Microgrid regulation method, program product and device based on intelligent data analysis

Abstract

The application provides a micro-grid regulation method based on intelligent data analysis, a program product and equipment, and relates to the field of power supply and distribution systems. The micro-grid regulation method comprises: obtaining sensing data of a human sensing device configured in a community; determining in-house time periods of each household in the community according to the sensing data; collecting power consumption data of each household; extracting in-house power consumption characteristics of the power consumption data of the household within the in-house time period; identifying the in-house power consumption characteristics to determine whether the household meets a preset reward condition; and in the case of meeting the reward condition, reducing the power consumption cost of the household according to the power consumption data. According to the scheme of the application, the in-house time of the household can be determined through analysis and processing of the sensing data, and the household that cooperates with the community operator to adjust the power consumption behavior can be accurately identified. The enthusiasm of the household for participating in power consumption regulation is stimulated by reducing the power consumption cost of the household.

Description

Technical Field

[0001] This invention relates to the field of power supply and distribution systems, and in particular to a microgrid control method, program product, and equipment based on intelligent data analysis. Background Technology

[0002] With the widespread adoption of distributed renewable energy sources (such as photovoltaics and energy storage systems), microgrids have become an important means of reducing electricity costs and improving energy efficiency. Microgrids have been widely used in various scenarios, such as industrial parks, public facilities, and residential communities.

[0003] In special residential communities such as long-term rental apartments and affordable rental housing communities, microgrids are managed by professional operation teams. They can supplement the power supply from self-generated electricity with the external public grid to meet the needs of tenants with high mobility and flexible electricity consumption. In order to ensure the stable operation of the microgrid and improve economic and social benefits, the community operator formulates corresponding microgrid control strategies and provides residents with electricity consumption suggestions to achieve the goals of absorbing renewable energy generation, reducing fluctuations in electricity purchases from the grid, and lowering electricity purchase costs.

[0004] To ensure resident satisfaction, community operators generally do not forcibly regulate residents' electricity load, but instead use economic measures to guide their electricity consumption behavior. However, resident electricity consumption behavior varies significantly in these communities; some respond to the community operator's guidance, while others only focus on their own electricity needs. Currently, there is a lack of technical means to accurately identify residents' proactive response to electricity consumption guidance, which leads to the economic guidance measures not achieving the expected results and having limited incentive effects on residents. The enthusiasm of residents responding to electricity consumption guidance continues to decline, further leading to a coexistence of self-generated and abandoned electricity and high-priced electricity purchases in the microgrid. This results in low renewable energy consumption efficiency and large fluctuations in grid-purchased electricity in the community microgrid. Summary of the Invention

[0005] One object of the present invention is to provide a microgrid control method based on intelligent data analysis that at least solves any of the above-mentioned technical problems.

[0006] A further objective of this invention is to accurately identify residents who cooperate in adjusting their electricity consumption behavior, thereby fully motivating tenants to participate in electricity consumption regulation.

[0007] Another further objective of this invention is to improve the economic benefits of community operators while meeting the needs of residents. Specifically, this invention provides a microgrid control method based on intelligent data analysis. This method includes:

[0008] Acquire sensor data from human body sensors deployed within the community, which is equipped with a microgrid to supply power to residents;

[0009] The time periods when each household is at home in the community are determined based on sensor data;

[0010] Collect electricity consumption data from each household;

[0011] Extract household electricity consumption data and its characteristics during the time period the household is in the household;

[0012] Identify the characteristics of household electricity consumption to determine whether the household meets the preset reward conditions;

[0013] If the reward conditions are met, the household's electricity bill will be reduced based on electricity consumption data, thereby encouraging the household to actively regulate the use of electricity in the microgrid.

[0014] Optionally, the step of determining the time periods at home for each household in the community based on sensor data includes:

[0015] Multiple entrance and exit sensor sets are formed based on the location of the human body sensor, and each entrance and exit sensor set corresponds to one entrance and exit line of the resident.

[0016] Organize the sensor data of human body sensors in the same set of entrance and exit sensors into a time sequence of sensor data;

[0017] The time period at the household is estimated based on the time sequence of the sensor data.

[0018] Optionally, the step of estimating the time period in the household based on the time series of sensing data includes:

[0019] Human body sensors belonging to the same set of entrance and exit sensors are used as graph nodes, and the estimated walking time of residents between adjacent human body sensors is used as edge weights to construct a graph neural network.

