Multi-dimensional sensing method and system for small industrial load regulation capability of power distribution network

Abstract

The invention discloses a multi-dimensional sensing method and system for the small industrial load regulation capacity of a power distribution network, and relates to the technical field of power distribution network load response scheduling, and the method comprises the steps: collecting data in real time, and analyzing and integrating the data; performing first evaluation on the load regulation capability, and generating an instruction through first analysis; and predicting the load regulation capability, and generating an optimal scheme. According to the power distribution network small industrial load regulation capability multi-dimensional sensing method provided by the invention, comprehensive sensing and efficient response of the small industrial load of the medium-voltage access power distribution network are realized through real-time acquisition of the cloud edge collaborative architecture and the edge device, and high prediction accuracy and automatic response capability of the small industrial load are utilized; according to the method, the adjustment efficiency is improved, the response cost is reduced, the scheduling efficiency of the power distribution network is improved through the combination of the artificial intelligence technology and the load response model, and the method is suitable for various power distribution network scenes, has wide applicability and achieves better effects in the aspects of the adjustment efficiency, the response cost and the applicability.

Description

Technical Field

[0001] The present invention relates to the technical field of load response scheduling of distribution networks, and in particular to a multi-dimensional perception method of small industrial load regulation capability of distribution networks. Background Art

[0002] With the continuous evolution of smart grid technology, the load response capability of distribution networks plays a vital role in the operation and management of power systems. Especially in the context of the increasing scale of renewable energy power generation and grid connection, the power grid needs to have stronger flexibility and regulation capabilities to cope with the dynamic changes in the imbalance between power supply and demand. Traditional load response methods are mainly aimed at low-voltage residential users and high-voltage industrial users, and their response characteristics are relatively mature. However, small industrial loads connected to medium voltage are an important load type between the two. They are huge in number and have significant regulation potential, making them an important object of renewed attention in power grid dispatching. In recent years, the popularization of technologies such as cloud computing, artificial intelligence, and edge computing has provided advanced technical means for the perception and optimal regulation of medium-voltage industrial loads. These technologies have shown great application prospects in improving load forecasting accuracy, response efficiency, and cost control.

[0003] Although the development of relevant technologies has laid the foundation for improving the load regulation capability of power grids, the existing methods still have significant deficiencies when applied to medium-voltage access to small industrial loads. On the one hand, traditional load response methods lack real-time and comprehensiveness. Existing monitoring equipment and communication methods can usually only collect single-dimensional data, such as load power or voltage status, while ignoring multi-dimensional information such as meteorological conditions and equipment operating status. This lack of information directly limits the accuracy of load regulation schemes. On the other hand, the collaborative management capability of distributed small industrial loads is weak. Existing schemes mostly adopt single-node optimization and regulation, resulting in a large number of load resources not being fully utilized and poor systematic optimization effects. In addition, although industrial loads have high automated response capabilities, existing technologies lack effective response probability modeling and economic optimization strategies, making it difficult to provide regulation schemes that minimize costs and meet power grid needs. In summary, existing technologies are still unable to fully perceive the dynamic characteristics of medium-voltage industrial loads, let alone achieve efficient management of regional load regulation through intelligent optimization. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problems solved by the present invention are: the existing load regulation capability perception methods have poor real-time performance, insufficient multi-dimensional information perception, lack of collaborative optimization capabilities, and how to achieve precise load regulation and high economic optimization.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a multi-dimensional perception method of the small industrial load regulation capability of a distribution network, including real-time data collection, analysis and integration of data; a first evaluation of the load regulation capability, and generating instructions through the first analysis; predicting the load regulation capability and generating the optimal solution.

[0007] As a preferred solution of the multi-dimensional perception method of the small industrial load regulation capability of the distribution network described in the present invention, the real-time data collection includes real-time collection of multi-dimensional load data.

[0008] As a preferred solution of the multi-dimensional perception method of the small industrial load regulation capability of the distribution network described in the present invention, wherein: the analysis and integration of data includes summarizing and analyzing the multi-dimensional load data.

[0009] As a preferred solution of the multi-dimensional perception method of small industrial load regulation capability of the distribution network described in the present invention, wherein: the first evaluation of the load regulation capability includes evaluating the load regulation capability of each load regulation characteristic.

[0010] As a preferred solution of the multi-dimensional perception method of the small industrial load regulation capability of the distribution network described in the present invention, wherein: the generating instructions through the first analysis includes generating scheduling instructions for each time scale.

[0011] As a preferred solution of the multi-dimensional perception method of the small industrial load regulation capability of the distribution network described in the present invention, wherein: the predicted load regulation capability includes learning and analyzing the multi-dimensional load data.

