Cooperative energy efficiency management and control system and method based on load characteristic analysis

Abstract

The invention discloses a collaborative energy efficiency management and control system based on load characteristic analysis, and the system comprises a management and control time sequence feature generation module which carries out the feature extraction of an energy efficiency management and control target, and generates a management and control time sequence feature; the load time sequence feature generation module further extracts controllable features, collaborative features and second time sequence features, and generates load time sequence features; the management and control time sequence instruction generation module uses a time priority function to sort and recombine the load time sequence characteristics to generate a management and control time sequence instruction; and the collaborative energy efficiency control module executes the control time sequence instruction to perform collaborative energy efficiency control on the energy efficiency control target. The energy efficiency management level of the power grid is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy efficiency management and control, and specifically to a collaborative energy efficiency management and control system and method based on load characteristic analysis. Background Art

[0002] In today's society, the efficient and stable operation of the power grid system is crucial to ensuring social and economic development and people's daily lives. With the widespread access to new energy and the diversification of various types of power-consuming equipment, the load characteristics of the power grid have become increasingly complex, and accurate analysis and coordinated energy efficiency management have become key issues that need to be solved urgently.

[0003] The inventors found the following deficiencies in the research on existing load characteristic analysis and collaborative energy efficiency control. For example, Chinese patent number CN202411636539.6 discloses an energy efficiency management system based on air conditioning power consumption. This invention mainly focuses on energy efficiency management in air conditioning power consumption scenarios, and adjusts the energy efficiency of air conditioning groups by predicting the flow of people. However, when it is applied to the macro power grid system, there are obvious limitations, specifically:

[0004] This technology is aimed at the load of a single device such as air conditioners, and its analysis method and regulation strategy are difficult to extend to the various types of loads with different characteristics in the power grid. The loads in the power grid cover a variety of fields such as industry, commerce, and residents. The characteristics and changing laws of each load are very different, and this technology cannot fully capture these complex load characteristics.

[0005] This technology only realizes the control within the air conditioning system, and lacks the coordination mechanism with other equipment and systems in the power grid. In the power grid system, various energy devices need to cooperate with each other and adjust dynamically according to the load characteristics to achieve the optimal energy efficiency of the entire power grid. However, this technology does not take into account the coordinated work with power generation equipment, energy storage equipment, etc. in the power grid, and cannot meet the coordinated energy efficiency control needs of the power grid system based on load characteristics. Summary of the invention

[0006] The purpose of the present invention is to provide a collaborative energy efficiency management system and method based on load characteristic analysis, which improves the energy efficiency management level of the power grid.

[0007] To achieve this purpose, the present invention designs a collaborative energy efficiency management and control system based on load characteristic analysis, which includes:

[0008] The control time series feature generation module is used to extract features of the energy efficiency control target, obtain energy efficiency control features and the first time series features, and generate control time series features from the energy efficiency control features and the first time series features;

[0009] The load time - series feature generation module is used to perform load characteristic analysis based on the control time - series characteristics and extract features, obtaining controllable features, collaborative features, and second time - series features, and generating load time - series features from the controllable features, collaborative features, and second time - series features;

[0010] The control time - series instruction generation module is used to calculate the time priority by using a preset time - priority function in combination with the first time - series feature and the second time - series feature, thereby sorting and reorganizing the load time - series features, obtaining the reorganized load time - series features, and generating control time - series instructions through the reorganized load time - series features;

[0011] The collaborative energy - efficiency control module is used to execute the control time - series instructions to perform collaborative energy - efficiency control on the energy - efficiency control target.

[0012] Preferably, the collaborative energy - efficiency control module is also used to, after collaborative energy - efficiency control, monitor the operating state of the energy - efficiency control target in real - time. When the reorganized load time - series features, the feedback of grid real - time monitoring data, the evaluation result of control effect, and the feedback of environmental real - time monitoring data change, the collaborative energy - efficiency control system will make corresponding adjustments to the control time - series instructions, so that the load characteristics of the collaborative energy - efficiency control system meet the preset energy - efficiency control threshold;

[0013] The specific process of extracting features from the energy - efficiency control target to obtain energy - efficiency control features, first time - series features, and generating control time - series features is as follows:

[0014] Based on the historical energy - efficiency data of the energy - efficiency control target, the current energy - efficiency data of the energy - efficiency control target, the key indicators of the current energy - efficiency data of the energy - efficiency control target, and the energy - efficiency control feature calculation formula, the energy - efficiency control features are calculated;

[0015] Among them, the energy - efficiency control feature calculation formula is:

[0016]

[0017] Among them, α1 is a preset first weighting coefficient, α2 is a preset second weighting coefficient, H i is the historical energy - efficiency data, C i is the current energy - efficiency data corresponding to the historical energy - efficiency data H i C cur is the key indicator of the current energy - efficiency data, n is the number of current energy - efficiency data, and E is the calculated energy - efficiency control feature;

[0018] Using a time - series analysis model to perform a correlation analysis on the expected execution time of energy - efficiency management of the energy - efficiency control target, obtaining the first time - series feature T1;

[0019] Combine the energy efficiency control feature E and the first timing feature T1 and generate a control timing feature.