[0020] The time-series data of the sensed data is organized into the state sequence of each node and then input into the graph neural network.

[0021] Using graph neural networks to perform spatial correlation inference, predict residents' entry and exit events;

[0022] The time period at home is determined based on the time when a resident enters or leaves the home.

[0023] Optionally, the step of organizing the time-series sequence of the sensing data into a state sequence for each node includes:

[0024] The presence of missing values ​​in the time series of sensor data is identified by a pre-trained long short-term memory network model, which is trained using historical records of entry and exit events and the time series of sensor data.

[0025] If so, fill in the missing values ​​and organize the time-series sequence of the sensing data after filling in the missing values ​​into a state sequence according to the node identifier.

[0026] Optionally, the steps for extracting the household electricity consumption data during the household time period include:

[0027] Align electricity consumption data with the time period of household use to separate household electricity consumption data;

[0028] Extract household electricity consumption characteristics from household electricity consumption data.

[0029] Optionally, the steps for identifying the characteristics of household electricity usage include:

[0030] Acquire power application data of the microgrid and split the data according to the set evaluation cycle. Power application data includes: power purchase data from the external public grid, self-generated power data of the microgrid's self-configured power generation equipment, and total power consumption data of the microgrid.

[0031] The expected electricity consumption characteristics and reward points limit for each assessment period are generated based on the electricity application data within that assessment period.

[0032] Calculate the similarity between the household electricity consumption characteristics and the expected electricity consumption characteristics for each assessment period within the household time period;

[0033] Reward points are generated for the corresponding evaluation period based on the similarity value within the reward point limit. The reward points increase accordingly as the similarity increases.

[0034] The bonus points for each assessment period during the period of household stay are accumulated to obtain the bonus accumulation points;

[0035] Residents whose accumulated reward points exceed the preset value are deemed to meet the reward conditions.

[0036] Optionally, the steps to reduce the household's electricity bill based on electricity usage data include:

[0037] Extract the characteristics of residents' electricity consumption during the time they are away from their homes based on electricity consumption data;

[0038] A correction factor is generated based on the characteristics of off-site electricity consumption.

[0039] Use a correction factor to adjust the accumulated reward score;

[0040] The household's electricity bill reduction will be calculated based on the revised accumulated reward points and the original electricity bill within the preset billing cycle.

[0041] Optionally, the steps for calculating the household's electricity bill reduction based on the revised accumulated reward points and the original electricity bill within the pre-designed billing cycle include:

[0042] Calculate the economic benefits of power generation equipment in a microgrid during the billing cycle;

[0043] The economic benefits are distributed according to the accumulated reward points, resulting in the reduction in electricity prices.

[0044] According to another aspect of the present invention, a computer program product is also provided, comprising a computer program that, when executed by a processor, implements the steps of any of the above-described microgrid control methods based on intelligent data analysis.

[0045] According to another aspect of the present invention, a computer-readable storage medium is also provided, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of any of the above-described microgrid control methods based on intelligent data analysis.

[0046] According to another aspect of the present invention, a computer device is also provided, which includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the microgrid control method based on intelligent data analysis described above.

[0047] This invention presents a microgrid control method based on intelligent data analysis. Human body sensors are deployed within the community, located in public spaces, to detect human activity. The sensor data does not involve residents' personal privacy data, thus posing no information security risks. Residents' electricity consumption behavior during their time at home reflects their response to electricity usage guidance. This invention's method, through analysis and processing of the sensor data, can determine residents' time at home, accurately identifying residents who cooperate with the community operator in adjusting their electricity consumption behavior. By reducing the electricity fees for these residents, the method incentivizes their participation in electricity usage control. This solution balances microgrid operation optimization with resident benefit protection, achieving synergistic development, promoting the local utilization of renewable energy, and reducing the adverse impact of the community microgrid on the external power grid. It also helps improve the operating revenue of the community operator and ensures stable electricity purchases from the public grid.

[0048] Furthermore, the microgrid control method based on intelligent data analysis of the present invention organizes human body sensing devices into an entry / exit sensing set according to their locations and arranges them into a time sequence of sensing data, providing a hardware and data foundation for accurately estimating the time periods when residents are at home. This method utilizes the spatial relationship between the sensing devices and the temporal sequence characteristics of the sensing data, and compared to processing single sensing data, it can more accurately determine the time periods when residents are at home, thus providing a foundation for subsequent analysis.

