413 results about "Time series database" patented technology

The invention provides a beverage production whole process tracing method, which comprises the following steps of: establishing a node attribute data structure according to beverage raw material batch numbers and production line numbers, marking raw material warehousing and production starting time by adopting timestamps, and representing use proportions of raw materials in different production batches through edge weights to obtain a preliminary raw material finished product association diagram; a graph database is adopted to store a beverage raw material finished product association graph, a corresponding relation between raw material batches and production batches is established through processing procedure attributes of edges between nodes, and a complete traceability chain graph structure is formed; for heterogeneous data in the traceability chain graph structure, storing dynamic production parameters by adopting a time sequence database, and establishing a mapping relationship between the raw material batches and the production parameters in the corresponding time periods through a time window algorithm; the method comprises the following steps: starting from a finished product batch node, tracing to a raw material batch node step by step through edge attributes in a graph database, and extracting production parameters in a corresponding time window to obtain a preliminary traceability data set;

The invention relates to the technical field of wind power generation equipment data processing. The invention provides a time sequence database data compression method, system and device and a storage medium. The method comprises the steps of dynamically partitioning time sequence data based on a preset time window; hybrid coding compression is performed on each data block, and a composite strategy of difference coding and run length coding is adopted for numerical data; a metadata index of the compression blocks is established, the time range, the data feature statistics and the compression parameters of each data block are recorded, and the metadata index comprises extreme value distribution, variance features and data fluctuation frequency indexes; and dynamically adjusting a compression strategy according to a historical data feature analysis result, predicting data fluctuation modes of different equipment sensors through a machine learning model, and automatically selecting an optimal coding combination and compression granularity for subsequent data blocks. The problems that when wind power plant time sequence data are processed through an existing method, time sequence characteristics are difficult to adapt, the storage cost is high and the query efficiency is low are solved.

The invention relates to the technical field of municipal road construction, and discloses a municipal road construction section scheduling optimization method and system based on artificial intelligence, and the method comprises the steps: collecting the multi-source dynamic data of a construction region through Internet of Things equipment and a satellite remote sensing technology, and constructing a time sequence database; a multi-objective optimization model is established, and an initial scheduling scheme is generated by adopting a non-dominated sorting genetic algorithm with the goal of minimizing construction period, resource waste and traffic jam influence. Dynamically adjusting the priority of the construction section by using a reinforcement learning algorithm, and updating a construction task sequence; a graph neural network is utilized to detect space-time conflicts of construction sections, and conflict-free scheduling constraint conditions are generated; and optimizing resource allocation based on mixed integer linear programming, simulating a construction process in combination with a digital twinborn technology, correcting a construction progress deviation by using a Kalman filtering algorithm, and outputting a final scheduling instruction. According to the invention, optimization of municipal road construction section scheduling is realized, the construction period is effectively shortened, resource waste is reduced, and traffic jam is relieved.

The invention relates to the technical field of data processing, and discloses a PTP network performance monitoring method and system based on big data analysis, and a medium. The method comprises the following steps: acquiring PTP message data, equipment state data and RTP stream data; preprocessing the data and calculating a clock error; constructing a time sequence database and an analysis model; real-time monitoring and anomaly detection are executed; performing performance scoring and fault positioning by applying machine learning; and carrying out network optimization and predictive maintenance. According to the PTP network performance monitoring method based on big data analysis, global state monitoring, intelligent anomaly detection, accurate fault positioning and predictive maintenance of the PTP network are achieved, and therefore the high-precision time synchronization requirement of a broadcast and television IP making and broadcasting system is guaranteed.

The invention discloses a garden landscape plant health assessment method, and belongs to the technical field of resource assessment. Comprising the following steps: step 1, constructing a time sequence database of environmental factors and plant growth states; step 2, according to different plant species and growth stages thereof, dynamically calculating and generating a health reference value adapted to the current environmental condition; step 3, in the optimal evaluation time window, performing preliminary evaluation on the plant health condition, extracting original health indexes, and performing correction in combination with an environment disturbance compensation factor; step 4, performing double comparative analysis on the corrected health assessment result, eliminating false anomalies caused by environmental fluctuation, and calculating an anomaly confirmation credibility index; step 5, grading the plant health conditions, visually displaying the plant health conditions in a thermodynamic diagram form, and marking the environmental interference degree; and step 6, based on an evaluation result, automatically generating a targeted maintenance suggestion, and designing a corresponding maintenance effect verification scheme.