[0020] Preferably, the specific process of performing load characteristic analysis and feature extraction based on the control timing feature to obtain controllable features, cooperative features, and a second timing feature and generating the load timing feature is as follows:

[0021] Monitor the load data and its change rate in the control timing feature to obtain the response characteristics of different types of loads to regulation, and perform clustering based on the response characteristics to obtain controllable features M;

[0022] Calculate the load correlation degree based on the number of data points and its standard deviation of different types of loads in the control timing feature to obtain cooperative features; wherein, the formula for calculating the load correlation degree is:

[0023]

[0024] z is the number of data points of the first type of load i, m is the number of data points of the second type of load j, σ L is the standard deviation of the load data, is the average value of the load data, L i is the load data of load i, L j is the load data of load j, R is the calculated load correlation degree; and S = R, S is the cooperative feature;

[0025] Collect time series data related to the load based on the control timing feature, perform feature extraction on the time series data to obtain the time when the load is executed with energy efficiency control, and use a time series analysis model to model and analyze the time when the load is executed with energy efficiency control to obtain a second timing feature T2;

[0026] Combine the controllable feature M, the cooperative feature S, and the second timing feature T2 and generate a load timing feature.

[0027] Preferably, the specific process of generating the control timing instruction is as follows:

[0028] Use a preset time priority function, combine the first timing feature and the second timing feature to calculate the time priority, thereby sort and reorganize the load timing feature to obtain the reorganized load timing feature, use a preset operation instruction to map the reorganized load timing feature to the corresponding operation instruction, and define the mapped operation instruction as the control timing instruction.

[0029] Preferably, when the restructured load time series characteristics change, the specific process of the collaborative energy efficiency control system adjusting the control time series instructions based on the restructured load time series characteristics is as follows:

[0030] Calculate the control weights of different types of loads based on the controllable characteristics and the collaborative characteristics in the restructured load time series characteristics, and adjust the control time series instructions of the corresponding loads based on the control weights;

[0031] Among them, the calculation formula for the control weight of each type of load is:

[0032] W D = β1 * M + β2 * S

[0033] Among them, M is the controllable characteristic, S is the collaborative characteristic, β1 is the preset first weight coefficient, and β2 is the preset second weight coefficient; obtain the control time series instruction I ori of the original execution intensity of the corresponding load, and calculate the new control time series instruction I act = I ori * W D .

[0034] Preferably, when both the real-time power grid monitoring data feedback and the control effect evaluation result change, the specific process of the collaborative energy efficiency control system adjusting the control time series instructions based on the real-time power grid monitoring data feedback and the control effect evaluation result is as follows:

[0035] Calculate the dynamic adjustment amount of the control time series instruction based on the control historical effect evaluation result in the real-time power grid monitoring data feedback and the control effect evaluation result, and adjust the control time series instruction based on the dynamic adjustment amount;

[0036] Calculate the dynamic adjustment amount ΔI = f(G, E his ), where G is the data obtained from the real-time power grid monitoring data feedback, and E his is the control historical effect evaluation result in the control effect evaluation result, and f() is the mapping relationship between G and E his obtained by using machine learning technology; calculate the adjusted control time series instruction through the formula I adj = I bef + ΔI, where I bef is the control time series instruction before adjustment.

[0037] Preferably, when both the restructured load time series characteristics and the control effect evaluation result change, the specific process of the collaborative energy efficiency control system adjusting the control time series instructions based on the restructured load time series characteristics and the control effect evaluation result is as follows:

[0038] Calculate the collaborative adjustment amount of the control time series instruction based on the collaborative feature in the recombined load time series feature and the control expectation effect evaluation result in the control effect evaluation result, and adjust the control time series instruction based on the collaborative adjustment amount;

[0039] Calculate the collaborative adjustment amount A = c * S * E exp , where c is a preset collaborative adjustment coefficient, S is the collaborative feature, and E exp is the control expectation effect evaluation result in the control effect evaluation result; when there is , adjust the control time series instruction of the load with a collaborative relationship based on the calculated collaborative adjustment amount A, where A τ is a preset collaborative adjustment amount threshold.

[0040] Preferably, when the real-time environmental monitoring data feedback changes, the specific process of the collaborative energy efficiency control system adjusting the control time series instruction based on the real-time environmental monitoring data feedback is as follows:

[0041] Update the recombined load time series feature based on the real-time environmental monitoring data feedback to obtain the updated load time series feature, and regenerate a new control time series instruction based on the updated load time series feature;

[0042] Use the preset environmental adjustment function T' load = h(E new , T load ) to update the recombined load time series feature T load to obtain the updated load time series feature T', load where E new is the data obtained from the real-time environmental monitoring data feedback, h() is the mapping relationship between E new and T load obtained using machine learning technology, and T' load is the updated load time series feature, and regenerate an adjusted new control time series instruction based on the updated load time series feature.

