CN-121539917-B - Lithium bromide heat pump waste heat recovery collaborative management system based on distributed calculation force

CN121539917BCN 121539917 BCN121539917 BCN 121539917BCN-121539917-B

Abstract

The invention relates to the technical field of cooperative calculation of waste heat recovery, and discloses a lithium bromide heat pump waste heat recovery cooperative management system based on distributed computing power. The system consists of an edge computing device and a collaborative management device which are distributed at each heat pump device. The collaborative management device establishes a device connection topological graph and issues a unified data acquisition template to enable each edge node to acquire and store data according to specifications. The system disassembles the analysis task into a plurality of calculation stages according to the topological graph and dynamically distributes the calculation stages to each node. Each node calculates by utilizing the local data and the intermediate result transmitted by the adjacent node, and transmits the result along the topological path to form the pipeline cooperative calculation of the cross-equipment. According to the scheme, the data specification is unified from the source, the optimal scheduling and task coordination of calculation force along the equipment network are realized, the data transmission quantity is reduced, and the analysis optimization efficiency and the instantaneity of the whole system are improved.

Inventors

ZHANG BO
SU MINGSHENG
SONG ZHENG
LI NANA
BAI GUIYONG
ZHU FEI
JING CHAOCHENG

Assignees

陕西拓普索尔电子科技有限责任公司

Dates

Publication Date: 20260512
Application Date: 20260120

Claims (6)

1. The lithium bromide heat pump waste heat recovery collaborative management system based on distributed computing power is characterized by comprising a plurality of edge computing power devices and a collaborative management device, wherein each edge computing power device is deployed near one lithium bromide heat pump device and is used for collecting operation state data of the corresponding lithium bromide heat pump device; The collaborative management device establishes a global equipment topological graph, nodes in the global equipment topological graph correspond to one lithium bromide heat pump equipment and an edge computing device thereof, and edges in the global equipment topological graph represent physical or logical connection relations between two lithium bromide heat pump equipment; the collaborative management device issues a data acquisition template to each edge computing device, the data acquisition template prescribes the acquisition type and the acquisition time sequence of the running state data, and the edge computing device acquires and stores the running state data based on the data acquisition template to form a local state data set; The collaborative management device initiates a collaborative analysis task based on a global equipment topological graph, the collaborative analysis task comprises a plurality of calculation stages, each calculation stage is distributed to one node in the global equipment topological graph, an edge computing device corresponding to the node executes the calculation stage, the calculation stage utilizes a local state data set and intermediate data transmitted from adjacent nodes in the global equipment topological graph to generate an intermediate calculation result, and the intermediate calculation result is transmitted to the next node appointed by the collaborative management device; Before initiating a collaborative analysis task, the collaborative management device divides a global equipment topological graph to obtain a plurality of topological subgraphs, wherein each topological subgraph comprises at least one node, and the nodes in the topological subgraphs are directly connected through edges; The collaborative management device distributes a calculation stage set for each topological sub-graph, and the calculation stages in the calculation stage set correspond to nodes in the topological sub-graph one by one; The collaborative management device issues a starting instruction of a collaborative analysis task and a corresponding calculation stage set to a node with the minimum load value in each topological sub-graph, and the node is designated as a subtask coordination node of the topological sub-graph; After receiving the starting instruction and the calculation stage set, the subtask coordination node determines the execution sequence of each calculation stage in the calculation stage set according to the connection relation between the nodes in the topology subgraph to form a subtask execution chain; The subtask coordination node sequentially activates edge computing devices of corresponding nodes in the topological subgraph to execute computing stages according to the subtask execution chain, and after the edge computing devices complete the computing stages, the generated intermediate computing results are transmitted to the edge computing devices corresponding to the next computing stage along the subtask execution chain; When the calculation stage needs to rely on intermediate data of other topological subgraphs in the global equipment topological graph, the subtask coordination node sends a data request to the cooperative management device; the cooperative management device locates sub-task coordination nodes of other topological subgraphs holding the needed intermediate data according to the data request, and establishes a data channel between the current sub-task coordination node and the target sub-task coordination node; The data is transmitted through the data channel, and the receiving side subtask cooperative control point injects the received intermediate data into a designated calculation stage of a subtask execution chain maintained by the receiving side subtask cooperative control point; after each topology sub-graph calculation is completed, the subtask coordination node generates a topology sub-graph result and uploads the topology sub-graph result to the collaborative management device; And the collaborative management device collects all topological sub-graph results, fuses all the topological sub-graph results based on the global equipment topological graph and generates a global analysis result.
2. The distributed computing power-based lithium bromide heat pump waste heat recovery collaborative management system according to claim 1, wherein the collaborative management device calculates a load value of each node based on historical computing power consumption data and real-time running state data of an edge computing power device corresponding to each node; The node with the smallest load value meets the condition that the sum of the average value of the historical calculation power consumption data and the current calculation power occupancy rate reflected by the real-time running state data is lower than a preset load threshold value.
3. The collaborative management system for lithium bromide heat pump waste heat recovery based on distributed computing power according to claim 1, wherein the collaborative management device determines fusion weights among topological sub-graph results based on connection attributes of edges in a global equipment topological graph, wherein the connection attributes comprise connection types and connection strengths; and the collaborative management device performs weighted calculation on the topological sub-graph result according to the fusion weight, and performs normalization processing on the weighted calculation result to obtain a global analysis result.
4. The lithium bromide heat pump waste heat recovery collaborative management system based on distributed computing power according to claim 1, wherein the edge computing power device periodically checks the data integrity of a local state data set, and when data loss is detected, the edge computing power device re-acquires or interpolates and fills the data of the loss period according to the acquisition time sequence in a data acquisition template; after the data integrity meets the requirement, the edge computing device performs data compression on the local state data set, and synchronizes the metadata of the compressed local state data set to the collaborative management device.
5. The distributed computing power-based lithium bromide heat pump waste heat recovery collaborative management system according to claim 1, wherein the subtask coordination node verifies the data integrity status of an edge computing power device of a node in a topological subgraph before activating the edge computing power device to execute a computing phase; If the data integrity status is incomplete, the subtask coordination control point delays the activation of the calculation stage and instructs the edge computing device to preferentially complete the data integrity repair operation.
6. The distributed computing power-based lithium bromide heat pump waste heat recovery collaborative management system according to claim 1, wherein the collaborative management device maps global analysis results back to a global equipment topological graph, and generates a control parameter adjustment suggestion for each node; and the collaborative management device transmits the control parameter adjustment suggestion to an edge computing device of the corresponding node, and the edge computing device drives the local lithium bromide heat pump equipment to execute parameter adjustment.

