Park resource evolution deployment method and system based on cross-time scale collaboration

Abstract

The application provides a park resource evolution allocation method and system based on cross-time scale collaboration, relates to the technical field of park resource scheduling, and comprises the following steps: collecting real-time running state information and historical running state information of multiple types of heterogeneous resources in a smart park; performing capability feature extraction based on the real-time running state information and the historical running state information, performing time correlation analysis on a resource capability feature set, and extracting resource evolution features; performing demand decoupling processing on business request information; inputting the resource capability feature set, the resource evolution features, and a demand intention feature set into a multi-agent scheduling processing channel, and performing collaborative scheduling and adaptive analysis; and performing intelligent optimization scheduling management according to a scheduling result. The application can solve the technical problem that park resource allocation cannot accurately match real-time business demand in the prior art, and can achieve the technical effect of real-time sensing of resource states, thereby improving resource utilization efficiency.

Description

Technical Field

[0001] This application relates to the field of park resource scheduling technology, and in particular to a method and system for park resource evolution and allocation based on cross-timescale collaboration. Background Technology

[0002] With the rapid development of smart park construction, the number of heterogeneous resources such as energy, space, equipment services, and computing within the parks is constantly increasing. These resources are complex and diverse, and business needs are becoming increasingly dynamic, placing higher demands on efficient resource scheduling and collaborative management. During operation, various resources within a smart park are affected by load fluctuations, changes in available capacity, and state transitions. Furthermore, different businesses have varying response speeds, service assurance requirements, and execution sequences, making resource supply and demand matching highly uncertain and complex. Efficient resource scheduling not only affects park operational efficiency but also directly impacts business service quality and user experience. Therefore, a technical solution is needed that can perceive resource status in real time, accurately characterize resource capabilities, and intelligently optimize scheduling based on business needs.

[0003] Currently, existing smart park resource scheduling technologies mainly rely on static resource allocation or rule-based scheduling methods, responding to business requests through preset resource allocation strategies and fixed scheduling rules. However, these methods typically fail to fully consider the changes in the sustainable supply capacity of resources under different load conditions, and lack dynamic characterization of the evolution characteristics of resource capacity over time and the costs of state switching. This can lead to scheduling decisions that may not accurately match real-time business needs in actual operation. Furthermore, existing scheduling methods often lack the ability to perform refined analysis of resources and business needs over time and the ability to process correlations across time scales. This makes them prone to problems such as insufficient resource supply, business delays, or service interruptions under load fluctuations or sudden increases in demand, thereby affecting the overall operational efficiency of the park and the continuity of business services.

[0004] In summary, existing technologies suffer from a lack of dynamic characterization of resource capacity evolution characteristics with load levels and time, as well as cross-timescale scheduling adaptation analysis. This results in resource allocation failing to accurately match real-time business needs, further impacting the continuity of smart park business execution, resource utilization efficiency, and overall service quality. Summary of the Invention

[0005] The purpose of this application is to provide a method and system for the evolution and allocation of park resources based on cross-timescale collaboration, in order to solve the technical problems in the existing technology that, due to the lack of dynamic characterization of resource capacity as load level and time evolution characteristics and cross-timescale scheduling adaptation analysis, resource allocation cannot accurately match real-time business needs, which further affects the continuity of smart park business execution, resource utilization efficiency and overall service quality.

[0006] In view of the above problems, this application provides a method and system for the evolution and allocation of park resources based on cross-timescale collaboration.

[0007] Firstly, this application provides a method for the evolution and allocation of park resources based on cross-timescale collaboration, implemented through a park resource evolution and allocation system based on cross-timescale collaboration. The method includes: during the operation of a smart park, collecting real-time and historical operational status information of various heterogeneous resources within the smart park, including energy resources, space resources, equipment service resources, and computing resources; performing capability feature extraction based on the real-time and historical operational status information to establish a resource capability feature set; conducting time correlation analysis on the resource capability feature set to extract resource evolution features reflecting resource status change trends and load evolution characteristics; synchronously reading business request information from the smart park; performing demand decoupling processing on the business request information to establish a demand intent feature set; inputting the resource capability feature set, resource evolution features, and demand intent feature set into a multi-entity scheduling processing channel to perform collaborative scheduling adaptation analysis and establish scheduling results; and performing intelligent optimization scheduling management based on the scheduling results.

[0008] Preferably, the method for coordinating park resource evolution and allocation across time scales further includes: in the resource capacity evolution scheduling sub-channel, using the resource scheduling entities corresponding to each resource, based on the resource capacity feature set and resource evolution characteristics, independently evaluating the sustainable supply range of resources under different load levels at the first time scale, and outputting resource capacity evolution constraint information; in the demand intention stability scheduling sub-channel, using the demand scheduling entities corresponding to each business, based on the demand intention feature set, evaluating the stability range and delayable boundary of business demand at the second time scale, and outputting demand stability constraint information, wherein the second time scale is different from the first time scale; activating the conflict adjustment scheduling sub-channel, performing cross-time scale correlation analysis on the resource capacity evolution constraint information and demand stability constraint information, and using the cross-time scale correlation analysis results to perform rearrangement processing of resource capacity release rhythm or demand execution sequence, and establishing scheduling results.

[0009] Preferably, the method for coordinating park resource evolution and allocation across time scales further includes: mapping the resource capability evolution constraint information to multiple consecutive effective resource capability segments according to a first time scale, each effective resource capability segment representing the maximum releaseable capability threshold, capability decay trend, and state switching cost within the corresponding time segment; mapping the demand stability constraint information to multiple stable demand execution segments according to a second time scale, each stable demand execution segment representing the minimum service guarantee requirements, delay limit, and timing adjustment tolerance of business demands within the corresponding time segment; performing overlap analysis on the effective resource capability segments and stable demand execution segments on the time axis to identify capability gap segments or capability redundancy segments formed by the effective resource capability segments and stable demand execution segments within the time overlap area, and establishing segment labels; and performing a rearrangement of the resource capability release rhythm or demand execution timing based on the segment labels to establish scheduling results.

