CN-115936362-B - Area scheduling method and device based on differentiated edge demand and storage medium

CN115936362BCN 115936362 BCN115936362 BCN 115936362BCN-115936362-B

Abstract

The embodiment of the specification provides a platform area scheduling method, device and storage medium based on differentiated edge requirements, wherein the method comprises the steps of obtaining load requirement information of a power utilization user and a differentiated price type response model of the power utilization user, inputting the load requirement information and the differentiated price type response model into a price-requirement prediction model trained in advance to obtain price-requirement relation data, and determining a scheduling strategy of a platform area according to the price-requirement relation data, preset constraint conditions and preset platform area cost. The technical scheme provided by the application is used for solving the problem that the electric quantity variation and the electric price variation are set to be in a linear relation in the prior art, so that the expected effect of the platform area dispatching is still difficult to achieve.

Inventors

JIA DEXIANG
FU CHENGCHENG
LIU JIANYE
Yin Guanting
HUANG HE
WANG JING
ZHANG CEN
DENG YUAN
CHEN GUOXIANG
Feng Yemu
GAO FAN
CHEN GUANG
MENG SHANSHAN
GAO XIAONAN
LI XINDA
ZHOU YU
LV GANYUN
WANG ZHONGDONG
GAO JIAN
ZHANG DONG
ZHANG XUE
XUE XINRAN

Assignees

国网能源研究院有限公司
国网江苏省电力有限公司营销服务中心

Dates

Publication Date: 20260505
Application Date: 20221205

Claims (7)

1. The platform area scheduling method based on the differentiated edge requirements is characterized by comprising the following steps of: acquiring load demand information of a power utilization user and a differentiated price type response model of the power utilization user; inputting the load demand information and the differentiated price type response model into a pre-trained price-demand prediction model to obtain price-demand relation data; Determining a dispatching strategy of the platform according to the price-demand relation data, the preset constraint condition and the preset platform cost; the determining a dispatching strategy of the platform area according to the price-demand relation data, the preset constraint condition and the preset platform area operation cost comprises the following steps: Determining the electricity purchasing cost of the platform area according to the price-demand relation data; Determining an objective function according to the electricity purchasing cost and the platform region running cost; Determining the minimum value of the dispatching total cost of the station area according to the constraint condition and the objective function; determining a scheduling strategy of the station area according to the minimum value of the total scheduling cost; The load demand information comprises load type and real-time electricity price data; The obtaining the load demand information of the electricity user comprises the following steps: acquiring the load type and the real-time electricity price data corresponding to the electricity utilization user; The load demand information also includes user satisfaction; The obtaining the load demand information of the electricity user comprises the following steps: obtaining the user satisfaction according to the following formula; Wherein, the Is the electricity satisfaction; 、 Respectively is Load amount and load transfer amount before time period demand response; For the scheduling period.
2. The method of claim 1, wherein the step of determining the position of the substrate comprises, The load type comprises one or more of resident electric loads, industrial electric loads and electric automobile charging pile electric loads; The method for obtaining the differentiated price type response model of the electricity utilization user comprises the following steps: acquiring the ratio of the load of each load type to the total load of the platform area and the electric quantity and electricity price requirement balance relation data corresponding to each load type; And respectively determining a differentiated price type response model corresponding to each load type according to the ratio of the load of each load type to the total load of the platform area and the electric quantity and electricity price requirement balance relation data corresponding to each load type.
3. The method of claim 1, wherein the step of determining the position of the substrate comprises, The area comprises a plurality of edge computing nodes; the step of inputting the load demand information and the differentiated price type response model into a preset price-demand prediction model to obtain price-demand relation data, comprising the following steps: Acquiring response behavior data of users of the edge computing nodes to price changes; Classifying each edge computing node according to each response behavior data to obtain a node cluster; Respectively calculating price-demand relation data of each node cluster; and obtaining the price-demand relation data of the platform area based on the price-demand relation data of each node cluster.
4. The method of claim 1, wherein the step of determining the position of the substrate comprises, The platform region operation cost comprises one or more of operation maintenance cost, carbon treatment cost, satisfaction loss cost and photovoltaic electricity selling income; The objective function is specifically: Wherein, the Scheduling a total cost for the region; Optimizing a scheduling period for the day before; The electricity purchasing cost is realized; The operation and maintenance cost is; is the carbon treatment cost; cost is lost for satisfaction; And the method is used for photovoltaic electricity selling benefits.
5. The method of claim 1, wherein the step of determining the position of the substrate comprises, The constraint conditions comprise one or more of power balance constraint, platform region admittance capability constraint, access point voltage out-of-limit constraint, photovoltaic inverter capacity constraint, storage battery charge and discharge constraint, platform region carbon emission constraint, power grid interaction power constraint and user satisfaction constraint; The power balance constraint is: Is that Time period photovoltaic power generation; 、 Respectively is as follows The charge and discharge power of the storage battery in the period; the zone admission capacity constraint is: Maximum capacity for low voltage area to photovoltaic; The access point voltage out-of-limit constraint is: 、 the upper and lower voltage limits are respectively set; 、 the power-voltage sensitivity coefficients corresponding to the purchase power and the photovoltaic power generation power are respectively set; the photovoltaic inverter capacity constraint is: Rated capacity of the photovoltaic inverter; The storage battery charge-discharge constraint is as follows: 、 the maximum charge and discharge power of the storage battery are respectively; in the accumulator The state of charge of the time period; 、 The maximum and minimum charge states of the storage battery are respectively; Is the rated capacity of the storage battery; 、 The charge and discharge rates of the storage battery are respectively; The district carbon emission constraint is: Is that Carbon emission of the time zone; maximum allowable carbon emission for a bay; the power grid interaction power constraint is as follows: 、 Respectively the maximum value and the minimum value of the power purchase power; 、 The maximum value and the minimum value of the electric power are respectively; the user satisfaction constraint is: Is the lowest electricity satisfaction.
6. The platform area scheduling device based on the differentiated edge demand is characterized by comprising an acquisition module and a data processing module; The acquisition module is used for acquiring load demand information of the electricity utilization user and a differentiated price type response model of the electricity utilization user; the data processing module is used for inputting the load demand information and the differentiated price type response model into a preset price-demand prediction model to obtain price-demand relation data; the determining a dispatching strategy of the platform area according to the price-demand relation data, the preset constraint condition and the preset platform area operation cost comprises the following steps: Determining the electricity purchasing cost of the platform area according to the price-demand relation data; Determining an objective function according to the electricity purchasing cost and the platform region running cost; Determining the minimum value of the dispatching total cost of the station area according to the constraint condition and the objective function; determining a scheduling strategy of the station area according to the minimum value of the total scheduling cost; The load demand information comprises load type and real-time electricity price data; The obtaining the load demand information of the electricity user comprises the following steps: acquiring the load type and the real-time electricity price data corresponding to the electricity utilization user; The load demand information also includes user satisfaction; The obtaining the load demand information of the electricity user comprises the following steps: obtaining the user satisfaction according to the following formula; Wherein, the Is the electricity satisfaction; 、 Respectively is Load amount and load transfer amount before time period demand response; For the scheduling period.
7. A storage medium, comprising: For storing computer-executable instructions which, when executed, implement the method of any of claims 1-5.