[0043] A collaborative energy efficiency control method based on load characteristic analysis, which includes the following steps:

[0044] Extract the characteristics of the energy efficiency control target to obtain the energy efficiency control characteristics and the first time series characteristics, and generate the control time series characteristics from the energy efficiency control characteristics and the first time series characteristics;

[0045] Based on the control time series characteristics, conduct load characteristic analysis and feature extraction to obtain controllable characteristics, collaborative characteristics, and the second time series characteristics, and generate the load time series characteristics from the controllable characteristics, collaborative characteristics, and the second time series characteristics;

[0046] Calculate the time priority by using a preset time priority function in combination with the first timing feature and the second timing feature, so as to sort and reorganize the load timing feature, obtain the reorganized load timing feature, and generate a control timing instruction through the reorganized load timing feature;

[0047] Execute the control timing instruction to perform collaborative energy efficiency control on the energy efficiency control target.

[0048] A computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0049] Advantages of the present invention:

[0050] The present invention can perform multi-dimensional feature extraction on the energy efficiency control target, provide a refined decision-making basis for energy efficiency control, and significantly improve the accuracy of control; the present invention can achieve coordinated control between different loads, and this coordination mechanism can optimize the overall energy efficiency and avoid the low efficiency problem caused by the independent control of a single device or load, thereby improving the overall energy efficiency performance of the coordinated energy efficiency control system; the present invention can dynamically adjust the control timing instruction, ensuring that the coordinated energy efficiency control system can still operate efficiently and stably in the face of power grid fluctuations, environmental changes or changes in load characteristics, enhancing the robustness and flexibility of the coordinated energy efficiency control system; the present invention realizes the full-process automation from feature extraction to coordinated control. This intelligent control method reduces manual intervention, reduces operation complexity, and at the same time improves the operation efficiency and reliability of the coordinated energy efficiency control system, provides an efficient technical solution for large-scale energy efficiency management, realizes the coordinated energy efficiency control of multiple devices in the power grid, and copes with the complex power grid load characteristics brought by new energy access and device diversification, and improves the overall energy efficiency management level of the power grid. Brief Description of the Drawings

[0051] Figure 1 It is a structural schematic diagram of the present invention;

[0052] Figure 2 It is a flowchart of the present invention. Detailed Embodiments

[0053] The following further describes the present invention in detail with reference to the drawings and specific embodiments:

[0054] Embodiment 1

[0055] A coordinated energy efficiency control system based on load characteristic analysis, as Figure 1 shown, it includes:

[0056] The control time series feature generation module is used to extract features from the energy efficiency control target (the energy efficiency control target refers to the specific object that the collaborative energy efficiency control system needs to optimize and manage), obtain the energy efficiency control feature (the energy efficiency control feature is used to characterize the energy efficiency optimization expectation and its priority of the energy efficiency control) and the first time series feature (the first time series feature is used to characterize the feature of the expected execution time of the energy efficiency management for the energy efficiency control target), and generate the control time series feature from the energy efficiency control feature and the first time series feature (the control time series feature is used to characterize the key characteristics of the energy efficiency control target in the time series, and this key characteristic is used for load characteristic analysis). This design characterizes the expected target and priority of the energy efficiency optimization through the energy efficiency control feature, enabling the collaborative energy efficiency control system to clarify the optimization direction and key points. The first time series feature reflects the expected execution time of the energy efficiency management, providing basic data for time series analysis. The generated control time series feature provides the key input for subsequent load characteristic analysis, ensuring that the subsequent modules can analyze and make decisions based on accurate time series characteristics;

[0057] The load time series feature generation module is used to perform load characteristic analysis and feature extraction based on the control time series feature, obtain the controllable feature (the controllable feature is used to characterize the expected controllable degree of the load), the collaborative feature (the collaborative feature is used to characterize the coordinable degree between the load and other loads when the load is subject to energy efficiency control), and the second time series feature (the second time series feature is used to characterize the feature of the time when the load is subject to energy efficiency control), and generate the load time series feature from the controllable feature, the collaborative feature, and the second time series feature (the load time series feature is used to characterize the change characteristics of the grid load in the time dimension, and this change characteristic is used to reflect the fluctuation and trend of the load). This design analyzes the control time series feature, extracts the controllable feature, the collaborative feature, and the second time series feature, enabling the collaborative energy efficiency control system to identify which loads can be effectively controlled and which loads can be collaboratively optimized, and at the same time can describe in detail the controllable degree, collaborative ability, and time characteristics of the load when implementing energy efficiency control. The generated load time series feature can reflect the fluctuation and trend of the grid load in the time dimension, providing strong support for collaborative energy efficiency control;