[0049] Furthermore, the microgrid control method based on intelligent data analysis of this invention organizes the time-series of induction data into node state sequences and inputs them into a graph neural network for spatial correlation estimation and prediction of household entry and exit events, thereby determining the time periods when residents are in the house. Leveraging the powerful spatial correlation analysis capabilities of the graph neural network, it can fully explore the spatial relationships between sensing devices and the activity patterns of residents in these spatial locations, making the prediction of resident entry and exit events more accurate. The time-series of induction data uses a pre-trained long short-term memory network model to identify and fill in missing values, ensuring data integrity. The solution of this invention can avoid analytical errors caused by missing data and improve the reliability of the entire control method based on induction data processing.

[0050] The above and other objects, advantages and features of the present invention will become more apparent to those skilled in the art from the following detailed description of specific embodiments of the invention in conjunction with the accompanying drawings. Attached Figure Description

[0051] The following sections will describe some specific embodiments of the invention in detail by way of example and not limitation, with reference to the accompanying drawings. The same reference numerals in the drawings denote the same or similar parts or portions. Those skilled in the art should understand that these drawings are not necessarily drawn to scale. In the drawings:

[0052] Figure 1 This is a schematic diagram of the device connections of a microgrid according to an embodiment of the present invention;

[0053] Figure 2 This is a schematic diagram of a microgrid control method based on intelligent data analysis according to an embodiment of the present invention;

[0054] Figure 3 This is a schematic diagram illustrating the determination of the time period for users in a microgrid control method based on intelligent data analysis according to an embodiment of the present invention.

[0055] Figure 4 This is a schematic diagram of processing human body sensing data in a microgrid control method based on intelligent data analysis according to an embodiment of the present invention;

[0056] Figure 5 This is a schematic diagram illustrating the determination of whether reward conditions are met in a microgrid control method based on intelligent data analysis according to an embodiment of the present invention.

[0057] Figure 6 This is a schematic diagram illustrating the method for reducing household electricity costs in a microgrid control system based on intelligent data analysis according to an embodiment of the present invention.

[0058] Figure 7 This is a schematic diagram of a computer program product according to an embodiment of the present invention;

[0059] Figure 8 This is a schematic diagram of a computer-readable storage medium according to an embodiment of the present invention;

[0060] Figure 9 This is a schematic block diagram of a computer device according to an embodiment of the present invention. Detailed Implementation

[0061] Those skilled in the art should understand that the embodiments described below are merely a part of the embodiments of the present invention, and not all of the embodiments of the present invention. These partial embodiments are intended to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention. Based on the embodiments provided by the present invention, all other embodiments obtained by those skilled in the art without creative effort should still fall within the scope of protection of the present invention.

[0062] This embodiment of the microgrid control method based on intelligent data analysis is primarily aimed at regulating microgrids in special residential communities where the microgrid is managed by a community operator. These community microgrids involve two main parties: the community operator and the community residents (or tenants). The community operator is both the operator of the entire microgrid and the manager of optimizing the electricity load of all residents. The microgrid is equipped with power generation equipment, including equipment utilizing distributed renewable energy sources such as wind and solar power, as well as energy storage equipment. When the self-generated power from the microgrid's own equipment is insufficient to supply the needs of the residents, the microgrid purchases electricity from the external public grid.

[0063] Figure 1 This is a schematic diagram of the device connections of a microgrid according to an embodiment of the present invention. A microgrid generally includes: power generation equipment, power consumption equipment 14, grid connection equipment 13, intelligent controller 31, power metering equipment 32, and human body sensing device 33.

[0064] The power generation equipment may include renewable energy power generation equipment 11 such as wind and solar power, and energy storage equipment 12. Energy storage equipment 12 utilizes energy storage battery packs to store and release electrical energy, addressing the mismatch between peak electricity demand periods and peak power generation periods of renewable energy power generation equipment 11. During peak demand periods, it releases stored electrical energy to alleviate grid supply pressure; during off-peak periods, it absorbs electrical energy from the grid for storage, reducing electricity costs and achieving optimal allocation of power resources. Energy storage equipment 12 can also perform charging and discharging operations based on the electricity price of the external public grid 21, discharging during peak electricity price periods and charging during periods of low electricity price periods, thereby reducing the electricity purchase costs for the community operator.

