Energy consumption management platform based on big data

Abstract

The invention discloses an energy consumption management platform based on big data, and belongs to the technical field of energy consumption management, and the platform specifically comprises a building level energy consumption tracking module which collects energy consumption data of different levels of a building in real time, binds energy consumption equipment with a building space, maps sub-item energy consumption equipment to corresponding level nodes according to physical positions, and transmits the energy consumption data to the building level energy consumption tracking module; constructing an energy consumption flow direction topological graph according to a total-score table relation; the visual energy consumption display module is used for dynamically generating a multi-level energy consumption distribution thermodynamic diagram according to the topological graph, setting different color gradients according to the energy consumption loss rate, calculating a loss rate threshold value by means of a dynamic threshold value algorithm in combination with historical and environmental data, and marking abnormal nodes if the loss rate threshold value is exceeded; and the energy consumption repair positioning module is used for generating a diagnosis report containing fault equipment positioning and energy consumption waste reasons based on the historical monitoring data and the user operation log of the corresponding energy consumption equipment after detecting the abnormal node.

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption management, and particularly relates to an energy consumption management platform based on big data. Background Art

[0002] Under the background of the global advocacy of energy conservation, emission reduction and sustainable development, energy management has become the focus of attention in various industries. With the acceleration of the urbanization process, the number and scale of buildings have been continuously increasing, and their energy consumption ratio has been rising continuously. Therefore, it is urgent to efficiently manage building energy. The rise of advanced technologies such as big data and the Internet of Things has brought new opportunities to the field of energy management. Many enterprises and research institutions are committed to using new technologies to improve energy management efficiency and reduce energy waste.

[0003] At present, traditional energy consumption management mostly relies on manual meter reading and simple data statistical analysis, and it is difficult to achieve real-time and accurate tracking of energy consumption at different hierarchical structures in buildings. Some management methods that introduce information systems can collect some energy consumption data, but there are obvious deficiencies in the association between energy consumption equipment and building space and the presentation of energy consumption flow between levels. In the visualization display of energy consumption data, most are static charts, which cannot dynamically adjust the display content according to real-time energy consumption, and it is difficult to accurately judge energy consumption anomalies by combining historical data and environmental parameters.

[0004] Therefore, the existing energy consumption management technology has defects in the real-time and accuracy of building-level energy consumption tracking and the dynamics of energy consumption data visualization display, and it is difficult to meet the refined and intelligent energy management requirements of modern buildings. There is an urgent need for an innovative energy consumption management platform based on big data. Summary of the Invention

[0005] The purpose of the present invention is to provide an energy consumption management platform based on big data to solve the following technical problems:

[0006] The existing energy consumption management technology has defects in the real-time and accuracy of building-level energy consumption tracking and the dynamics of energy consumption data visualization display.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] An energy consumption management platform based on big data, comprising:

[0009] A building-level energy consumption tracking module, which is used to collect energy consumption data of different hierarchical structures in a building in real time, map different types of sub-item energy consumption equipment to nodes at corresponding levels according to the binding relationship between energy consumption equipment and building space, and establish a topological graph of energy consumption flow between levels based on the relationship between the main meter and sub-meters.

[0010] The visual energy consumption display module is used to dynamically generate a multi-level energy consumption distribution heat map according to the energy consumption flow topology map. The heat map is defined as different color gradients according to the energy consumption loss rate from low to high. Through the dynamic threshold algorithm, combined with historical year-on-year and month-on-month energy consumption data and environmental parameters, the energy consumption loss rate threshold of each level node is calculated in real time. If the current loss rate exceeds the energy consumption loss rate threshold, the abnormal node is marked in the heat map.

[0011] The energy consumption repair and positioning module is used to generate a diagnostic report including the positioning of faulty equipment and the reasons for energy consumption waste according to the historical monitoring data of the corresponding energy consumption equipment and the user operation log after detecting an abnormal node.

[0012] As a further solution of the present invention: in the building-level energy consumption tracking module, the energy consumption flow topology map collects the usage data of sub-item energy consumption equipment in real time according to a preset time granularity, and eliminates abnormal collected values through the logical verification of the total and sub-meter data. The energy consumption flow topology map takes the total and sub-meter as the root node, and layer by layer associates the sub-item meter data of the building, floor, and room downward to form a tree-shaped energy consumption flow path, and marks the energy consumption ratio and loss rate of each node in the path.