[0058] The control timing instruction generation module is used to calculate the time priority by using a preset time priority function in combination with the first timing feature and the second timing feature, so as to sort and reorganize the load timing feature, obtain the reorganized load timing feature, and generate a control timing instruction through the reorganized load timing feature (the control timing instruction is used to represent an operation instruction with a time series for the collaborative energy efficiency control of the power grid based on the reorganized load timing feature. This instruction has a time series and provides the corresponding moment for execution). This design can generate an operation instruction with a time series, ensure the efficient execution of energy efficiency control, provide dynamic input for the generation of the control timing instruction through the reorganized load timing feature, enable the instruction to be adjusted according to the actual operation situation, and be able to adapt to the changes in the power grid operation state;

[0059] The collaborative energy efficiency control module is used to execute the control timing instruction to perform collaborative energy efficiency control on the energy efficiency control target. This design can enable the energy efficiency control tasks of different loads to be executed in an orderly manner according to the time priority. Through precise time scheduling and collaborative optimization, it can minimize energy waste and improve the overall energy efficiency optimization level, providing strong support for the stable operation and energy efficiency improvement of the power grid.

[0060] In the above technical solution, the collaborative energy efficiency control module is also used to, after collaborative energy efficiency control, monitor the operation state of the energy efficiency control target in real time. When there are changes in the reorganized load timing feature, power grid real-time monitoring data feedback (the data of power grid real-time monitoring includes load data (different from the load timing feature in that it has specific electricity consumption load conditions), power supply data (how much electricity is supplied)), control effect evaluation result (the control effect evaluation result is jointly obtained based on the energy efficiency control feature and the power grid real-time monitoring data feedback, and the control effect evaluation result can directly reflect how much energy efficiency is saved), and environmental real-time monitoring data feedback, the collaborative energy efficiency control system will make corresponding adjustments to the control timing instruction, so that the load characteristics of the collaborative energy efficiency control system meet the preset energy efficiency control threshold (the load characteristics meet the preset energy efficiency control threshold, that is, the load characteristics before energy efficiency control are A, and the load characteristics after energy efficiency control are B. It is required that (B - A) / A < C after energy efficiency control; C is the preset energy efficiency control threshold, which needs to be determined according to specific application scenarios, equipment characteristics, energy efficiency control objectives, and actual operation conditions, and C can take a value of 10%). This design can monitor the operation state of the energy efficiency control target in real time and adjust the control instruction according to the real-time data feedback to ensure the stable operation and energy efficiency optimization of the collaborative energy efficiency control system;

[0061] The specific process of extracting features from the energy efficiency control target to obtain the energy efficiency control feature, the first timing feature, and generating the control timing feature is as follows:

[0062] Based on the historical energy efficiency data for the energy efficiency control target, the current energy efficiency data of the energy efficiency control target (the energy efficiency data in this embodiment is data collected for energy efficiency control based on the common knowledge of energy efficiency control known to those skilled in the art, and the data for energy efficiency control is pre - processed using existing data processing techniques to meet the data requirements for generating the control time - series characteristics in this embodiment), the key indicators of the current energy efficiency data of the energy efficiency control target, and the energy efficiency control feature calculation formula, calculate the energy efficiency control feature;

[0063] Among them, the energy efficiency control feature calculation formula is:

[0064]

[0065] Among them, α1 is a preset first weighting coefficient (α1 = 0.3 can be taken), α2 is a preset second weighting coefficient (α2 = 0.7 can be taken), H i is the historical energy efficiency data, C i is the current energy efficiency data corresponding to the historical energy efficiency data H i cur is the key indicator of the current energy efficiency data, n is the number of current energy efficiency data, and E is the calculated energy efficiency control feature;

[0066] Use a time - series analysis model (such as an LSTM model or a Transformer - based model TimesFM. Among them, the LSTM model is used to capture the long - term and short - term dependencies in the time series, and the TimesFM model is used to process large - scale time series data) to perform a correlation analysis on the expected execution time of energy efficiency management for the energy efficiency control target (the expected execution time of energy efficiency management refers to the originally planned time for executing the corresponding energy efficiency management) to obtain the first time - series feature T1;

[0067] Concatenate and combine the energy efficiency control feature E and the first time - series feature T1 (directly concatenate the energy efficiency control feature vector and the first time - series feature vector together to form a new feature vector, and this new feature vector is the control time - series feature) and generate the control time - series feature; The above - mentioned technology realizes the feature extraction of the energy efficiency control target from the perspectives of energy efficiency data and time, provides more targeted and time - series control time - series features for subsequent power grid load characteristic analysis and collaborative energy efficiency control processes based on this, so as to guide subsequent operations.

