Energy station management method and system based on GIS

Abstract

The invention relates to a GIS-based energy station management method and system, and belongs to the technical field of energy station management. The method comprises the following steps: acquiring energy station position information, an energy station operation state, weather data and building position information through a GIS (Geographic Information System); obtaining a building envelope, and obtaining building cooling and heating load data through a cooling and heating energy load calculation model according to the weather data and the building envelope; obtaining historical building electrical load data, and obtaining building electrical load data through the electrical energy load prediction model according to the historical building electrical load data; and obtaining an energy scheduling decision through an energy scheduling model according to the energy station position information, the energy station operation state, the building position information, the building cooling and heating load data and the building electrical load data. Energy station management based on the GIS is realized, and the energy utilization efficiency is improved.

Description

Technical Field

[0001] This invention belongs to the field of energy station management technology, specifically relating to a GIS-based energy station management method and system. Background Technology

[0002] Currently, the energy structure is undergoing transformation, with increasingly close connections between the energy supply and demand sides. Energy stations can effectively utilize cooling, heating, electricity, and gas, and through coordinated energy planning and collaborative management, they can achieve interactive coupling and mutual complementarity of energy resources. How to improve energy utilization efficiency and reduce energy consumption and operating costs by managing energy stations and scheduling energy from different stations is a major direction of energy structure transformation.

[0003] Traditional job scheduling strategies based on minimum scheduling, max-min scheduling, and first-come, first-served scheduling algorithms require specific conditions to be used, and suffer from poor real-time performance and high computational resource consumption. Heuristic scheduling strategies are prone to local optima and unstable service performance. In contrast, scheduling strategies based on deep reinforcement learning combine the data processing and analysis capabilities of deep learning with the decision-making capabilities of reinforcement learning, which can effectively handle the complex data of energy stations and obtain optimal energy scheduling results. However, there are still shortcomings in the calculation of building load during the energy scheduling process. Summary of the Invention

[0004] To address the aforementioned problems in the existing technology, this invention provides a GIS-based energy station management method and system. The objective of this invention can be achieved through the following technical solutions: A GIS-based energy station management method includes: The location information, operational status, weather data, and building location information of energy stations are obtained through GIS. Obtain the building envelope, and based on the weather data and the building envelope, obtain the building's heating and cooling load data through a heating and cooling energy load calculation model; Obtain historical building electrical load data, and use the electrical energy load prediction model based on the historical building electrical load data to obtain building electrical load data; Energy dispatching decisions are obtained through an energy dispatching model based on the energy station location information, the energy station operating status, the building location information, the building heating and cooling load data, and the building electrical load data.

[0005] Preferably, obtaining the building's heating and cooling load data based on the weather data and the building envelope through a heating and cooling energy load calculation model includes: A preset building heat transfer dynamic balance model is used to obtain the building temperature based on the weather data and the building envelope. A preset temperature is used to calculate the building's heating and cooling load data using TRNSYS software based on the building's internal temperature and the preset temperature.

[0006] Preferably, the building heat transfer dynamic balance model includes an air node model and ventilation temperature control rules, specifically including: Based on the weather data, the building location information, and the building envelope, the convection gain and radiative heat flux are calculated using EnergyPlus building energy consumption simulation software. The convection gain includes convection gain through windows, convection gain of internal shading devices, convection gain of the building exterior surface, and internal gain. The radiative heat flux includes radiative heat flux absorbed by the inner surface, radiative heat flux absorbed by the outer surface, combined convective and radiative heat flux of the inner surface, and combined convective and radiative heat flux of the outer surface. The air node heat transfer data is obtained through the air node heat transfer model based on the convection gain through the window, the convection gain of the internal shading device, the convection gain of the building exterior, and the internal gain. The wall heat conduction data is obtained by means of the ventilation temperature control rules based on the radiant heat flow absorbed by the inner surface, the radiant heat flow absorbed by the outer surface, the combined convective and radiative heat flow of the inner surface, and the combined convective and radiative heat flow of the outer surface. The building temperature is calculated by summing the heat transfer data of the air nodes and the heat conduction data of the walls.

