Method for Suppressing Grid Energy Disturbance by Collaboratively Transmitting Electrothermal Gas State Information

Abstract

The present application provides a method for suppressing power grid energy disturbances through the transmission and coordination of electro-thermal-gas state information, which relates to the field of information technology and includes: obtaining multi-source heterogeneous state information of the electro-thermal-gas energy network; for the multi-source heterogeneous state information, using an adaptive communication protocol conversion technology to dynamically convert heterogeneous communication protocols into a unified protocol format; for the decoupled state information, using a distributed stream computing framework for parallel processing to improve the real-time performance and scalability of state information processing. The present invention uses a distributed stream computing framework to build an efficient processing pipeline, uses blockchain technology to ensure the integrity and reliability of data transmission, and applies deep learning algorithms to build an intelligent analysis model to mine the coupling relationship and evolution law of multi-energy flows. The present invention fuses the data processing results of each link to form a global state information view, provides decision support for suppressing power grid energy disturbances, and realizes the efficient processing, analysis, and visualization of the state information of the electro-thermal-gas multi-energy flow system.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a method for suppressing power grid energy disturbances in coordination with transmission of electric, thermal, and gas state information. Background Art

[0002] The coordinated transmission of electricity, heat, and gas status information faces numerous technical challenges and contradictions. First, grid energy disturbance suppression places extremely high demands on the real-time and reliability of electricity, heat, and gas status information transmission. Transmission delays and data loss directly impact the timeliness and accuracy of grid control. Second, the physical characteristics of electricity, heat, and gas energy systems differ significantly, resulting in varying frequencies, data formats, and timescales for collecting status information. This poses a significant challenge in achieving interoperability and convergence of status information across heterogeneous energy networks. Furthermore, energy networks span vast geographical areas and incorporate a wide variety of devices, resulting in varying communication modes and protocol standards across different regions and devices. This makes unified coordination of various communication resources challenging. Furthermore, the strong coupling of electricity, heat, and gas energy fluctuations means that state changes in a single energy system can rapidly propagate to other energy networks, leading to the mutual influence of multiple energy flows and the consequent difficulty in decoupling and tracing the source of status information. Finally, the volume of electricity, heat, and gas status information is enormous and experiencing explosive growth, posing significant challenges for the real-time processing and intelligent analysis of this large-scale, multi-source, heterogeneous state information. In short, to achieve efficient and coordinated transmission of electricity, heat and gas status information and lay a solid information foundation for suppressing grid energy disturbances, it is also necessary to work together from multiple technical dimensions such as communication, computing, and control to break through key bottlenecks. Summary of the Invention

[0003] The present invention provides a method for suppressing power grid energy disturbances by coordinating the transmission of electric, thermal, and gas status information, which mainly includes:

[0004] Acquire multi-source heterogeneous state information of the electric, thermal and gas energy network; for the multi-source heterogeneous state information, adopt adaptive communication protocol conversion technology to dynamically convert the heterogeneous communication protocol into a unified protocol format; for the converted state information, construct a multi-energy flow coupling relationship diagram of the energy network based on the graph model, and realize the decoupling and traceability of the state information through the causal reasoning analysis method; for the decoupled state information, adopt a distributed stream computing framework for parallel processing to improve the real-time and scalability of state information processing; use a blockchain-based security consensus mechanism to confirm and verify the results of the stream computing to ensure the credibility of the state information; construct a state information intelligent analysis model based on the deep learning algorithm to explore the correlation characteristics and evolution laws contained in the multi-energy flow data; generate a global state information view of the electric, thermal and gas energy network through visualization technology to provide auxiliary decision-making for energy network scheduling optimization.

[0005] Furthermore, the acquisition of multi-source heterogeneous state information of the electric-thermal-gas energy network includes: determining the acquisition frequency, data format, and time scale of the state information of each energy system according to the physical characteristics of the electric-thermal-gas energy network; converting the state information of the heterogeneous energy network into a unified format through data standardization processing; and realizing the interoperability and fusion of the state information.

[0006] Furthermore, the adoption of the adaptive communication protocol conversion technology to dynamically convert heterogeneous communication protocols into a unified protocol format includes: dynamically matching and converting various communication protocols for the communication mode and protocol standard differences in different regions and devices; adopting technologies such as data sharding and parallel transmission to improve communication efficiency; and ensuring communication security through lightweight encryption and digital signatures.

[0007] Furthermore, the construction of the multi-energy flow coupling relationship diagram of the energy network based on the graph model and the decoupling and traceability of the state information through the causal reasoning analysis method include: adopting the graph model to characterize the correlation structure of the multi-energy flow data for the strong coupling of the electric-thermal-gas energy fluctuations; learning the implicit dependence relationship of the multi-energy flow data through graph embedding and graph neural network; and combining the law of energy conservation to construct a causal reasoning rule library to trace the influence chain of the state change of a single energy system.

[0008] Furthermore, the adoption of the distributed stream computing framework for parallel processing includes: constructing an efficient state information processing pipeline for the massive multi-source heterogeneous state information; improving the real-time performance and scalability of the state information processing through technologies such as data sharding and parallel computing; and adopting optimization strategies such as in-memory computing and incremental processing to reduce the computing overhead.

[0009] Furthermore, the adoption of the security consensus mechanism based on blockchain for rights confirmation and verification includes: dividing the stream computing results into blocks, generating hash fingerprints and timestamps; realizing the collaborative verification of nodes in the blockchain network through the consensus algorithm and smart contract; and storing the verified state information on the chain to ensure the data is tamper-proof and traceable.

[0010] Furthermore, the construction of the intelligent analysis model of the state information based on the deep learning algorithm includes: adopting the transfer learning method to realize cross-domain knowledge fusion for the multi-source heterogeneous state information; mining the dynamic change law of the state information through the spatio-temporal sequence prediction model; and combining the reinforcement learning framework to adaptively optimize the scheduling strategy of the energy network.

