Real-time monitoring method and system for multi-modal industrial internet of things data

Abstract

The present application relates to the technical field of power distribution network, in particular to a real-time monitoring method and system for multi-modal industrial internet of things data. According to the correlation degree of the fluctuation of the power index of each node in the virtual power plant and any other node within the monitoring period, and the electrical connection density and production state similarity of the corresponding two nodes, the running influence degree of each node on any other node at the current time is obtained. According to the deviation degree and deviation time of the power index of each node in the virtual power plant relative to the state similar time, and the running influence degree, the impedance affected degree of each node at the current time is obtained, and combined with the power supply and consumption capacity, the response priority of each node in the virtual power plant at the current time is obtained, and the sequence of executing the virtual power plant scheduling instruction of each node is determined. The present application considers the influence of line impedance and the mutual influence between devices, makes the response priority more reliable, and enhances the operation flexibility, safety and stability of the industrial park power distribution network.

Description

Technical Field

[0001] This invention relates to the field of power distribution network technology, and more specifically to a real-time monitoring method and system for multimodal industrial IoT data. Background Technology

[0002] In the field of industrial power distribution networks, virtual power plants are an important technical means to integrate distributed resources and participate in power distribution network dispatch. Virtual power plants have dispersed resources and limited capabilities, while power grid dispatching needs are real-time and variable. In order to meet power grid needs in the lowest cost and most reliable way, virtual power plants must intelligently allocate tasks and determine the priority of each node in the virtual power plant in responding to its dispatching instructions.

[0003] Industrial production systems are cyber-physical systems with deeply coupled power and production modes. Currently, power consumption monitoring in industrial parks is typically based on multimodal industrial IoT data from nodes in a virtual power plant. The virtual power plant receives power control commands from the local distribution network and power supply and consumption data from equipment, determining response priorities based on the inherent power supply and consumption capabilities of nodes or fixed scheduling models. However, equipment in industrial parks is tightly interconnected through rigorous production processes. An abnormal operating state of a single device can lead to abnormal fluctuations such as sudden current spikes in its upstream and downstream equipment. Furthermore, the line impedance of equipment changes with industrial production processes, causing the node's power indicators to fail to reflect the true power state. This results in biases in the assessment of node response capabilities, i.e., response priorities. Summary of the Invention

[0004] To address the technical problem of biased response priority assessment caused by ignoring dynamic impedance changes in node lines, the present invention aims to provide a real-time monitoring method and system for multimodal industrial IoT data. The specific technical solution adopted is as follows:

[0005] In a first aspect, one embodiment of the present invention provides a real-time monitoring method for multimodal industrial IoT data, the method comprising:

[0006] Obtain different types of power indicators for each node in the virtual power plant of the industrial park at each moment during the current monitoring period;

[0007] Based on the correlation between the fluctuations of the same power index between each node in the virtual power plant and any other node during the monitoring period, as well as the electrical connection tightness and production status similarity between the corresponding two nodes, the operational impact of each node in the virtual power plant on any other node at the current moment is obtained.

[0008] Select a state-similar moment from the monitoring period; based on the degree and time of deviation of the power index of each node in the virtual power plant relative to the state-similar moment, and the operational impact of each node on the other nodes, obtain the impedance impact of each node in the virtual power plant at the current moment.

[0009] Based on the power supply and consumption capacity of each node at the current moment and the degree of impedance influence, the response priority of each node in the virtual power plant at the current moment is determined, and the order in which each node executes the virtual power plant dispatching instructions is determined.

[0010] Furthermore, obtaining the degree of operational influence of each node in the virtual power plant on any other node at the current moment includes:

[0011] Arrange the same power index of each node at all times during the monitoring period in chronological order to obtain the power sequence of each power index;

[0012] Calculate the transfer entropy of the power sequence of the same power index from each node in the virtual power plant to any other node, and take the average of the transfer entropy corresponding to all types of power indexes as the degree of correlation of each node's response to any other node at the current moment.

[0013] Obtain the power mode topology and the production mode topology;

[0014] Obtain the distance between each node in the virtual power plant and any other node in the power mode topology and the production mode topology, respectively, and use the product of the two distances as the power production mode distance between the corresponding two nodes;

[0015] Based on the correlation degree of the response and the distance of the power production mode, the operational influence of each node in the virtual power plant on any other node at the current moment is obtained.