[0007] Preferably, the weather data includes solar radiation, temperature, humidity, and wind speed intensity.

[0008] Preferably, obtaining the building electrical load data based on the historical building electrical load data through the electrical energy load prediction model includes: Based on the historical building electrical load data, K-means clustering was used to obtain the historical building electrical load cluster centers; Obtain real-time building electrical load data, and obtain the real-time building electrical load cluster center through K-means clustering based on the real-time building electrical load data; Based on the historical building electrical load cluster centers and the real-time building electrical load cluster centers, similar cluster center data are calculated using Euclidean distance; The building electrical load data is calculated using the least squares support vector machine regression function based on the data of similar cluster centers.

[0009] Preferably, the step of obtaining energy dispatching decisions through an energy dispatching model based on the energy station location information, the energy station operating status, the building location information, the building heating and cooling load data, and the building electrical load data includes: The energy station information, the building heating and cooling load data, and the building electrical load data are used as the state space, and the scheduling action is used as the action space. The scheduling action represents the action of the energy station to schedule energy to the building. Obtain the current scheduling action and transmission speed; obtain the building location information through GIS based on the current action; and calculate the transmission time delay based on the energy station location information, building location information, and transmission speed. The scheduling reward function is obtained by defining the reward function based on the state space, the action space, and the transmission time delay. The energy scheduling decision is obtained through a deep deterministic policy gradient function algorithm based on the state space, the action space, and the scheduling reward function.

[0010] A GIS-based energy station management system includes a data acquisition module, a cooling and heating load calculation module, an electrical load forecasting module, and an energy optimization scheduling module. The data acquisition module is used to acquire energy station location information, energy station operating status, weather data, and building location information through GIS; The heating and cooling load calculation module is used to obtain the building envelope and obtain the building heating and cooling load data through the heating and cooling energy load calculation model based on the weather data and the building envelope. The electrical load prediction module is used to acquire historical building electrical load data and obtain building electrical load data based on the historical building electrical load data through an electrical energy load prediction model. The energy optimization scheduling module is used to obtain energy scheduling decisions through an energy scheduling model based on the energy station location information, the energy station operating status, the building location information, the building heating and cooling load data, and the building electrical load data.

[0011] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described GIS-based energy station management method.

[0012] A storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the aforementioned GIS-based energy station management method.

[0013] The beneficial effects of this invention are as follows: (1) By integrating the geographical location information, operating status and weather data of energy stations and buildings through the GIS system, the real-time positioning of energy stations and buildings is realized; at the same time, by comprehensively considering the building envelope and weather changes, the building's heating and cooling loads and electrical loads can be estimated more accurately, providing factual basis for subsequent energy dispatch.

[0014] (2) By using the heating and cooling load calculation model, the differences in the building's internal maintenance structure and weather differences are fully considered to improve the accuracy of heating and cooling load calculation; Since electrical load has regularity, the electrical load is predicted by the electrical load prediction model based on historical electrical load data, which reduces the complexity of calculation, helps to achieve optimal energy allocation, and improves energy utilization efficiency.

[0015] (3) By defining the state space, action space and reward through the energy dispatch model, and automatically generating energy dispatch decisions based on the deep deterministic strategy gradient algorithm, the energy station can dynamically adapt to changes in building demand, improve energy utilization efficiency, and reduce operating costs and energy consumption. Attached Figure Description

[0016] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0017] Figure 1 This is a flowchart illustrating a GIS-based energy station management method according to the present invention. Detailed Implementation

[0018] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided.

[0019] Please see Figure 1 A GIS-based energy station management method includes: S1: Obtain energy station location information, energy station operating status, weather data, and building location information through GIS; S2: Obtain the building envelope, and based on the weather data and the building envelope, obtain the building's heating and cooling load data through a heating and cooling energy load calculation model; S3: Obtain historical building electrical load data, and obtain building electrical load data based on the historical building electrical load data through an electrical energy load prediction model; S4: Based on the energy station location information, the energy station operating status, the building location information, the building heating and cooling load data, and the building electrical load data, an energy dispatch decision is obtained through an energy dispatch model.