[0012] As a preferred solution of the multi-dimensional perception method of small industrial load regulation capability of the distribution network described in the present invention, wherein: generating the optimal solution includes generating the optimal load regulation solution.

[0013] Another object of the present invention is to provide a multi-dimensional perception system for the regulation capability of small industrial loads in a distribution network, which can generate response instructions through an evaluation and analysis module using an optimization algorithm, thereby solving the problem that the currently generated regulation instructions are often delayed and difficult to match actual needs.

[0014] As a preferred solution of the multi-dimensional perception system of small industrial load regulation capability of the distribution network described in the present invention, it includes: a collection and integration module, an evaluation and analysis module, and a solution generation module; the collection and integration module is used to collect data in real time, analyze and integrate data; the evaluation and analysis module is used to perform a first evaluation of the load regulation capability, and generate instructions through the first analysis; the solution generation module is used to predict the load regulation capability and generate the optimal solution.

[0015] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that the processor executes the computer program to implement a step of a multi-dimensional perception method of the small industrial load regulation capability of a distribution network.

[0016] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of a multi-dimensional perception method of the small industrial load regulation capability of a distribution network are implemented.

[0017] Beneficial effects of the invention: The multi-dimensional perception method of the small industrial load regulation capability of the distribution network provided by the invention realizes comprehensive perception and efficient response of small industrial loads connected to the medium voltage distribution network through real-time collection of the cloud-edge collaborative architecture and edge devices, and utilizes the high prediction accuracy and automated response capability of small industrial loads to improve the regulation efficiency and reduce the response cost. Through the combination of artificial intelligence technology and load response models, a load response solution with minimized costs is provided, thereby improving the dispatching efficiency of the distribution network. The invention is suitable for various distribution network scenarios such as cities, industries, and rural areas, and has wide applicability. The invention achieves better results in terms of regulation efficiency, response cost, and applicability. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0019] Figure 1 An overall flow chart of a multi-dimensional perception method of small industrial load regulation capability of a distribution network provided for the first and second embodiments of the present invention.

[0020] Figure 2 An overall module diagram of a multi-dimensional perception system for small industrial load regulation capability of a distribution network provided in accordance with the fourth embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0022] Example 1

[0023] Reference Figure 1 , which is an embodiment of the present invention, provides a multi-dimensional perception method of small industrial load regulation capability of a distribution network, comprising:

[0024] S1: Collect, analyze and integrate data in real time.

[0025] Furthermore, real-time data collection includes real-time collection of multi-dimensional load data.

[0026] It should be noted that the edge device is deployed at a small industrial load node with medium voltage access. It collects multi-dimensional information through the sensing unit, including load capacity, equipment status, meteorological conditions, production process data, etc. In particular, the characteristics of industrial loads are diverse and highly dynamic. The collected real-time data not only covers basic power and voltage information, but also includes the load change characteristics during the production process. For the kiln system of cement production, the edge device can collect its operating thermal stability and equipment load status to ensure the accuracy of the data. The collected real-time data is efficiently uploaded to the cloud through the communication unit;

[0027] The collection process solves the limitations of single-point monitoring in traditional methods, and also forms wide-area perception capabilities through the distributed deployment of edge devices, making up for the shortcomings of existing perception systems in data comprehensiveness. Multi-dimensional real-time collection improves the system's response speed when dealing with dynamic grid load changes.

[0028] Furthermore, analyzing and integrating data includes summarizing and analyzing multi-dimensional load data.

[0029] It should be noted that the collected multi-dimensional data is pre-processed by the edge device and then transmitted to the high-performance computing cluster in the cloud. The cloud uses data aggregation and deep analysis technology to uniformly model and integrate the data from different edge devices. The high-load stability data from steel companies, the dynamic load characteristic data from cement production, and the short-time response data from metal processing are aggregated to form a comprehensive analysis model of the load regulation capability of the entire network. The cloud system uses artificial intelligence algorithms to perform correlation analysis on key indicators such as load capacity, regulation characteristics, and response probability, predict potential regulation needs, and generate more operational load regulation strategies. The architecture that combines distributed edge collection with centralized cloud integration improves the accuracy and real-time performance of load response plans.

[0030] Example 2

[0031] Reference Figure 1 , which is an embodiment of the present invention, provides a multi-dimensional perception method of small industrial load regulation capability of a distribution network, comprising:

[0032] S2: Perform a first evaluation on the load regulation capability and generate instructions through a first analysis.