[0011] Furthermore, the generation of the global state information view of the electric-thermal-gas energy network through the visualization technology includes: designing a multi-level visualization view for the multi-dimensional and multi-granularity state information; supporting the dynamic query and correlation analysis of the state information through the human-computer interaction interface; and combining virtual reality and augmented reality technologies to construct an immersive visualization scenario to improve the intuitive understandability of the system operation.

[0012] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0013] The present invention discloses a method for suppressing power grid energy disturbances in coordination with the transmission of electric, thermal and gas state information. In view of the strong coupling and heterogeneity of the electric, thermal and gas energy network, the present invention adopts adaptive communication protocol conversion technology to achieve unified coordination of various communication resources, and constructs a multi-energy flow coupling relationship diagram through a causal reasoning method based on a graphical model to achieve decoupling and traceability of state information. In order to process massive multi-source heterogeneous state information, the present invention adopts a distributed stream computing framework to construct an efficient processing pipeline. At the same time, blockchain technology is used to ensure the integrity and reliability of data transmission, and a deep learning algorithm is applied to construct an intelligent analysis model to explore the multi-energy flow coupling relationship and evolution law. Finally, the present invention integrates the data processing results of each link to form a global state information view, provides decision support for power grid energy disturbance suppression, and realizes efficient processing, analysis and visualization of the state information of the electric, thermal and gas multi-energy flow system. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a flow chart of the method for suppressing power grid energy disturbances in coordination with the transmission of electric, heat and gas status information of the present invention.

[0015] Figure 2 Schematic diagram of the grid energy disturbance suppression method coordinated with the transmission of electric, heat and gas state information of the present invention.

[0016] Figure 3 This is another schematic diagram of the grid energy disturbance suppression method coordinated with the transmission of electricity, heat and gas status information of the present invention. DETAILED DESCRIPTION

[0017] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. All other embodiments derived by those skilled in the art based on the embodiments in this specification without creative effort shall fall within the scope of protection of this specification.

[0018] like Figures 1 - 3 The method for suppressing power grid energy disturbances by coordinating the transmission of electricity, heat, and gas status information in this embodiment may specifically include:

[0019] In step S101, the acquisition frequency, data format, and time scale of the status information of each energy system are determined based on the physical characteristics of the electric, heat, and gas energy network. Through data standardization, the status information of the heterogeneous energy network is converted into a unified format to achieve interoperability and integration of the status information.

[0020] According to the physical characteristics of the electro-thermal-gas energy network, obtain the state information of each energy system, including parameters such as energy flow, temperature, and pressure. Aiming at the problem of inconsistent data acquisition frequencies and time scales for different energy systems, through the linear interpolation algorithm, unify the acquisition frequencies and time scales so that the state information of each energy system is aligned in the time dimension. Aiming at the problem of inconsistent data formats for different energy systems, design a unified data format, including the data types and units of parameters such as energy flow, temperature, and pressure. Then, through data mapping and conversion rules, convert the state information of the heterogeneous energy network into a unified data format to achieve data standardization. According to the unified data format, use the relational model to design the data model of the energy network state information, define the data tables and association relationships of parameters such as energy flow, temperature, and pressure, and establish a standardized data storage structure. Through the Kalman filter algorithm, fuse the state information of different energy systems, comprehensively consider the measurement errors and process noises of each energy system, and obtain the global state estimate value of the entire energy network to improve the accuracy and reliability of the state information. According to the global state information, use the linear programming algorithm, consider factors such as energy balance constraints, equipment capacity constraints, and energy prices, and calculate the optimal allocation scheme of energies such as electricity, heat, and gas to achieve the economic optimal scheduling of the energy network. Send the optimized scheduling strategy to each energy system, and through the PID control algorithm, dynamically adjust the operating parameters of each energy system according to the set value of the scheduling strategy and the feedback value of the actual state information to achieve the coordinated optimal control of the electro-thermal-gas energy network and improve the energy utilization efficiency and system stability.

[0021] Specifically, the electro-thermal-gas energy network is a complex system composed of a power system, a thermal system, and a gas system. To achieve coordinated optimal control, it is first necessary to obtain the state information of each energy system. For example, the state information of the power system includes voltage, current, frequency, power, etc.; the state information of the thermal system includes temperature, pressure, flow rate, etc.; the state information of the gas system includes pressure, flow rate, composition, etc. These information are collected through sensors and measuring instruments, such as smart meters, temperature sensors, pressure sensors, etc. Since the data acquisition frequencies and time scales of different energy systems are inconsistent, they need to be unified. For example, the acquisition frequency of the power system may be at the second level, while the acquisition frequency of the thermal system may be at the minute level. In this case, a linear interpolation algorithm can be used to interpolate the low-frequency data to the high-frequency time scale. Suppose the temperatures of the thermal system at 0 minute and 1 minute are 60°C and 62°C respectively, then the temperature at 5 minutes can be estimated to be 61°C through linear interpolation. This can align the data of different energy systems in the time dimension, facilitating subsequent data analysis and processing. The data formats of different energy systems may also be inconsistent. For example, the unit of temperature may be Celsius or Fahrenheit, and the unit of power may be kilowatt or megawatt. Therefore, a unified data format needs to be designed. For example, temperature is uniformly used in Celsius, and power is uniformly used in megawatt. Then, through data mapping and conversion rules, the state information of the heterogeneous energy network is converted into a unified data format to achieve data standardization. For example, convert Fahrenheit to Celsius and convert kilowatt to megawatt. After data standardization, it is convenient for data exchange and sharing between different systems. The unified data can be stored in a relational database. Data tables can be designed to store the state information of electricity, heat, and gas respectively. For example, the "Electricity" table contains fields such as time, voltage, current, frequency, power, etc.; the "Heat" table contains fields such as time, temperature, pressure, flow rate, etc.; the "Gas" table contains fields such as time, pressure, flow rate, composition, etc. The "Time" field is used as the primary key to associate the data of different energy systems. This normalized data storage structure facilitates data query and management. To improve the accuracy and reliability of the state information, the Kalman filter algorithm can be used to fuse the state information of different energy systems. The Kalman filter algorithm can comprehensively consider the measurement errors and process noises of each energy system. For example, there may be errors in the voltage measurement value of the power system, and there may also be errors in the temperature measurement value of the thermal system. The Kalman filter algorithm can estimate a more accurate state value based on these measurement values and the state equation of the system. This can reduce the influence of measurement errors on state estimation. Based on the global state information, a linear programming algorithm can be used for economic optimal scheduling of the energy network. For example, considering factors such as the energy balance constraints, equipment capacity constraints, and energy prices of electricity, heat, and gas, calculate the optimal energy configuration plan. Suppose the electricity price is low, then electricity can be preferentially used for energy supply; if the heat demand is high, then the output of the thermal system can be increased.The linear programming algorithm can help find the optimal solution that satisfies all the constraints, thus achieving the economic optimal scheduling of the energy network. After the optimized scheduling strategy is sent to each energy system, the operation parameters of each energy system are dynamically adjusted through the PID control algorithm. The PID control algorithm calculates the control quantity according to the set value of the scheduling strategy and the feedback value of the actual state information, such as adjusting the opening of the valve, the output of the generator, etc. For example, if the set temperature of the thermal system is 70 °C and the actual temperature is 65 °C, the PID control algorithm will calculate a control quantity according to the deviation to increase the output of the thermal system and make the temperature reach the set value. The PID control algorithm can realize the coordinated optimal control of the electric-thermal-gas energy network, improve the energy utilization efficiency and system stability.