[0020] Specifically, the GIS is a geographic information system that can collect, store, manage, analyze, and visualize geospatial data; through the GIS, the geographical location, equipment status, energy type, weather data, and the geographical location and building envelope of the energy station can be obtained.

[0021] In this embodiment, considering that building load accounts for 75% of urban energy consumption, the design of the energy station management method mainly focuses on analyzing the load characteristics of buildings.

[0022] Specifically, the building envelope includes walls, roof, windows, doors, and floors.

[0023] In step S2, the cooling and heating energy load calculation model is based on the building heat transfer dynamic balance model, and the cooling and heating energy load calculation model includes: S201: Preset building heat transfer dynamic balance model, and obtain the building temperature based on the weather data and the building envelope through the building heat transfer dynamic balance model; S202: Preset a specified temperature, and calculate the building's heating and cooling load data using TRNSYS software based on the building's internal temperature and the specified temperature.

[0024] In step S201, the building heat transfer dynamic balance model includes an air node model and ventilation temperature control rules, specifically including: S201-1: Convection gain and radiative heat flux are calculated using EnergyPlus building energy consumption simulation software based on the weather data, the building location information, and the building envelope. The convection gain includes convection gain through windows, convection gain of internal shading devices, convection gain of the building exterior surface, and internal gain. The radiative heat flux includes radiative heat flux absorbed by the inner surface, radiative heat flux absorbed by the outer surface, combined convective and radiative heat flux of the inner surface, and combined convective and radiative heat flux of the outer surface. S201-2: Based on the convection gain through the window, the convection gain of the internal shading device, the convection gain of the building exterior, and the internal gain, the air node heat transfer data is obtained through the air node heat transfer model. The expression for the air node heat transfer model is: , in, This represents the heat transfer data of the air node. This indicates the convective gain of the building's exterior surface. Indicates permeation gain. Indicates ventilation gain. Indicates boundary gain. Indicates the convection gain through the window. Indicates internal gain. This indicates the convection gain of the internal shading device. Indicates volumetric flow rate, Indicates the outside air temperature. Indicates indoor air temperature. Indicates ventilation temperature. The region's air temperature is represented by ρ, and the air density by c. p This indicates the specific heat capacity of air; S201-3: Based on the radiative heat flow absorbed by the inner surface, the radiative heat flow absorbed by the outer surface, the combined convective and radiative heat flow of the inner surface, and the combined convective and radiative heat flow of the outer surface, the wall heat conduction data is obtained through the ventilation temperature control rules. The wall heat conduction data includes heat conduction data inside the wall and heat conduction data outside the wall. The ventilation temperature control rules include: , in, This indicates the heat conduction data within the wall. This indicates the combined convective and radiative heat flow on the inner surface. This indicates that the inner surface absorbs radiative heat flow. This indicates the external heat conduction data. This indicates the combined heat flow from the outer surface convective radiation. W represents the radiative heat flux absorbed by the outer surface, and W represents the solar radiation intensity. S201-4: The building temperature is obtained by summing the air node heat transfer data and the wall heat conduction data.

[0025] Specifically, the building heat transfer dynamic balance model is a model that reflects the influence of building envelope and heat transfer on the temperature inside the building.

[0026] Specifically, the weather data includes solar radiation, temperature, humidity, and wind speed intensity.

[0027] Specifically, the convection gain through the window is the convection gain of the building radiation through the window on the air node; the convection gain of the internal shading device is the convection gain of the internal shading device absorbing the building radiation on the air node; the external convection gain is the convection gain of the building radiation on the building's external surface on the air node; and the internal gain is the gain of people, lighting, and equipment on the air node.

[0028] In this embodiment, by building a dynamic balance model of building heat transfer in TRNSYS software, the building's heating and cooling load data are obtained by calculating the temperature difference between the building's internal temperature and a specified temperature using the weather data and the building envelope.

