Method and system for autonomously regulating and controlling power consumption of water level monitoring equipment by adopting context awareness

Abstract

The invention relates to the technical field of Internet of Things equipment power consumption management, and particularly discloses a water level monitoring equipment power consumption autonomous regulation and control method and system adopting context awareness. Firstly, multi-source external information is accessed through low power consumption, local historical hydrological data are combined, and a multi-level context sensing layer and a model are constructed; collecting multi-dimensional operation data of the equipment, analyzing a coupling relationship between the multi-dimensional operation data and the situation model, and evaluating a power consumption value to determine a regulation and control level; abstracting a device module as an energy consumption node, constructing a power consumption topology and generating a power consumption reduction scheme group; then building a digital twinborn body, and selecting the optimal toughness index of the simulation evaluation scheme; and finally, deploying an optimal scheme, continuously monitoring an environment and a strategy effect, and performing backtracking iteration when a triggering condition is met, thereby realizing accurate and adaptive regulation and control.

Description

Technical Field

[0001] This invention relates to the field of power consumption management technology for Internet of Things (IoT) devices, specifically to a method and system for autonomous power consumption control of water level monitoring devices that employs context-awareness. Background Technology

[0002] Water level monitoring equipment is a critical infrastructure in hydrological monitoring, flood warning, and water resource management, and is widely deployed in outdoor environments such as rivers, lakes, reservoirs, and coastal areas. This equipment typically relies on batteries supplemented by solar energy for power, and its energy management directly determines the equipment's continuous operating life and the reliability of the entire monitoring network. Against the backdrop of frequent extreme weather events, higher demands are placed on the real-time performance and reliability of water level monitoring, creating a significant contradiction with the limited energy supply available to these devices.

[0003] Currently, power consumption control of water level monitoring equipment mainly relies on the following traditional technologies: First, a fixed-time periodic sampling and sleep mechanism is used, where the device is woken up at a preset time to collect and transmit data, and remains in a low-power sleep state at other times. While simple to implement, this method lacks flexibility and cannot adaptively adjust to actual hydrological conditions. During long dry seasons, this fixed cycle leads to ineffective energy waste; and in emergencies such as torrential rains and floods, insufficient sampling frequency may result in missed critical data, causing early warning failures. Second, trigger-based control based on a single threshold is used, where the device increases its operating frequency when the water level exceeds a preset limit. This method is slow to respond to environmental changes, and threshold settings usually rely on historical experience, making it difficult to cope with complex and ever-changing climate patterns and watershed characteristics.

[0004] In recent years, with the development of IoT technology, some methods have emerged that attempt to optimize power consumption based on environmental parameters. For example, some solutions propose fine-tuning the device's operating mode based on ambient temperature or light intensity. However, most of these methods only consider a few isolated parameters, failing to systematically integrate the macroscopic environmental background, the device's real-time operating status, and long-term hydrological patterns. The lack of a multi-dimensional contextual awareness and decision-making framework results in power consumption strategies often being localized optimizations, unable to achieve optimal global energy allocation while ensuring the reliability of monitoring tasks. Summary of the Invention

[0005] To address the issues of poor flexibility, insufficient environmental adaptability, and lack of forward-looking verification in existing technologies, the present invention aims to provide a method and system for autonomous power consumption control of water level monitoring equipment using context-aware technology. By constructing a multi-level context-aware mechanism, the method dynamically assesses the operational value and environmental risks of the equipment, intelligently constructs the internal power consumption topology of the equipment, and combines digital twin technology to conduct resilience verification of the control scheme, thereby achieving an adaptive balance between power consumption and monitoring performance.

[0006] The specific technical solution of this application is as follows:

[0007] One objective of this invention is to provide a method for autonomous power consumption control of water level monitoring equipment employing context-awareness, comprising:

[0008] S100: Constructs a multi-level context awareness layer, accesses external information sources in a low-power manner, extracts context labels that represent the macro-environmental background, and combines them with local historical hydrological patterns to form a context model.

[0009] S200: Real-time acquisition of multi-dimensional operating status data; based on the coupling relationship between multi-dimensional operating status data and contextual model, perform context-enhanced dynamic power consumption value assessment to determine the power consumption control level that matches the monitoring stage of the device and the environmental risk level.

[0010] S300: Based on the power consumption control level and the current context scenario model, the sensor, processor, communication unit and storage unit are regarded as energy consumption nodes that can be flexibly combined. The power consumption topology of the internal functional modules of the water level monitoring equipment is constructed. According to the differences in the power consumption topology requirements under different scenarios, a group of schemes to reduce power consumption is generated.