[0068] In the above - mentioned technical solution, the specific process of performing load characteristic analysis based on the control time - series feature and extracting features to obtain controllable features, collaborative features, and a second time - series feature and generating the load time - series feature is as follows:

[0069] ​Monitor the load data and its change rate in the control time sequence characteristics to obtain the response characteristics of different types of loads to regulation (for example, some loads can quickly respond to regulation instructions, while others may respond slowly. Through clustering methods, loads with similar response characteristics are grouped into one category to obtain controllable characteristics; these characteristics directly reflect which loads can be effectively controlled and provide a basis for subsequent energy efficiency control). Cluster based on the response characteristics to obtain controllable characteristic M;

[0070] Calculate the load correlation based on the number of data points and the standard deviation of different types of loads in the control time sequence characteristics (the load correlation reflects the degree of mutual influence between different loads. For example, some loads may be interdependent during operation or have a complementary relationship in energy consumption; by calculating the load correlation, a co - operative characteristic can be obtained, which can provide data support for co - operative energy efficiency control) to obtain the co - operative characteristic; where the load correlation calculation formula is:

[0071]

[0072] z is the number of data points of the first - type load i, m is the number of data points of the second - type load j, σ L is the standard deviation of the load data, is the average value of the load data, L i is the load data of load i, L j is the load data of load j, R is the calculated load correlation; and S = R, S is the co - operative characteristic;

[0073] Collect time - series data related to the load based on the control time sequence characteristics, extract features from the time - series data (the extracted features include: the periodic pattern of the load execution time (such as the start - up and stop rules of the load within a specific time period); the lag effect of the load execution time (such as the influence of the load state in the previous time period on the current state); the statistical characteristics of the load execution time (such as the average execution time, the fluctuation range of the execution time)) to obtain the time when the load is subject to energy - efficiency control (the time when the load is subject to energy - efficiency control refers to the energy - efficiency control through existing energy - efficiency management methods, such as reducing power). Use the time - series analysis model to model and analyze the time when the load is subject to energy - efficiency control (extract the time - series in the energy - efficiency control work plan through analysis) to obtain the second time - sequence characteristic T2;

[0074] Combine the controllable feature M, the collaborative feature S, and the second time series feature T2 (directly combine M, S, and T2 together to form a new feature vector, which is the load time series feature) and generate the load time series feature; the above technology realizes the comprehensive characteristic analysis of the power grid load in terms of controllability, collaborative ability, and time dimension, providing rich load time series information for generating more accurate and effective control time series instructions in the future.

[0075] In the above technical solution, the specific process of generating the control time series instruction is as follows:

[0076] Use a preset time priority function (the preset time priority function is a priority scheduling function based on time series), combine the first time series feature and the second time series feature to calculate the time priority (calculating the time priority can, but is not limited to, assigning weights to the first time series feature and the second time series feature to sort and reorganize the load time series feature), so as to sort and reorganize the load time series feature, obtain the reorganized load time series feature, use a preset operation instruction (energy efficiency control instruction) to map the reorganized load time series feature to the corresponding operation instruction, and define the mapped operation instruction as the control time series instruction; the above technology realizes the feature sorting and reorganization based on the time dimension, converts the load time series feature into an operation instruction with a time series, enables the control time series instruction to be executed in an orderly manner according to the time priority, and ensures the rationality and effectiveness of the collaborative energy efficiency control in terms of time.

[0077] In the above technical solution, when the reorganized load time series feature changes, the specific process of the collaborative energy efficiency control system adjusting the control time series instruction based on the reorganized load time series feature is as follows:

[0078] Calculate the control weights of different types of loads based on the controllable feature and the collaborative feature in the reorganized load time series feature, and adjust the control time series instruction of the corresponding load based on the control weights;

[0079] Among them, the calculation formula for the control weight of each type of load is:

[0080] W D =β1*M + β2*S

[0081] Among them, M is the controllable feature, S is the collaborative feature, β1 is a preset first weight coefficient (β1 = 0.4 can be taken), β2 is a preset second weight coefficient (β2 = 0.6 can be taken); obtain the control time series instruction I ori of the original execution intensity of the corresponding load, calculate the control time series instruction I act of the new execution intensity after adjustment of the corresponding load, and ori =I​D ; The above technology calculates the control weights of different types of loads using the controllable features and collaborative features in the recombined load time series features, and adjusts the execution intensity of the control time series instructions for the load based on the control weights, achieving differential adjustment of the execution intensity of the control time series instructions based on the controllability and collaborativeness of the load, making the control operation more in line with the characteristics of different types of loads and improving the accuracy and flexibility of collaborative energy efficiency control.