[0022] In step S102, for the differences in communication modes and protocol standards of different regions and devices, the adaptive communication protocol conversion technology is adopted to dynamically match and convert various communication protocols, so as to achieve the unified coordination of various communication resources and ensure the efficient transmission of the electric-thermal-gas state information.

[0023] According to the differences in communication modes and protocol standards of different regions and devices, obtain the pre-established communication protocol knowledge base, which contains information such as the formats, parameters, and conversion rules of various communication protocols. For the received electro-thermal-gas status information, extract its communication protocol type and parameters, match and compare them with the protocols in the communication protocol knowledge base, and determine whether protocol conversion is required. If protocol conversion is required, according to the conversion rules in the communication protocol knowledge base, use the Scapy library in Python to dynamically generate a protocol conversion script to perform format and parameter conversion processing on the original communication protocol. After protocol conversion, obtain the electro-thermal-gas status information data in a unified format. According to the preset data format standard, use the Pandas library in Python to perform format verification on the converted data, and use the NumPy library to perform numerical range and integrity verification to ensure the accuracy and integrity of the data. Transmit the verified electro-thermal-gas status information data efficiently through the Mosquitto message queue service according to the unified JSON format and MQTT protocol standard, and use Grafana for real-time monitoring and quality control of the transmission process. In the process of communication resource coordination, adopt a dynamic resource allocation algorithm based on device priority. According to the communication modes, data volumes, and preset device priorities of devices in different regions, use the Schedule library in Python to dynamically schedule and allocate communication resources such as MQTT topics and QoS to ensure the efficiency and reliability of data transmission. For the real-time requirements of electro-thermal-gas status information, by setting the retain flag and QoS level of MQTT messages, and using the CoAP protocol to asynchronously report status change data, minimize the data transmission delay to ensure that the status information can be transmitted to the data center in a timely and accurate manner. On the data center side, use the Kafka message queue to cache the received status information, and use SparkStreaming for real-time data processing and analysis to extract key feature parameters to achieve real-time monitoring and fault warning of electro-thermal-gas devices.

[0024] Specifically, in an electro-thermal-gas energy network, the communication modes and protocol standards vary greatly among different regions and devices. Therefore, a communication protocol knowledge base is needed to store the formats, parameters, and conversion rules of various communication protocols. For example, the power system may use the Modbus protocol, while the thermal system may use the BACnet protocol. Through the pre-established communication protocol knowledge base, data from different systems can be quickly identified and processed. When the status information of the power system is received, the system first identifies that it uses the Modbus protocol, and then generates a protocol conversion script using the Scapy library according to the conversion rules in the knowledge base to convert the Modbus protocol into the unified communication format of the system. The converted data needs further format verification and numerical range checking to ensure the accuracy and integrity of the data. The Pandas library in Python can be used to verify the data format to ensure that all data fields conform to the preset standards, such as the timestamp format, numerical type, etc. At the same time, the NumPy library is used to check the numerical range of the data, for example, whether the values of current and voltage are within a reasonable range. This step ensures the quality of the data before it enters the analysis and processing process. To efficiently transmit this verified data, the system adopts the JSON format and the MQTT protocol. Through the Mosquitto message queue service, data can be efficiently transmitted between different systems and devices. For example, the data transmitted from the power generation station to the dispatching center can ensure the reliability of data transmission by setting the QoS level of MQTT. At the same time, Grafana is used for real-time monitoring of the transmission process, and the data flow status and possible transmission bottlenecks can be viewed in real time. During the communication resource coordination process, the dynamic resource allocation algorithm dynamically schedules communication resources according to the priority of the device and the data volume. For example, for data transmission of critical devices such as substations, the system may allocate a higher QoS level and a more frequent message sending interval. This priority-based resource allocation strategy ensures the timely transmission of critical data without affecting the operation efficiency of the entire energy network due to network congestion. To meet the real-time requirements of electro-thermal-gas status information, the system greatly reduces the data transmission delay by setting the retain flag and QoS level of MQTT messages and using the CoAP protocol for asynchronous reporting of status changes. This is very crucial for quickly responding to system changes, such as sudden failures or demand changes. For example, if a sudden voltage drop is detected in a certain area, the system can immediately report this change through the CoAP protocol, and the dispatching center can quickly respond and adjust the operating status of relevant devices. On the data center side, the Kafka message queue is used to cache the received status information, and SparkStreaming is used for real-time data processing and analysis. This step can extract key feature parameters from a large amount of real-time data to achieve real-time monitoring and fault warning of electro-thermal-gas devices.For example, by analyzing the continuously received temperature data, the system can predict the overheating risk of the device and notify the maintenance team in a timely manner for inspection or adjustment, thus avoiding possible device failures.