[0010] Preferably, the method for resource evolution and allocation in the park based on cross-timescale collaboration further includes: performing combined analysis on multiple interconnected segment labels based on temporal adjacency and resource association to construct a segment collaboration relationship set reflecting the mutual influence of segment labels in the time and resource dimensions; evaluating the collaborative compensation capabilities of capacity gap segments and capacity redundancy segments in different time segments based on the segment collaboration relationship set, identifying candidate collaborative scheduling paths for collaborative balance through cross-segment resource capacity transfer, release time-series shifting, or demand execution window adjustment; and evaluating the capability decay trend, state switching cost, and time-series adjustment tolerance matching degree of the candidate collaborative scheduling paths to establish scheduling results.

[0011] Preferably, the park resource evolution and allocation method based on cross-timescale collaboration further includes: the resource capability feature set includes a feature set characterizing the resource supply intensity, response latency characteristics, continuous availability time window, operating state switching cost, and coupling dependency relationship between resources.

[0012] Preferably, the method for resource evolution and allocation in the park based on cross-timescale collaboration further includes: the demand intention feature set is a demand set that includes rigid service constraints, allowable delay intervals, alternative resource types, and service experience tolerance thresholds.

[0013] Preferably, the method for resource evolution and allocation in the park based on cross-timescale collaboration further includes: establishing a time-series verification window based on the scheduling results; using the time-series verification window to perform execution monitoring of the scheduling results and establish time-series monitoring feedback; and using the time-series monitoring feedback to configure a scheduling self-optimization strategy and perform self-optimization management.

[0014] Preferably, the method for coordinating park resource evolution and allocation across time scales further includes: the real-time operating status information includes utilization rate, load fluctuation, available capacity, and status switching history.

[0015] Preferably, the method for resource evolution and allocation in the park based on cross-timescale collaboration further includes: determining whether there is an adaptation anomaly signal based on collaborative scheduling adaptation analysis; if there is an adaptation anomaly signal, establishing an anomaly warning information and generating a scheduling adaptation strategy with demand taboos based on the anomaly warning information; and reporting the anomaly warning information and the scheduling adaptation strategy simultaneously.

[0016] Secondly, this application also provides a park resource evolution and allocation system based on cross-timescale collaboration, used to execute the park resource evolution and allocation method based on cross-timescale collaboration as described in the first aspect, including: a real-time operation status information acquisition module, used to collect real-time operation status information and historical operation status information of multiple heterogeneous resources in the smart park during the operation of the smart park, wherein the multiple heterogeneous resources include energy resources, space resources, equipment service resources and computing resources; and a resource evolution feature extraction module, used to perform capability feature extraction based on the real-time operation status information and historical operation status information, and establish a resource capability feature set. The system integrates a resource capability feature set, performs time correlation analysis on the resource capability feature set to extract resource evolution features reflecting resource status change trends and load evolution characteristics; a demand intent feature set establishment module is used to synchronously read business request information from the smart park, perform demand decoupling processing on the business request information, and establish a demand intent feature set; a scheduling result establishment module is used to input the resource capability feature set, resource evolution features, and demand intent feature set into a multi-entity scheduling processing channel, perform collaborative scheduling adaptation analysis, and establish a scheduling result; and an intelligent optimization scheduling management execution module is used to perform intelligent optimization scheduling management based on the scheduling result.

[0017] The technical solution provided in this application has at least the following technical effects or advantages: by achieving the technical goal of dynamic optimization management of smart park resources based on multi-subject collaborative scheduling, it can achieve the technical effects of being able to perceive resource status in real time, accurately characterize the evolution characteristics of resource capabilities, and perform intelligent scheduling across time scales in combination with business needs, thereby improving resource utilization efficiency, ensuring business execution continuity, and optimizing overall service quality.

[0018] The above description is merely an overview of the technical solution of this application. To enable a clearer understanding of the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this application 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 merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the park resource evolution and allocation method based on cross-timescale collaboration proposed in this application.

[0021] Figure 2 This is a schematic diagram of the structure of the park resource evolution and allocation system based on cross-timescale collaboration in this application.

[0022] Figure labeling: 1. Real-time operation status information acquisition module; 2. Resource evolution feature extraction module; 3. Demand intent feature set establishment module; 4. Scheduling result establishment module; 5. Intelligent optimization scheduling management execution module. Detailed Implementation

[0023] This application provides a method and system for resource evolution and allocation in smart parks based on cross-timescale collaboration. It addresses the technical problem in existing technologies where the lack of dynamic characterization of resource capabilities as they evolve with load levels and time, and the absence of cross-timescale scheduling adaptation analysis, leads to resource allocation failing to accurately match real-time business needs. This, in turn, impacts the continuity of smart park business execution, resource utilization efficiency, and overall service quality. The application achieves the technical goal of dynamic optimization management of smart park resources based on multi-entity collaborative scheduling. It enables real-time perception of resource status, accurate characterization of resource capability evolution, and intelligent cross-timescale scheduling in conjunction with business needs, thereby improving resource utilization efficiency, ensuring business execution continuity, and optimizing overall service quality.

[0024] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0025] Example 1, please refer to the appendix. Figure 1 This application provides a method for the evolution and allocation of park resources based on cross-timescale collaboration, which is applied to a park resource evolution and allocation system based on cross-timescale collaboration. The method specifically includes the following steps: During the operation of the smart park, real-time and historical operating status information of various heterogeneous resources within the smart park is collected. These heterogeneous resources include energy resources, space resources, equipment service resources, and computing resources.

[0026] Furthermore, this application also includes: the real-time operating status information includes utilization rate, load fluctuation, available capacity, and status switching history.