[0082] In the above technical solution, when both the real-time power grid monitoring data feedback and the control effect evaluation result change, the specific process of the collaborative energy efficiency control system adjusting the control time series instruction based on the real-time power grid monitoring data feedback and the control effect evaluation result is as follows:

[0083] Calculate the dynamic adjustment amount of the control time series instruction based on the historical control effect evaluation result in the real-time power grid monitoring data feedback and the control effect evaluation result, and adjust the control time series instruction based on the dynamic adjustment amount;

[0084] Calculate the dynamic adjustment amount ΔI = f(G, E his ), where G is the data obtained from the real-time power grid monitoring data feedback, and E his is the historical control effect evaluation result in the control effect evaluation result, and f() is the mapping relationship between G and E his obtained using machine learning technology; Calculate the adjusted control time series instruction through the formula I adj = I bef +ΔI, where I bef is the control time series instruction before adjustment; The above technology calculates the dynamic adjustment amount through the mapping relationship obtained by the existing machine learning technology and adjusts the control time series instruction based on the dynamic adjustment amount, realizing dynamic adjustment of the control time series instruction based on the historical control effect evaluation result in the real-time power grid monitoring data feedback and the control effect evaluation result, enabling the collaborative energy efficiency control operation to respond to the real-time changes of the power grid in a timely manner and improving the real-time performance and adaptability of the collaborative energy efficiency control.

[0085] In the above technical solution, when both the recombined load time series features and the control effect evaluation result change, the specific process of the collaborative energy efficiency control system adjusting the control time series instruction based on the recombined load time series features and the control effect evaluation result is as follows:

[0086] Calculate the collaborative adjustment amount of the control time series instruction based on the collaborative feature in the recombined load time series features and the expected control effect evaluation result in the control effect evaluation result, and adjust the control time series instruction based on the collaborative adjustment amount;

[0087] Calculate the collaborative adjustment amount A = c * S * Eexp , where c is a preset collaborative adjustment coefficient (the value range is 0 to 1, and c = 0.5 can be taken), S is a collaborative feature, and E exp is the control expected effect evaluation result in the control effect evaluation result; when there is , based on the calculated collaborative adjustment amount A, adjust the control time sequence instruction of the load with a collaborative relationship, where A τ is a preset collaborative adjustment amount threshold (A τ is obtained by fitting and is a preset expected value); the above technology calculates the collaborative adjustment amount by using the collaborative feature in the recombined load time sequence feature and the control expected effect evaluation result in the control effect evaluation result, and judges whether to adjust the control time sequence instruction of the load with a collaborative relationship based on the collaborative adjustment amount and the preset collaborative adjustment amount threshold, so as to realize the targeted adjustment of the control time sequence instruction of the collaborative load according to the collaborative characteristics between loads and the control expected effect evaluation result, and ensure the effectiveness of the collaboration between loads and the overall effect of energy efficiency control.

[0088] In the above technical solution, when the environmental real-time monitoring data feedback changes, the specific process of the collaborative energy efficiency control system for correspondingly adjusting the control time sequence instruction based on the environmental real-time monitoring data feedback is as follows:

[0089] Update the recombined load time sequence feature based on the environmental real-time monitoring data feedback to obtain the updated load time sequence feature, and regenerate a new control time sequence instruction based on the updated load time sequence feature;

[0090] Use the preset environmental adjustment function T' load = h(E new , T load ) to update the recombined load time sequence feature T load to obtain the updated load time sequence feature T' load , where E new is the data obtained from the environmental real-time monitoring data feedback, h() is the mapping relationship between E new and T load obtained by using machine learning technology, and T' load is the updated load time sequence feature, and generate a new adjusted control time sequence instruction based on the updated load time sequence feature; the above technology updates the load time sequence feature through a preset environmental adjustment function based on the impact of the environmental real-time monitoring data feedback on the energy efficiency control, so that the control time sequence instruction can consider environmental factors, ensure that the collaborative energy efficiency control system can adapt to environmental changes, adapt to the access of new energy, and improve the energy efficiency control performance of the power grid in different environments.

[0091] Embodiment 2

[0092] A collaborative energy efficiency control method based on load characteristic analysis, as Figure 2 shown, perform feature extraction on the energy efficiency control target to generate control timing features; further extract controllable features, collaborative features, and second timing features, and generate load timing features; use the time priority function to sort and reorganize the load timing features to generate control timing instructions; execute the control timing instructions to perform collaborative energy efficiency control on the energy efficiency control target.

[0093] The specific method for performing collaborative energy efficiency control includes the following steps:

[0094] Perform feature extraction on the energy efficiency control target to obtain energy efficiency control features and first timing features, and generate control timing features from the energy efficiency control features and the first timing features;

[0095] Based on the control timing features, perform load characteristic analysis and feature extraction to obtain controllable features, collaborative features, and second timing features, and generate load timing features from the controllable features, collaborative features, and second timing features;

[0096] Use the preset time priority function to calculate the time priority in combination with the first timing feature and the second timing feature, so as to sort and reorganize the load timing features, obtain the reorganized load timing features, and generate control timing instructions through the reorganized load timing features;

[0097] Execute the control timing instructions to perform collaborative energy efficiency control on the energy efficiency control target.