[0025] In step S103, aiming at the strong coupling of electro-thermal-gas energy fluctuations, a causal reasoning method based on a graph model is adopted to construct a multi-energy flow coupling relationship graph. Through causal relationship reasoning, trace the impact of the state change of a single energy system on other energy networks, and achieve the decoupling and tracing of state information.

[0026] Obtain the real-time state data of electric energy, thermal energy and gas energy, preprocess the data, and extract the key features reflecting the energy fluctuations. According to the physical coupling relationship between each energy, use a graph model to construct a multi-energy flow coupling relationship graph to characterize the mutual influence between energies. Among them, the nodes of the graph represent different energies, and the edges represent the coupling relationship between energies. For the nodes and edges in the graph model, define the quantitative causal relationship strength through physics knowledge and expert experience to form the basis of causal reasoning. When the state characteristic value of a certain energy system is detected to exceed the preset threshold, it is judged that a significant state change has occurred in this energy system, and trace the potential impact of this change on other energies on the causal graph. Through the shortest path search algorithm based on the graph, judge the propagation path and influence range of the state change in the multi-energy flow network. According to the causal reasoning result, obtain the affected energy system and the corresponding state change amplitude. For the state change information of each energy system, perform feature dimension reduction and information decoupling through the principal component analysis method to obtain the independent state change information of each energy system, and achieve the tracing and decoupling of state information.

[0027] Specifically, obtain the real-time status data of electric energy, thermal energy, and gas energy. For example, obtain the electricity consumption of each household per minute through a smart meter, obtain the heating temperature and flow rate through sensors in the heat station, and obtain the natural gas usage through a flow meter in the gas pipeline. Preprocess the data, such as interpolating missing data, removing abnormal data, and performing data smoothing to reduce noise interference. Extract key features reflecting energy fluctuations, such as the peak, valley, and average values of electricity consumption, the change rate of heating temperature, and the fluctuation amplitude of natural gas usage, etc. These features can reflect the operating status and change trends of the energy system. To study the mutual influence between different energies, it is necessary to construct a multi-energy flow coupling relationship diagram. The nodes of the diagram represent different types of energy, such as electric energy, thermal energy, and gas energy. The edges represent the coupling relationships between energies. For example, natural gas can be used for power generation, thus converting gas energy into electric energy; electric energy can be used to drive a heat pump to convert electric energy into thermal energy; natural gas can be directly used for heating to convert gas energy into thermal energy. The weights on the nodes and edges can represent the efficiency or proportional relationship of energy conversion. For example, the efficiency of gas-fired power generation can be set to 4, indicating that for every 1 unit of natural gas input, 4 units of electric energy can be generated. For the nodes and edges in the graph model, define the quantitative causal relationship strength through physical knowledge and expert experience. For example, an increase in gas price will lead to more users using electric energy for heating, so the causal relationship strength of gas energy on electric energy can be set to 8, indicating that an increase in gas price has a strong impact on the demand for electric energy. If a large number of heat pumps are used for heating in a certain area, then the impact of electricity price fluctuations on the demand for thermal energy will also be relatively large, so the causal relationship strength of electric energy on thermal energy can be set to 7. These causal relationship strength values form the basis of causal reasoning. Suppose it is detected that the power load suddenly rises and exceeds the preset threshold, then it is judged that a significant state change has occurred in the power system. At this time, it is necessary to trace the potential impact of this change on other energies on the causal graph. Through the shortest path search algorithm based on the graph, the impact path of the rising power load can be found. For example, if the path is "electric energy - thermal energy", it indicates that the rising power load mainly affects the thermal energy system. Suppose a large number of electric heat pumps are used for heating in this area, and due to an increase in electricity price or other reasons, the power load rises. Users may reduce the use of heat pumps, resulting in a decrease in the demand for thermal energy. According to the results of causal reasoning, the affected energy system and the corresponding state change amplitude can be obtained. For example, through causal reasoning, it can be concluded that a 10% increase in the power load may lead to a 5% decrease in the demand for thermal energy. This information can be used to guide the coordinated operation and optimal control of the multi-energy system. Finally, in order to distinguish the state changes of different energy systems themselves and the state changes affected by other energy systems, it is necessary to decouple the state information. For example, suppose the power load rises by 10%, and at the same time, due to a decrease in temperature, the demand for thermal energy rises by 8%.Through the principal component analysis method for feature dimensionality reduction and information decoupling, the increase in power load and the increase in heat energy demand can be separated, and the independent state change information of the power system and the heat energy system can be obtained respectively. This helps to analyze the operating status of each energy system more accurately and conduct more targeted regulation. For example, according to the decoupled information, it can be judged whether the main reason for the increase in power load is external factors (such as a decrease in temperature) or internal factors of the system (such as equipment failure), and corresponding measures can be taken.

[0028] Step S104, for the real-time processing of massive multi-source heterogeneous state information, a distributed stream computing framework is adopted to construct an efficient state information processing pipeline. Through technologies such as data sharding and parallel computing, the real-time performance and scalability of state information processing are improved.