[0065] Based on their functions and usage characteristics, electrical equipment 14 can include both indoor electrical equipment and community public electrical equipment. Community public equipment can include: elevators, public facility electrical equipment, public lighting equipment, security equipment, communication equipment, public charging stations, etc. Community public electrical equipment is managed and can be controlled by the community operator. Indoor electrical equipment can include lighting, refrigerators, televisions, air conditioners, washing machines, disinfection cabinets, indoor charging equipment, etc. Indoor electrical equipment is generally used by residents according to their individual needs, and the community operator will not directly adjust it.

[0066] The grid connection device 13 is used to enable the flow of electrical energy between the microgrid and the external public power grid 21. The grid connection device 13 may include transformer equipment, switchgear, monitoring and protection equipment, etc.

[0067] The intelligent controller 31 executes localized control strategies, processes data locally, and can interact with the cloud or other network service devices. By implementing the microgrid control method based on intelligent data analysis in this embodiment, the intelligent controller 31 achieves the management goals of the community operator and meets the electricity requirements of community residents.

[0068] The electricity metering device 32 is installed at the connection point of the power generation equipment, the electrical equipment 14, and the power grid connection equipment 13, and is used to measure the power generation of the power generation equipment, the power consumption of the electrical equipment 14, and the power purchased from the power grid by the power grid connection equipment 13. The electricity metering device 32 may include smart meters, electricity acquisition devices, etc., to realize time-of-use electricity metering. The electricity metering device 32 can perform electricity metering for each household separately.

[0069] The human body sensor 33 is used to detect whether human activity occurs within a preset detection range. In this embodiment, the human body sensor 33 is deployed in the public areas of the community, such as at nodes of residents' entrance and exit routes, such as community entrances, building entrances, and elevator doors. Its placement is required to avoid infringing on residents' privacy; it only identifies human body signals and will not be used to identify residents' identities or other private information, thus ensuring residents' privacy and security. The human body sensor 33 can use infrared sensors, millimeter-wave radar, etc. The type of human body sensor 33 can be selected according to the environmental characteristics and sensing requirements of the placement location.

[0070] The equipment types in the microgrid described above are merely illustrative examples. Those skilled in the art can configure the necessary equipment according to their needs and power planning, such as adding power conversion devices (e.g., inverters, converters), various environmental monitoring devices (e.g., solar irradiance monitoring devices, wind power monitoring devices, etc.), and communication devices (e.g., wireless communication modules, network routers, etc.).

[0071] This embodiment provides a microgrid control method based on intelligent data analysis, which balances microgrid operation optimization with the protection of residents' interests, achieving synergistic development of both. It promotes the local utilization of renewable energy and reduces the adverse impact of the community microgrid on the external power grid. This is beneficial for improving the operating revenue of the community operator and ensuring stable electricity purchases from the public grid. Figure 2 This is a schematic diagram of a microgrid control method based on intelligent data analysis according to an embodiment of the present invention. The microgrid control method based on intelligent data analysis of this embodiment generally includes:

[0072] Step S201: Obtain the sensing data from the human body sensing devices configured within the community.

[0073] Step S202: Determine the time periods when each resident is at home in the community based on the sensor data. By analyzing the human body sensor data, the numerical value of human bodies appearing at corresponding locations at each time can be determined. Furthermore, based on the temporal relationship of the changes in human body appearance in the sensor data, the direction and route of human movement can be deduced, further determining the resident's entry and exit times, thereby further deriving the resident's time periods at home.

[0074] Step S203: Collect electricity consumption data for each household. This data can be obtained from each household's in-home electricity metering device (e.g., a smart meter). The data can be collected over time, resulting in timestamped data. For example, in some embodiments, electricity consumption data can be collected every 5, 10, 15, and 30 minutes, recording the time information. The timing of the human body sensing data must be consistent with the electricity consumption data to determine in-home and out-of-home electricity consumption data.

[0075] Step S204: Extract the household electricity consumption characteristics during the household's in-home period. In-home electricity consumption characteristics refer to the features of the household's electricity consumption data during the in-home period. These characteristics may include: average power, maximum power, power fluctuation, peak power change, and frequency of change.

[0076] Step S205: Identify the household electricity usage characteristics to determine whether the household meets the preset reward conditions. If the reward conditions are met, proceed to step S206.

[0077] Step S206: Reduce the household's electricity bill based on the electricity consumption data, thereby guiding the household to actively regulate the use of electricity in the microgrid.