[0016] Furthermore, obtaining the impedance influence degree of each node in the virtual power plant at the current moment includes:

[0017] The power indicators include current values; based on the difference in current values ​​of each node at the current time and at a time similar to the state, target deviation times are selected from the time similar to the state; several target deviation time periods are formed by consecutive target deviation times within the monitoring period; the maximum value of the duration of all target deviation time periods and the maximum value of the duration of the remaining time periods within the monitoring period excluding the target deviation time periods are recorded as the deviation time length;

[0018] The overall impact of each node in the virtual power plant on the operation of all other nodes at the current moment is averaged to obtain the overall impact of each node at the current moment.

[0019] The absolute values ​​of the current differences between each node at the current time and at all times with similar states are averaged to obtain the overall current difference of each node at the current time.

[0020] Based on the deviation time length, the overall influence degree, and the overall current difference, the impedance influence degree of each node in the virtual power plant at the current moment is obtained.

[0021] Furthermore, the selection of the target deviation time among the similar state times includes:

[0022] Calculate the mean value of the current value of each node at all times during the monitoring period, and record the difference between the current value of the corresponding node at the current time and the mean value as the reference current difference of each node.

[0023] Calculate the difference in current value between each node at the current time and all similar times in the state. Select the similar times in the state corresponding to the current value difference that is greater than the reference current difference and record them as the target deviation time.

[0024] Furthermore, determining the response priority of each node in the virtual power plant at the current moment includes:

[0025] Obtain the actual power supply and consumption of each node in the virtual power plant at the current moment; take the difference between the preset maximum power supply and consumption of each node in the virtual power plant and the actual power supply and consumption of the corresponding node at the current moment as the power supply and consumption capacity value of each node at the current moment.

[0026] Calculate the mean of the impedance influence of all nodes in the virtual power plant at the current time, and take the ratio of the impedance influence of each node at the current time to the mean as the impedance significance value of each node at the current time.

[0027] Based on the power supply and consumption capacity value and the impedance significance value, the response command capability value of each node in the virtual power plant at the current moment is obtained; the node with the larger the response capability value, the higher the response priority at the current moment.

[0028] Furthermore, selecting a state-similar moment from the monitoring period includes:

[0029] Based on the current values ​​of the public access point of the virtual power plant at all times during the current monitoring period, the monitoring period is divided into different sub-periods.

[0030] The range of the current values ​​at all times within each sub-period of the public access point is recorded as the current fluctuation value.

[0031] Select any moment within the monitoring period as the example moment. Based on the difference in current value between the public access point at the current moment and the example moment, as well as the difference in duration between the sub-periods of the two moments and the difference in current fluctuation value, obtain the state similarity value between the current moment and the example moment.

[0032] For the current moment, the state similarity with other moments within the monitoring period is used to select the other moments whose state similarity values ​​are greater than the preset similarity threshold and record them as the state similar moments of the current moment.

[0033] Furthermore, the power supply and consumption capacity value is positively correlated with the response command capacity value, and the impedance significance value is negatively correlated with the response command capacity value.

[0034] Furthermore, the method for dividing the monitoring period into different sub-periods is an adaptive piecewise constant approximation algorithm.

[0035] Furthermore, the last moment within the monitoring period is the current moment.

[0036] Secondly, another embodiment of the present invention provides a real-time monitoring system for multimodal industrial IoT data, the system comprising:

[0037] The data acquisition module is used to acquire different types of power indicators for each node in the virtual power plant of the industrial park at each moment during the current monitoring period.

[0038] The node impact analysis module is used to obtain the degree of operational impact of each node in the virtual power plant on any other node at the current moment, based on the degree of correlation between the fluctuation of the same power index between each node and any other node in the monitoring period, as well as the electrical connection tightness and production status similarity between the corresponding two nodes.

[0039] The impedance impact analysis module is used to select a state-similar moment from the monitoring period; based on the degree and time of deviation of the power index of each node in the virtual power plant relative to the state-similar moment, and the operational impact of each node on the other nodes, the impedance impact degree of each node in the virtual power plant at the current moment is obtained.

[0040] The priority analysis module is used to determine the response priority of each node in the virtual power plant at the current moment based on the power supply and consumption capacity of each node at the current moment and the degree of impedance influence, and to determine the order in which each node executes the virtual power plant scheduling instructions.