The invention discloses an industrial data real-time acquisition monitoring system fusing edge computing and 5G, and belongs to the technical field of industrial Internet of Things. The system is composed of a multi-source heterogeneous data acquisition module, an edge computing node cluster, a 5G communication network and a cloud analysis platform, an edge-cloud collaborative architecture is innovatively adopted, a multi-protocol adapter is integrated to realize unified access of heterogeneous data of industrial equipment, a low-delay transmission channel is constructed by using a 5G network slicing technology, and the heterogeneous data of the industrial equipment is transmitted to the cloud analysis platform. And transmitting the preprocessed data to the edge computing node in parallel. And the edge layer realizes dynamic resource scheduling by adopting a containerization technology, and realizes millisecond-level response and local decision feedback. And meanwhile, through an edge-cloud data synchronization mechanism, a distributed time sequence database is constructed, and visual monitoring and deep analysis of multi-dimensional data are supported. The system improves the real-time processing capability of industrial field data and the reliability of the system, and has the technical advantages of low time delay, high concurrency and optimized resource utilization rate.

The invention discloses a distributed time sequence library data management method supporting cold and hot data level-to-level management, and relates to the technical field of computer databases, comprising: receiving a write-in request of time sequence data, and executing preliminary write-in data aggregation and sorting; dynamically identifying data cold and hot attributes based on a multi-dimensional data cold and hot degree calculation model in combination with a write-in behavior and an access behavior of time series data; according to the cold and hot attribute recognition result, in combination with the hierarchy boundary of self-adaptive division, automatic hierarchical storage of the time series data is executed; based on a cold and hot data dynamic migration and scheduling mechanism, according to the access frequency and time decay characteristics of the time series data, dynamically adjusting the storage hierarchy of the time series data, and executing a data migration task; and constructing a hierarchical index system adaptive to different cold and hot attribute time series data, and combining query frequency dynamic identification and index structure automatic upgrading. By adopting a cold and hot data automatic identification and hierarchical storage mechanism, the overall performance and the resource utilization rate of the system are improved.

The invention relates to a building module data interface intelligent monitoring system based on the Internet of Things and a deployment method, and belongs to the technical field of building information monitoring. The system is composed of a distributed sensing unit, an edge computing gateway, a cloud platform and a visual terminal, a self-adaptive filtering algorithm and an abnormal mode recognition model are built in the edge computing gateway, the cloud platform adopts a time sequence database to construct a multi-dimensional data warehouse, and structural health degree evaluation is carried out by fusing an LSTM neural network and a random forest algorithm. The deployment method comprises the steps of optimizing a sensor distribution strategy based on a BIM model, establishing a wireless Mesh ad hoc network communication architecture, and configuring a grading early warning mechanism and a fault tracing function. The innovation point is that a dynamic threshold adjustment algorithm and an interface performance degradation prediction model are provided, and real-time monitoring of the connection state of the building module and life prediction are realized. The system has the advantages of flexible deployment, high detection precision and low maintenance cost, and the intelligent level of building structure safety monitoring is effectively improved.

Techniques for performing a scratch space flush of cold tier upsert data into cold tier storage while allowing continued hot tier ingestion are described. Data points to be written into a time series database having a hot tier and a cold tier may be designated to be written directly into the cold tier, bypassing the hot tier that typically stores new data points that eventually are aged out into the cold tier. New data points for insertion directly into the cold tier may be stored to a scratch space storage and moved into the cold tier according to a non-blocking protocol that allows for continued hot tier ingestion without significant service disruptions.

The invention discloses a park energy storage intelligent scheduling system and method based on big data, and relates to the technical field of big data park energy storage intelligent scheduling, and the method comprises the following steps: S100, collecting the real-time operation data of multiple types of energy systems in a park, constructing a time sequence database, and carrying out the preprocessing; s200, predicting load change based on an energy demand scene, and constructing a polymorphic energy storage model in combination with dynamic characteristics of energy storage equipment; s300, defining a multi-objective optimization function taking energy loss, renewable energy utilization rate and energy storage efficiency as cores, establishing a total energy balance model, and setting constraint conditions of charging and discharging and heat and cold storage power of energy storage equipment; and S400, updating the load demand and the energy storage state by using the real-time data, calculating the load deviation and correcting the target function, and readjusting the charging and discharging of the energy storage equipment and the heat storage and cold storage power distribution according to the corrected target function.