[0078] Residents' electricity consumption behavior during their time at home reflects their response to electricity consumption guidance. The method of this invention can determine the time residents spend at home by analyzing and processing the sensing data, accurately identify residents who cooperate in adjusting their electricity consumption behavior, and incentivize residents to participate in electricity consumption regulation by reducing their electricity fees.

[0079] Figure 3 This is a schematic diagram illustrating the determination of in-home time periods in a microgrid control method based on intelligent data analysis according to an embodiment of the present invention. The steps described above for determining the in-home time periods of each household in a community based on sensing data may include:

[0080] Step S301: Multiple entry / exit sensor sets are formed based on the locations of the human body sensors. Each entry / exit sensor set corresponds to one entry / exit route for the resident. The human body sensors can be arranged along the resident's entry / exit route within the community, for example, at the community entrance, building entrance, unit entrance, elevator car, elevator lobby, and apartment door. Thus, an entry / exit sensor set is formed for each resident. For example, a resident's entry / exit sensor set may include: a human body sensor at the elevator lobby of that resident's floor, a human body sensor at the elevator car, and a human body sensor at the building unit entrance.

[0081] Compared to the method of placing a single human body sensor at the entrance door to determine the time of entry and exit, the solution in this embodiment uses a group of human body sensors to determine the resident's entry and exit events, which can be more accurate, can distinguish between entering and exiting the house, and can eliminate data interference caused by the resident's short-term temporary activities near the residence.

[0082] Step S302: Organize the sensing data of human body sensing devices in the same set of entry and exit sensors into a sensing data time sequence.

[0083] Step S303: Calculate the time period at the residence based on the time sequence of the sensing data. In some embodiments, the time period at the residence is inferred from the sensing times of each human body sensor in a plurality of entrance and exit sensor sets. For example, if the human body sensor at the elevator lobby of the residence's floor, the human body sensor in the elevator car, and the human body sensor at the building unit entrance / exit sequentially show changes in sensing data within a set time period, it is determined that the resident has left the residence (the departure route is from the elevator lobby of the residence's floor to the elevator car to the building unit entrance / exit). Conversely, if the human body sensor at the building unit entrance / exit, the human body sensor in the elevator car, and the human body sensor at the elevator lobby of the residence's floor show changes in sensing data within a set time period, it is determined that the resident has entered the residence (the entry route is from the building unit entrance / exit to the elevator car to the elevator lobby of the residence's floor).

[0084] In some embodiments, the estimation of in-home time periods can also be implemented using a Graph Neural Network (GNN). A GNN processes feature information of nodes, edges, or the entire graph. It updates the representation of the current node by aggregating the feature information of neighboring nodes, thereby capturing the dependencies between nodes in the graph. For example, the steps of estimating in-home time periods based on the time series of sensor data may include: using human body sensors belonging to the same set of entry / exit sensors as graph nodes, and using the estimated travel time of residents between adjacent human body sensors as edge weights to construct a graph neural network; organizing the time series of sensor data into state sequences of each node and inputting them into the graph neural network; using the graph neural network to perform spatial correlation estimation to predict resident entry / exit events; and determining the in-home time period based on the occurrence time of the resident's entry / exit events. The attributes of each graph node may include the location of the human body sensor, the sensing location, and the ID of the resident involved. GNN learns the dependencies between nodes through a message passing mechanism. For example, it calculates the probability that a resident entering the elevator car will enter either room 301 or 302 on the third floor. It then outputs spatial correlation feature vectors (e.g., the probability of a person appearing in the elevator lobby on a certain floor after the elevator's human body sensor detects human data at a certain moment), further determining the probability of residents entering their apartments on each floor. Through long-term learning and training of GNN, the method in this embodiment can also distinguish scenarios where multiple people are traveling together, short-term outings, or unconventional routes are difficult to identify.

[0085] Figure 4 This is a schematic diagram illustrating the processing of human body sensing data in a microgrid control method based on intelligent data analysis according to an embodiment of the present invention. The step of organizing the time-series sequence of sensing data into a state sequence of each node may include:

[0086] Step S401 involves identifying whether missing values ​​exist in the time-series of sensor data using a pre-trained Long Short-Term Memory (LSTM) network model. The LSTM network model is trained using historical records of entry / exit events and the time-series of sensor data. If missing values ​​exist, step S402 can be executed to complete the data. When processing the time-series of sensor data, the LSTM model predicts the value for each point using a sliding window and compares it with the actual value. If there is a significant deviation between the actual and predicted values, the sensor data before and after that point, as well as sensor data from other relevant human body sensors, can be used to infer whether a missing value actually exists. If a missing value is found, it is marked.

