Optical storage and charging station knowledge graph construction method

Abstract

The invention discloses an optical storage and charging station knowledge graph construction method, and relates to the field of optical storage and charging station modeling, and the method comprises the steps: constructing a knowledge graph of an optical storage and charging station, and effectively integrating and mining data and association relationships among a photovoltaic unit, an energy storage unit and a charging station; firstly, through detailed modeling of characteristics and interaction of each operation unit, the data transparency is improved, so that the operation management of the station is more efficient and scientific; secondly, potential power association can be found and utilized by utilizing association mining, energy distribution and use efficiency can be optimized, and energy waste can be reduced; besides, through prediction analysis, potential problems can be identified in advance, the response speed and the service quality of the station are improved, and finally operation cost reduction and energy utilization maximization are achieved. Therefore, the method not only enhances the data processing and analysis capability of the optical storage and charging station, but also remarkably improves the overall operation efficiency and economic benefits through accurate data driving decision.

Description

Technical Field

[0001] The present invention relates to the field of photovoltaic storage and charging station modeling, and specifically to a method for constructing a knowledge graph of photovoltaic storage and charging stations. Background Art

[0002] In the current rapid development of the energy industry, photovoltaic storage and charging stations, as an important part of the new energy network, play a key role in regulating energy supply and demand, ensuring grid stability and promoting energy transformation. These stations integrate photovoltaic power generation, energy storage and power charging functions, and their efficient and coordinated operation is the core of improving the utilization rate of renewable energy and the responsiveness of the grid. Therefore, in-depth research on the operation mechanism of photovoltaic storage and charging stations and optimizing their management and scheduling strategies are not only of great significance to promoting the widespread application of green energy, but also crucial to achieving the optimization of energy structure and improving the economy and environmental friendliness of the energy system.

[0003] However, existing research and practice have obvious deficiencies in the data management and utilization of photovoltaic storage and charging stations. Due to the complex interactions between the operating units and the huge amount of data, traditional methods often find it difficult to effectively integrate and analyze this data, resulting in low station operation efficiency and difficulty in maximizing the utilization of data assets. In addition, existing technologies are also unable to mine the potential power correlation between photovoltaic storage and charging stations, which limits the possibility of in-depth understanding and prediction of the station's operating status and increases operation and maintenance costs and risks.

[0004] In view of this, there is an urgent need to develop a new method to build a comprehensive knowledge graph of photovoltaic storage and charging stations to solve the above technical problems. Summary of the invention

[0005] The purpose of the present invention is to provide a method for constructing a knowledge graph of a photovoltaic storage and charging station to solve the problems raised in the prior art.

[0006] To achieve the above object, the present invention provides the following technical solution: a method for constructing a knowledge graph of a photovoltaic storage and charging station, the construction method comprising the following steps:

[0007] S1. Establish the knowledge entity of each operating unit in the photovoltaic storage and charging station;

[0008] S2. Establishing the association relationship between the operating units in the photovoltaic storage and charging station;

[0009] S3, using the association relationship of known photovoltaic storage and charging stations to mine the association relationship of each operating unit in potential photovoltaic storage and charging stations;

[0010] S4: Establish a knowledge graph of photovoltaic storage and charging stations based on the associations established in S2 and the associations mined in S3.

[0011] According to the above technical solution, the establishment of the association relationship in step S2 includes the following steps:

[0012] S201, constructing a relationship framework between the operating units in the photovoltaic storage and charging station;

[0013] S202, using triples to formalize the association relationship between the operating units in the photovoltaic storage and charging station;

[0014] S203: Define a weight value for the association relationship established in S202.

[0015] According to the above technical solution, in step S201, the association relationship framework includes physical connection relationship, energy transmission relationship, information flow relationship and dependency relationship;

[0016] In step S202, the association relationship is specifically: i ,r k ,e j );

[0017] Among them, e i and e j Represented as the i-th and j-th knowledge entities in the solar storage and charging station, r k Represents the association relationship between the i-th and j-th photovoltaic storage and charging stations;

[0018] In step S203, the association relationship between the operating units in the photovoltaic storage and charging station after the weight value is defined is expressed as: w(e i ,r k ,e j );

[0019] Among them, w represents the weight value of the association relationship.

[0020] According to the above technical solution, the establishment of the association relationship also includes the establishment of an association relationship path search and a relationship query model, which is expressed as:

[0021] d(v)=min(d(v),d(u)+w(u,v))for each(u,v)∈E;

[0022] Among them, u represents the knowledge entity in the current solar storage and charging station knowledge graph, v is the knowledge entity in any solar storage and charging station knowledge graph directly connected to u, and E represents the knowledge entity set of the knowledge graph.