[0027] Specifically, during the operation of a smart park, collecting real-time and historical operational status information of various heterogeneous resources within the park refers to the continuous acquisition and integration of operational status parameters of different types of resources at the current moment and operational status records from previous periods during the park's daily operation phase, through sensor acquisition units, management system interfaces, or data aggregation modules. Real-time operational status information includes utilization rate, load fluctuation, available capacity, and status switching history. Utilization rate refers to the proportion of resources occupied or accessed by business requests per unit of time. It quantifies the relationship between the actual output capacity and the rated supply capacity of resources, reflecting the current operational intensity and resource allocation strain. Load fluctuation is a dynamic indicator representing the magnitude and frequency of load level changes over continuous operation. It depicts the characteristics of load increases, decreases, or unstable changes over time, reflecting the stability and potential risk trends during resource operation. Available capacity refers to the remaining capacity that resources can still release or allocate under the current operational state. It is characterized by the remaining capacity after deducting allocated load, reflecting the schedulable space and carrying capacity of resources in subsequent scheduling cycles. State switching history refers to historical information used to record the time sequence, number of switches, and corresponding state types of resource switching between different operating states. State switching history reflects the frequency of resource operating mode changes, switching stability, and switching cost characteristics. Historical operating state information reflects the long-term operating characteristics, change patterns, and cumulative behavioral characteristics of resources. Multiple heterogeneous resources are used to characterize resource sets that differ in their inherent functional attributes, operating mechanisms, and scheduling methods within the park. Energy resources characterize resource units that provide basic energy support, such as electricity and heating / cooling sources. Spatial resources characterize physical spaces or functional areas that can be occupied, allocated, or reconfigured by business activities. Equipment service resources characterize equipment and facilities that provide specific operational or service capabilities to business operations. Computing resources characterize computing units or computing nodes that support data processing, business computing, and intelligent decision-making.

[0028] Based on the real-time and historical operating status information, capability features are extracted to establish a resource capability feature set. Time correlation analysis is then performed on the resource capability feature set to extract resource evolution features that reflect the trend of resource status changes and load evolution characteristics.

[0029] Furthermore, this application also includes: the resource capability feature set includes a feature set characterizing the resource supply strength, response latency characteristics, continuous availability time window, operating state switching cost, and coupling dependency relationship between resources.

[0030] Specifically, capability feature extraction based on real-time and historical operational status information refers to using currently collected resource operational status data and accumulated operational status data from historical periods to perform structured analysis on resources' supply capacity, response capacity, and stable operation capacity, transforming raw status parameters into capability features that characterize the overall capability level of resources. Furthermore, establishing a resource capability feature set involves organizing and aggregating the multi-dimensional capability features obtained through capability feature extraction according to resource type, operational attributes, and scheduling relevance, forming a feature set structure that uniformly describes the capability status of various resources within the park. This resource capability feature set supports capability alignment among multiple resources, the construction of scheduling constraints, and subsequent analysis and processing.

[0031] The resource capability feature set includes a feature characterizing resource supply strength, which describes the upper limit and sustainability of a resource's ability to stably output to services within a unit of time. Resource supply strength quantifies the relationship between resource output capacity and load-bearing capacity, reflecting the resource's basic supply capacity within a scheduling cycle. Simultaneously, the resource capability feature set includes a feature characterizing response latency, which describes the time elapsed between receiving a scheduling instruction or service request and actually starting to provide service. Response latency reflects the resource's response speed to scheduling instructions and its adaptability to time-sensitive services. Further, the resource capability feature set includes a feature characterizing continuous availability time window, which describes the time interval within which a resource can remain available without interruption or state change. Continuous availability time window reflects the resource's stability in continuous operation scenarios and its ability to support long-term services. Additionally, the resource capability feature set includes a feature characterizing operational state switching cost, which describes the comprehensive cost of increased energy consumption, performance degradation, or time consumption incurred when switching resources between different operational states or working modes. Operational state switching cost reflects the impact of frequent scheduling or state changes on resource operating efficiency. Furthermore, the resource capability feature set includes a characterization of the coupling dependency relationship between resources, which refers to the feature parameters used to describe the mutual dependence or constraint relationship between different resources in terms of function, timing or operating conditions. The coupling dependency relationship between resources is used to reflect the linkage constraints and synergistic effects formed in the process of multi-resource collaborative supply.

[0032] Subsequently, time correlation analysis of the resource capability feature set refers to the correlation modeling of resource capability features corresponding to different time points on the time axis. By analyzing the continuity, periodicity or abruptness of capability features changing over time, the time dependency relationship between resource capability features is established, which is used to reveal the evolution logic of resource capabilities over time.

[0033] Therefore, extracting resource evolution features that reflect the trend of resource status changes and load evolution characteristics refers to extracting evolution feature parameters from the resource capability feature set based on the results of time correlation analysis. These parameters can describe the long-term direction and rate of change of resource status, as well as the process of load growth or decay. They are used to characterize the dynamic evolution characteristics of resources under different operating stages and provide a time-series awareness basis for subsequent scheduling decisions.

[0034] Synchronously read the business request information of the smart park, perform demand decoupling processing on the business request information, and establish a set of demand intent features.

[0035] Furthermore, this application also includes: the demand intent feature set is a demand set that includes rigid service constraints, allowable delay intervals, alternative resource types, and service experience tolerance thresholds.

[0036] Specifically, synchronously reading business request information of the smart park means that during the operation of the smart park, service request data from different business entities are obtained through the business management system interface, service orchestration module or scheduling access unit within the same time window of resource status collection. The business request information is used to characterize the overall request content of the business in terms of functional requirements, service level, timing requirements and resource consumption, thereby ensuring the consistency of business requirement acquisition and resource status perception in the time dimension.