[0029] Obtain a large amount of heterogeneous status information from multiple data sources, preprocess and clean the raw data, filter out invalid, duplicate, and abnormal data, and improve data quality. Parse and convert the data formats and protocols of different data sources, and unify them into a standardized data format, such as JSON or Avro. According to the characteristics and processing requirements of the status information, design a reasonable data sharding strategy to divide the status information into multiple data shards, and each shard contains a part of the status information. The data sharding strategy can be divided according to dimensions such as the timestamp of the status information and the device ID to ensure the balance of the data volume of each shard. For each data shard, use a distributed stream computing framework such as Apache Flink for parallel processing. In Flink, build a computational topology for status information processing, define operators such as data source (Source), data transformation (Transformation), and data output (Sink), and specify the data flow and dependency relationships between operators. In the data transformation operator, perform real-time processing on the status information of each data shard. Through operations such as data transformation and data aggregation, extract key information, calculate relevant metrics, and generate processing results. Common transformation operations include Map, Filter, Aggregate, etc. Use a message queue such as Kafka to summarize and merge the processing results of the distributed stream computing framework to obtain the complete status information processing result. Format and store the processing result, and write it into the distributed file system HDFS or the database system HBase for subsequent analysis and application. Monitor the running status and performance metrics of the stream computing framework, and use the built-in monitoring and measurement system of Flink to collect metrics such as the processing latency and throughput of each operator. For operators with high processing latency or heavy load, optimize them by increasing the parallelism, adjusting the resource allocation of the operator, etc., to ensure the real-time and stability of status information processing. According to the changing requirements of status information processing and the growth of data volume, flexibly expand the computing resources of the stream computing framework. By increasing the number of working nodes in the Flink cluster, improve the parallel processing ability of the system. At the same time, optimize the data sharding strategy, adjust the granularity and distribution of data shards, balance the data volume and processing load of each shard, and improve the scalability and throughput of the system.

[0030] Specifically, in modern data processing scenarios, in the face of a vast amount of heterogeneous state information from multiple data sources, the first step is data preprocessing and cleaning. For example, a large-scale power monitoring system may collect data from thousands of smart meters. This data may contain outliers caused by equipment failures or transmission errors. By setting thresholds, these abnormal data can be identified and eliminated, such as when a meter suddenly reports a negative or extremely high electricity consumption value. In addition, data deduplication is another crucial step to ensure the accuracy of analysis. For instance, duplicate data records at the same time point need to be merged or deleted. The unification of data formats is another important aspect of processing heterogeneous data. Suppose the data obtained from different meters has various formats, some in XML format and some in CSV format. By writing conversion scripts, all data is converted into JSON format. The flexibility and easy-to-parse characteristics of this format make subsequent processing more efficient. In the design of data sharding strategies, data can be divided according to the timestamp and device ID of the data. For example, data within a day can be sharded by hour, and each shard contains the data of all devices within that hour. This method not only helps balance the data volume of each shard but also optimizes the subsequent parallel processing performance. When using Apache Flink for real-time processing of data streams, the constructed computing topology will include multiple components such as data sources, transformations, and outputs. During the data transformation process, for example, a timestamp field can be added to each piece of data through a Map operation, and the total electricity consumption for each hour can be calculated through an Aggregate operation. The results of these real-time calculations can be aggregated through Kafka and then uniformly stored in HDFS or HBase to provide support for subsequent data analysis and decision-making. Monitoring the running status of the stream computing framework is the key to ensuring system stability. Through Flink's monitoring system, the processing latency and throughput of each operator can be collected and analyzed in real time. If it is found that the latency of a certain operator increases abnormally, its resource allocation may need to be adjusted, such as increasing the parallelism, to ensure the efficiency and stability of the entire data processing process. With the growth of data volume and the change of processing requirements, the scalability of the system is also particularly important. By increasing the number of nodes in the Flink cluster, the processing capacity of the system can be improved. At the same time, optimizing the data sharding strategy and adjusting the sharding granularity and distribution can further improve the processing efficiency and load balancing of the system. The implementation of these steps and strategies not only improves the efficiency and accuracy of data processing but also ensures that the system can flexibly respond to changing business requirements and data scales, thereby supporting complex data analysis and intelligent decision-making.

[0031] In step S105, in response to the high reliability requirement of power grid energy disturbance suppression for state information transmission, a blockchain-based data security transmission mechanism is adopted. By utilizing the characteristics of blockchain such as decentralization and immutability, the data integrity and non-repudiation during the state information transmission process are guaranteed, and the transmission reliability is enhanced.

[0032] Obtain the data of the change in state information caused by power grid energy disturbances, and preprocess the data, including operations such as denoising and normalization, to improve the data quality. Judge whether the state information exceeds the allowable range according to the preset threshold. If it exceeds, trigger the blockchain data transmission mechanism. Use blockchain technology to build a decentralized state information transmission network. Each node verifies the authenticity and integrity of the state information through the Raft consensus algorithm to ensure that the data is not tampered with. Use the SHA-256 encryption algorithm to encrypt the state information data and then store it on the chain. Utilize the chain structure and hash pointers of the blockchain to ensure the timeliness and immutability of the data. During the state information transmission process, write smart contracts through Solidity to automatically perform data verification and integrity checks. Set data verification rules and integrity requirements in the contract. Once it is found that the data is tampered with or lost, immediately start the data recovery mechanism to obtain complete data from other nodes. Based on the differential privacy algorithm, achieve multi-party participation in state information fusion calculation without revealing the original data. Each node locally adds random noise to the original data using the differential privacy algorithm, and then uploads the noisy data to the blockchain network for fusion calculation to improve the accuracy of data analysis and decision-making. Utilize the non-repudiation feature of the blockchain to record the data transmission and reception behaviors of each node, and store the operation logs on the blockchain. Once a dispute occurs, the responsibility can be traced according to the log information to improve the cooperation reliability of all parties. Optimize the throughput and latency of the blockchain network. Introduce the Merkle tree structure to store state information to reduce the storage overhead. Use the PBFT consensus algorithm to replace the Raft algorithm to improve the consensus efficiency. Improve the real-time transmission efficiency of state information while ensuring security.