[0033] Furthermore, performing a first evaluation on the load regulation capability includes performing a load regulation capability evaluation on each load regulation characteristic.

[0034] In the embodiment of the present application, the first evaluation is the evaluation of the edge-cloud collaborative load regulation capability. Through multi-dimensional modeling, the load regulation capability is quantitatively analyzed and probabilistically described. The modeling content includes the upper and lower limits of the adjustment power. The system determines the load adjustment power range based on the real-time collected data and historical operating rules, combined with the equipment characteristics, load type and external environment. The adjustable range is within a certain power range, which depends on the rated power of the load equipment, the current load level and the requirements for power supply stability;

[0035] Response probability and delay analysis: Through the probabilistic random model, the system can quantify the response success rate and response delay of the load under different power regulation targets. When the power regulation target is low, the response success rate is close to 100%, while when the regulation target is close to the load limit, the success rate will gradually decrease. The analysis of response delay can provide a reference for the optimization of the time window of subsequent scheduling instructions.

[0036] Regulation cost assessment, in which a preliminary estimate of the direct or indirect costs of load regulation is required, including factors such as the potential impact of load regulation on the production process, changes in energy consumption, and fluctuations in electricity prices;

[0037] During the assessment, the system will conduct a preliminary analysis of the load regulation capability at different time scales (seconds, minutes, and hours). The second-level regulation capability is mainly aimed at dynamic frequency adjustment needs, such as scenarios where power grid emergencies require rapid response. In the second-level assessment, the system will focus on analyzing the short-term flexibility of the load and the instantaneous response speed of the equipment. The minute-level regulation capability is usually used for peak shaving or valley filling or regulation balance of regional loads. At this time scale, the assessment pays more attention to the stability of the load and the automatic regulation capability of the equipment. The hour-level regulation capability is mainly used for load adjustment over a long period of time, such as optimizing load curves or responding to continuous changes in electricity supply and demand. The hour-level assessment is usually combined with more external data (such as meteorological conditions and electricity price changes) to analyze the long-term regulation potential of the load.

[0038] Through a quick preliminary evaluation, the system screens out load nodes with high regulation potential and matches them with reasonable regulation targets. For example, the calculation results of the upper and lower limits of regulation power and the response probability can be directly used to generate load regulation instructions at the second and minute levels. At the same time, the cost analysis in the preliminary evaluation also provides a direction for the system to optimize regulation costs.

[0039] In an optional embodiment, the first evaluation can also be implemented in other ways, such as distributed collaborative load regulation evaluation. Under the distributed collaborative computing architecture, each edge device not only collects local load data, but also exchanges evaluation data with neighboring devices through a dedicated communication unit. For example, in an industrial park in a certain area, multiple edge devices are deployed at different industrial load nodes (such as steel plants, cement plants, metal processing enterprises, etc.). These devices upload load data in real time and also receive evaluation results of other devices to conduct a joint evaluation of cross-node regulation capabilities.

[0040] The edge devices share their own key data such as upper and lower limits of load regulation, response probability and cost estimation in real time. Each edge device independently runs the evaluation algorithm based on the received data from neighboring nodes and the characteristics of the local load. Through weighted average or priority sorting methods, a preliminary evaluation result of the load regulation capacity in the area is obtained. Each edge device feeds back the local evaluation result to the dispatch control center.

[0041] Distributed collaborative evaluation relies on algorithm sharing and computational result interaction between edge devices. Each edge device establishes a load regulation capability model based on locally collected data and historical load operation rules. After exchanging modeling results between devices, the load regulation capability in the region is jointly evaluated through distributed algorithms (such as iterative solution and distributed linear programming). For example, when three devices perform collaborative calculations, the algorithm generates an evaluation result of the comprehensive regulation capability in the region by comparing the response success rate and regulation cost of each node. After the collaborative calculation is completed, each edge device independently generates preliminary results of the regional load regulation capability. For example, for a scenario with a total power regulation demand of 30MW, the device concludes through distributed evaluation that node A provides 15MW (lowest cost), node B provides 10MW (highest response probability), and node C provides 5MW (higher load flexibility).

[0042] Furthermore, generating instructions through the first analysis includes generating scheduling instructions for each time scale.