The invention discloses an intelligent operation and maintenance method for modular data acquisition and analysis sewage treatment equipment, which comprises the following steps: designing a modular data acquisition unit, configuring an acquisition module with a standardized interface, and realizing quick access of multi-source equipment; protocol conversion, data compression and timestamp completion are completed by using an edge computing gateway, and stable data reporting under a complex network is realized by combining an MQTT protocol; a time sequence database is adopted to store and fuse OA / ERP system data, and an information island is broken; remote diagnosis, intelligent early warning and visual decision making are realized by means of a remote fault analysis interface, a user-defined rule engine and a configurable billboard; and operation and maintenance closed-loop management is achieved in cooperation with a workflow engine. The method effectively solves the problems of low data acquisition integration level, unstable communication, weak analysis capability and the like in traditional operation and maintenance, has the characteristics of modularization, intelligence, high efficiency and the like, remarkably improves the operation and maintenance management level of the sewage treatment equipment, reduces the operation and maintenance cost, and has a wide application prospect.

The invention discloses a switch fault diagnosis and intelligent analysis management method and device, equipment and a storage medium, and relates to the technical field of network equipment fault diagnosis and intelligent analysis, and the method comprises the steps: obtaining monitoring container index information, carrying out the data preprocessing based on the monitoring container index information, synchronizing a preset time sequence database, and determining synchronous data; extracting time sequence common characteristics based on the synchronous data, matching a corresponding fault mode, and determining a root cause probability sequence; and positioning a fault propagation path based on the root cause probability sequence, triggering topology to generate a marked target fault path, determining a display topological graph, and completing switch fault diagnosis and intelligent analysis management based on the display topological graph. According to the method, the time sequence features are extracted, the fault modes are matched to determine the root cause probability sorting, and the fault paths are reasoned to dynamically mark the topological graph, so that data islands are broken, multi-source data association analysis is realized, the diagnosis time is shortened, the real-time performance and accuracy are improved, and the visualization effect is optimized.

The invention belongs to the technical field of intelligent power grids, and particularly relates to an intelligent power grid monitoring data storage system which comprises a data acquisition module, a data preprocessing module, a hierarchical data storage module, an intelligent data retrieval and management module and a data analysis and visualization module. Power grid operation data are collected in real time through various sensors; the data preprocessing module is used for cleaning, denoising and formatting the collected data and identifying data abnormal values by adopting a dynamic threshold detection method; the hierarchical data storage module adopts a hierarchical storage strategy of hot data, temperature data and cold data, stores the data in different media respectively, and introduces a time sequence database; the intelligent data retrieval and management module retrieves the stored data by using a multi-condition complex query algorithm, and improves the query efficiency through an intelligent data indexing and retrieval mechanism; and the data analysis and visualization module generates a report and a visualization chart through an advanced data analysis algorithm.

The invention provides a cross-border e-commerce big data analysis system and method, and the method comprises the steps: obtaining multi-dimensional original business data of a cross-border e-commerce platform, carrying out the real-time collection through a distributed data collection system, and obtaining a structured business data set; data collected in real time is cleaned, converted and structured, a unified data model is constructed, and integration of heterogeneous data sources is achieved; storing the processed structured data in a time sequence database to provide data support for real-time analysis; performing real-time aggregation and statistical analysis on the newly added data to generate business index and key performance index data; a Lambda framework is adopted, batch processing and stream processing are combined, the historical data and the real-time data are subjected to full-amount analysis, and an analysis result is obtained; based on an analysis result, a data mining algorithm is adopted to identify a service mode and predict a future trend; a multi-dimensional data cube is constructed, multi-dimensional and multi-granularity data exploration and interactive analysis are supported, and management decision making is assisted.

The invention discloses a transaction processing mechanism optimization method and system for time series data, and belongs to the technical field of databases, and the method realizes a differentiated ACID support mechanism, strengthens atomicity and durability guarantee, and weakens consistency and isolation requirements; comprising the following steps: designing a collaborative architecture of a transaction system and a pre-write log WAL, and establishing a binding relationship between a transaction state and WAL writing; generating a WAL record only for the successfully submitted transaction operation, and performing persistent storage by adopting a batch group submission strategy; transaction scheduling is realized through a lightweight transaction manager, and the life cycle of a transaction request is managed; the functions of efficient writing of transaction granularity, log storage and rapid recovery are realized through a pre-writing log manager; through intelligent Checkpoint background service, based on a periodic incremental check point mechanism, compression merging and space recovery of the WAL file are realized. According to the invention, the performance breakthrough of the time sequence database in a high-concurrency write-in scene can be realized.