[0013] As a further solution of the present invention: in the building-level energy consumption tracking module, during the process of collecting the usage data of sub-item energy consumption equipment in real time, based on the unique equipment identifier and time stamp, the multi-source data of the same-level nodes are aligned in time series; when it is detected that there is data break or overlap of the same equipment within adjacent time granularities, the missing data is filled in by the interpolation algorithm, or the overlapping data is distributed according to the time weight; the aligned data is updated to the heat map in real time, and the energy consumption time series change trend of each node is displayed as a dynamic line chart in the visualization interface.

[0014] As a further solution of the present invention: the logical verification of the total and sub-meter relationship is specifically:

[0015] Through the layer-by-layer aggregation calculation of the total and sub-meter data, verify whether the sum of the sub-item data matches the total and sub-meter reading; if there is a difference, when the difference is within the fault tolerance range, the total and sub-meter data is automatically corrected according to the energy consumption distribution weight ratio of the sub-item equipment; when the difference exceeds the fault tolerance range, it is marked as abnormal data and an alarm is triggered.

[0016] The energy consumption distribution weight is dynamically adjusted based on historical year-on-year and month-on-month data, and the total and sub-meter difference is dynamically allocated to each sub-item equipment according to the average energy consumption ratio of the sub-item equipment in the same period in the past and the current environmental parameters; the corrected data is updated to the energy consumption flow topology map in real time, and the correction path is marked with a highlighted dotted line in the visualization module, and a data correction log is generated at the same time.

[0017] As a further solution of the present invention: the building-level energy consumption tracking module further includes a cross-level energy consumption collaborative optimization unit:

[0018] The cross - level energy consumption collaborative optimization unit is used to automatically associate the energy consumption data of adjacent levels when abnormal energy consumption of a certain level node is detected. Through the load balancing algorithm, part of the energy consumption load of the abnormal node is intelligently allocated to adjacent low - load nodes; based on the device operation parameters and environmental conditions, the collaborative operation timing of cross - level devices is dynamically adjusted; the optimized energy consumption allocation scheme is updated to the topology map in real time, and the load migration path is marked with dynamic arrows in the heat map.

[0019] As a further scheme of the present invention: in the visual energy consumption display module, the dynamic threshold algorithm is specifically as follows:

[0020] Analyze the correlation between historical traffic volume, environmental parameters and energy consumption data through a linear regression model, predict the energy consumption fluctuation trend in the future period, and expand or contract the threshold range based on the prediction results; the dynamic threshold is superimposed and displayed in the form of a semi - transparent color band in the heat map, and the width of the color band reflects the change of the threshold range. When the actual loss rate is close to the threshold boundary, a warning halo is displayed at the edge of the heat map node.

[0021] As a further scheme of the present invention: in the visual energy consumption display module, the dynamic threshold algorithm also includes:

[0022] Analyze the user operation mode through a clustering algorithm to identify the energy consumption management preferences of different user groups; based on the type of energy consumption management preferences, introduce weight coefficients corresponding to different preference types of users in the dynamic threshold algorithm to adjust the threshold sensitivity; the optimized threshold is distinguished by gradient - colored blocks in the heat map to show the influence range of user groups, and an option for manually calibrating the weight coefficient is provided.

[0023] As a further scheme of the present invention: for the energy consumption repair and location module, the location of faulty devices specifically includes:

[0024] After detecting an abnormal node, according to the energy consumption flow topology map, trace back from the abnormal node to the total meter upwards and extend downwards to the sub - item meters, layer by layer comparing the energy consumption data to identify the specific layer where the energy consumption suddenly increases or decreases; if the energy consumption loss rate of a certain layer is significantly higher than the historical year - on - year and month - on - month data, it is marked as a suspicious layer; in the suspicious layer, compare the real - time energy consumption of each sub - item energy consumption device with the historical average value, and screen out the devices with energy consumption deviation exceeding the preset threshold; screen out the devices with abnormal energy consumption.

[0025] For the devices with abnormal energy consumption, extract the time - series data of the operation parameters of the device and match them with the typical fault characteristics in the historical fault mode library; if a specific fault mode is matched, the mode includes motor overload, sensor drift, pipeline leakage, then generate a fault location report, marking the fault type and occurrence time; if no clear fault mode is matched, infer the potential fault cause by combining environmental parameters and user operation logs.