[0037] Furthermore, performing requirement decoupling processing on business request information refers to separating and parsing the composite functional requirements, performance constraints, and resource dependencies within the business request information. This breaks down the multi-dimensional requirement elements originally coupled to a single business request into independent and separately analyzable requirement units. Requirement decoupling processing reduces the complexity of business requests and improves the structured nature of requirement expression. The specific process of requirement decoupling processing includes: a) parsing the business request information and retrieving a preset business requirement template based on the business type identifier. This template defines standard decoupling items for that type of business, such as computational load, storage load, bandwidth, response time, and reliability level; b) splitting composite business requests according to functional modules or temporal dependencies to generate multiple sub-requirement units. The splitting rules include: splitting parallel processing modules into independent sub-requirements; splitting serial processes by stage; merging shared resource modules into common sub-requirements; c) extracting the rigid service constraints, allowable latency range, alternative resource types, and service experience tolerance threshold for each sub-requirement unit; d) assigning weights and priorities to each sub-requirement unit and feature item according to a business priority strategy, forming a structured set of requirement intent features.

[0038] Subsequently, establishing a set of demand intent features refers to abstractly modeling the various demand units obtained after the demand decoupling process, extracting intent features that can reflect the real service purpose, constraint priority, and tolerance boundary of the business, and organizing them according to business type, scheduling relevance, and service constraint attributes to form a set of demand intent features for scheduling analysis.

[0039] The demand intent feature set includes a set of demands with rigid service constraints. These constraints describe the set of conditions that business demands must be strictly met during service provision and cannot be reduced or violated. Rigid service constraints characterize the minimum guarantee standards that the business must achieve in terms of functional integrity, service level, or security requirements. Simultaneously, the demand intent feature set includes a set of demands with allowable delay intervals. These parameters describe the time range within which business demands can be postponed or delayed in execution. Allowable delay intervals reflect the business's tolerance for execution timing flexibility, providing a boundary basis for timing adjustments during scheduling. Further, the demand intent feature set includes a set of demands with alternative resource types. These parameters describe the range of different resource categories or service methods acceptable to business demands while meeting business functional objectives. Alternative resource types reflect the business's adaptability to diverse resource choices and its dependence on a single resource. Finally, the demand intent feature set includes a set of demands with service experience tolerance thresholds. These parameters describe the upper limit of performance fluctuations acceptable to the business in terms of service quality, response speed, or execution continuity. Service experience tolerance thresholds reflect the business's sensitivity to changes in service quality and the optimization space during scheduling.

[0040] The resource capability feature set, resource evolution feature set, and demand intention feature set are input into the multi-entity scheduling processing channel to perform collaborative scheduling adaptation analysis and establish scheduling results.

[0041] Furthermore, this application also includes: a multi-entity scheduling processing channel comprising a resource capability evolution scheduling sub-channel, a demand intent stability scheduling sub-channel, and a conflict adjustment scheduling sub-channel; the collaborative scheduling adaptation analysis includes: in the resource capability evolution scheduling sub-channel, utilizing the resource scheduling entities corresponding to each resource based on the resource capability feature set and resource evolution characteristics, independently evaluating the sustainable supply range of resources under different load levels at a first time scale, and outputting resource capability evolution constraint information; in the demand intent stability scheduling sub-channel, utilizing the demand scheduling entities corresponding to each business based on the demand intent feature set, evaluating the stability range and delayable boundary of business demand at a second time scale, and outputting demand stability constraint information, wherein the second time scale is different from the first time scale; activating the conflict adjustment scheduling sub-channel, performing cross-time scale correlation analysis on the resource capability evolution constraint information and demand stability constraint information, and using the cross-time scale correlation analysis results to perform rearrangement processing of resource capability release rhythm or demand execution sequence, and establishing scheduling results. The specific decision-making algorithms for each scheduling subchannel are as follows: In the resource capacity evolution scheduling subchannel, each resource scheduling entity adopts a sustainable supply interval assessment algorithm based on load level: taking the load prediction curve in the resource evolution characteristics as input, and combining the available supply intensity, continuous availability time window, and switching cost in the resource capacity characteristic set, it calculates the maximum sustainable output capacity sequence of resources in the next N first time scale periods under the predicted load, under the constraints of switching cost threshold and availability time window, forming resource capacity evolution constraint information, i.e., the capacity upper limit set in each period; In the demand intention stability scheduling subchannel, each demand scheduling entity adopts a demand stability interval assessment algorithm: taking the demand intention characteristic set as input, and based on the dynamic characteristics of the business type and the allowable The latency interval and service experience tolerance threshold are used to calculate the elastic range of the execution time window for business requirements within the second time scale period, under the premise of satisfying rigid constraints and tolerance thresholds. This forms the demand stability constraint information, namely the earliest execution time, latest completion time, and quality fluctuation range of the demand within each period. The conflict adjustment scheduling sub-channel adopts a cross-time scale correlation analysis algorithm based on multi-objective optimization: after mapping the above two constraint information to a unified time axis, the optimization objectives are to minimize the total capacity gap, minimize the total state switching cost, and maximize the timing adjustment matching degree. With resource capacity constraints, demand rigid constraints, and timing dependency constraints as constraints, an integer programming model is constructed to solve for the optimal resource capacity release rhythm adjustment amount and demand execution timing adjustment amount, thereby generating the scheduling result. When the model is not feasible, an adaptation anomaly signal is output.

[0042] Furthermore, this application also includes: mapping the resource capability evolution constraint information into multiple consecutive effective resource capability segments according to a first time scale, each effective resource capability segment corresponding to the maximum releaseable capability threshold, capability decay trend, and state switching cost within the corresponding time segment; mapping the demand stability constraint information into multiple stable demand execution segments according to a second time scale, each stable demand execution segment corresponding to the minimum service guarantee requirements, delay limit, and timing adjustment tolerance of business demands within the corresponding time segment; performing overlap analysis on the effective resource capability segments and stable demand execution segments on the time axis to identify capability gap segments or capability redundancy segments formed by the effective resource capability segments and stable demand execution segments within the time overlap area, and establishing segment labels; and performing a rearrangement of the resource capability release rhythm or demand execution timing based on the segment labels to establish a scheduling result.