[0041] The present invention has the following beneficial effects:

[0042] In this embodiment of the invention, the degree of correlation of power index fluctuations between nodes reflects the response under the power production mode. The tightness of electrical connections between nodes and the similarity of production status jointly determine the degree of mutual influence between nodes. Comprehensive analysis can avoid the limitations of starting from a single power mode or simple power grid topology, reveal the real mutual influence relationship between nodes under complex production processes, and obtain the operational influence degree. By the degree and time of deviation of power index of each node relative to the state similarity moment, the impedance influence is separated from the instantaneous fluctuation interference. Combined with the operational influence degree, the impedance influence degree of the node is accurately assessed. The priority assessment references the real power status of the node, which fundamentally solves the problem of response priority assessment deviation caused by ignoring the dynamic impedance changes of the node line. The power supply and consumption capacity and the impedance influence degree represent the node's ability and efficiency to respond to the virtual power plant command, respectively. Combining the two further makes the response priority more reliable. This solution follows the changes in production processes and power grid status, ensuring that the response priority of nodes is synchronized with the actual operating status of the industrial park. Based on the response priority, the order in which each node executes the virtual power plant dispatching instructions is determined. This not only improves the response reliability of the virtual power plant, but also suppresses abnormal fluctuations in the local power grid through precise load allocation, thereby enhancing the operational resilience and safety stability of the industrial park's distribution network. Attached Figure Description

[0043] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a flowchart illustrating the steps of a real-time monitoring method for multimodal industrial IoT data provided in one embodiment of the present invention.

[0045] Figure 2 This is a flowchart illustrating a method for obtaining the degree of impedance influence according to an embodiment of the present invention.

[0046] Figure 3 This is a system architecture diagram of a real-time monitoring system for multimodal industrial IoT data provided in one embodiment of the present invention;

[0047] Figure 4 This is a schematic diagram of a computer device for real-time monitoring of multimodal industrial IoT data, provided as an embodiment of the present invention. Detailed Implementation

[0048] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a real-time monitoring method and system for multimodal industrial IoT data proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0050] The following description, in conjunction with the accompanying drawings, details a specific scheme for a real-time monitoring method and system for multimodal industrial IoT data provided by this invention.

[0051] Example 1:

[0052] This invention proposes a real-time monitoring method for multimodal industrial IoT data. Please refer to [link / reference]. Figure 1 The diagram illustrates a flowchart of a real-time monitoring method for multimodal industrial IoT data according to an embodiment of the present invention. The method includes:

[0053] Step S1: Obtain the different types of power indicators for each node in the virtual power plant of the industrial park at each time during the current monitoring period.

[0054] The power-consuming equipment, power generation equipment, and energy storage equipment within the industrial park are considered nodes in a virtual power plant. Power generation equipment typically refers to new energy equipment such as photovoltaic power generation devices. Multimodal data collection is performed on the virtual power plant of the industrial park. Specifically, smart meters are used to collect different types of power indicators for each node in the virtual power plant at each moment within the current monitoring period. The last moment of the monitoring period is taken as the current moment. In this embodiment, the power indicators include: voltage value, current value, and output power.

[0055] In one implementation of this invention, the data acquisition frequency of the smart meter for collecting electricity indicators is set to once per second, and the monitoring period is 24 hours. The implementer can set this according to the specific circumstances.

[0056] Step S2: Based on the correlation between the fluctuation of the same power index between each node in the virtual power plant and any other node during the monitoring period, as well as the electrical connection tightness and production status similarity between the corresponding two nodes, obtain the degree of influence of each node in the virtual power plant on the operation of any other node at the current moment.

[0057] An industrial production system is a cyber-physical system with deeply coupled electrical and production modes. Within an industrial park, equipment (nodes) are tightly interconnected through rigorous production processes, forming a collaborative whole. Adjusting the operation of a single node based solely on its individual mode data may trigger a chain reaction due to a failure to perceive the overall system state. For example, reducing the load on a single node could cause abnormal fluctuations such as sudden current spikes in upstream and downstream equipment, thereby jeopardizing the stable operation of industrial equipment. Therefore, this study analyzes the correlation of fluctuations in electrical indicators among nodes in a virtual power plant to assess the response under the production electrical mode. Furthermore, considering the deep coupling between the electrical and production modes in an industrial production system, the tightness of electrical connections reflects the path of physical disturbance propagation, while the similarity of production states reflects functional dependencies and shared vulnerabilities. Thus, the tightness of electrical connections and the similarity of production states jointly determine the degree of mutual influence between nodes. By comprehensively analyzing the responses and mutual influence between nodes under the production electrical mode, the influence of each node on the operating state of other nodes is analyzed, yielding the operational impact degree.