[0043] In the embodiment of the present application, the first analysis is the load regulation instruction generation analysis, and the regulation target is determined according to the current demand of the power grid. For the second-level regulation demand, the goal is to quickly adjust the power to stabilize the power grid frequency. For the minute-level or hour-level regulation demand, it is necessary to reduce the peak and fill the valley or cope with load fluctuations. After clarifying the regulation target, the system combines the evaluation results to perform matching analysis on the currently available industrial loads;

[0044] Matching analysis is to combine the regulation potential and response capabilities of different load units. The system screens and sorts multiple load nodes through real-time uploaded data such as load capacity, equipment status, and response probability, giving priority to load units with high response success rate, low regulation cost, and strong equipment stability. When rapid response is required, load units with high equipment flexibility and short response delay are given priority. For long-term load adjustment, the system gives priority to industrial loads with larger power capacity to reduce the number of regulation nodes and improve efficiency.

[0045] After completing the adjustment target matching, the optimization stage begins. The optimization algorithm is used in combination with the evaluation results to generate specific adjustment instructions. The optimization content includes the calculation of the adjustment power target value. According to the load upper and lower limits and the response probability model, the adjustment target of each load unit is determined. For example, when the adjustment demand is 20MW, the system allocates 15MW to the load unit with a higher response probability, and the remaining 5MW is allocated to the suboptimal unit to ensure that the total power meets the adjustment demand, time window and allowable error range. For each adjustment target, the system simultaneously generates an execution time window and an allowable error range.

[0046] In an optional embodiment, the first analysis may also be implemented in other ways, such as group analysis of regional hierarchical priority strategies, where the industrial loads are divided into a number of priority groups, each group is divided based on its load characteristics and contribution to the grid regulation target, and by gradually evaluating the regulation potential of these priority groups, a preliminary regulation plan within the group is generated and a regional load regulation instruction is comprehensively generated;

[0047] Priority grouping is classified according to load type, equipment characteristics and real-time response capability. The edge device assigns priority to each load node by collecting real-time data and combining historical records. The nodes in the high-priority group are load units with high equipment flexibility, short response time and a success rate close to 100%. The medium-priority group includes nodes with slightly longer response time and large load fluctuations. The low-priority group is the load with complex core processes and low adjustment flexibility.

[0048] In each priority group, the system evaluates the regulation capabilities of all nodes in the group through a local optimization algorithm, calculates the upper and lower limits of regulation power, response probability, and regulation cost of each node, sorts the nodes using weight factors (such as cost priority, response success rate), and selects the best node to generate preliminary regulation instructions. For example, for the five nodes in the high priority group, the regulation demand is 20MW. The system selects the first three nodes with regulation potentials of 8MW, 7MW, and 5MW, respectively. The generated instructions are to give priority to node 1 and node 2, with node 3 as an alternative.

[0049] When the intra-group adjustment analysis is completed, the system generates a regional adjustment plan through cross-group integration. When the adjustment demand is small, the high-priority group is given priority to complete all adjustment tasks. When the adjustment demand is large, the task is completed through joint adjustment of the high- and medium-priority groups, and the low-priority group is called to supplement it as appropriate.

[0050] S3: Predict load regulation capability and generate the optimal solution.

[0051] Furthermore, the predictive load regulation capability includes learning and analysis of multi-dimensional load data.

[0052] It should be noted that the load response data is deeply learned through artificial intelligence neural network technology to predict the load regulation capability. During the training process, the system uses the real-time and historical data uploaded by the edge device to establish a time series model of the load response, and through the optimization iteration of the neural network, it predicts the regulation capability at different time scales (such as seconds, minutes and hours). For example, when predicting the load regulation capability of a steel enterprise, the system combines the load curve of the equipment operation, the historical response probability and the current production status to accurately predict the upper and lower limits of the regulation power and its response success rate. The prediction results provide data support for scheduling optimization and reduce the risks caused by data uncertainty in the scheduling process. Compared with the traditional linear model prediction method, the application of artificial intelligence technology improves the prediction accuracy.

[0053] Furthermore, generating the optimal solution includes generating an optimal load regulation solution.

[0054] It should be noted that on the basis of predicting the load regulation capability, the cost-minimizing regulation plan is generated through the optimization algorithm, which not only considers the direct cost of load response (such as production loss and electricity cost), but also comprehensively considers factors such as the success rate of regulation response, delay time and equipment safety. When responding to the hourly regulation needs of the power grid, the system gives priority to load units with lower costs and higher response success rates for regulation. For example, in response to the load regulation needs of cement production enterprises, the system achieves the regulation target by reducing the power of auxiliary equipment while ensuring the normal operation of core production equipment. The optimized regulation cost is lower than that of traditional solutions.

[0055] Example 3

[0056] An embodiment of the present invention provides a multi-dimensional perception method for the small industrial load regulation capability of a distribution network. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0057] The experiment selected six typical medium-voltage small industrial loads, representing different production processes and equipment characteristics, including load type A (blast furnace load of steel enterprises), load type B (cement production kiln system load), load type C (metal processing equipment load), load type D (high-energy consumption equipment load), load type E (continuous production equipment load), and load type F (finishing equipment load). The experimental scenario simulated the regulation needs under the real industrial operating environment, covering load responses in seconds, minutes, and hours.