[0043] Furthermore, this application also includes: performing combined analysis on multiple interconnected segment labels based on temporal adjacency and resource association to construct a segment collaboration relationship set reflecting the mutual influence of segment labels in the time and resource dimensions; based on the segment collaboration relationship set, evaluating the collaborative compensation capabilities of capacity gap segments and capacity redundancy segments in different time segments, identifying candidate collaborative scheduling paths for collaborative balance through cross-segment resource capacity transfer, release time-series shifting, or demand execution window adjustment; and performing performance adaptation evaluation on the candidate collaborative scheduling paths based on capacity decay trends, state switching costs, and time-series adjustment tolerance matching degrees to establish scheduling results.

[0044] Furthermore, this application also includes: determining whether there is an adaptation anomaly signal based on the collaborative scheduling adaptation analysis; if there is an adaptation anomaly signal, establishing an anomaly warning message, and generating a scheduling adaptation strategy with demand prohibitions based on the anomaly warning message; and reporting the anomaly warning message and the scheduling adaptation strategy simultaneously.

[0045] Specifically, the process involves inputting the resource capability feature set, resource evolution feature set, and demand intention feature set into a multi-entity scheduling processing channel, performing collaborative scheduling adaptation analysis, and establishing scheduling results. This means that after completing resource capability modeling, resource evolution characterization, and demand intention modeling, the multi-source feature information is uniformly sent into a scheduling processing structure with multi-entity decision-making capabilities. Through the parallel participation of multiple scheduling entities in the analysis, collaborative matching between resource supply capabilities and business demand intentions is achieved, and an executable scheduling result is generated based on a comprehensive evaluation.

[0046] Meanwhile, the multi-entity scheduling and processing channel includes a resource capability evolution scheduling sub-channel, a demand intent stability scheduling sub-channel, and a conflict adjustment scheduling sub-channel. This means that within the scheduling and processing structure, multiple functional sub-channels are divided according to the scheduling focus dimension. Different sub-channels are responsible for the processing tasks of resource-side capability assessment, demand-side stability assessment, and conflict coordination between resources and demands, respectively. The multi-entity scheduling and processing channel completes the complex scheduling adaptation analysis process through the collaborative work between sub-channels.

[0047] Furthermore, in the resource capacity evolution scheduling sub-channel, the resource scheduling entities corresponding to each resource independently assess the sustainable supply range of resources under different load levels at the first time scale based on the resource capacity feature set and resource evolution characteristics, and output resource capacity evolution constraint information. This means that for independent scheduling decision-making entities of different resource configurations in the park, based on the current capacity status of resources and the evolution characteristics of capacity changes over time, they assess the capacity range of resources that can be stably and continuously supplied under various load conditions within a first time scale of finer granularity or shorter period, and output the assessment results in the form of constraints to characterize the resource capacity release range and evolution boundary.

[0048] Subsequently, in the demand intent stability scheduling sub-channel, the demand scheduling entities corresponding to each business are used to evaluate the stability range and delayable boundaries of business demands on a second time scale based on the demand intent feature set, and output demand stability constraint information. The second time scale is different from the first time scale. It means that an independent demand scheduling entity is set up for different business requests. Based on the demand intent feature set, from the perspective of business continuity and service experience, the stability range of business demands in the time dimension and the boundary range of allowed delayed execution are analyzed in a second time scale that is different from the resource evaluation cycle, and the analysis results are output as demand-side constraint information.

[0049] Furthermore, activating the conflict adjustment and scheduling sub-channel and mapping the resource capability evolution constraint information into multiple continuous effective resource capability segments according to the first time scale means that, based on the time-related characteristics reflected in the resource capability evolution constraint information, the resource capability is segmented according to the first time scale, so that the resource capability forms a continuously distributed capability segment on the time axis. Each effective resource capability segment is used to characterize the capability boundary conditions that the resource can release externally within the corresponding time segment. The maximum releaseable capability threshold is used to characterize the capability upper limit, the capability decay trend is used to characterize the decline or stabilization law of capability over time, and the state switching cost is used to characterize the comprehensive cost required for the resource to change its operating state.

[0050] Meanwhile, mapping demand stability constraint information into multiple demand stability execution segments according to the second time scale means that, based on the business timing characteristics reflected in the demand stability constraint information, the business demand is segmented and modeled according to a second time scale different from the first time scale, so that the business demand forms multiple stable execution segments on the time axis. Each demand stability execution segment is used to characterize the basic requirements of the business demand for service assurance within the corresponding time segment. The minimum service assurance requirement is used to characterize the service bottom line that cannot be reduced, the maximum delay limit is used to characterize the maximum delay range of the demand in time, and the time sequence adjustment tolerance is used to characterize the degree to which the demand accepts changes in the execution order.

[0051] Furthermore, the overlapping analysis of effective resource capacity segments and stable demand execution segments on the time axis refers to mapping effective resource capacity segments and stable demand execution segments to the same time coordinate system, analyzing the cross-relationship of different segments in the time dimension, thereby identifying the matching status between resource supply capacity and demand execution requirements in the time overlap area. When resource supply is insufficient to cover demand requirements, a capacity gap segment is formed; when resource supply exceeds demand requirements, a capacity redundancy segment is formed. Corresponding segment labels are established for different types of segments to distinguish scheduling status.

[0052] Based on temporal adjacency and resource association, this study combines and analyzes multiple interconnected segment labels to construct a set of segment collaboration relationships that reflects the mutual influence of segment labels in the temporal and resource dimensions. This involves jointly analyzing multiple related segment labels based on their temporal adjacency order and the functional dependencies, supply linkages, or shared constraints between the corresponding resources of the segments. By describing the interaction between segments at different time positions and in different resource dimensions, a set of segment collaboration relationships is formed to characterize the collaboration potential and constraints between segments.