[0058] Step S3: Select a state-similar moment from the monitoring period; based on the degree and time of deviation of the power index of each node in the virtual power plant relative to the state-similar moment, and the degree of influence of each node on the operation of other nodes, obtain the impedance influence of each node in the virtual power plant at the current moment.

[0059] When evaluating the responsiveness of nodes to virtual power plant commands based on multimodal IoT data related to "power-production," it is crucial to focus on whether their response behavior will have a cascading impact on the stability of the local power grid, making it difficult for nodes in the local grid to maintain stable operation. A key challenge lies in the fact that the dynamic impedance of the lines can cause the node's power indicators to fail to reflect the true power state, weakening the node's own stability maintenance capability. Furthermore, the degree to which each node is affected by impedance varies with changes in industrial production processes. Therefore, it is necessary to analyze the impedance impact on nodes at the current moment.

[0060] The fluctuations in a node's power indicators are jointly influenced by changes in its own power generation or consumption behavior and changes in the dynamic impedance of the power grid lines. To isolate the individual impact of dynamic impedance, it is necessary to control the node's operating state and determine a moment similar to the current operating state, i.e., the state-similar moment. The instantaneous fluctuations caused by changes in a node's own power generation or consumption behavior are extremely short-lived and result in drastic changes in power indicators. The power indicator changes caused by line impedance are relatively stable and last for a longer period. Therefore, by analyzing the degree and duration of deviation of each node's power indicators from the state-similar moment in the virtual power plant, the degree of impedance influence on that node at the current moment can be determined. Combined with the degree of influence of each node on the operation of other nodes, the degree of impedance influence on each node at the current moment can be obtained.

[0061] Step S4: Based on the power supply and consumption capacity and impedance influence of each node at the current moment, determine the response priority of each node in the virtual power plant at the current moment, and determine the order in which each node executes the virtual power plant dispatching instructions.

[0062] In a virtual power plant, a node's responsiveness refers to its ability to quickly and reliably execute virtual power plant dispatch commands. Power supply and consumption capacity represent a node's ability to respond to virtual power plant commands, while impedance sensitivity represents the efficiency of that response. Analyzing both together makes response prioritization more reliable. Prioritizing nodes with higher response priority to execute virtual power plant dispatch commands, such as increasing or decreasing generation capacity, not only improves the reliability of the virtual power plant's response but also, through precise load allocation, suppresses abnormal fluctuations in the local power grid, enhancing the operational resilience and stability of the industrial park's distribution network.

[0063] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the operational impact degree includes: arranging the same power indicators of each node at all times during the monitoring period in chronological order to obtain the power sequence of each power indicator; calculating the transfer entropy of the power sequence of the same power indicator from each node in the virtual power plant to any other node, and taking the average of the transfer entropies corresponding to all types of power indicators as the response correlation degree of each node to any other node at the current time; obtaining the power mode topology and the production mode topology; obtaining the distance between each node in the virtual power plant and any other node in the power mode topology and the production mode topology respectively, and taking the product of the two distances as the power production mode distance between the two corresponding nodes; and obtaining the operational impact degree of each node in the virtual power plant to any other node at the current time based on the response correlation degree and the power production mode distance.

[0064] In this embodiment of the invention, an electrical wiring diagram of the physical connection relationships of all equipment in an industrial park is obtained. Based on the electrical wiring diagram, cables between nodes in a virtual power plant are used as edges to construct a power modal topology. The manufacturing execution system, production planning system, and programmable logic controllers of the equipment in the industrial park define the product's process flow, clearly specifying which processes are required to produce a product and the order of these processes. The product production process flow and the corresponding process of the equipment in the virtual power plant can be directly determined. Each node in the virtual power plant is connected according to the process flow of its corresponding equipment to form a production modal topology. The power modal topology is an undirected graph, and the production modal topology is a directed graph. The distance between any two nodes in the power modal topology refers to the minimum number of edges (i.e., cable segments) required to connect the corresponding equipment of the two nodes. The distance between two nodes in the production modal topology refers to the minimum number of processes required to reach one node from another along the directed process flow between the two nodes.