[0023] According to the above technical solution, mining the association relationship between the operating units in the potential photovoltaic storage and charging station in step S3 includes the following steps:

[0024] S301, pre-processing power information of each operating unit in the solar storage and charging station;

[0025] S302, using Granger causality test to analyze the state correlation relationship between the operating units of the photovoltaic storage and charging station;

[0026] S303. Use statistics to perform significance analysis.

[0027] According to the above technical solution, in step S301, the preprocessing includes cleaning, standardization, processing missing values, processing outliers and data normalization;

[0028] In step S302, Granger causality test is used to analyze the association relationship, specifically:

[0029]

[0030] Among them, Y t is the dependent variable at time t. t-i is the independent variable at time ti, being tested for Y t Granger cause of α 0 is the intercept term; β i ,γ i They are Y t and X t The coefficient at the i-th lag; t′ is the error term.

[0031] According to the above technical solution, in step S303, the significance analysis is specifically as follows:

[0032]

[0033] Among them, RSS 0 To exclude X t The residual sum of squares of the model; RSS 1 To include X t is the residual sum of squares of the model; n is the sample size; p is the number of lags in the model, and F represents the statistic.

[0034] According to the above technical solution, the operating unit includes a photovoltaic unit, an energy storage unit and a charging station unit.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] The present invention effectively integrates and mines the data and associations between photovoltaic units, energy storage units and charging stations by constructing a knowledge graph of photovoltaic storage and charging stations. First, by modeling the characteristics and interactions of each operating unit in detail, the present invention improves data transparency, making the operation and management of the station more efficient and scientific. Secondly, by mining association relationships, potential power associations can be discovered and utilized, energy distribution and utilization efficiency can be optimized, and energy waste can be reduced. In addition, through predictive analysis, the present invention can identify potential problems in advance, improve the response speed and service quality of the station, and ultimately achieve reduced operating costs and maximized energy utilization. Therefore, the present invention not only enhances the data processing and analysis capabilities of photovoltaic storage and charging stations, but also significantly improves overall operational efficiency and economic benefits through precise data-driven decision-making.

[0037] The present invention improves the data transparency and operation efficiency of photovoltaic storage and charging stations, optimizes resource allocation, reduces operation and maintenance costs, and enhances the station's ability to respond to fluctuations in energy demand. In addition, the invention also uses intelligent data analysis tools to explore and discover potential power relationships between photovoltaic storage and charging stations that are not clearly perceived, so as to scientifically guide station operation and scheduling decisions, thereby promoting more efficient use of renewable energy and sustainable development of energy systems.

[0038] This invention can not only fully explore and utilize existing data resources, but also optimize the operation and management strategies of the station by discovering unnoticed data correlations, and ultimately achieve efficient, safe and sustainable use of energy. This innovative knowledge graph construction method will provide strong technical support for the scientific management and decision support of photovoltaic storage and charging stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 Schematic diagram showing the performance comparison between the conventional method and the method of the present invention in establishing a photovoltaic storage and charging station model;

[0040] Figure 2 Schematic diagram of the iterative process of the knowledge graph model of the photovoltaic storage and charging station of the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] The present invention provides a technical solution for a method for constructing a knowledge graph of a photovoltaic storage and charging station, and the construction method comprises the following steps:

[0043] S1. Establish the knowledge entity of each operating unit in the photovoltaic storage and charging station;

[0044] Further, the following steps are included:

[0045] S101: Establish the knowledge entity of the photovoltaic unit in the photovoltaic storage and charging station. The photovoltaic unit mainly includes photovoltaic panels, inverters, monitoring equipment and other components. Each photovoltaic unit is a knowledge entity with its specific attributes and relationships.

[0046] Specifically, the properties include:

[0047] Photovoltaic panels: model, maximum power output, dimensions, efficiency, manufacturer, installation date;

[0048] Inverter: model, input / output power range, efficiency, manufacturer, installation date;

[0049] Monitoring equipment: type, monitoring parameters (such as light intensity, temperature, etc.), manufacturer, installation location;

[0050] The relationships include: PV panels are connected to inverters, inverters are connected to the grid, and monitoring equipment monitors the operating status of PV panels and inverters;

[0051] S102: Establish knowledge entities of energy storage units in the photovoltaic charging and storage station. The energy storage unit includes a battery pack, a management system, connection equipment, etc. Each energy storage unit is a knowledge entity with its specific attributes and relationships.

[0052] Specifically, the properties include:

[0053] Battery pack: type, capacity, output power, cycle life, manufacturer, installation date;

[0054] Management system: type, control function (such as charging control, discharging control, etc.), manufacturer;

[0055] Connected equipment: type, connection method, manufacturer;

[0056] The relationships include: the battery pack is connected to the grid through the management system, the management system controls the charging and discharging process of the battery pack, and the connection equipment ensures the physical connection between the battery pack and other systems;

[0057] S103: Establish the knowledge entity of the charging station unit in the solar storage charging station. The charging station unit includes charging piles, monitoring systems, etc. Each charging station unit is a knowledge entity with its specific attributes and relationships.