[0011] S400: Based on the contextual model and real-time operating data, a digital twin of the water level monitoring equipment is built, a group of power reduction solutions are loaded, and the optimal power reduction solution is determined by quantitatively evaluating the system resilience index of the solution group under risk scenarios.

[0012] S500: Deploy the optimal power reduction scheme to each node in the actual water level monitoring network and continuously monitor environmental changes and policy execution effects. When a change in environmental mode or a decrease in policy performance is detected, it automatically triggers and returns to the execution step S100.

[0013] As a further option of the present invention, the contextual model is: ;in, Modeling functions for the context For contextual models, For contextual labels, H represents local historical hydrological data.

[0014] As a further option of the present invention, in step S100, the contextual modeling formation step includes:

[0015] Contextual labels are constructed based on multi-source external information. It also integrates local historical hydrological data H; where the contextual label is... Where M is the context label dimension, This represents the value of the j-th context label at time t;

[0016] A weighted moving average method is used to smooth the context labels over time in order to extract trend values. ;

[0017] Inferring the current environmental state using hidden Markov models The state space is Environmental conditions The probability of being in each state at the current moment is calculated using a forward-backward algorithm, and the state with the highest probability is selected as the [state name]. ;

[0018] The contextual context model outputs an enhanced state vector containing contextual trends, environmental states, and state confidence. The enhanced state vector output by the contextual context model is as follows: ;in State confidence.

[0019] As a further option of the present invention, in step S200, the context-enhanced power consumption value dynamic assessment includes:

[0020] Based on the enhanced state vector output by the contextual model and the multi-dimensional operating state data of the device, a context-enhanced coupling relationship analysis is performed to form a coupling relationship matrix R;

[0021] The power consumption value index is calculated using the power consumption value function, where the power consumption value function is defined as follows: ;in, The power consumption value index For currently available energy, Total energy capacity Environmental risk level, The urgency of the task is denoted by α, β, and γ, which are weighting coefficients that satisfy the following conditions: ;

[0022] The power consumption control level is determined by comparing the power consumption value index with a preset threshold.

[0023] As a further option of the present invention, the context-enhanced coupling analysis includes:

[0024] context labels With environmental conditions Unified encoding as numerical feature vectors ,in For indicator functions, It is a numerical feature vector. State confidence; numerical feature vector The dimension is M+4;

[0025] For each state indicator Contextual features The correlation coefficient is obtained by using the Pearson correlation coefficient. ;

[0026] form 3D coupling matrix: .

[0027] As a further option of the present invention, the power consumption control level : ;in, and This is the threshold parameter.

[0028] As a further option of the present invention, in step S300, the power consumption topology of the internal functional modules of the constructed water level monitoring device includes:

[0029] The internal functional modules of the device are abstracted into an energy consumption node graph, where the node set includes sensor nodes, processor nodes, communication nodes and storage nodes, and the edge set represents the energy consumption dependency relationship between nodes;

[0030] Define a power consumption topology objective function to minimize total power consumption while satisfying performance constraints. The objective function is: The constraints include: ;in, To minimize total power consumption, As the minimum performance requirement, G is the energy consumption node diagram, i.e. Where V is the set of nodes and E is the set of edges. , , Each node in the node set V represents a node. Related power consumption, performance contribution, and state variables.

[0031] As a further option of the present invention, the generation of the power-reducing scheme group is performed using a greedy algorithm and a constraint solver, specifically including:

[0032] Based on the current power consumption topology, several feasible solutions are randomly generated;

[0033] A greedy search algorithm is used to gradually adjust the node states starting from the initial solution in order to reduce power consumption.

[0034] Verify that each solution satisfies the constraints;

[0035] Generate a set of solutions to reduce power consumption Each plan It corresponds to one topology configuration.

[0036] As a further option of the present invention, in step S400, the system resilience index is quantified by the following formula: ;in, The actual power consumption at time t. This is the nominal power consumption. The attenuation coefficient is... and The simulation start and end times;

[0037] By comparing the resilience indicators of each scheme, the optimal scheme is selected in descending order.

[0038] The second objective of this invention is to provide a context-aware water level monitoring device power consumption autonomous control system, comprising:

[0039] The context awareness and modeling module is used to build a multi-level context awareness layer. It accesses external information sources in a low-power manner, extracts contextual labels that represent the macro-environmental background, and combines them with local historical hydrological patterns to form a contextual model.