[0053] Simultaneously, based on the segment collaboration relationship set, the collaborative compensation capabilities of capacity gap segments and capacity surplus segments in different time segments are evaluated. Candidate collaborative scheduling paths for achieving collaborative balance through cross-segment resource capacity transfer, release time shifting, or demand execution window adjustment are identified. This means that under the constraints of the segment collaboration relationship set, a matching analysis is performed on segments with insufficient capacity and segments with surplus capacity. The analysis assesses whether multiple segments that are misaligned in time or related in resources have the potential to achieve supply and demand balance through capacity transfer, capacity release time adjustment, or demand execution time window adjustment. Feasible collaborative adjustment methods are then abstracted into candidate collaborative scheduling paths.

[0054] Furthermore, based on the candidate collaborative scheduling paths, an adaptation evaluation is performed on the capacity decay trend, state switching cost, and timing adjustment tolerance matching degree to establish the scheduling result. This means that for different candidate collaborative scheduling paths, the adaptability evaluation of each candidate path is performed by comprehensively considering the decay characteristics of resource capacity over time, the cost of switching resources between different operating states, and the acceptability of timing adjustments to business requirements, and the final executable scheduling result is determined on the basis of satisfying multi-dimensional constraints.

[0055] The process of reordering the release rhythm of resources or the execution sequence of demands by utilizing the results of cross-timescale correlation analysis to establish scheduling results refers to the unified correlation analysis of constraint information formed at different time scales through the conflict adjustment scheduling sub-channel after identifying resource-side constraints and demand-side constraints. This process identifies supply-demand mismatches or timing conflicts, and adjusts and rearranges the release rhythm of resources or the execution sequence of business operations based on the analysis results, thereby generating a final scheduling result that satisfies multiple constraints.

[0056] Determining whether there are adaptation anomaly signals based on collaborative scheduling adaptation analysis refers to monitoring and evaluating the scheduling matching results based on the completion of resource capacity, demand intention and segment collaborative analysis. By detecting deviations, conflicts or unmet conditions between resource supply capacity and business demand execution requirements, abnormal signals that may lead to supply and demand imbalance or scheduling failure under the current scheduling arrangement are identified. Adaptation anomaly signals are used to characterize potential risk points or unsatisfactory matching states in the scheduling process.

[0057] If an adaptation anomaly signal exists, an anomaly warning message is established, and a demand prohibition scheduling adaptation strategy is generated based on the anomaly warning message. This means that after identifying the adaptation anomaly signal, the abnormal situation is described in an informational way to form an anomaly warning message for the scheduling system or management entity. The anomaly warning message is used to indicate the risk of potential resource conflicts, insufficient capacity, or demand delays. At the same time, a scheduling adaptation strategy is formulated based on the anomaly warning message. The demand prohibition scheduling strategy is used to specify business requirements that are not allowed to be executed or must be adjusted under abnormal conditions, so as to ensure that scheduling adjustments can avoid or mitigate the impact of anomalies.

[0058] Simultaneous reporting of abnormal early warning information and scheduling adaptation strategies refers to outputting both types of information to the monitoring terminal or scheduling execution module through the scheduling management system or interface after the abnormal early warning information is generated and the emergency scheduling strategy is formulated. This enables the scheduling system to receive abnormal prompts in real time and adjust resource allocation or business execution order according to the strategy, thereby achieving controllable management of scheduling abnormalities.

[0059] Intelligent optimization scheduling management is performed based on the scheduling results.

[0060] Furthermore, this application also includes: establishing a timing verification window based on the scheduling result; using the timing verification window to perform execution monitoring of the scheduling result and establishing timing monitoring feedback; using the timing monitoring feedback to configure a scheduling self-optimization strategy and perform self-optimization management.

[0061] Specifically, establishing a time-series verification window based on scheduling results means that after completing the collaborative scheduling analysis of resources and business requirements and generating scheduling results, a time interval is defined for verifying the scheduling execution based on the resource allocation and business execution time arrangements in the scheduling results. The time-series verification window is used to limit the observation scope of scheduling execution and provide a time benchmark for real-time verification of scheduling order, resource usage and business response.

[0062] Utilizing a time-series verification window to monitor the execution of scheduling results and establish time-series monitoring feedback refers to continuously monitoring the resource allocation and business execution status in the scheduling results within the time range defined by the time-series verification window. By collecting actual resource usage, business completion progress, and abnormal triggering information, quantifiable time-series monitoring feedback data is formed to reflect the accuracy, deviation, and potential anomalies of the scheduling results in the actual execution process.

[0063] Utilizing time-series monitoring feedback to configure scheduling self-optimization strategies and perform self-optimization management refers to generating automatically adjustable scheduling self-optimization strategies based on the resource load imbalance, task delays, or execution anomalies shown in the feedback after obtaining time-series monitoring feedback data. By dynamically modifying the resource allocation rhythm, business execution order, or priority allocation, closed-loop optimization management of the scheduling scheme is achieved, thereby improving resource utilization efficiency and business service stability.

[0064] In summary, the park resource evolution and allocation method based on cross-timescale collaboration provided in this application has the following technical effects: by achieving the technical goal of dynamic optimization management of smart park resources based on multi-subject collaborative scheduling, it can realize the technical effects of real-time perception of resource status, accurate characterization of resource capability evolution characteristics, and intelligent scheduling across timescales in combination with business needs, thereby improving resource utilization efficiency, ensuring business execution continuity, and optimizing overall service quality.