[0058] Specifically, the properties include:

[0059] Charging station: type, maximum output power, interface type, manufacturer, installation date;

[0060] Monitoring system: type, monitored parameters (such as usage status, fault reporting, etc.), manufacturer;

[0061] The relationships include: the charging pile is connected to the power grid, and the monitoring system is used to monitor the status and performance of the charging pile in real time;

[0062] S2. Establishing the association relationship between the operating units in the photovoltaic storage and charging station;

[0063] Further, the following steps are included:

[0064] S201, constructing a relationship framework between the operating units in the photovoltaic storage and charging station;

[0065] Specifically, the association relationship framework includes:

[0066] Physical connection relationship: expresses the direct physical connection between devices, such as photovoltaic panels connected to inverters;

[0067] Energy transfer relationships: describe how energy is transferred from one device to another, such as from a photovoltaic panel to an energy storage system;

[0068] Information flow relationship: involves the flow of data or control commands, such as the monitoring system sending information to the management system;

[0069] Dependency: The operation of some operating units may depend on the status of other units, such as the operation of a charging station may depend on the power status of an energy storage unit;

[0070] S202, using triples to formalize the association relationship between the operating units in the photovoltaic storage and charging station;

[0071] Specifically, the relationship is as follows: i ,r k ,e j );

[0072] Among them, e i and e j Represented as the i-th and j-th knowledge entities in the solar storage and charging station, r k Represents the association relationship between the i-th and j-th photovoltaic storage and charging stations;

[0073] S203, defining a weight value for the association relationship established in S202;

[0074] Specifically, the association relationship between the operating units in the photovoltaic storage and charging station after the weight value is defined is expressed as: w(e i ,r k ,e j );

[0075] Among them, w represents the weight value of the association relationship;

[0076] Furthermore, the establishment of the association relationship also includes the establishment of an association relationship path search and a relationship query model, which is expressed as:

[0077] d(v)=min(d(v),d(u)+w(u,v))for each(u,v)∈E;

[0078] Among them, u represents the knowledge entity in the current solar storage and charging station knowledge graph, v is the knowledge entity in any solar storage and charging station knowledge graph directly connected to u, and E represents the knowledge entity set of the knowledge graph.

[0079] S3, using the association relationship of known photovoltaic storage and charging stations to mine the association relationship of each operating unit in potential photovoltaic storage and charging stations;

[0080] Furthermore, mining the association relationship between the operating units in the potential photovoltaic storage and charging station includes the following steps:

[0081] S301, pre-processing power information of each operating unit in the solar storage and charging station;

[0082] Specifically, the preprocessing includes cleaning, standardization, processing of missing values, processing of outliers and data normalization;

[0083] S302, using Granger causality test to analyze the state correlation relationship between the operating units of the photovoltaic storage and charging station;

[0084] Specifically, Granger causality test is used to analyze the association relationship, specifically:

[0085]

[0086] Among them, Y t is the dependent variable at time t. t-i is the independent variable at time ti, being tested for Y t Granger cause of α 0 is the intercept term; β i ,γ i They are Y t and X t The coefficient at the i-th lag; t′ is the error term.

[0087] S303, using statistics to perform significance analysis;

[0088] Specifically, the significance analysis is as follows:

[0089]

[0090] Among them, RSS 0To exclude X t The residual sum of squares of the model; RSS 1 To include X t is the residual sum of squares of the model; n is the sample size; p is the number of lags in the model, and F represents the statistic.

[0091] The operating unit includes a photovoltaic unit, an energy storage unit and a charging station unit.

[0092] S4: Establish a knowledge graph of photovoltaic storage and charging stations based on the associations established in S2 and the associations mined in S3.

[0093] In one embodiment, in order to verify the effectiveness of the present invention, we selected a photovoltaic storage and charging station connected to a distribution network as a research object.

[0094] Station composition:

[0095] Photovoltaic unit: 10 photovoltaic panels of different power and area.

[0096] Energy storage unit: 5 lithium-ion batteries of different capacities.

[0097] Charging station: includes 3 fast charging and 5 slow charging stations.

[0098] Data Generation For the PV cells, the power output was recorded every 15 minutes.

[0099] For energy storage units, the charging and discharging status are recorded every 15 minutes.

[0100] For charging stations, the charging power demand is recorded every 15 minutes.

[0101] like Figure 1 As shown, the performance comparison between the traditional method and the method of the present invention in establishing a photovoltaic storage and charging station model is demonstrated: the blue bar chart represents the running time of the two methods.