[0065] It should be noted that the transfer entropy reflects the degree of correlation between the fluctuations of power indicators of two nodes. The degree of response correlation is obtained by comprehensively analyzing the response using the average transfer entropy of all types of power indicators and multimodal data. The greater the degree of response correlation, the more significant the impact of changes in the power indicators of any node on the fluctuation response of any other node. If the power production mode distance is smaller, the electrical connections between the two nodes are closer, and the production states of the two nodes are more similar, resulting in closer process connections, then the mutual influence between the two nodes is more significant. Therefore, the degree of response correlation is positively correlated with the degree of operational influence, while the power production mode distance is negatively correlated with the degree of operational influence. In this embodiment of the invention, the ratio of the degree of response correlation of each node to any other node at the current moment to the power production mode distance is normalized to obtain the degree of operational influence. If the degree of operational influence is larger, the impact of each node on the operation of the equipment corresponding to any other node is more significant. Among them, the negative correlation mapping of the distance between power production modes is achieved by taking the reciprocal, and the Sigmoid function is used for normalization. Alternatively, the data to be processed can be used as the exponent of an exponential function with the natural constant as the base to achieve the negative correlation mapping. Function transformation and other normalization methods are not limited here.

[0066] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining state similarity moments includes: dividing the monitoring period into different sub-periods based on the current values ​​of the common access point of the virtual power plant at all times within the monitoring period at the current time; recording the range of the current values ​​of the common access point at all times within each sub-period as the current fluctuation value; selecting any moment within the monitoring period as the example moment; obtaining the state similarity value between the current moment and the example moment based on the difference in the current value of the common access point at the current moment and the example moment, as well as the difference in the duration of the sub-periods and the difference in the current fluctuation value between the two moments; and selecting the remaining moments corresponding to the state similarity values ​​of the current moment and the other moments within the monitoring period that are greater than a preset similarity threshold as the state similarity moments of the current moment.

[0067] It should be noted that the common access point is the only interface connecting the virtual power plant to the main power grid. Its power indicators represent the overall operating status of the virtual power plant. Dividing the monitoring period into sub-periods for different operating modes based on the power indicators of the common access point can avoid inaccurate division of operating modes due to deviations caused by local factors affecting nodes. Because the current value has the most significant response to impedance among voltage, current, and output power, the analysis is based on the current value to determine the similarity of states and the degree of impedance influence. In this embodiment of the invention, an adaptive piecewise constant approximation algorithm is used to divide the monitoring period into sub-periods based on the current values ​​at all times within the monitoring period. The adaptive piecewise constant approximation algorithm is a well-known technique to those skilled in the art and will not be described in detail here.

[0068] The current value reflects the instantaneous operating state of the virtual power plant. The smaller the difference in current values ​​between two moments, the more similar the overall operating state of the virtual power plant is at those two moments. The current fluctuation value reflects the current fluctuation amplitude of a sub-time period. The smaller the current fluctuation value of the sub-time periods at two moments, the closer the load changes are to the two sub-time periods, resulting in a more similar operating state. The smaller the difference in duration of the sub-time periods at two moments, the closer the operating modes are to the two sub-time periods, resulting in a more similar operating state. Therefore, the difference in current value between the common access point at the current moment and the example moment, the difference in duration of the corresponding sub-time periods, and the difference in current fluctuation value are all negatively correlated with the state similarity value. In this embodiment of the invention, the absolute values ​​of the difference in current value between the common access point at the current moment and the example moment, the absolute values ​​of the difference in duration of the corresponding sub-time periods, and the absolute values ​​of the difference in current fluctuation value are negatively correlated and normalized to obtain the state similarity value between the current moment and the example moment. The larger the state similarity value, the more similar the operating state of the virtual power plant is to the example moment.

[0069] In this embodiment, the data to be processed is used as the exponent of an exponential function with the natural constant as the base, so as to achieve negative correlation and normalization of the data to be processed. Other methods can also be used, which are not limited here.

[0070] In one implementation of this invention, the preset similarity threshold is set to 0.5.

[0071] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the degree of impedance influence is described in [reference needed]. Figure 2 The diagram illustrates a flowchart of a method for obtaining the degree of impedance influence provided by an embodiment of the present invention, the method comprising:

[0072] Step S310: Based on the difference in current value between each node at the current time and at a similar state time, select the target deviation time among the similar state times; constitute several target deviation time periods by the continuous target deviation times within the monitoring period; record the maximum value of the duration of all target deviation time periods and the maximum value of the duration of the remaining time periods excluding the target deviation time periods within the monitoring period as the deviation time length.