The invention discloses an operation and maintenance platform data acquisition system based on big data, and relates to the technical field of big data, and the system comprises the steps: capturing a data packet from a network flow of an operation and maintenance platform, and storing the data packet in a buffer area; performing preliminary screening on the data packets in the buffer area, and allocating priorities for the data packets based on a dynamic weight scheduling mechanism to complete preliminary preprocessing of the data packets; based on a circular sorting and block optimization technology, distributing the plurality of decomposed analysis tasks to a plurality of threads for parallel processing; formatting the analysis result, and performing batch parallel processing according to the data scale of the analysis result; formatting the analyzed data, writing the formatted data into a time sequence database according to a time sequence, and generating an index based on the tag field; through a dynamic cache management mechanism, the cache size is dynamically adjusted according to the throughput and the maximum delay of the network flow, and the problems of data loss and processing delay are avoided.

The invention provides an IoTDB and AI collaborative driving welding robot parameter self-optimization method, which comprises the following steps: performing data alignment processing on an obtained original data set of a welding robot, generating time-space alignment features, and storing the time-space alignment features in an IoTDB time sequence database; performing cross-modal feature fusion and quality prediction through a pre-trained neural network based on all space-time alignment features in the I oTDB time sequence database, generating a quality prediction value, and writing the quality prediction value into the I oTDB time sequence database; and on the basis of the current space-time alignment features and the corresponding quality predicted values in the IoTDB time sequence database, optimized welding parameters are generated through an incremental reinforcement learning algorithm, and the optimized welding parameters are used for indicating the welding robot to conduct parameter adjustment. By adopting the method, the dynamic response capability and the process stability of intelligent manufacturing can be improved through long-term feature extraction of the time series data and collaborative optimization of an incremental learning mechanism.

The invention discloses an intelligent elevator host bearing fault diagnosis system based on AI and fault physical fusion, and belongs to the technical field of elevator diagnosis. Comprising an edge end which is connected with a cloud end; when fault diagnosis is carried out, the edge end firstly collects a high-frequency signal through a sensor, sequentially executes signal preprocessing, feature extraction, anomaly detection and data compression, and finally sends compressed feature data to the cloud end; after the cloud end receives and verifies the integrity of the data, the feature data is stored in a time series database, deep analysis is executed through a data analysis engine, a lightweight model is optimized based on historical data, an analysis result is displayed through a remote monitoring platform, and an alarm notification is sent when abnormity is detected; meanwhile, the cloud end issues the optimized lightweight model to the edge end to form a continuously optimized closed loop. Through the feature extraction and data compression technology of the edge end, the data volume needing to be transmitted is greatly reduced, and the network bandwidth requirement and the transmission delay are remarkably reduced.

The invention discloses a power grid equipment anomaly detection method and system, and the method comprises the steps: obtaining node-level power grid equipment state time sequence data from a local distributed time sequence database of each power grid partition, and constructing a topological graph corresponding to the power grid partition based on the power grid equipment state time sequence data, wherein the power grid equipment state time sequence data are written into the distributed time sequence database in parallel according to equipment nodes and time windows in advance; constructing a graph neural network based on the topological graph corresponding to each power grid partition, and modeling a spatial dependency relationship among equipment nodes in the topological graph based on a graph attention mechanism; the graph neural network corresponding to each power grid partition is trained on a locally deployed distributed time sequence database through a joint optimization loss function of point prediction and quantile prediction, and model parameter optimization is carried out through a federated learning algorithm and a federated server; and obtaining a trained graph neural network for performing equipment anomaly detection in a corresponding power grid partition.

Techniques leveraging hallucinations from generative AI for challenge-response in secure access are described and may be performed at least in part by a generative AI engine. An indication of a memorable event associated with a user is received. Time series sensor data associated with the user for a period of time associated with the memorable event is received from a time series database. Parameters for determining one or more plausible events that are similar to the memorable event are received by an authentication server. The parameters include a level of hallucination for generating the one or more plausible events. One or more plausible events are generated based at least in part on the memorable event, the time series sensor data, and the parameters. A challenge and response to be used as a challenge-response authentication from the user to access a network resource is generated and transmitted to the authentication server.