[0029] In step S3, the electrical energy load prediction model includes: S301: Based on the historical building electrical load data, obtain the historical building electrical load cluster center through K-means clustering; The K-means clustering expression is: , Where f represents the cluster center of the electrical load of the historical building, |c i | indicates the number of historical building electrical load data, c i This represents the electrical load data of the historical buildings, where x represents the electrical load data of each historical building; S302: Obtain real-time building electrical load data, and obtain the real-time building electrical load cluster center through K-means clustering based on the real-time building electrical load data; S303: Based on the historical building electrical load cluster center and the real-time building electrical load cluster center, similar cluster center data is calculated using Euclidean distance. The similar cluster center data includes similar real-time building electrical load data and similar historical building electrical load data. S304: The building electrical load data is calculated using the least squares support vector machine regression function based on the data of similar cluster centers; The expression for the least squares support vector machine regression function is as follows: , Where y(x) is the least squares support vector machine regression function used to output the building electrical load data, k represents the kth similar historical building electrical load data, N represents the number of similar historical building electrical load data, and α k Let K(x,x) represent the Lagrange multipliers. k ) represents the kernel function, which is used to calculate the similarity between the cluster center data, and x represents the similar real-time building electrical load data. k This represents the electrical load data of the similar historical buildings, where b is the bias term.

[0030] In this embodiment, the historical building electrical load data is obtained through the following steps: building electrical load data are collected at 15-minute intervals as a set, with each set containing no more than 105 data points, and the historical building electrical load data is constructed using data at 3-hour intervals.

[0031] In step S4, the energy dispatch model includes: S401: The energy station information, the building heating and cooling load data, and the building electrical load data are used as the state space, and the scheduling action is used as the action space. The scheduling action represents the action of the energy station to schedule energy to the building. S402: Obtain the current scheduling action and transmission speed; obtain the building location information through GIS based on the current action; calculate the transmission time delay based on the energy station location information, building location information, and transmission speed. The expression for calculating the transmission time is: , Where timecost represents the transmission time delay, D energy D represents the location information of the energy station. building The location information of the building is represented by v, and the transmission speed is represented by v. S403: Based on the state space, the action space, and the transmission time delay, a scheduling reward function is defined using a reward function definition; The reward function is defined as follows: , Where R(s,a) represents the scheduling reward function, α, β, γ, and η are weighting coefficients, L(s,a) represents the energy loss of performing action a in state s, C(s,a) represents the economic cost of performing action a in state s, Q(s,a) represents the impact of performing action a in state s on energy quality, timecost represents the transmission time delay, and R i For resistance, I i For current; S404: The energy scheduling decision is obtained by using the deep deterministic policy gradient function algorithm based on the state space, the action space, and the scheduling reward function.

[0032] A GIS-based energy station management system includes a data acquisition module, a cooling and heating load calculation module, an electrical load forecasting module, and an energy optimization scheduling module. The data acquisition module is used to acquire energy station location information, energy station operating status, weather data, and building location information through GIS; The heating and cooling load calculation module is used to obtain the building envelope and obtain the building heating and cooling load data through the heating and cooling energy load calculation model based on the weather data and the building envelope. The electrical load prediction module is used to acquire historical building electrical load data and obtain building electrical load data based on the historical building electrical load data through an electrical energy load prediction model. The energy optimization scheduling module is used to obtain energy scheduling decisions through an energy scheduling model based on the energy station location information, the energy station operating status, the building location information, the building heating and cooling load data, and the building electrical load data.

[0033] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0034] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit programs for use by or in connection with an instruction execution system, apparatus, or device.

[0035] The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof. The computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages—such as Java, Smalltalk, and C++—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0036] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A GIS-based energy station management method, characterized in that, Includes the following steps: The location information, operational status, weather data, and building location information of energy stations are obtained through GIS. Obtain the building envelope, and based on the weather data and the building envelope, obtain the building's heating and cooling load data through a heating and cooling energy load calculation model; Obtain historical building electrical load data, and use the electrical energy load prediction model based on the historical building electrical load data to obtain building electrical load data; Energy dispatching decisions are obtained through an energy dispatching model based on the energy station location information, the energy station operating status, the building location information, the building heating and cooling load data, and the building electrical load data.