[0026] Advantages of the present invention:

[0027] Through the building-level energy consumption tracking module, the present invention can accurately collect energy consumption data of different hierarchical structures in a building in real time, establish a topological graph of energy consumption flow and eliminate abnormal collected values, and can also achieve time-series alignment and complementation of multi-source data. Combining with the cross-level energy consumption collaborative optimization unit, it intelligently distributes the energy consumption load, greatly improving the real-time performance, accuracy and energy-saving effect of energy consumption tracking; the visual energy consumption display module uses a dynamic threshold algorithm to calculate the energy consumption loss rate threshold in real time based on historical and environmental parameters, dynamically generates a multi-level energy consumption distribution heat map and marks abnormal nodes, realizing dynamic and intelligent visualization of energy consumption data; after detecting an abnormal node, the energy consumption repair and positioning module can generate a diagnostic report including the positioning of faulty equipment, the reasons for energy consumption waste, and the sorting of repair priorities based on historical monitoring data and user operation logs, and intelligently complete the generation of fault diagnosis and repair suggestions, effectively solving the deficiencies of existing energy consumption management technologies in building-level energy consumption tracking, visual display and intelligent diagnostic analysis, and meeting the refined and intelligent energy management requirements of modern buildings. Brief Description of the Drawings

[0028] The present invention will be further described below with reference to the accompanying drawings.

[0029] Figure 1 is a schematic flow chart of the present invention;

[0030] Figure 2 is a schematic diagram of the modules of the present invention. Detailed Embodiments

[0031] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0032] Please refer to Figure 1 - Figure 2 as shown, the present invention is an energy consumption management platform based on big data, including:

[0033] The building-level energy consumption tracking module occupies a core position in the entire energy consumption management system, and undertakes the key task of obtaining energy consumption data within the building and sorting out its hierarchical flow. By leveraging IoT sensing technology, this module can collect energy consumption data of different hierarchical structures within the building in real time, covering everything from the total energy consumption of the entire building to electricity, water, and gas consumption of detailed energy-consuming equipment on each floor and in each room. By establishing a precise binding relationship between energy-consuming equipment and building space, the system can cleverly map different types of sub-item energy-consuming equipment to corresponding hierarchical nodes based on their physical locations. This process is like building a precise energy consumption "map", and each energy-consuming device can find its exact location identifier on this map. Based on the relationship between the total and sub-tables, the module further constructs a topological diagram of the energy consumption flow between levels, providing an intuitive and orderly framework for sorting and analyzing energy consumption data.

[0034] The energy consumption flow topology map offers exceptional real-time and accuracy. It continuously collects real-time consumption data for each energy-consuming device at a preset granularity, such as every 15 minutes or every hour. To ensure data reliability, the collected data is rigorously screened through a logical verification mechanism for the master and sub-table data. During this verification process, the system aggregates the master and sub-table data layer by layer, summing the energy consumption data for each item in the sub-table. The result then verifies that the accumulated result accurately matches the master and sub-table readings. If there is a discrepancy between the two, the system quickly activates an intelligent judgment mechanism. If the discrepancy falls within a pre-set tolerance, the system automatically adjusts the master and sub-table data based on dynamically adjusted energy consumption allocation weights based on historical year-over-year and year-over-year data. These energy consumption allocation weights are not static; instead, they are closely integrated with the average energy consumption percentage of the sub-table devices over the same period in the past, as well as current environmental parameters such as season, weather conditions, and indoor and outdoor temperatures, dynamically and appropriately allocating the difference between the master and sub-table data to each sub-device. Once data corrections are complete, the new data is immediately updated in real time to the energy consumption flow topology. The correction path is clearly marked with a highlighted dashed line in the visualization module, allowing managers to easily trace the data adjustment process. A detailed data correction log is automatically generated for subsequent query and analysis. If the difference exceeds the tolerance range, the system will decisively mark the data as abnormal and quickly trigger an alarm mechanism, notifying relevant managers through various means such as text messages and pop-up windows, ensuring that abnormal energy consumption data can be detected and handled promptly.