[0058] By deploying edge devices, key operating parameters of each load object are collected in real time, including load power, operating status, meteorological conditions (temperature, humidity, etc.), equipment response characteristics and electricity price data. All data are pre-processed by the edge devices and uploaded to the cloud computing cluster. Based on the collected data, the cloud high-performance computing platform is used to conduct the first-stage evaluation of the regulation capability of each load type. By analyzing its power range, response success rate and real-time load fluctuation characteristics, specific second-level regulation instructions are generated to ensure the immediacy and accuracy of load response. The system predicts the load regulation capability through artificial intelligence neural networks, combines actual response data and regulation cost models, formulates the optimal load regulation plan, and sends it to the edge device for execution. After the load changes, the device records the response effect in real time and feeds back to the cloud to complete the closed-loop regulation process.

[0059] As shown in Table 1, the response success rate of all load types exceeds 85%, among which load type D reaches 92%, which is higher than the traditional method (generally less than 80%). The present invention combines edge devices with artificial intelligence optimization strategies to improve response accuracy. The average response delay is 5 seconds, which is lower than the 10-second delay level of the prior art. The present invention ensures the immediacy of adjustment instructions through real-time data acquisition and optimization analysis. The lowest adjustment fee is 110 yuan / MW (load type D) and the average is 118 yuan / MW, which is about 9.2% lower than the average fee of 130 yuan / MW of the existing solution. The optimization algorithm achieves a reduction in adjustment costs. The real-time load fluctuation range is between 1.0-1.8MW, indicating that the present invention effectively stabilizes the dynamic changes of industrial loads and further verifies the technical advantages of multi-dimensional perception and adjustment optimization.

[0060] Table 1 Experimental data table

[0061]

[0062] Example 4

[0063] Reference Figure 2 , which is an embodiment of the present invention, provides a multi-dimensional perception system for the regulation capability of small industrial loads in a distribution network, including: a collection and integration module, an evaluation and analysis module, and a solution generation module.

[0064] The collection and integration module is used to collect data in real time, analyze and integrate data; the evaluation and analysis module is used to perform a first evaluation of the load regulation capability and generate instructions through the first analysis; the solution generation module is used to predict the load regulation capability and generate the optimal solution.

[0065] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0066] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0067] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0068] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0069] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A multi-dimensional perception method for the regulation capability of small industrial loads in a distribution network, characterized in that: include: Collect, analyze and integrate data in real time; Performing a first evaluation of load regulation capability and generating instructions through a first analysis; Predict load regulation capabilities and generate optimal solutions.

2. The multi-dimensional perception method of small industrial load regulation capability of a distribution network according to claim 1, characterized in that: The real-time data collection includes real-time collection of multi-dimensional load data.

3. The multi-dimensional perception method of small industrial load regulation capability of a distribution network as claimed in claim 2, characterized in that: The analyzing and integrating data includes summarizing and analyzing multi-dimensional load data.

4. The multi-dimensional perception method of small industrial load regulation capability of a distribution network as claimed in claim 3, characterized in that: The first evaluation of the load regulation capability includes evaluating the load regulation capability of each load regulation characteristic.

5. The multi-dimensional perception method of small industrial load regulation capability of a distribution network as claimed in claim 4, characterized in that: The generating of instructions through the first analysis includes generating scheduling instructions for each time scale.

6. The multi-dimensional perception method of small industrial load regulation capability of a distribution network according to claim 5, characterized in that: The predictive load regulation capability includes learning and analyzing multi-dimensional load data.

7. The multi-dimensional perception method of small industrial load regulation capability of a distribution network according to claim 6, characterized in that: The generating the optimal solution includes generating the optimal load adjustment solution.

8. A system using the multi-dimensional perception method of small industrial load regulation capability of a distribution network as claimed in any one of claims 1 to 7, characterized in that: It includes collection and integration module, evaluation and analysis module, and solution generation module; The acquisition and integration module is used to collect data in real time, analyze and integrate data; The evaluation and analysis module is used to perform a first evaluation on the load regulation capability and generate instructions through the first analysis; The solution generation module is used to predict the load regulation capability and generate the optimal solution.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for multi-dimensional perception of the small industrial load regulation capability of a distribution network according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for multi-dimensional perception of small industrial load regulation capability of a distribution network according to any one of claims 1 to 7 are implemented.

Images