2. The GIS-based energy station management method according to claim 1, characterized in that, The process of obtaining building heating and cooling load data based on the weather data and the building envelope through a heating and cooling energy load calculation model includes: A preset building heat transfer dynamic balance model is used to obtain the building temperature based on the weather data and the building envelope. A preset temperature is used to calculate the building's heating and cooling load data using TRNSYS software based on the building's internal temperature and the preset temperature.

3. The GIS-based energy station management method according to claim 2, characterized in that, The building heat transfer dynamic balance model includes an air node model and ventilation temperature control rules, specifically including: Based on the weather data, the building location information, and the building envelope, the convection gain and radiative heat flux are calculated using EnergyPlus building energy consumption simulation software. The convection gain includes convection gain through windows, convection gain of internal shading devices, convection gain of the building exterior surface, and internal gain. The radiative heat flux includes radiative heat flux absorbed by the inner surface, radiative heat flux absorbed by the outer surface, combined convective and radiative heat flux of the inner surface, and combined convective and radiative heat flux of the outer surface. The air node heat transfer data is obtained through the air node heat transfer model based on the convection gain through the window, the convection gain of the internal shading device, the convection gain of the building exterior, and the internal gain. The wall heat conduction data is obtained by means of the ventilation temperature control rules based on the radiant heat flow absorbed by the inner surface, the radiant heat flow absorbed by the outer surface, the combined convective and radiative heat flow of the inner surface, and the combined convective and radiative heat flow of the outer surface. The building temperature is calculated by summing the heat transfer data of the air nodes and the heat conduction data of the walls.

4. The GIS-based energy station management method according to claim 3, characterized in that, The weather data includes solar radiation, temperature, humidity, and wind speed intensity.

5. The GIS-based energy station management method according to claim 1, characterized in that, The process of obtaining building electrical load data based on the historical building electrical load data through an electrical energy load prediction model includes: Based on the historical building electrical load data, K-means clustering was used to obtain the historical building electrical load cluster centers; Obtain real-time building electrical load data, and obtain the real-time building electrical load cluster center through K-means clustering based on the real-time building electrical load data; Based on the historical building electrical load cluster centers and the real-time building electrical load cluster centers, similar cluster center data are calculated using Euclidean distance; The building electrical load data is calculated using the least squares support vector machine regression function based on the data of similar cluster centers.

6. The GIS-based energy station management method according to claim 1, characterized in that, The step of obtaining energy dispatching decisions through an energy dispatching model based on the energy station location information, the energy station operating status, the building location information, the building heating and cooling load data, and the building electrical load data includes: The energy station information, the building heating and cooling load data, and the building electrical load data are used as the state space, and the scheduling action is used as the action space. The scheduling action represents the action of the energy station to schedule energy to the building. Obtain the current scheduling action and transmission speed; obtain the building location information through GIS based on the current action; and calculate the transmission time delay based on the energy station location information, building location information, and transmission speed. The scheduling reward function is obtained by defining the reward function based on the state space, the action space, and the transmission time delay. The energy scheduling decision is obtained through a deep deterministic policy gradient function algorithm based on the state space, the action space, and the scheduling reward function.

7. A GIS-based energy station management system, characterized in that, It includes a data acquisition module, a cooling and heating load calculation module, an electrical load forecasting module, and an energy optimization and scheduling module; The data acquisition module is used to acquire energy station location information, energy station operating status, weather data, and building location information through GIS; The heating and cooling load calculation module is used to obtain the building envelope and obtain the building heating and cooling load data through the heating and cooling energy load calculation model based on the weather data and the building envelope. The electrical load prediction module is used to acquire historical building electrical load data and obtain building electrical load data based on the historical building electrical load data through an electrical energy load prediction model. The energy optimization scheduling module is used to obtain energy scheduling decisions through an energy scheduling model based on the energy station location information, the energy station operating status, the building location information, the building heating and cooling load data, and the building electrical load data.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the GIS-based energy station management method as described in any one of claims 1-6.

9. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the GIS-based energy station management method as described in any one of claims 1-6.

Images