[0087] Step S402: Fill in the missing values ​​and organize the time series of sensed data after missing value filling into a state sequence according to the node identifier. The LSTM model fills in the predicted values ​​at the marked missing positions. The sequence after missing value filling is sorted by time (including timestamp, filled sensed value, event marker) and extracted to form a complete state time series sequence.

[0088] Furthermore, the steps for extracting the household electricity consumption data and its characteristics during the household time period include:

[0089] Step S403: Time-align the electricity consumption data with the in-home time period to separate the in-home electricity consumption data. For example, if it is determined that the resident is in the house from 18:00 to 07:30 the next day, then the electricity consumption data during the period from 18:00 to 07:30 the next day is considered as the in-home electricity consumption data. In some embodiments, the determined in-home time period may partially overlap with the electricity consumption data collection period. For example, if the electricity consumption data collection period is from 07:30 to 07:45, but the resident is determined to have left at 07:36 based on sensor data, then during time alignment, the entire incomplete in-home time period can be included in the in-home time period. For example, in the above example, if the resident leaves at 07:36, the in-home time period will be extended to 07:45.

[0090] Step S404: Extract household electricity consumption characteristics from the household electricity consumption data. Household electricity consumption characteristics may include average power, maximum power, power fluctuation, peak power change, and frequency of change.

[0091] Figure 5 This is a schematic diagram illustrating the determination of whether reward conditions are met in a microgrid control method based on intelligent data analysis according to an embodiment of the present invention. The steps for identifying household electricity consumption characteristics include:

[0092] Step S501: Obtain the power application data of the community microgrid and split the data according to the set evaluation cycle. The power application data includes: the power purchase data of the power purchased from the external public grid, the self-generated power data of the microgrid's self-configured power generation equipment, and the total power consumption data of the microgrid.

[0093] Step S502: Generate the expected electricity consumption characteristics and reward points limit for each assessment period based on the electricity application data within that assessment period. Factors influencing the expected electricity consumption characteristics may include: the grid's electricity purchase price, renewable energy curtailment, the size of self-generated electricity, and the size of purchased electricity. The electricity consumption behavior corresponding to the expected electricity consumption characteristics can help achieve the following objectives: fully utilizing renewable energy generation, reducing electricity purchase costs, and mitigating power supply fluctuations in the public grid. In some embodiments, the above objectives can be integrated, with high self-generated electricity consumption rate, off-peak electricity purchase ratio, and stable electricity consumption curve as targets. These targets are then broken down into the expected electricity consumption characteristics of each household based on their adjustable load. Expected electricity consumption characteristics may include: average power, maximum power, minimum power, power change amplitude, and power change rate.

[0094] Step S503: Calculate the similarity between the on-site electricity consumption characteristics and the expected electricity consumption characteristics for each assessment period within the on-site time period. The on-site electricity consumption characteristics and the expected electricity consumption characteristics adopt a unified dimension and are constructed as normalized feature vectors. Similarity can be calculated using multi-dimensional similarity methods such as Euclidean distance. Considering that different electricity consumption characteristics may have different importance to achieving microgrid goals, weights can be assigned to each feature dimension, and the quantified similarity is finally obtained by calculating a weighted sum of distances.

[0095] Step S504: Generate reward points for the corresponding assessment period based on the similarity value within the reward point limit. The reward points increase accordingly as the similarity increases. The reward points can be linearly correlated with the similarity value. In some embodiments, the reward points can be linearly correlated with the similarity value. For example, the assessment period can be set to 15 minutes, meaning that reward points are obtained every 15 minutes within that period. Considering that the time spent at home may not be completely aligned with the assessment period, for example, a resident may only be at home for 6 minutes within a 15-minute period, in some embodiments, the entire assessment period in which the resident was not fully at home can be counted as the time spent at home. That is, as long as the assessment period overlaps with the time spent at home within the 15-minute assessment period, the assessment period is still considered as the entire time spent at home.

[0096] Step S505: Accumulate the reward points for each assessment period within the household time period to obtain the accumulated reward points. This involves summing all reward points accumulated within the household time period.

[0097] Step S506: Residents whose accumulated reward points exceed the preset value are deemed to meet the reward conditions.