[0098] Embodiment 3

[0099] A computer program product includes a computer program, characterized in that when the computer program is executed by a processor, it implements the steps of the method described in Embodiment 2.

[0100] In the embodiments provided in the present application, it should be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code, or any suitable combination thereof. For hardware implementation, the processor can be implemented in one or more of the following units: Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), processor, controller, microcontroller, microprocessor, or other electronic units designed to implement the functions described herein, or a combination thereof. For software implementation, part or all of the processes of the embodiments can be completed by instructing the relevant hardware through a computer program. When implemented, the above program can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. The computer-readable storage medium includes computer storage media and communication media, where the communication media includes any medium that facilitates the transmission of a computer program from one place to another. The storage medium can be any available medium that can be accessed by a computer. The computer-readable storage medium can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM, or other optical disk storage, magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer.

[0101] Finally, it should be noted that the above are only the preferred embodiments of the present application and are not intended to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0102] The content not described in detail in this specification belongs to the prior art well-known to those skilled in the art.

Claims

1. A collaborative energy efficiency management and control system based on load characteristic analysis, characterized in that, It includes: The control timing feature generation module is used to extract features from the energy efficiency control target, obtain the energy efficiency control features and the first timing feature, and generate the control timing feature from the energy efficiency control features and the first timing feature; The load timing feature generation module is used to perform load characteristic analysis and feature extraction based on the control timing feature, obtain the controllable feature, the collaborative feature and the second timing feature, and generate the load timing feature from the controllable feature, the collaborative feature and the second timing feature; The control timing instruction generation module is used to calculate the time priority by using a preset time priority function in combination with the first timing feature and the second timing feature, so as to sort and reorganize the load timing feature, obtain the reorganized load timing feature, and generate the control timing instruction through the reorganized load timing feature; The collaborative energy efficiency control module is used to execute the control timing instruction to perform collaborative energy efficiency control on the energy efficiency control target.

2. The collaborative energy efficiency control system based on load characteristic analysis according to claim 1, wherein: The collaborative energy efficiency control module is also used to, after collaborative energy efficiency control, monitor the operation state of the energy efficiency control target in real time. When the reorganized load timing feature, the real-time monitoring data feedback of the power grid, the control effect evaluation result and the real-time monitoring data feedback of the environment change, the collaborative energy efficiency control system will make corresponding adjustments to the control timing instruction, so that the load characteristics of the collaborative energy efficiency control system meet the preset energy efficiency control threshold; The specific process of extracting features from the energy efficiency control target, obtaining the energy efficiency control features and the first timing feature and generating the control timing feature is as follows: The energy efficiency control feature is calculated based on the historical energy efficiency data of the energy efficiency control target, the current energy efficiency data of the energy efficiency control target, the key indicators of the current energy efficiency data of the energy efficiency control target and the energy efficiency control feature calculation formula; Among them, the energy efficiency control feature calculation formula is: Wherein, α1 is the preset first weighting coefficient, α2 is the preset second weighting coefficient, H i is the historical energy efficiency data, C i The historical energy efficiency data H i The corresponding current energy efficiency data, C cur is the key indicator of the current energy efficiency data, n is the number of current energy efficiency data, and E is the calculated energy efficiency control feature; Use the time series analysis model to perform correlation analysis on the expected execution time of energy efficiency management of the energy efficiency control target to obtain the first timing feature T1; The energy efficiency control feature E and the first timing feature T1 are spliced and combined to generate the control timing feature.

3. The collaborative energy efficiency management and control system based on load characteristic analysis according to claim 1, wherein: The specific process of performing load characteristic analysis and feature extraction based on the control timing feature, obtaining the controllable feature, the collaborative feature and the second timing feature and generating the load timing feature is as follows: Monitor the load data and its change rate in the control timing feature to obtain the response characteristics of different types of loads to regulation, and perform clustering based on the response characteristics to obtain the controllable feature M; Calculate the load correlation degree based on the number of data points and the standard deviation of different types of loads in the control timing feature to obtain the collaborative feature; among them, the load correlation degree calculation formula is: z is the number of data points of the first category load i, m is the number of data points of the second category load j, and σ L is the standard deviation of the load data, is the mean value of the load data, L i is the load data of load i, L j is the load data of load j, R is the calculated load correlation degree; and S = R, where S is the co - operative feature; Collect time series data related to the load based on the control timing feature, perform feature extraction on the time series data to obtain the time when the load is subjected to energy efficiency control, and use the time series analysis model to model and analyze the time when the load is subjected to energy efficiency control to obtain the second timing feature T2; The controllable feature M, the collaborative feature S and the second timing feature T2 are spliced and combined to generate the load timing feature.