[0033] Specifically, in modern power grid management systems, the real-time monitoring and processing of power grid energy disturbances are of crucial importance. First of all, for the data collected from sensors and smart meters, denoising and normalization are necessary steps. For example, if a certain area in the power grid generates noise due to equipment failures, such as abnormal voltage fluctuations, the denoising algorithm can effectively identify and filter out these abnormal fluctuations, while the normalization process ensures that data from different devices can be compared under the same standard, thereby improving the accuracy of data processing. After data preprocessing, the system determines whether the status information is normal according to preset thresholds. For example, the normal operating range of voltage is set to 220V ± 5V. If the voltage at a certain time point is detected to exceed this range, the system regards this as an abnormal event and triggers the blockchain data transmission mechanism. The introduction of this mechanism is to utilize the decentralized and immutable characteristics of the blockchain to ensure the authenticity and integrity of abnormal data. In the blockchain network, each node uses the Raft consensus algorithm to verify the authenticity of the data. The Raft algorithm ensures that the leader node in the network has the latest and correct data status through an election mechanism, and other nodes will update based on the leader's data, so that the status information can be synchronized quickly and accurately across the entire network. At the same time, the SHA-256 encryption algorithm is used to encrypt the data to ensure the security of the data during transmission. Smart contracts play the role of automatically executing data verification and integrity checks in this process. By writing specific data verification rules in the contract, such as checking whether the data is within the normal range, and integrity requirements, such as whether the data packet is complete without being truncated or tampered with. Once the smart contract detects data problems, it will automatically trigger a data recovery mechanism, such as requesting missing or tampered data segments from other nodes in the blockchain network. In addition, the application of differential privacy algorithms allows for cross-node data fusion calculations without revealing specific user data. Each node adds random noise to the data locally and then uploads it to the blockchain for centralized calculation. This method not only protects user privacy but also improves the accuracy and reliability of data processing. Finally, to improve the processing efficiency of the blockchain network, the Merkle tree structure can be introduced to optimize data storage, and a more efficient PBFT consensus algorithm may be adopted to replace the Raft algorithm, which not only ensures the security of the network but also improves the real-time transmission efficiency of status information. The comprehensive application of these technologies not only improves the efficiency and accuracy of power grid status information processing but also ensures that the system can flexibly respond to changing business requirements and data scales, thereby supporting complex data analysis and intelligent decision-making.

[0034] Step S106, for the intelligent analysis requirements of status information, a deep learning algorithm is adopted to construct an intelligent analysis model of status information. Through the training and learning of historical status information, the multi-energy flow coupling relationship and evolution law are mined to achieve the intelligent analysis and prediction of status information.

[0035] According to the historical status information, first, data cleaning techniques such as removing missing values and outliers are used to preprocess the data, and then standardization is performed to scale the data to a unified range, obtaining a normalized status information dataset. For the normalized status information dataset, feature engineering methods such as statistical features, time-domain features, and frequency-domain features are used to extract key features that can reflect the status characteristics. Then, feature selection techniques such as the filtering method and the wrapper method are used to select the most discriminative and relevant feature subset. The processed dataset is divided into a training set and a test set according to a certain ratio, such as 8:2. The training set is used for model training, and the test set is used for model evaluation. According to the dimension of the optimal feature subset, the input layer of the convolutional neural network is designed. Then, by stacking multiple convolutional layers and pooling layers, high-level features of the data are extracted. The convolutional layer uses a 3x3 or 5x5 convolutional kernel, and the activation function uses ReLU. The pooling layer uses max pooling to reduce the size of the feature map. Finally, through the fully connected layer and the Softmax layer, the classification prediction of the status is realized. During model training, the cross-entropy loss function is used, and the Adam optimization algorithm is used for optimization. Hyperparameters such as the learning rate, batch size, and number of iterations are tuned through methods such as grid search to improve the performance of the model. For new input data, first, preprocessing and feature extraction are performed in the same way as the training data, and then it is input into the trained model to obtain the status prediction result. Using dimensionality reduction algorithms such as t-SNE, the high-dimensional status features are mapped onto a two-dimensional plane, and the distribution and relationship between different statuses are intuitively displayed through a scatter plot. Methods such as Markov chains are used to analyze the transition probability between statuses, construct a status transition map, and reveal the status evolution law. Visualization libraries such as Matplotlib and Seaborn are used to generate line charts, bar charts, heatmaps, etc., to display the status change trend, distribution, and correlation. An interactive interface is designed to allow users to explore and analyze the status data through operations such as filtering, zooming, and hovering, providing intuitive decision support.