[0073] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the target deviation time includes: power indicators including current values; calculating the average current value of each node at all times during the monitoring period, and recording the difference between the current value of the corresponding node at the current time and the average value as the reference current difference for each node; calculating the difference in current value between each node at the current time and all similar times, and selecting the similar times corresponding to current value differences greater than the reference current difference as the target deviation time. Here, difference refers to the absolute value of the difference.

[0074] It should be noted that the average current value of a node during the monitoring period represents the baseline level of normal current. The baseline current difference reflects the normal deviation of the current from the baseline level. If the difference between the current value at the current moment and the current at a similar state moment is greater than the normal deviation, i.e., the baseline current difference, it indicates that the node's current at the current moment deviates abnormally from the current at a similar state moment. In this case, the similar state moment is the target deviation moment. The longer the duration of the target deviation period formed by consecutive target deviation moments, the greater the deviation time, and the longer the power index fluctuation of each node deviates from the stable state, making the node more susceptible to impedance influence at the current moment.

[0075] Step S320: For each node in the virtual power plant, calculate the average impact of its operation on all other nodes at the current moment to obtain the overall impact of each node at the current moment.

[0076] It should be noted that the overall impact is the overall level of influence of each node on the operating status of the other nodes. If the overall impact is greater, the greater the possibility that the fluctuation of the power index of each node will cause drastic fluctuations in the power index of the other line nodes, and the less the node is affected by impedance at the current moment.

[0077] Step S330: Average the absolute values ​​of the current differences of each node at the current time with those at all similar times to obtain the overall current difference of each node at the current time.

[0078] It should be noted that if the overall current difference is larger, the current change of each node at the current moment is more drastic compared to the moment when the state is similar, which directly indicates that the node is less affected by impedance at the current moment.

[0079] Step S340: Based on the deviation time length, overall influence degree and overall current difference, obtain the impedance influence degree of each node in the virtual power plant at the current moment.

[0080] It should be noted that the smaller the overall influence and the larger the overall current difference, the smaller the deviation time length, and the less impedance influence each node in the virtual power plant is affected by at the current moment, thus the greater the impedance influence. Therefore, the overall influence and the overall current difference are negatively correlated with the impedance influence, while the deviation time length is positively correlated with the impedance influence. In this embodiment of the invention, a negative correlation mapping is performed on the overall current difference and the overall influence of each node at the current moment, and the product of the two mapping results and the deviation time length is taken as the impedance influence of each node at the current moment.

[0081] In this embodiment of the invention, the data to be processed is used as the exponent of an exponential function with the natural constant as the base to achieve a negative correlation mapping of the data to be processed. The negative correlation mapping can also be achieved through methods such as function transformation, and no limitation is made here.

[0082] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the response priority includes: obtaining the actual power supply and consumption of each node in the virtual power plant at the current moment; taking the difference between the preset maximum power supply and consumption of each node in the virtual power plant and the actual power supply and consumption of the corresponding node at the current moment as the power supply and consumption capacity value of each node at the current moment; calculating the average impedance influence degree of all nodes in the virtual power plant at the current moment, and taking the ratio of the impedance influence degree of each node at the current moment to the average as the impedance significance value of each node at the current moment; obtaining the response command capability value of each node in the virtual power plant at the current moment based on the power supply and consumption capacity value and the impedance significance value; the node with the larger the response capability value has a higher response priority at the current moment.

[0083] It should be noted that if a node corresponds to a power generation device or an energy storage device, the actual power supply and consumption is the actual power supplied; if a node corresponds to an application device, the actual power supply and consumption is the actual power consumed; the preset maximum power supply and consumption of each node refers to the maximum operating power of the device corresponding to the node, which is a theoretical or design upper limit and can be read from the device's instruction manual.

[0084] Power supply and consumption capacity typically refers to the additional output power a node can generate in its current state, i.e., its remaining power supply and consumption capacity. A larger power supply and consumption capacity value indicates that the actual power supply and consumption is further from the maximum power, meaning the node can provide more additional power at the current moment, resulting in a stronger power supply and consumption capacity and a stronger ability to respond to virtual power plant commands. The impedance significance value represents the degree of impedance influence on each node relative to all nodes. A smaller impedance significance value indicates a greater degree of impedance influence on each node relative to all nodes, meaning the fluctuations in each node's power indicators have a smaller impact on the power and production modes of other nodes, resulting in higher efficiency in responding to virtual power plant commands. A larger power supply and consumption capacity value and a smaller impedance significance value mean that the node has sufficient generation capacity and efficient power transmission capabilities, resulting in a stronger ability to respond to virtual power plant commands. Therefore, power supply and consumption capacity values ​​are positively correlated with command response capabilities, while impedance significance values ​​are negatively correlated with command response capabilities. In this embodiment of the invention, the product of the impedance value and the power supply and consumption capacity value of each node at the current moment is normalized to obtain the response command capability value of each node at the current moment.