4. The collaborative energy efficiency management and control system based on load characteristic analysis according to claim 1, wherein: The specific process of generating the control timing instruction is: Using a preset time priority function, combine the first timing feature and the second timing feature to calculate the time priority, thereby sorting and reorganizing the load timing feature to obtain the reorganized load timing feature. Use a preset operation instruction to map the reorganized load timing feature to a corresponding operation instruction, and define the mapped operation instruction as a control timing instruction.

5. The collaborative energy efficiency control system based on load characteristic analysis according to claim 2, wherein: When the reorganized load timing feature changes, the specific process of the collaborative energy efficiency control system adjusting the control timing instruction based on the reorganized load timing feature is as follows: Calculate the control weights of different types of loads based on the controllable feature and the collaborative feature in the reorganized load timing feature, and adjust the control timing instructions of the corresponding loads based on the control weights; Among them, the calculation formula for the control weight of each type of load is: W D = β1 * M + β2 * S Wherein, M is a controllable feature, S is a collaborative feature, β1 is a preset first weight coefficient, and β2 is a preset second weight coefficient; obtain the control timing instruction I of the original execution intensity corresponding to the load ori , and calculate the control timing instruction I of the new execution intensity after adjustment for the corresponding load act = I ori * W D .

6. The collaborative energy efficiency control system based on load characteristic analysis according to claim 2, wherein: When both the real-time grid monitoring data feedback and the control effect evaluation result change, the specific process of the collaborative energy efficiency control system adjusting the control timing instruction based on the real-time grid monitoring data feedback and the control effect evaluation result is as follows: Calculate the dynamic adjustment amount of the control timing instruction based on the control historical effect evaluation result in the real-time grid monitoring data feedback and the control effect evaluation result, and adjust the control timing instruction based on the dynamic adjustment amount; Calculate the dynamic adjustment amount ΔI = f(G, E his ), where G is the data obtained from the real-time monitoring data feedback of the power grid, and E his is the historical control effect evaluation result in the control effect evaluation result, and f() is the mapping relationship between G and E obtained by using machine learning technology his ; the adjusted control timing instruction is calculated through the formula I adj = I bef + ΔI, where I bef is the control timing instruction before adjustment.

7. The collaborative energy efficiency control system based on load characteristic analysis according to claim 2, characterized in that: When both the reorganized load timing feature and the control effect evaluation result change, the specific process of the collaborative energy efficiency control system adjusting the control timing instruction based on the reorganized load timing feature and the control effect evaluation result is as follows: Calculate the collaborative adjustment amount of the control timing instruction based on the collaborative feature in the reorganized load timing feature and the control expected effect evaluation result in the control effect evaluation result, and adjust the control timing instruction based on the collaborative adjustment amount; Calculate the collaborative adjustment amount A = c * S * E exp , where c is a preset collaborative adjustment coefficient, S is a collaborative feature, and E exp is the evaluation result of the control expected effect in the control effect evaluation result; when there is , based on the calculated collaborative adjustment amount A, adjust the control timing instruction of the load with a collaborative relationship, where A τ is a preset collaborative adjustment amount threshold.

8. The collaborative energy efficiency control system based on load characteristic analysis according to claim 2, wherein: When the real-time environmental monitoring data feedback changes, the specific process of the collaborative energy efficiency control system adjusting the control timing instruction based on the real-time environmental monitoring data feedback is as follows: Update the reorganized load timing feature based on the real-time environmental monitoring data feedback to obtain the updated load timing feature, and regenerate a new control timing instruction based on the updated load timing feature; Using the preset environment adjustment function T' load = h(E new , T load ) to update the reorganized load time series feature T load to obtain the updated load time series feature T' load , where E new is the data obtained from the feedback of the environmental real-time monitoring data, and h() is the mapping relationship between E new and T load obtained by using machine learning technology, and T' load is the updated load time series feature, and a new adjusted control time series instruction is regenerated based on the updated load time series feature.

9. A collaborative energy efficiency control method based on load characteristic analysis, characterized in that, It includes the following steps: Extract the features of the energy efficiency control target to obtain the energy efficiency control feature and the first timing feature, and generate the control timing feature from the energy efficiency control feature and the first timing feature; Conduct load characteristic analysis and feature extraction based on the control timing feature to obtain the controllable feature, the collaborative feature, and the second timing feature, and generate the load timing feature from the controllable feature, the collaborative feature, and the second timing feature; Use a preset time priority function to combine the first timing feature and the second timing feature to calculate the time priority, thereby sorting and reorganizing the load timing feature to obtain the reorganized load timing feature, and generate the control timing instruction through the reorganized load timing feature; Execute the control timing instruction to conduct collaborative energy efficiency control on the energy efficiency control target.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method described in claim 9.

Images