[0036] Specifically, the high-reliability requirement for power grid energy disturbance suppression in state information transmission has prompted the adoption of more advanced data processing and machine learning technologies. To ensure the accuracy and reliability of state information, it is first necessary to clean the original data. For example, there may be missing values or outliers in the voltage data collected by sensors. For instance, a reading of -1000V due to sensor failure is obviously unreasonable. Missing values can be supplemented by interpolation method, and outliers can be removed using the 3σ criterion. The abnormal -1000V can be replaced with the voltage value at the adjacent moment. The data after cleaning is more real and reliable, laying a foundation for subsequent analysis. Next, it is necessary to standardize the cleaned data. For example, the unit of voltage is volt and the unit of current is ampere, and their numerical ranges vary greatly. To eliminate the influence of dimensions, the voltage and current data can be scaled between 0 and 1, so that data with different characteristics can be compared on the same scale, avoiding some characteristics having too much impact on model training due to large numerical values. After obtaining the normalized state information dataset, key features need to be extracted. For example, statistical features such as the mean and variance of voltage can be calculated to reflect the overall level and fluctuation of voltage. Time-domain features such as the zero-crossing rate and frequency of voltage can also be extracted to reflect the change speed and periodicity of voltage. In addition, spectral features of voltage can be extracted to reflect the energy distribution of different frequency components in voltage. These features can describe the power grid state more comprehensively and provide richer information for subsequent model training. Not all extracted features are helpful for state prediction. Therefore, feature selection is required. For example, the filtering method can be used to calculate the correlation coefficient between each feature and the target variable, and features with higher correlation are selected. Or the wrapper method can be used to select the feature subset that maximally improves the model performance through repeated model training. Suppose that after feature selection, three features, namely the voltage mean, variance, and zero-crossing rate, are finally selected as the optimal feature subset. Dividing the dataset into a training set and a test set is also a very important step. For example, 80% of the data can be used as the training set to train the model, and the remaining 20% of the data can be used as the test set to evaluate the performance of the model. Such a division can effectively avoid model overfitting and improve the generalization ability of the model. According to the selected feature subset, the structure of the convolutional neural network can be designed. For example, if three features are selected, the input layer dimension of the convolutional neural network is 3. The convolutional layer can use a 3x3 convolutional kernel, and the ReLU activation function can effectively avoid the problem of gradient disappearance. The pooling layer can adopt max pooling to reduce the size of the feature map and reduce the computational amount. The fully connected layer integrates the extracted high-level features, and finally the Softmax layer outputs the prediction result of the state. For example, the power grid state is divided into three states: normal, warning, and fault. During the model training process, the cross-entropy loss function can be used to measure the gap between the model prediction result and the true label. The Adam optimization algorithm can adaptively adjust the learning rate and accelerate the model convergence speed.By methods such as grid search, the optimal hyperparameters such as learning rate, batch size, and number of iterations can be found to further improve the performance of the model. For new input data, it needs to be processed according to the same preprocessing and feature extraction steps as the training data, and then input into the trained model to obtain the state prediction result. For example, if the new input data is the voltage and current values at a certain moment, these data need to be cleaned and standardized first, and then features such as voltage mean, variance, and zero-crossing rate are extracted. Finally, these features are input into the trained model to obtain the prediction result of the power grid state. To more intuitively display the relationship between states, dimensionality reduction algorithms such as t-SNE can be used to map high-dimensional features onto a two-dimensional plane. For example, the sample points of different states can be represented by different colors to observe their distribution on the two-dimensional plane. If the sample points of different states can be clearly separated, it indicates that the classification effect of the model is good. Markov chains can be used to analyze the transition probabilities between states. For example, the probability of the power grid transitioning from the normal state to the warning state and the probability of transitioning from the warning state to the fault state can be calculated. These probabilities can help better understand the evolution law of the power grid state and take preventive measures in advance. Visualization libraries such as Matplotlib and Seaborn can be used to generate various charts. For example, a line chart can be used to show the change trend of voltage over time, a bar chart can be used to show the number of samples in different states, and a heatmap can be used to show the correlation between features. An interactive interface allows users to more conveniently explore and analyze data. For example, users can click on a sample point to view its detailed information or zoom in and out of the chart by dragging the mouse. These visualization means can provide more intuitive support for decision-making.

[0037] Step S107, finally, fuse and correlate the data processing results of each link to form a global view of the electro-thermal-gas state information, and intuitively present the real-time operating state of the multi-energy flow system through visualization technology, providing information support and decision-making basis for power grid energy disturbance suppression.

[0038] Obtain the real-time operation data of the power grid, heat grid and gas grid, comprehensively perceive the operation status of each energy network and conduct unified modeling to form the global status information of the multi-energy flow system. Preprocess the obtained multi-source heterogeneous data, improve the data quality through operations such as data cleaning and normalization, and extract key feature parameters. For the real-time status data of the multi-energy flow system after preprocessing, adopt data fusion technologies such as Kalman filtering for correlation analysis, explore the internal connections and mutual influence laws between different energy networks, and realize the integrated representation of multi-source heterogeneous data. Train the historical operation data of the multi-energy flow system through the long short-term memory (LSTM) neural network, establish an energy disturbance prediction model, and judge the power grid energy disturbance risk in real time. When a large energy disturbance is predicted, timely output early warning information. According to the global status information of the multi-energy flow system and the energy disturbance prediction results, adopt the particle swarm optimization algorithm to automatically generate the power grid energy disturbance suppression strategy, and feedback the strategy decision information to the power grid dispatching control system. Use the JavaScript Djs library to visually present information such as the real-time operation status, energy disturbance prediction and suppression strategy of the electric-thermal-gas multi-energy flow system, and form a global multi-energy flow monitoring view through dynamic interactive charts to provide auxiliary decision-making support for power grid dispatchers. Continuously analyze the historical operation data of the multi-energy flow system through the association rule mining algorithm, summarize the characteristic patterns and coping experiences of power grid energy disturbances, dynamically adjust the LSTM model hyperparameters and particle swarm algorithm parameters, and continuously improve the adaptive ability of the system. Build a distributed data management platform based on Hadoop and HBase to realize the distributed storage of multi-source data such as electric-thermal-gas, MapReduce parallel processing and API shared applications, and provide efficient and scalable data infrastructure support for power grid energy disturbance suppression.

[0039] Specifically, obtaining the real-time operation data of the power grid, heat grid, and gas grid is the first step in the management of the multi-energy flow system. For example, in an energy management center of a city, through intelligent sensors installed at different nodes, the voltage and current data of the power grid, the temperature and flow data of the heat grid, and the pressure and flow data of the gas grid can be monitored in real time. These data are transmitted back to the data center through a high-speed communication network, forming a comprehensive dataset of the operation status of the energy network. For these multi-source heterogeneous data, it is necessary to perform data cleaning and normalization first. Data cleaning includes removing error readings and duplicate data. For example, if sensor failures result in abnormal voltage readings at a certain moment, these data need to be identified and processed. Normalization is to convert data with different dimensions to the same scale. For example, both voltage and temperature data are converted to the range of 0 to 1, which helps with subsequent data analysis and model training. After data preprocessing, data fusion technologies such as Kalman filtering are used to perform correlation analysis on the data, which can effectively explore the mutual influences between different energy networks. For example, a sudden increase in the load of the power grid may affect the operation efficiency of the heat grid. Through Kalman filtering, the degree of this influence can be estimated in real time, and predictions can be made about future states. Using a Long Short-Term Memory (LSTM) neural network to train historical data can establish an energy disturbance prediction model. This model can learn the time series characteristics of the power grid load changes, so as to judge and warn of possible energy disturbance risks in real time during actual operation. For example, if the model predicts a large-scale load increase in the power grid within the next hour, the system can adjust the power generation plan in advance or activate the backup energy system. According to the prediction results, a particle swarm optimization algorithm is used to automatically generate power grid energy disturbance suppression strategies. The particle swarm optimization algorithm finds the optimal solution by simulating the foraging behavior of bird flocks and can quickly find the best energy allocation strategy among multiple possible scheduling schemes. These strategies can then be implemented through the power grid scheduling system to ensure the stable operation of the power grid. Through the Djs library of JavaScript, information such as the real-time operation status, energy disturbance prediction, and suppression strategies of the electric-thermal-gas multi-energy flow system can be visually presented. Dynamic interactive charts can not only display the current energy flow situation but also simulate the future energy distribution situation, providing an intuitive decision-making support tool for dispatchers. In addition, through continuous association rule mining, patterns in historical data can be analyzed to summarize the characteristics and response strategies of power grid energy disturbances. This information can be used to dynamically adjust the parameters of the LSTM model and the particle swarm algorithm, improving the adaptability and prediction accuracy of the system. Finally, building a distributed data management platform based on Hadoop and HBase can achieve the efficient processing and storage of multi-source data such as electricity, heat, and gas. Using MapReduce parallel processing technology, large-scale datasets can be quickly processed, ensuring the response speed of real-time data analysis and providing strong data support for power grid energy disturbance suppression.