[0098] Figure 6 This is a schematic diagram illustrating the reduction of household electricity costs in a microgrid control method based on intelligent data analysis according to an embodiment of the present invention. The step of reducing the household's electricity costs based on electricity consumption data may further include:

[0099] Step S601: Extract the electricity consumption characteristics of residents during the time they are away from home based on the electricity consumption data. The electricity consumption characteristics are used to determine whether residents have significantly exceeded the electricity consumption limit or wasted electricity during the time they are away from home.

[0100] Step S602: Generate a correction factor based on the electricity consumption characteristics of residents leaving their homes. The correction factor is used to reduce the bonus amount based on the load characteristics when the resident leaves.

[0101] Step S603: Adjust the accumulated reward points using a correction factor. For example, if the electricity load significantly exceeds the necessary load during off-peak hours, the accumulated reward points will be reduced or even cancelled based on the extent of the excess.

[0102] Step S604: Calculate the reduction in the household's electricity bill based on the size of the corrected accumulated reward points and the original electricity bill within the pre-designed billing cycle.

[0103] The reward system takes into account residents' electricity consumption when they leave the house, ensuring fairness and preventing residents who respond to the guidance during their in-home hours but waste electricity significantly when they leave from receiving the full reward. This ensures that rewards are only given to residents who use electricity reasonably throughout the day and actively cooperate with the control measures. It encourages residents to develop energy-saving habits throughout the day, not only responding to the electricity consumption guidance during in-home hours but also proactively turning off unnecessary electrical equipment when leaving the house.

[0104] In some embodiments, the step of calculating the household's electricity bill reduction based on the corrected accumulated reward points and the original electricity cost within the pre-designed billing cycle may further include: calculating the economic benefit of the power generation equipment in the microgrid during the billing cycle; allocating the economic benefit according to the corrected accumulated reward points to obtain the electricity bill reduction. The economic benefit can be calculated as follows: calculating the replacement cost of the grid electricity required to purchase replacement power generation within the billing cycle based on the microgrid's self-generated power data; calculating the cost of self-generated power based on the self-generated power data; and using the difference between the replacement cost and the cost as the economic benefit. The cost of self-generated power may include: equipment depreciation costs, operation and maintenance costs, and the equipment's own energy consumption costs.

[0105] The electricity compensation amount comes from the revenue of the power generation equipment in the microgrid and will not impose an additional economic burden on the community operator. In some embodiments, the allocation method can be: using the accumulated reward points as the compensation weight to allocate economic benefits.

[0106] The microgrid control method based on intelligent data analysis in this embodiment can, in practical applications, explain to residents the data required for the control plan and allow them to choose whether to participate in the control. The relevant data analysis and electricity cost reduction are conducted only for residents who explicitly agree. Furthermore, the relevant human body sensing data and data on time spent at home are all anonymous data completely unrelated to personal identity.

[0107] This embodiment also provides a computer program product 810, a computer-readable storage medium 820, and a computer device 830. Figure 7 This is a schematic diagram of a computer program product 810 according to an embodiment of the present invention. Figure 8 This is a schematic diagram of a computer-readable storage medium 820 according to an embodiment of the present invention. Figure 9 This is a schematic block diagram of a computer device 830 according to an embodiment of the present invention.

[0108] Computer program product 810 includes computer program 811, which, when executed by processor 831, implements the steps of any of the above-described microgrid control methods based on intelligent data analysis. Computer-readable storage medium 820 stores the aforementioned computer program 811, which, when executed by processor 831, implements the steps of any of the above-described embodiments of the microgrid control method based on intelligent data analysis. Computer device 830 may include memory 832, processor 831, and computer program 811 stored in memory 832 and running on processor 831.

[0109] The computer program 811 used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, status setting data, integrated circuit configuration data, or source code or object code written in any combination of one or more programming languages ​​and procedural programming languages.

[0110] Computer program 811 may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer may be connected to the user's computer via any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, to perform aspects of the invention, electronic circuits including, for example, programmable logic circuits, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs) may execute computer-readable program instructions to personalize the electronic circuits by utilizing state information of computer-readable program instructions.

[0111] For the purposes of this embodiment, computer program product 810 is a related product that includes computer program 811.

[0112] For the purposes of this embodiment, a computer-readable storage medium 820 is a tangible device capable of holding and storing a computer program 811. It can be any device that includes, stores, communicates, propagates, or transmits the computer program 811 for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable storage medium 820 include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable optical disc read-only memory (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanical encoding device, and any suitable combination thereof.

