and solves a dispatch plan based on source charge power prediction. The method improves economy through an optimization algorithm, but has the limitations that firstly, dynamic characteristics of source load uncertainty (such as light Fu Fuzhao salt spray drift and load tide fluctuation) are not fully considered, prediction deviation possibly causes disjoint of a scheduling instruction and actual operation, deviation assessment risk is increased, secondly, the scheduling model only takes economic cost as a core, environmental constraints such as a carbon footprint factor and the like are not introduced, compliance cost is possibly increased due to carbon risk overrun, and thirdly, punishment cost (such as photovoltaic pouring) is simplified into fixed parameters, and is not coupled with market signals or real-time carbon intensity, so that self-adaptive adjustment capability for an uncertainty scene is lacked. Therefore, the prior art is difficult to realize the balance between the high efficiency and the compliance of the micro-grid dispatching of the charging and replacing station under the complex market and environment fluctuation, and especially lacks of deep modeling on source load uncertainty, dynamic association of carbon footprint and multi-target cooperation, so that the problem that economic benefit and environmental protection targets are easy to conflict in the real-time application of a dispatching strategy is caused. Disclosure of Invention Aiming at the defects or shortcomings, the invention provides a micro-grid carbon footprint scheduling method, a micro-grid carbon footprint scheduling system, electronic equipment and a micro-grid carbon footprint scheduling medium for a port exchange station, which can solve the problem that the existing scheduling strategy is easy to conflict with an environmental protection target in real-time application. The invention provides a micro-grid carbon footprint scheduling method of a port power exchange station, which comprises the following steps: and acquiring multisource operation data of the micro-grid of the port power exchange station. And sequentially executing physical consistency processing of time mark alignment, outlier rejection and data correction on the multi-source operation data to obtain the trusted data. And performing photovoltaic output prediction and load power prediction based on the trusted data to obtain a predicted power value and an uncertainty parameter. And calculating the dynamic carbon footprint parameter according to the predicted power value and the uncertainty parameter. And generating a multi-target cooperative scheduling instruction of the micro-grid of the port exchange station accordi