[0065] Example 2: Based on the same inventive concept as the cross-timescale collaborative park resource evolution and allocation method in the foregoing examples, this application also provides a cross-timescale collaborative park resource evolution and allocation system. Please refer to the appendix. Figure 2The system includes: a real-time operation status information acquisition module 1, used to collect real-time and historical operation status information of various heterogeneous resources within the smart park during its operation, including energy resources, space resources, equipment service resources, and computing resources; a resource evolution feature extraction module 2, used to extract capability features based on the real-time and historical operation status information, establish a resource capability feature set, and perform time correlation analysis on the resource capability feature set to extract resource evolution features reflecting resource status change trends and load evolution characteristics; a demand intent feature set establishment module 3, used to synchronously read business request information from the smart park, perform demand decoupling processing on the business request information, and establish a demand intent feature set; a scheduling result establishment module 4, used to input the resource capability feature set, resource evolution features, and demand intent feature set into a multi-entity scheduling processing channel, perform collaborative scheduling adaptation analysis, and establish a scheduling result; and an intelligent optimization scheduling management execution module 5, used to execute intelligent optimization scheduling management based on the scheduling result.

[0066] Furthermore, the park resource evolution and allocation system based on cross-timescale collaboration is also used for: in the resource capacity evolution scheduling sub-channel, using the resource scheduling entities corresponding to each resource, based on the resource capacity feature set and resource evolution characteristics, to independently evaluate the sustainable supply range of resources under different load levels at the first time scale, and output resource capacity evolution constraint information; in the demand intention stability scheduling sub-channel, using the demand scheduling entities corresponding to each business, based on the demand intention feature set, to evaluate the stability range and delayable boundary of business demand at the second time scale, and output demand stability constraint information, wherein the second time scale is different from the first time scale; activating the conflict adjustment scheduling sub-channel, performing cross-timescale correlation analysis on the resource capacity evolution constraint information and demand stability constraint information, and using the cross-timescale correlation analysis results to perform rearrangement processing of resource capacity release rhythm or demand execution sequence, and establishing scheduling results.

[0067] Furthermore, the park resource evolution and allocation system based on cross-timescale collaboration is also used to: map the resource capability evolution constraint information into multiple consecutive effective resource capability segments according to a first time scale, each effective resource capability segment corresponding to the maximum releaseable capability threshold, capability decay trend, and state switching cost within the corresponding time segment; map the demand stability constraint information into multiple demand stability execution segments according to a second time scale, each stable demand execution segment corresponding to the minimum service guarantee requirements, delay limit, and timing adjustment tolerance of business demands within the corresponding time segment; perform overlap analysis on the effective resource capability segments and stable demand execution segments on the time axis, identify capability gap segments or capability redundancy segments formed by the effective resource capability segments and stable demand execution segments in the time overlap area, and establish segment labels; and perform reordering of resource capability release rhythm or demand execution timing based on the segment labels to establish scheduling results.

[0068] Furthermore, the park resource evolution and allocation system based on cross-timescale collaboration is also used for: combining and analyzing multiple interconnected segment labels based on temporal adjacency and resource association to construct a segment collaboration relationship set reflecting the mutual influence of segment labels in the time and resource dimensions; based on the segment collaboration relationship set, evaluating the collaborative compensation capabilities of capacity gap segments and capacity redundancy segments in different time segments, identifying candidate collaborative scheduling paths for collaborative balance through cross-segment resource capacity transfer, release time-series shifting, or demand execution window adjustment; and performing performance adaptation evaluation on the candidate collaborative scheduling paths based on capacity decay trends, state switching costs, and time-series adjustment tolerance matching degrees to establish scheduling results.

[0069] Furthermore, the park resource evolution and allocation system based on cross-timescale collaboration is also used for: the resource capability feature set includes a feature set that characterizes the resource supply intensity, response latency characteristics, continuous availability time window, operating state switching cost, and coupling dependency relationship between resources.

[0070] Furthermore, the park resource evolution and allocation system based on cross-timescale collaboration is also used for: the demand intention feature set is a demand set including rigid service constraints, allowable delay intervals, alternative resource types and service experience tolerance thresholds.

[0071] Furthermore, the park resource evolution and allocation system based on cross-timescale collaboration is also used for: establishing a time-series verification window based on the scheduling results; using the time-series verification window to perform execution monitoring of the scheduling results and establish time-series monitoring feedback; and using the time-series monitoring feedback to configure a scheduling self-optimization strategy and perform self-optimization management.

[0072] Furthermore, the park resource evolution and allocation system based on cross-timescale collaboration is also used for: the real-time operating status information includes utilization rate, load fluctuation, available capacity and status switching history.

[0073] Furthermore, the park resource evolution and allocation system based on cross-timescale collaboration is also used to: determine whether there is an adaptation anomaly signal based on collaborative scheduling adaptation analysis; if there is an adaptation anomaly signal, establish an anomaly warning information and generate a scheduling adaptation strategy with demand taboos based on the anomaly warning information; and report the anomaly warning information and the scheduling adaptation strategy simultaneously.

[0074] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The park resource evolution and allocation method and specific examples based on cross-timescale collaboration in the aforementioned embodiment 1 are also applicable to the park resource evolution and allocation system based on cross-timescale collaboration in this embodiment. Through the foregoing detailed description of the park resource evolution and allocation method based on cross-timescale collaboration, those skilled in the art can clearly understand the park resource evolution and allocation system based on cross-timescale collaboration in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0075] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0076] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for resource evolution and allocation in industrial parks based on cross-timescale collaboration, characterized in that, The method includes: During the operation of the smart park, real-time and historical operating status information of various heterogeneous resources within the smart park is collected. These heterogeneous resources include energy resources, space resources, equipment service resources, and computing resources. Based on the real-time and historical operating status information, the performance capability features are extracted, a resource capability feature set is established, and time correlation analysis is performed on the resource capability feature set to extract resource evolution features that reflect the trend of resource status changes and load evolution characteristics. Synchronously read the business request information of the smart park, perform demand decoupling processing on the business request information, and establish a set of demand intent features; The resource capability feature set, resource evolution feature set, and demand intention feature set are input into the multi-entity scheduling processing channel to perform collaborative scheduling adaptation analysis and establish scheduling results. Intelligent optimization scheduling management is performed based on the scheduling results.