Description

Area scheduling method and device based on differentiated edge demand and storage medium Technical Field The present document relates to the field of user marketing, and in particular, to a method, an apparatus, and a storage medium for scheduling a platform area based on differentiated edge requirements. Background The demand side response (Demand Respnose, DR) is an important means for stabilizing the output of the distributed power supply and improving the new energy consumption rate, and the influence caused by the demand side response needs to be fully considered in the optimizing and dispatching of the station area. Some scholars have studied the demand response characteristics of the area. Dan Wen is superior to building a user DR model based on an elastic coefficient matrix of real-time electricity price, meanwhile, analyzing charging load demands of an electric automobile, building an active distribution network robust optimal scheduling model, liu Jinyuan and the like propose an active distribution network double-layer collaborative configuration model for taking demand response into account, exciting electric automobile charging and discharging so as to reduce peak-valley difference of loads, adapting to various planning demands of EV charging stations, jinpeng and the like apply evaluation of running states of distribution network areas based on fuzzy comprehensive judgment to excitation type demand response, realize comprehensive optimization of voltage and load of the distribution network areas while reducing peak load, zhu Chaoting and the like consider user participation of the demand response, build an active distribution network optimal scheduling model based on price type and excitation type demand response, fully play the flexibility of demand response, gefei and the like to describe uncertainty of demand response by using triangular fuzzy numbers, build a distribution network master-slave game economic model with minimum user and maximum wind power consumption as targets, and achieve game balance by optimizing real-time electricity price strategies and demand response strategies. However, the existing related studies set the amount of power change and the amount of power price change to a linear relationship in the modeling process, which does not conform to the actual situation, thus resulting in that the response resources cannot be fully utilized and that the area scheduling still has difficulty in achieving the expected effect. Disclosure of Invention In view of the above analysis, the present application aims to provide a method, an apparatus and a storage medium for dispatching a platform area based on differentiated edge requirements, so that the electric quantity variation and the electric price variation more conform to the actual situation. In a first aspect, one or more embodiments of the present disclosure provide a method for scheduling a region based on differentiated edge requirements, including: acquiring load demand information of a power utilization user and a differentiated price type response model of the power utilization user; inputting the load demand information and the differentiated price type response model into a pre-trained price-demand prediction model to obtain price-demand relation data; and determining a dispatching strategy of the station area according to the price-demand relation data, the preset constraint condition and the preset station area cost. Further, the load demand information includes load type and real-time electricity price data; The obtaining the load demand information of the electricity user comprises the following steps: and acquiring the load type and the real-time electricity price data corresponding to the electricity utilization user. Further, the load demand information further includes user satisfaction; The obtaining the load demand information of the electricity user comprises the following steps: obtaining the user satisfaction according to the following formula; Wherein, the Is the electricity satisfaction;、 Respectively is Load amount and load transfer amount before time period demand response; For the scheduling period. Further, the load type comprises one or more of a resident electric load, an industrial electric load and an electric vehicle charging pile electric load; The method for obtaining the differentiated price type response model of the electricity utilization user comprises the following steps: acquiring the ratio of the load of each load type to the total load of the platform area and the electric quantity and electricity price requirement balance relation data corresponding to each load type; And respectively determining a differentiated price type response model corresponding to each load type according to the ratio of the load of each load type to the total load of the platform area and the electric quantity and electricity price requirement balance relation data corresponding to each load type. Further, t