[0035] In the process of real-time collecting the usage data of sub-item energy consumption equipment, based on the powerful data identification and marking system of equipment unique identifiers and timestamps, the system can efficiently perform time-series alignment on multi-source data of nodes at the same level. This means that data from different energy consumption equipment and different collection channels can be accurately arranged in chronological order. When the system detects data gaps or overlaps of the same equipment within adjacent time granularities, it will flexibly use advanced algorithms for processing. In case of data gaps, the system will start the interpolation algorithm, and according to the data characteristics of the previous and subsequent time points, intelligently complete the missing data to ensure the integrity and continuity of the energy consumption data; if data overlap occurs, it will allocate the overlapping data reasonably according to the time weight allocation algorithm to make the data return to the correct time series. The data after time-series alignment processing will be immediately updated in real time to the energy consumption distribution heat map, providing accurate data support for the visual energy consumption display module, and at the same time, in the form of a dynamic line chart in the visual interface, intuitively showing the energy consumption time-series change trend of each node. By observing the dynamic line chart, managers can clearly see the fluctuations of energy consumption data over time, and timely discover the time nodes and trend directions of abnormal energy consumption changes, providing a strong basis for subsequent energy consumption analysis and management decisions.

[0036] The building-level energy consumption tracking module also includes a cross-level energy consumption collaborative optimization unit. When an abnormal energy consumption situation is detected at a certain level node, this unit first automatically establishes a close connection with the energy consumption data of adjacent levels. It uses advanced data mining techniques to comprehensively and deeply analyze the real-time energy consumption data, historical energy consumption data, and equipment operation status data of adjacent levels. Through complex load balancing algorithms, it accurately identifies adjacent low-load nodes, which are like the "potential stocks" of energy reserves and have the ability to undertake additional energy consumption loads. Subsequently, the system allocates the part of the energy consumption load of the abnormal node that exceeds the normal range to these low-load nodes in an intelligent and efficient manner. For example, in a commercial office building, if the energy consumption of an office area on a certain floor surges abnormally due to the concentrated use of equipment, while some areas on adjacent floors have low-load operation of equipment due to fewer office staff, the cross-level energy consumption collaborative optimization unit can quickly transfer the energy consumption loads of some non-urgent equipment on the abnormal floor, such as the power consumption loads of some lighting equipment and non-critical office appliances, to the adjacent low-load floors reasonably, realizing the balanced distribution of energy and avoiding energy supply tension or equipment failures caused by excessive local energy consumption.

[0037] At the same time, based on the continuous monitoring of equipment operating parameters and the precise perception of real-time environmental conditions, the cross-level energy consumption collaborative optimization unit can dynamically adjust the collaborative operation sequence of cross-level equipment. It will comprehensively consider the operating characteristics of the equipment, energy requirements, and environmental factors, such as the impact of temperature and humidity on equipment energy consumption. Taking the air-conditioning system as an example, during the high temperature period in summer, if the air-conditioning energy consumption on a certain floor is abnormal, the unit can adjust the start and stop time and operating power of the air-conditioning equipment on different floors according to the temperature conditions and air-conditioning operating status of the adjacent floors, so that the air-conditioning system on each floor can achieve optimal energy utilization while meeting the indoor comfort level. At night or during non-peak hours, the operating power of equipment on some floors can be appropriately reduced to stagger operation and further optimize energy consumption.

[0038] The optimized energy allocation plan is immediately updated in real time to the energy flow topology map. This update process ensures that the topology map always reflects the latest and most accurate energy allocation status within the building, providing managers with a clear and intuitive overview of energy flows. In the heat map of the energy visualization module, dynamic arrows highlight load migration paths. These dynamic arrows not only show the specific trajectory of energy consumption shifting from abnormal nodes to adjacent low-load nodes, but also reflect the direction and intensity of load migration in real time.

[0039] As the core interactive interface of the energy management platform, the Visual Energy Consumption Display Module plays a key role in transforming complex energy consumption data into intuitive and easy-to-understand information. This module closely leverages the energy consumption flow topology created by the Building-Level Energy Consumption Tracking Module to dynamically generate multi-level energy consumption distribution heat maps, presenting users with a clear and comprehensive picture of energy consumption at each level within the building.

[0040] In generating the multi-level energy consumption distribution heat map, the system carefully defines a series of different color gradients based on energy loss rates, from low to high. Low energy loss rates are represented by cool colors, such as light blue, symbolizing efficient energy use and low energy waste. As energy loss rates gradually increase, the colors transition to warmer colors, such as orange and red, intuitively highlighting areas with higher energy consumption and greater losses. This color-based visualization allows users to quickly locate high-energy consumption areas, providing a convenient entry point for subsequent energy-saving analysis and management.