[0085] In this embodiment of the invention, the Sigmoid function is used for normalization. However, other normalization methods such as function transformation or max-min normalization can also be used, and no limitation is made here.

[0086] This invention is now complete.

[0087] Example 2:

[0088] This invention proposes a real-time monitoring system for multimodal industrial IoT data. Please refer to [link / reference]. Figure 3 This diagram illustrates a system architecture of a real-time monitoring system for multimodal industrial IoT data, provided by an embodiment of the present invention. The system includes:

[0089] The data acquisition module 510 is used to acquire different types of power indicators of each node in the virtual power plant of the industrial park at each moment during the current monitoring period.

[0090] The node impact analysis module 520 is used to obtain the degree of operational impact of each node in the virtual power plant on any other node at the current moment, based on the degree of correlation between the fluctuation of the same power index between each node and any other node in the virtual power plant during the monitoring period, as well as the electrical connection tightness and production status similarity between the corresponding two nodes.

[0091] The impedance influence analysis module 530 is used to select the state similarity moment from the monitoring period; based on the degree of deviation and deviation time of the power index of each node in the virtual power plant relative to the state similarity moment, as well as the degree of influence of each node on the operation of other nodes, the impedance influence of each node in the virtual power plant at the current moment is obtained.

[0092] The priority analysis module 540 is used to determine the response priority of each node in the virtual power plant at the current moment based on the power supply and consumption capacity and impedance influence of each node at the current moment, and to determine the order in which each node executes the virtual power plant dispatching instructions.

[0093] It should be noted that the devices provided in the above embodiments are only illustrative examples of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. Furthermore, the real-time monitoring system for multimodal industrial IoT data and the real-time monitoring method for multimodal industrial IoT data provided in the above embodiments belong to the same concept, and their specific implementation processes are detailed in the method embodiments, which will not be repeated here.

[0094] Example 3:

[0095] Figure 4 This is a schematic diagram of a computer device for real-time monitoring of multimodal industrial IoT data, provided as an embodiment of the present invention. For example, as shown... Figure 4 As shown, the computer device includes: a memory 601, a processor 602, and a computer program 603 stored in the memory 601 and running on the processor 602, wherein when the processor 602 executes the computer program 603, the computer device can execute any of the aforementioned real-time monitoring methods for multimodal industrial IoT data.

[0096] Furthermore, embodiments of this application also protect an apparatus that may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to perform a real-time monitoring method for multimodal industrial IoT data provided in embodiments of this application.

[0097] This embodiment can divide the device into functional modules based on the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0098] It should be understood that the device provided in this embodiment is used to execute the above-described real-time monitoring method for multimodal industrial IoT data, and therefore can achieve the same effect as the above-described implementation method.

[0099] When using integrated units, the device may include a processing module and a storage module. When applied to a workpiece, the processing module can be used to control and manage the workpiece's operations. The storage module can be used to support the execution of program code by the workpiece.

[0100] The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits contained in conjunction with the disclosure of this application. The processor may also be a combination of functions that implement computing capabilities, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and microprocessors, etc., and the storage module may be a memory.