[0102] It can be seen that the traditional method takes a little longer, while the running time of the method of the present invention is extremely short, indicating that its computational efficiency is high.

[0103] The red line graph shows the resulting values ​​of the two methods.

[0104] The correlation coefficient obtained by the traditional method shows a slight negative correlation between photovoltaic output and charging demand, while the result value of the method of the present invention is higher, which indicates that the proposed knowledge graph model of photovoltaic storage and charging stations reveals more complex data associations.

[0105] like Figure 2 As shown in the figure, the iterative process of the knowledge graph model of the photovoltaic storage and charging station is demonstrated, where the green curve is the actual photovoltaic storage and charging station knowledge graph association relationship, and the red curve is the association relationship learned by the knowledge graph.

[0106] It can be seen that the method proposed in the present invention can continuously mine and learn the correlation relationship of the knowledge graph of photovoltaic storage and charging stations, and generate a knowledge graph of photovoltaic storage and charging stations that conforms to the actual operation scenario.

[0107] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A method for constructing a knowledge graph of a photovoltaic storage and charging station, characterized in that: The construction method comprises the following steps: S1. Establish the knowledge entity of each operating unit in the photovoltaic storage and charging station; S2. Establishing the association relationship between the operating units in the photovoltaic storage and charging station; S3, using the association relationship of known photovoltaic storage and charging stations to mine the association relationship of each operating unit in potential photovoltaic storage and charging stations; S4: Establish a knowledge graph of photovoltaic storage and charging stations based on the associations established in S2 and the associations mined in S3.

2. A method for constructing a knowledge graph of a photovoltaic storage and charging station according to claim 1, characterized in that: The establishment of the association relationship in step S2 includes the following steps: S201, constructing a relationship framework between the operating units in the photovoltaic storage and charging station; S202, using triples to formalize the association relationship between the operating units in the photovoltaic storage and charging station; S203: Define a weight value for the association relationship established in S202.

3. A method for constructing a knowledge graph of a photovoltaic storage and charging station according to claim 2, characterized in that: In step S201, the association relationship framework includes physical connection relationship, energy transmission relationship, information flow relationship and dependency relationship; In step S202, the association relationship is specifically: i ,r k ,e j ); Among them, e i and e j Represented as the i-th and j-th knowledge entities in the solar storage and charging station, r k Represents the association relationship between the i-th and j-th photovoltaic storage and charging stations; In step S203, the association relationship between the operating units in the photovoltaic storage and charging station after the weight value is defined is expressed as: w(e i ,r k ,e j ); Among them, w represents the weight value of the association relationship.

4. A method for constructing a knowledge graph of a photovoltaic storage and charging station according to claim 2, characterized in that: The establishment of the association relationship also includes the establishment of an association relationship path search and a relationship query model, which is expressed as: d(v)=min(d(v),d(u)+w(u,v))for each(u,v)∈E; Among them, u represents the knowledge entity in the current solar storage and charging station knowledge graph, v is the knowledge entity in the knowledge graph of any solar storage and charging station directly connected to u, E represents the knowledge entity set of the knowledge graph; d represents the shortest path of the association relationship.

5. The method for constructing a knowledge graph of a photovoltaic storage and charging station according to claim 1, characterized in that: In step S3, mining the association relationship between the operating units in the potential photovoltaic storage and charging station includes the following steps: S301, pre-processing power information of each operating unit in the solar storage and charging station; S302, using Granger causality test to analyze the state correlation relationship between the operating units of the photovoltaic storage and charging station; S303. Use statistics to perform significance analysis.

6. A method for constructing a knowledge graph of a photovoltaic storage and charging station according to claim 5, characterized in that: In step S301, the preprocessing includes cleaning, standardization, processing missing values, processing outliers and data normalization; In step S302, Granger causality test is used to analyze the association relationship, specifically: Among them, Y t is the dependent variable at time t; Y t-i is the dependent variable at time ti; X t-i is the independent variable at time ti, being tested for Y t Granger reason; α0 is the intercept term; β i ,γ i They are Y t and X t The coefficient at the i-th lag; t′ is the error term.

7. The method for constructing a knowledge graph of a photovoltaic storage and charging station according to claim 5, characterized in that: In step S303, significance analysis is used to determine whether there is a significant correlation between the variables; specifically: Among them, RSS0 does not include X t The residual sum of squares of the model including X t is the residual sum of squares of the model; n is the sample size; p is the number of lags in the model, and F represents the significance analysis result. When F is greater than the set threshold, there is a significant correlation between the variables.

8. A method for constructing a knowledge graph of a photovoltaic storage and charging station according to any one of claims 1 to 7, characterized in that: The operating unit includes a photovoltaic unit, an energy storage unit and a charging station unit.

Images