[0113] Therefore, those skilled in the art should recognize that although numerous exemplary embodiments of the present invention have been shown and described in detail herein, many other variations or modifications conforming to the principles of the present invention can be directly determined or derived from the disclosure of the present invention without departing from the spirit and scope of the invention. Thus, the scope of the present invention should be understood and construed as covering all such other variations or modifications.

Claims

1. A microgrid control method based on intelligent data analysis, characterized in that, include: Acquire sensing data from human body sensing devices configured within the community, which is equipped with a microgrid for supplying power to residents; Multiple entrance and exit sensor sets are formed based on the location of the human body sensor, and each entrance and exit sensor set corresponds to one entrance and exit line of the resident. The sensor data of the human body sensors in the same set of entry and exit sensors are organized into a time-series sequence of sensor data; the human body sensors belonging to the same set of entry and exit sensors are used as graph nodes, and the estimated travel time of the resident between adjacent human body sensors is used as edge weights to construct a graph neural network; the time-series sequence of sensor data is organized into a state sequence of each node and input into the graph neural network; the graph neural network is used to perform spatial correlation calculation to predict the resident's entry and exit events; The time period during which a resident is at home is determined based on the time when the resident enters or leaves the home; Collect electricity consumption data for each of the aforementioned households; Extract the household's electricity consumption data and its characteristics during the household's in-house time period; The household electricity consumption characteristics are identified to determine whether the household meets the preset reward conditions; If the reward conditions are met, the household's electricity bill will be reduced based on the electricity consumption data, thereby guiding the household to actively regulate the electricity use of the microgrid.

2. The microgrid control method based on intelligent data analysis according to claim 1, characterized in that, The steps of organizing the time-series of the sensed data into a state sequence for each node include: The presence of missing values ​​in the time series of the sensing data is identified by a pre-trained long short-term memory network model, which is trained using historical records of entry and exit events and the time series of sensing data. If so, fill in the missing values, and organize the time sequence of the sensing data after filling in the missing values ​​into the state sequence according to the node identifier.

3. The microgrid control method based on intelligent data analysis according to claim 1, characterized in that, The steps for extracting the household's electricity consumption data and its characteristics during the household's in-house time period include: The electricity consumption data is time-aligned with the in-house time period to separate the in-house electricity consumption data. The household electricity consumption features are extracted from the household electricity consumption data.

4. The microgrid control method based on intelligent data analysis according to claim 1, characterized in that, The steps for identifying the characteristics of household electricity usage include: The power application data of the microgrid is acquired and the data is split according to the set evaluation cycle. The power application data includes: the amount of electricity purchased from the external public grid, the self-generated power of the power generation equipment configured by the microgrid, and the total power consumption data of the microgrid. The expected electricity consumption characteristics and reward point limits for each evaluation period are generated based on the electricity application data within that evaluation period. Calculate the similarity between the household electricity consumption characteristics and the expected electricity consumption characteristics for each evaluation period within the household time period; Based on the similarity value within the reward score limit, a reward score corresponding to the evaluation period is generated, and the reward score increases accordingly as the similarity increases. The reward points for each evaluation period during the in-home period are accumulated to obtain the cumulative reward points; Residents whose accumulated reward points exceed a preset value are deemed to meet the reward conditions.

5. The microgrid control method based on intelligent data analysis according to claim 4, characterized in that, The steps for reducing the household's electricity bill based on the electricity usage data include: Based on the electricity consumption data, extract the electricity consumption characteristics of the residents during the time they are away from home; A correction factor is generated based on the characteristics of off-site electricity consumption; The accumulated reward score is corrected using the correction factor. The household's electricity bill reduction will be calculated based on the revised accumulated reward points and the original electricity bill within the preset billing cycle.

6. The microgrid control method based on intelligent data analysis according to claim 5, characterized in that, The steps for calculating the household's electricity bill reduction based on the revised accumulated reward points and the original electricity bill within the pre-designed billing cycle include: Calculate the economic benefits of the power generation equipment in the microgrid during the billing cycle; The economic benefits are allocated according to the revised accumulated reward points to obtain the electricity price reduction.

7. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the microgrid control method based on intelligent data analysis as described in any one of claims 1 to 6.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the microgrid control method based on intelligent data analysis as described in any one of claims 1 to 6.

Images