[0101] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0102] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0103] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A real-time monitoring method for multi-modal industrial Internet of Things data, characterized in that, The method comprises: acquiring different kinds of power indexes of each node in the virtual power plant of the industrial park at each time in a monitoring period at a current time; acquiring an operation influence degree of each node in the virtual power plant on any other node at the current time according to a fluctuation correlation degree of the same kind of power indexes of each node and any other node in the virtual power plant in the monitoring period, and an electrical connection closeness and a production state similarity of the corresponding two nodes; selecting a state similar time at the current time from the monitoring period; acquiring an impedance affected degree of each node in the virtual power plant at the current time according to a power index deviation degree and a deviation time of each node relative to the state similar time, and the operation influence degree of each node on any other node; determining a response priority of each node in the virtual power plant at the current time according to a power supply and consumption capacity of each node at the current time and the impedance affected degree, and determining a sequence of executing a virtual power plant scheduling instruction of each node. 2.The real-time monitoring method for multi-modal industrial Internet of Things data according to claim 1, characterized in that, The operation influence degree of each node in the virtual power plant on any other node at the current time comprises: arranging all the same kind of power indexes of each node at all times in the monitoring period in time sequence to obtain a power sequence of each kind of power index; calculating a transfer entropy of the power sequence of the same kind of power indexes from each node to any other node in the virtual power plant, the transfer entropy reflecting a fluctuation correlation degree of the power indexes of the two nodes, and taking an average value of all kinds of power indexes corresponding to the transfer entropy as a response correlation degree of each node on any other node at the current time; acquiring a power modal topology structure and a production modal topology structure; acquiring distances of each node and any other node in the virtual power plant in the power modal topology structure and the production modal topology structure respectively, the distance of each node and any other node in the power modal topology structure reflecting an electrical connection closeness of the corresponding two nodes, and the distance of each node and any other node in the production modal topology structure reflecting a production state similarity of the corresponding two nodes, and taking a product of the two distances as a power production modal distance of the corresponding two nodes; acquiring an operation influence degree of each node in the virtual power plant on any other node at the current time according to the response correlation degree and the power production modal distance. 3.The real-time monitoring method for multi-modal industrial Internet of Things data according to claim 1, characterized in that, The determination of the response priority of each node in the virtual power plant at the current time comprises: acquiring an actual power supply and consumption power of each node in the virtual power plant at the current time; taking a difference value between a preset maximum power supply and consumption power of each node in the virtual power plant and the actual power supply and consumption power of the corresponding node at the current time as a power supply and consumption capacity value of each node at the current time; calculating an average value of the impedance affected degrees of all nodes in the virtual power plant at the current time, and taking a ratio of the impedance affected degree of each node at the current time to the average value as an impedance affected significant value of each node at the current time; acquiring a response instruction capacity value of each node in the virtual power plant at the current time according to the power supply and consumption capacity value and the impedance affected significant value; the higher the response instruction capacity value of a node at the current time, the higher the response priority of the node at the current time. 4.The real-time monitoring method for multi-modal industrial Internet of Things data according to claim 1, wherein, The state similar time point of the current time point in the monitoring time period comprises: The monitoring time period is divided into different sub-time periods based on the current values of the current of the public access point of the virtual power plant at all time points in the monitoring time period of the current time point; The range of the current values of the current of the public access point at all time points in each sub-time period is recorded as the current fluctuation value; The state similarity value of the current time point and the example time point is obtained according to the difference between the current values of the current of the public access point at the current time point and the example time point, and the difference between the time length difference of the sub-time periods in which the two time points are located and the current fluctuation value; For the state similarity degrees of the current time point and the remaining time points in the monitoring time period of the current time point, the remaining time point corresponding to the state similarity value greater than the preset similarity threshold is selected as the state similar time point of the current time point. 5.The real-time monitoring method for multi-modal industrial Internet of Things data according to claim 3, characterized in that, The supply and consumption power capability value is positively correlated with the response instruction capability value, and the impedance significant value is negatively correlated with the response instruction capability value. 6.The real-time monitoring method for multi-modal industrial Internet of Things data according to claim 4, characterized in that, The method for dividing the monitoring time period into different sub-time periods is an adaptive piecewise constant approximation algorithm. 7.The real-time monitoring method for multi-modal industrial Internet of Things data according to claim 1, wherein, The last time point in the monitoring time period is the current time point.

8. A real-time monitoring system for multi-modal industrial IoT data, characterized in that, The system comprises: The data acquisition module is configured to acquire different types of power indicators of each node in the virtual power plant of the industrial park at each time point in the monitoring time period of the current time point; The node influence analysis module is configured to obtain the operation influence degree of each node in the virtual power plant on any other node in the virtual power plant at the current time point according to the fluctuation correlation degree of the same type of power indicators of each node and any other node in the virtual power plant in the monitoring time period, and the electrical connection tightness and production state similarity of the corresponding two nodes; The impedance influence analysis module is configured to select a state similar time point of the current time point from the monitoring time period, and obtain the impedance influence degree of each node in the virtual power plant at the current time point according to the power indicator deviation degree and deviation time of each node relative to the state similar time point, and the operation influence degree of each node on any other node. The priority analysis module is configured to determine the response priority of each node in the virtual power plant at the current time point and the execution sequence of the nodes in the virtual power plant in executing the virtual power plant scheduling instruction according to the supply and consumption power capability of each node at the current time point and the impedance influence degree.

Images