[0040] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments only. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the present invention, so that those skilled in the art can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A method for suppressing power grid energy disturbances through collaborative transmission of electro-thermal gas state information, characterized in that include: Obtain multi-source heterogeneous state information of electric, thermal and gas energy networks; Adopting adaptive communication protocol conversion technology to dynamically convert heterogeneous communication protocols into a unified protocol format for the multi-source heterogeneous state information; For the converted state information, a multi-energy flow coupling relationship diagram of the energy network is constructed based on a graphical model. The decoupling and traceability of the state information are achieved through causal reasoning analysis methods. These include: using a graphical model to characterize the correlation structure of multi-energy flow data to address the strong coupling of electric, thermal, and gas energy fluctuations; learning the implicit dependencies of multi-energy flow data through graph embedding and graph neural networks; and building a causal reasoning rule base based on the law of conservation of energy to trace the impact chain of state changes in a single energy system. For the decoupled state information, a distributed stream computing framework is used for parallel processing to improve the real-time and scalability of state information processing; The results of stream computing are authenticated and verified using a blockchain-based security consensus mechanism to ensure the credibility of status information. Build an intelligent analysis model for state information based on deep learning algorithms to mine the correlation characteristics and evolution laws contained in multi-energy flow data; Visualization technology is used to generate a global status information view of the electric, heat and gas energy network, providing auxiliary decision-making for energy network scheduling optimization.

2. The method according to claim 1, wherein The obtaining of multi-source heterogeneous state information of the electric, thermal and gas energy network includes: Determine the frequency, data format, and time scale for collecting status information of each energy system based on the physical characteristics of the electric, thermal, and gas energy network; Through data standardization, the status information of heterogeneous energy networks is converted into a unified format; Realize the interoperability and integration of status information.

3. The method according to claim 1, characterized in that, The adaptive communication protocol conversion technology is used to dynamically convert heterogeneous communication protocols into a unified protocol format, including: Dynamically match and convert various communication protocols based on differences in communication modes and protocol standards for different regions and devices; Use data sharding and parallel transmission technology to improve communication efficiency; Communication security is ensured through lightweight encryption and digital signatures.

4. The method according to claim 1, wherein The parallel processing using a distributed stream computing framework includes: Build an efficient state information processing pipeline for massive multi-source heterogeneous state information; Improve the real-time and scalability of state information processing through data sharding and parallel computing technology; Adopt the optimization strategy of memory computing and incremental processing to reduce computing overhead.

5. The method according to claim 1, wherein The blockchain-based security consensus mechanism is used for rights confirmation and verification, including: Divide the stream calculation results into blocks and generate hash fingerprints and timestamps; Through consensus algorithms and smart contracts, nodes in the blockchain network can be collaboratively verified; The verified status information is stored on the chain to ensure that the data cannot be tampered with and is traceable.

6. The method according to claim 1, wherein The state information intelligent analysis model based on the deep learning algorithm is constructed, including: For multi-source heterogeneous state information, transfer learning method is used to achieve cross-domain knowledge fusion; Through the spatiotemporal sequence prediction model, the dynamic change rules of state information are explored; Combined with the reinforcement learning framework, the scheduling strategy of the energy network is adaptively optimized.

7. The method according to claim 1, characterized in that, The generation of a global state information view of the electric, heat and gas energy network by visualization technology includes: Design multi-level visualization views for multi-dimensional and multi-granular status information; Through the human-computer interaction interface, it supports the dynamic query and correlation analysis of status information; Combined with virtual reality and augmented reality technologies, it constructs an immersive visualization scenario to enhance the intuitive understandability of system operation.

8. The method according to claim 3, wherein The dynamic matching and conversion of various communication protocols include: For the received electro-thermal-gas status information, extract its communication protocol type and parameters, match and compare them with the protocols in the communication protocol knowledge base, and judge whether protocol conversion is required; If protocol conversion is required, according to the conversion rules in the communication protocol knowledge base, use the Scapy library in Python to dynamically generate a protocol conversion script to perform format and parameter conversion processing on the original communication protocol.

9. The method according to claim 3, characterized in that: The use of data sharding and parallel transmission technologies to improve communication efficiency means that in the process of communication resource coordination, a dynamic resource allocation algorithm based on device priority is adopted. According to the communication modes, data volumes of devices in different regions and the preset device priorities, use the Schedule library in Python to dynamically schedule and allocate MQTT topics and QoS communication resources to ensure the efficiency and reliability of data transmission; In response to the real-time requirement of electrothermal gas status information, by setting the retention flag and QoS level of MQ TT messages, and using the CoAP protocol to asynchronously report the status change data.

Images