The invention discloses a power grid maintenance plan reliability post-evaluation method based on Monte Carlo simulation and data driving, and belongs to the technical field of power system operation and reliability analysis. The method comprises the following steps: firstly, collecting multi-source data such as historical load, renewable energy output, equipment operation state and maintenance record of a power grid, constructing a time sequence database through cleaning, time alignment and feature extraction, and establishing a load and renewable energy probability model; constructing a maintenance plan model containing a state variable, a constraint condition and a peak clipping weight mechanism, and establishing a continuous time Markov chain state model for the key equipment to generate an availability sequence; generating a large-scale random operation scene set through a Monte Carlo method based on multiple models, and carrying out supply-demand balance and power flow analysis on each scene; multi-dimensional indexes of reliability, economy and safety are calculated and subjected to weighted fusion, a comprehensive post-evaluation report is generated after results are counted, and finally the maintenance plan is optimized according to the report. According to the method, the uncertainty of the power system can be comprehensively considered, multi-dimensional quantitative evaluation and closed-loop optimization of the maintenance plan are realized, intelligent support is provided for power grid maintenance decision making, and the method is suitable for a power transmission network, a power distribution network and a micro-grid.

The invention relates to a time series data acquisition method and device based on a dynamic time window and fingerprint deduplication. The method comprises the following steps: establishing a sliding time window with a variable length by taking the current system time as a reference, and only querying incremental time sequence data in the window; adaptively zooming the window by calculating the ratio of the collected data volume to the expected volume in real time; setting the trigger interval as half of the length of the sliding time window to form a time overlap, thereby capturing out-of-order data; key features of each piece of time series data are extracted, and data fingerprints are generated; a bloom filter is used for primary screening, and accurate duplicate removal is carried out in a key-value storage system; compared with an existing fixed polling scheme, the method has the advantages that resources can be dynamically adjusted along with data flow rate, system load is reduced, real-time performance is improved, data integrity is guaranteed by overlapped windows, zero repeated acquisition is guaranteed by fingerprint two-stage duplicate removal, and the method is applicable to efficient incremental synchronization scenes of transactional log-free time sequence databases such as InfluxDB and the like.

The invention discloses a server non-perception resource scheduling method and system based on cluster telescopic self-adaptive reinforcement learning. The method comprises the following steps: step 1, using a monitoring assembly based on a time sequence database to collect various operation load indexes of a cluster server; and step 2, constructing a function resource scheduler by using a Kubernetes scheduling framework. And step 3, constructing a scheduling decision agent by using a cluster telescopic adaptive reinforcement learning algorithm, inputting a variable-length observation sequence, and outputting a node deployment action. And step 4, using a historical cloud service load data set to construct a load generator to simulate a production environment to train and strengthen an intelligent agent deep neural network. And 5, using the trained scheduling decision agent to make a production environment scheduling decision. According to the method, the existing reinforcement learning algorithm is subjected to elastic cluster-oriented algorithm optimization, the expansibility and robustness of the scheduling algorithm when the cluster executes node scaling are improved, and the method has practical application value.

The invention discloses a time sequence database architecture, a data writing method and electronic equipment, and the time sequence database architecture comprises a distributed storage module which enables data of the same equipment to be continuously distributed in a physical storage layer based on an equipment dimension fragmentation strategy; the independent index layer is decoupled from the data storage module and maintains a mapping relationship between the equipment identifier and the corresponding physical fragment through a metadata structure; the migration module is used for performing rolling updating on the hot data layer; and the query engine module is used for positioning the target physical fragment according to the equipment identifier and executing predicate push-down calculation on the compressed data. The data writing method comprises the following steps: receiving a data writing request, and analyzing a device identifier in the request; positioning a target physical fragment according to the equipment identifier in cooperation with a Hash algorithm; and adding the data to the column type storage file in the corresponding physical fragment according to a timestamp sequence, and synchronously updating the metadata mapping relationship of the independent index layer. According to the method, the data query performance and query efficiency can be improved, and the data storage cost is reduced.