2. The method for resource evolution and allocation in industrial parks based on cross-timescale collaboration as described in claim 1, characterized in that, The multi-entity scheduling processing channel includes a resource capacity evolution scheduling sub-channel, a demand intention stabilization scheduling sub-channel, and a conflict adjustment scheduling sub-channel. The collaborative scheduling adaptation analysis includes: In the resource capacity evolution scheduling sub-channel, the resource scheduling entity corresponding to each resource independently evaluates the sustainable supply range of resources under different load levels at the first time scale based on the resource capacity feature set and resource evolution characteristics, and outputs resource capacity evolution constraint information. In the demand intention stability scheduling sub-channel, the demand scheduling subject corresponding to each service evaluates the stability range and delayable boundary of service demand on the second time scale based on the demand intention feature set, and outputs demand stability constraint information. The second time scale is different from the first time scale. Activate the conflict adjustment and scheduling sub-channel, perform cross-timescale correlation analysis on the resource capacity evolution constraint information and demand stability constraint information, and use the cross-timescale correlation analysis results to perform rearrangement processing of resource capacity release rhythm or demand execution sequence to establish scheduling results.

3. The method for resource evolution and allocation in industrial parks based on cross-timescale collaboration as described in claim 2, characterized in that, Perform cross-timescale correlation analysis on the resource capacity evolution constraint information and demand stability constraint information, including: The resource capability evolution constraint information is mapped into multiple consecutive effective resource capability segments according to the first time scale. Each effective resource capability segment corresponds to the maximum releaseable capability threshold, capability decay trend and state switching cost within the corresponding time segment. The demand stability constraint information is mapped into multiple demand stability execution segments according to the second time scale. Each demand stability execution segment corresponds to the minimum service guarantee requirement, the upper limit of delay, and the tolerance for timing adjustment of the business demand in the corresponding time segment. Overlap analysis is performed on the effective resource capacity segments and stable demand execution segments on the time axis to identify capacity gap segments or capacity redundancy segments formed in the time overlap area between the effective resource capacity segments and stable demand execution segments, and segment labels are established. Based on the segment labels, the resource capacity release rhythm or demand execution sequence is rearranged to establish a scheduling result.

4. The method for resource evolution and allocation in industrial parks based on cross-timescale collaboration as described in claim 3, characterized in that, The process of reordering resource capacity release rhythm or demand execution sequence based on the segment labels includes: Based on temporal adjacency and resource association, we perform combined analysis on multiple interrelated segment labels to construct a segment collaboration relationship set that reflects the mutual influence of segment labels in the temporal and resource dimensions. Based on the aforementioned segment collaboration relationship set, the collaborative compensation capabilities of capacity gap segments and capacity redundancy segments in different time segments are evaluated, and candidate collaborative scheduling paths are identified through cross-segment resource capacity transfer, release time-series shift, or demand execution window adjustment to balance execution collaboration. Based on the candidate collaborative scheduling paths, an adaptation evaluation is performed on the capability decay trend, state switching cost, and timing adjustment tolerance matching degree to establish the scheduling result.

5. The method for resource evolution and allocation in industrial parks based on cross-timescale collaboration as described in claim 1, characterized in that, The resource capability feature set includes a set of features that characterize the strength of resource availability, response latency characteristics, continuous availability time window, operating state switching cost, and coupling dependencies between resources.

6. The method for resource evolution and allocation in industrial parks based on cross-timescale collaboration as described in claim 1, characterized in that, The set of demand intent features includes rigid service constraints, allowable delay intervals, alternative resource types, and service experience tolerance thresholds.

7. The method for resource evolution and allocation in industrial parks based on cross-timescale collaboration as described in claim 1, characterized in that, Based on the scheduling results, intelligent optimization scheduling management is performed, including: Establish a timing verification window based on the scheduling results; The execution monitoring of the scheduling results is performed using the aforementioned timing verification window, and timing monitoring feedback is established. The scheduling self-optimization strategy is configured using the time-series monitoring feedback, and self-optimization management is executed.

8. The method for resource evolution and allocation in industrial parks based on cross-timescale collaboration as described in claim 1, characterized in that, The real-time operating status information includes utilization rate, load fluctuation, available capacity, and status switching history.

9. The method for resource evolution and allocation in industrial parks based on cross-timescale collaboration as described in claim 1, characterized in that, Performing collaborative scheduling adaptation analysis also includes: Determine whether there are any adaptation anomaly signals based on the collaborative scheduling adaptation analysis; If an adaptation anomaly signal exists, an anomaly warning message is established, and a scheduling adaptation strategy that prohibits certain requirements is generated based on the anomaly warning message. The abnormal warning information and scheduling adaptation strategy are reported simultaneously.

10. A park resource evolution and allocation system based on cross-timescale collaboration, characterized in that, The steps for implementing the park resource evolution and allocation method based on cross-timescale collaboration as described in any one of claims 1 to 9 include: The real-time operation status information acquisition module is used to collect real-time and historical operation status information of various heterogeneous resources in the smart park during the operation of the smart park. The various heterogeneous resources include energy resources, space resources, equipment service resources and computing resources. The resource evolution feature extraction module is used to perform capability feature extraction based on the real-time operation status information and historical operation status information, establish a resource capability feature set, and perform time correlation analysis on the resource capability feature set to extract resource evolution features that reflect the trend of resource status changes and load evolution characteristics. The demand intent feature set establishment module is used to synchronously read the business request information of the smart park, perform demand decoupling processing on the business request information, and establish a demand intent feature set. The scheduling result establishment module is used to input the resource capability feature set, resource evolution feature set, and demand intention feature set into the multi-entity scheduling processing channel, perform collaborative scheduling adaptation analysis, and establish scheduling results; The intelligent optimization scheduling management execution module is used to perform intelligent optimization scheduling management based on the scheduling results.

Images