[0041] To more accurately identify energy consumption anomalies, the visual energy consumption display module utilizes an advanced dynamic threshold algorithm. This algorithm deeply integrates historical year-over-year and month-over-month energy consumption data with real-time environmental parameters such as season, weather, indoor and outdoor temperature, and humidity, to calculate energy loss rate thresholds for each node level in real time. Specifically, a linear regression model is constructed to conduct in-depth analysis of the complex correlations between historical business volume, environmental parameters, and energy consumption data. For example, in commercial buildings, seasonal changes in passenger flow (business volume) and the impact of outdoor temperature on indoor air conditioning energy consumption can be quantified using a linear regression model. Based on this analysis, the system can accurately predict energy consumption fluctuations over future cycles. If energy consumption is predicted to increase due to increased business volume or environmental changes, the system will expand the threshold range accordingly; conversely, if energy consumption is expected to decrease, the threshold range will be contracted. In the heat map, the dynamic threshold is displayed as a semi-transparent ribbon overlaid on each node level, and the width of the ribbon accurately reflects the changes in the threshold range. When the actual energy consumption loss rate approaches the threshold boundary, a warning halo will automatically appear on the edge of the heat map node, using eye-catching visual effects to remind users of potential energy consumption abnormality risks, allowing managers to take timely measures to intervene.

[0042] The visual energy consumption display module also features unique user behavior analysis capabilities. By using a clustering algorithm to deeply analyze and mine a large number of user operation patterns, it can accurately identify the energy management preferences of different user groups. For example, some users prefer to keep indoor lights on full blast during work hours, pursuing a bright office environment, while others prioritize energy conservation and flexibly adjust light brightness based on their needs. Based on these different energy management preferences, the system cleverly incorporates weighting coefficients corresponding to different preference types into the dynamic threshold algorithm to fine-tune the threshold sensitivity. For user groups with a strong energy-conscious mindset, the threshold sensitivity is appropriately lowered, allowing them to promptly detect even the slightest change in energy consumption. For user groups with higher requirements for environmental comfort and relatively high energy consumption, the threshold sensitivity is appropriately increased to avoid frequent warning triggering. The optimized thresholds are clearly distinguished by gradient color blocks in the heat map, allowing users to intuitively see the degree to which different areas are affected by user group preferences. At the same time, in order to meet the personalized needs of users, the system also provides a manual calibration weight coefficient option. Users can adjust the weight independently according to actual conditions, so that the threshold setting is more in line with their own energy consumption management goals and habits, further improving the flexibility and accuracy of energy consumption management.

[0043] After detecting an abnormal node, the energy consumption repair and positioning module is based on the historical monitoring data of the corresponding energy consumption equipment and the user operation log.

[0044] As one of the core functions of the energy consumption repair and location module, faulty equipment location operates with rigorous efficiency. Upon detecting an abnormal node, the module immediately begins data tracing based on the hierarchical structure constructed by the energy consumption flow topology. Starting from the abnormal node, the module traces back to the master and sub-table, which aggregates the overall energy consumption data for the entire building or area. By analyzing the master and sub-table data, the module can preliminarily determine whether the abnormal energy consumption stems from a sudden change in energy consumption in a larger area. Simultaneously, the module further delves into the itemized table, which records the energy consumption data of each specific energy-consuming device. This allows for a comprehensive analysis of energy consumption data from a macro to micro perspective. During this process, the module compares energy consumption data layer by layer, carefully identifying the specific level experiencing a sudden increase or decrease in energy consumption. For example, in a complex office building, if energy consumption on a specific level increases significantly over a short period of time, differing significantly from previous data for the same period, and if the energy loss rate for that level is significantly higher than historical year-on-year and month-on-month data, this level will be accurately flagged as suspicious and targeted for further investigation.