The invention relates to the technical field of data compression and storage, and discloses a monitoring data compression and storage method driven by a time sequence database, comprising the following steps: S1, preprocessing multi-source monitoring data, and constructing a dynamic tensor comprising a timestamp, a numerical index and a multi-dimensional label; s2, performing dynamic dimension reduction processing on the dynamic tensor to generate a core tensor and a multi-dimensional factor matrix; s3, based on the core tensor and the multi-dimensional factor matrix, determining a compression parameter, a decompression parallelism degree and an index granularity through a joint optimization model; and S4, performing hierarchical coding on residual data generated by the dynamic dimension reduction processing to generate a lightweight residual coding result. Through a dynamic tensor decomposition and incremental updating technology, low storage overhead and real-time dimension expansion capability of streaming monitoring data are realized, the problems of calculation redundancy and storage expansion caused by the fact that the streaming monitoring data cannot adapt to dynamic newly-added tags are solved, and meanwhile, frequent reconstruction cost caused by data dynamic expansion is avoided.

The invention discloses a mass data display method, device and equipment based on a browser client side and a medium, relates to the technical field of computers, is applied to a server side and comprises the steps that a data obtaining request sent by the browser client side is obtained; the data acquisition request carries a request time range and a target sampling frequency; obtaining original time sequence data in the request time range from a preset time sequence database, and determining the size of a sampling window based on the data frequency of the original time sequence data and the target sampling frequency; the data frequency is greater than the target sampling frequency; grouping the original time series data based on the size of the sampling window so as to obtain a plurality of data windows, and extracting a target feature point for representing data trend change in each data window; and merging the target feature points of the data windows to obtain a downsampled data sequence, and sending the data sequence to a browser client for display. According to the method and the device, effective visual display of mass data on the browser client can be realized.

A performance monitoring system includes a metric collector configured to receive, via metric exporters, telemetry data comprising metrics related to a network of computing devices. A metric time series database stores related metrics. An alert rule evaluator service is configured to evaluate rules using stored metrics. The performance monitoring system may include a machine learning module and is configured to determine optimized metric collection sampling intervals and rule evaluation intervals, and to automatically determine recommended alert rules.

The invention discloses a traffic facility monitoring and intelligent operation and maintenance management method and system based on Prometheus, and the method comprises the following steps: S1, taking a data collection service as a data pulling target of Prometheus, configuring the data collection service in a configuration file of Prometheus, enabling Prometheus to actively pull index data of various traffic facilities according to the configuration file, and storing the index data in a time sequence database; s2, analyzing and calculating the collected index data by utilizing PromQL in combination with the configured alarm rule, and judging whether alarm information is generated or not according to whether the configured alarm rule is triggered or not according to an analysis and calculation result; s3, based on the level of the alarm information, the system automatically generates an operation and maintenance work order to a service platform; and S4, carrying out association matching on the cleaned and filtered alarm information, the operation and maintenance work order information and the operation and maintenance record information to form case data and solution entry data, and providing a corresponding queriable API (Application Program Interface). The invention provides an efficient, intelligent, extensible and low-cost monitoring and operation and maintenance management method.

The invention relates to an Internet of Things sensor monitoring data encryption and storage processing method, and belongs to the field of Internet of Things sensor monitoring data acquisition, storage and application. The method comprises the following steps: establishing enterprise identification information, equipment identification information and data identification information, and adding identification information to acquired monitoring data information; the monitoring data information is encrypted through a multi-confusion encryption method, and finally a confusion ciphertext is output; establishing a time sequence database to store real-time monitoring data, and establishing a relational database to store abnormal monitoring data and related data; when decryption is needed, multiple confusion encryption is carried out on the real-time monitoring value in an enumeration mode according to the enterprise identification information, the equipment identification information and the data identification information, and the real-time monitoring value before encryption is determined according to a ciphertext. Aiming at the problems that the ciphertext is easy to repeat and high in regularity, the data storage and retrieval efficiency is improved, the data is prevented from being randomly tampered by means of the ciphertext information, and the data security protection capability is improved.

Provided are a method and apparatus for pre-aggregating time series data. The method comprises: acquiring at least one piece of time series data from a first device, the first device being a generation device of the at least one piece of time series data, or the first device being a node device of a time series database, and any one of the at least one piece of time series data comprising an identifier; determining a pre-aggregation method on the basis of the identifier of the at least one piece of time series data, the pre-aggregation method and the identifier of the at least one piece of time series data having a preset binding relationship; using the pre-aggregation method to process the at least one piece of time series data to generate pre-aggregated data; and when the use ratio of a memory meets a trigger condition, writing the pre-aggregated data and the at least one piece of time series data into a disk. The present invention can evenly distribute time series data and pre-aggregated data, so as to improve the utilization ratio of storage spaces.