Description

Lithium bromide heat pump waste heat recovery collaborative management system based on distributed calculation force Technical Field The invention relates to the technical field of cooperative calculation of waste heat recovery, in particular to a lithium bromide heat pump waste heat recovery cooperative management system based on distributed computing power. Background In the field of industrial waste heat recovery, operation monitoring and energy efficiency optimization of lithium bromide heat pump units generally depend on a centralized data acquisition and processing system. Such systems remotely transmit operational status data of all devices to a central server for unified analysis. Another common approach is to use edge computing units that are independent of each other, each unit being responsible for local data acquisition and simple processing only, lacking inter-device coordination. Under a centralized architecture, the remote transmission of massive real-time data causes huge network bandwidth pressure, obvious delay of analysis decision and difficulty in meeting the requirement of quick response under complex working conditions. The centralized processing of data also makes the central server a performance bottleneck and a single point of failure risk point. The simple independent edge computing mode relieves the data transmission pressure, but each node is isolated in computing task, and cannot utilize the physical association among equipment clusters and data logic to perform deeper collaborative analysis and optimization, and the dimension and depth of data analysis are limited. The prior art lacks a method capable of effectively organizing and distributing calculation force and carrying out cooperative calculation according to actual association relation among devices. Meanwhile, the time sequence and the type of data acquisition of each device are determined by the local self, so that huge data cleaning, alignment and integration loads are faced when the rear end performs multi-source data fusion analysis, the calculation efficiency is low, and the generation and the application of a real-time collaborative optimization strategy based on the whole system data are restricted. Disclosure of Invention The invention aims to provide a lithium bromide heat pump waste heat recovery collaborative management system based on distributed computing power, so as to solve the problems in the background technology. In order to achieve the above object, the present invention provides a lithium bromide heat pump waste heat recovery collaborative management system based on distributed computing power, the system comprising: the system comprises a plurality of edge computing devices and a cooperative management device, wherein each edge computing device is arranged near one lithium bromide heat pump equipment and is used for collecting the running state data of the corresponding lithium bromide heat pump equipment; The collaborative management device establishes a global equipment topological graph, nodes in the global equipment topological graph correspond to one lithium bromide heat pump equipment and an edge computing device thereof, and edges in the global equipment topological graph represent physical or logical connection relations between two lithium bromide heat pump equipment; the collaborative management device issues a data acquisition template to each edge computing device, the data acquisition template prescribes the acquisition type and the acquisition time sequence of the running state data, and the edge computing device acquires and stores the running state data based on the data acquisition template to form a local state data set; The collaborative management device initiates a collaborative analysis task based on the global equipment topological graph, the collaborative analysis task comprises a plurality of calculation stages, each calculation stage is distributed to one node in the global equipment topological graph, an edge computing device corresponding to the node executes the calculation stage, the calculation stage utilizes a local state data set and intermediate data transmitted from adjacent nodes in the global equipment topological graph to generate an intermediate calculation result, and the intermediate calculation result is transmitted to the next node appointed by the collaborative management device. Preferably, before initiating a collaborative analysis task, the collaborative management device divides a global equipment topological graph to obtain a plurality of topological subgraphs, each topological subgraph comprises at least one node, and nodes in the topological subgraphs are directly connected through edges; The collaborative management device distributes a calculation stage set for each topological sub-graph, and the calculation stages in the calculation stage set correspond to nodes in the topological sub-graph one by one; the collaborative management device issues a