[0045] After determining the suspicious level, the module further refines the investigation to the individual energy-consuming devices within that level. It compares the real-time energy consumption of each energy-consuming device with its historical average. This historical average is not a simple average value, but a reference value derived from long-term data accumulation and analysis, reflecting the energy consumption level of the device under normal operating conditions. Through rigorous comparison, devices with energy consumption deviations exceeding the preset threshold are screened out. The preset thresholds are set after extensive experimentation and data analysis, taking into account multiple factors such as device type, operating environment, and normal fluctuation range to ensure the accuracy and reliability of the screening results. Devices with energy consumption deviations exceeding the standard are "suspected devices" that may be faulty and causing abnormal energy consumption.

[0046] For devices identified as experiencing abnormal energy consumption, the module deeply analyzes their internal operating data. Specifically, it extracts time-series data on the device's operating parameters, covering various operational indicators at different points in time, such as motor speed, current, and temperature, sensor output signal values, and pipeline pressure and flow. This time-series data is then carefully matched against typical fault signatures in a pre-built historical fault pattern library. This library is constructed through the long-term collection and organization of various failure cases and corresponding fault signature data that have occurred during actual device operation. It includes common failure modes such as motor overload, sensor drift, and pipeline leaks, along with their detailed signatures. If the device's operating parameter time-series data closely matches a specific failure mode in the library, the module quickly generates a fault location report. The report clearly identifies the fault type (e.g., excessive current due to motor overload), as well as the precise time of the fault, providing critical information for subsequent repairs.

[0047] However, the actual situation is often complex and changeable, and not all abnormal energy consumptions can be clearly diagnosed by matching with the existing fault mode library. When no clear fault mode is matched, the module does not stop the investigation. Instead, it makes full use of multi-source data such as the environmental parameters and user operation logs collected by the platform for in-depth inference. Environmental parameters, such as indoor and outdoor temperature, humidity, air pressure, etc., may have a significant impact on the energy consumption of the equipment. For example, in a high-temperature environment, the air-conditioning equipment may need to consume more energy to maintain the indoor temperature. If the energy consumption of the air conditioner is abnormal at this time, it is necessary to combine the environmental temperature data to determine whether there is an increase in energy consumption caused by environmental factors such as poor heat dissipation. At the same time, the user operation logs record various operation behaviors of the user on the equipment, such as the start and stop time of the equipment, the adjustment frequency, etc. By analyzing these operation logs, the module can determine whether there is abnormal energy consumption caused by improper user operations, such as frequently turning the equipment on and off, setting parameters incorrectly, etc. By comprehensively considering environmental parameters and user operation logs, the module can infer the potential fault causes as accurately as possible, providing comprehensive and targeted guidance for the energy consumption repair work.

[0048] The above has described an embodiment of the present invention in detail, but the content described is only the preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the present invention application should still fall within the scope covered by the patent of the present invention.

Claims

1. An energy consumption management platform based on big data, characterized in that, Including: A building-level energy consumption tracking module, which is used to collect the energy consumption data of different hierarchical structures in a building in real time. Through the binding relationship between energy consumption devices and building spaces, different types of sub-item energy consumption devices are mapped to the corresponding hierarchical nodes according to their physical locations, and an energy consumption flow topology map between hierarchies is established based on the total-meter and sub-meter relationship; A visual energy consumption display module, which is used to dynamically generate a multi-level energy consumption distribution heat map according to the energy consumption flow topology map. The heat map is defined as different color gradients according to the energy consumption loss rate from low to high; through a dynamic threshold algorithm, combined with historical year-on-year and month-on-month energy consumption data and environmental parameters, the energy consumption loss rate threshold of each hierarchical node is calculated in real time. If the current loss rate exceeds the energy consumption loss rate threshold, the abnormal node is marked in the heat map; An energy consumption repair and location module, which is used to generate a diagnostic report including the location of faulty equipment and the reasons for energy consumption waste according to the historical monitoring data of the corresponding energy consumption device and the user operation log after detecting an abnormal node.

2. The energy consumption management platform based on big data according to claim 1, characterized in that, In the building-level energy consumption tracking module, the energy consumption flow topology map collects the usage data of sub-item energy consumption devices in real time according to a preset time granularity, and eliminates abnormal collected values through the logical verification of the total-meter and sub-meter data. The energy consumption flow topology map takes the total-meter as the root node, and layer by layer associates the sub-meter data of the building, floor, and room downward to form a tree-shaped energy consumption flow path, and marks the energy consumption ratio and loss rate of each node in the path.

3. An energy consumption management platform based on big data according to claim 2, characterized in that, In the building-level energy consumption tracking module, during the process of collecting the usage data of sub-item energy consumption devices in real time, the multi-source data of the same hierarchical node is time-aligned based on the device unique identifier and time stamp; When it is detected that there is data interruption or overlap of the same device within adjacent time granularities, the missing data is complemented through an interpolation algorithm, or the overlapping data is distributed according to the time weight; The aligned data is updated to the heat map in real time, and the energy consumption time series change trend of each node is displayed as a dynamic line chart in the visualization interface.

4. The energy consumption management platform based on big data according to claim 2, characterized in that, The logical verification of the total-meter and sub-meter relationship is specifically: Through the hierarchical aggregation calculation of the total-meter and sub-meter data, verify whether the sum of the sub-item data matches the total-meter reading; if there is a difference, when the difference is within the fault tolerance range, the total-meter data is automatically corrected according to the energy consumption distribution weight ratio of the sub-item devices; when the difference exceeds the fault tolerance range, it is marked as abnormal data and an alarm is triggered; The energy consumption distribution weight is dynamically adjusted based on historical year-on-year and month-on-month data, and the total-meter difference is dynamically allocated to each sub-item device according to the average energy consumption ratio of the sub-item devices in the past same period and the current environmental parameters; The corrected data is updated to the energy consumption flow topology map in real time, and the correction path is marked with a highlighted dotted line in the visualization module, and a data correction log is generated at the same time.

5. A big data-based energy consumption management platform according to claim 1, characterized in that, The building-level energy consumption tracking module further includes a cross-hierarchical energy consumption collaborative optimization unit: The cross - level energy consumption collaborative optimization unit is used to automatically associate the energy consumption data of adjacent levels when abnormal energy consumption of a certain level node is detected. Through the load balancing algorithm, some of the energy consumption load of the abnormal node is intelligently allocated to adjacent low - load nodes; based on the device operation parameters and environmental conditions, the collaborative operation timing of cross - level devices is dynamically adjusted; the optimized energy consumption allocation scheme is updated to the topology map in real - time, and the load migration path is marked with dynamic arrows in the heat map.

6. The energy consumption management platform based on big data according to claim 1, characterized in that, In the visual energy consumption display module, the dynamic threshold algorithm is specifically as follows: Analyze the correlation between historical traffic volume, environmental parameters and energy consumption data through a linear regression model, predict the energy consumption fluctuation trend in the future period, and expand or contract the threshold range based on the prediction results; the dynamic threshold is superimposed and displayed in the form of a semi - transparent color band in the heat map, and the width of the color band reflects the change of the threshold range. When the actual loss rate approaches the threshold boundary, a warning halo is displayed at the edge of the heat map node.

7. An energy consumption management platform based on big data according to claim 6, characterized in that, In the visual energy consumption display module, the dynamic threshold algorithm also includes: Analyze the user operation mode through a clustering algorithm to identify the energy consumption management preferences of different user groups; based on the type of energy consumption management preferences, introduce the weight coefficients corresponding to different types of users with preferences in the dynamic threshold algorithm to adjust the threshold sensitivity; the optimized threshold differentiates the influence range of user groups in the heat map with gradient - colored blocks and provides an option to manually calibrate the weight coefficients.

8. An energy consumption management platform based on big data according to claim 1, characterized in that, In the energy consumption repair and location module, the location of faulty equipment specifically includes: After detecting an abnormal node, according to the energy consumption flow topology map, trace back from the abnormal node to the total meter and sub - meters layer by layer, compare the energy consumption data layer by layer, and identify the specific layer where the energy consumption suddenly increases or decreases; if the energy consumption loss rate of a certain layer is significantly higher than the historical year - on - year and month - on - month data, it is marked as a suspicious layer; in the suspicious layer, compare the real - time energy consumption of each sub - item energy consumption device with the historical average value, and screen out the devices with energy consumption deviation exceeding the preset threshold; screen out the devices with abnormal energy consumption. For the devices with abnormal energy consumption, extract the time - series data of the operation parameters of the device and match them with the typical fault characteristics in the historical fault mode library; if a specific fault mode is matched, the mode includes motor overload, sensor drift, pipeline leakage, then generate a fault location report, marking the fault type and occurrence time; if no clear fault mode is matched, infer the potential fault cause in combination with environmental parameters and user operation logs.

Images