[0040] The dynamic assessment and decision-making module is used to collect multi-dimensional operating status data in real time. Based on the coupling relationship between the multi-dimensional operating status data and the contextual model, it performs a context-enhanced dynamic assessment of power consumption value and determines the power consumption control level that matches the monitoring stage of the device and the environmental risk level.

[0041] The power consumption scheme generation module is used to construct the power consumption topology of the internal functional modules of the water level monitoring equipment, based on the power consumption control level and the current context scenario model, treating the sensor, processor, communication unit and storage unit as energy consumption nodes that can be flexibly combined. According to the different power consumption topology requirements under different scenarios, it generates a group of schemes to reduce power consumption.

[0042] The digital twin and optimization module is used to build a digital twin of the water level monitoring equipment based on the contextual model and real-time operating data, load a group of power reduction solutions, and determine the optimal power reduction solution by quantitatively evaluating the system resilience index of the solution group under risk scenarios.

[0043] The strategy execution and feedback module is used to deploy the optimal power reduction scheme to each node in the actual water level monitoring network and continuously monitor environmental changes and strategy execution effects. When a change in environmental mode or a decrease in strategy performance is detected, the context awareness and modeling module is automatically triggered to restart.

[0044] The beneficial effects of this application are as follows:

[0045] This invention constructs a multi-level context-aware layer, systematically integrating macroscopic environmental background with local historical hydrological patterns, breaking through the limitations of traditional methods that rely on only a single or fixed parameter. This method can dynamically capture the temporal changes and spatial characteristics of environmental patterns, realizing a shift from "passive response" to "proactive perception," thus providing a precise and comprehensive contextual understanding foundation for power consumption control.

[0046] By employing a context-enhanced dynamic power consumption value assessment mechanism and dynamic power consumption topology construction theory, decision-making is made by deeply integrating the multi-dimensional operating status of the device with the external environmental background. This not only achieves precise matching between power consumption regulation levels and monitoring tasks and environmental risks, but also enables refined energy consumption management through modular topology optimization, solving the traditional problem of balancing global energy efficiency optimization and task reliability assurance.

[0047] By constructing digital twins of the equipment and quantifying system resilience indicators, this solution verifies and optimizes control strategies in virtual space, ensuring high robustness of the strategies in real, complex environments. Combined with continuous monitoring and closed-loop optimization mechanisms after deployment, the system possesses full lifecycle adaptive capabilities of self-sensing, self-decision-making, self-verification, and self-optimization, significantly improving the continuous working life and overall reliability of the water level monitoring network under extreme conditions. Attached Figure Description

[0048] Figure 1 This is a schematic diagram of the overall process of the autonomous power consumption control method for water level monitoring equipment that adopts context awareness; Figure 2 A detailed flowchart of steps S100 for the autonomous power consumption control method of water level monitoring equipment with context awareness; Figure 3 A detailed flowchart of the S200 steps of the autonomous power consumption control method for water level monitoring equipment using context-aware conditions; Figure 4 A detailed flowchart of the S300 steps for the context-aware autonomous power consumption control method for water level monitoring equipment; Figure 5 A detailed flowchart of the S400 method for autonomous power consumption control of water level monitoring equipment using context-aware conditions; Figure 6A detailed flowchart of the S500 method for autonomous power consumption control of water level monitoring equipment using context-aware conditions. Detailed Implementation

[0049] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0050] As a key component of water conservancy information systems, the autonomous power consumption regulation of water level monitoring equipment directly affects its long-term stable operation in field environments. In complex and ever-changing hydrological environments, power consumption management faces challenges such as dynamically changing environmental contexts, weak correlations in multi-dimensional state data, and poor adaptability of power consumption regulation strategies. This invention is based on four pillars: contextual scenario modeling theory, dynamic power consumption value assessment theory, topology construction theory, and system resilience quantification theory. It achieves accurate extraction of environmental background by constructing a multi-level contextual awareness layer, determines the regulation level using context-enhanced dynamic power consumption value assessment, generates a set of power consumption reduction schemes by combining dynamic power consumption topology construction, and ensures the reliability of regulation by quantifying system resilience indicators through digital twins.

[0051] The core theory is as follows:

[0052] First, the context-aware layer can be modeled as a multi-source information fusion system, and its state representation is as follows: ;in, For context labels, M represents the dimension of the context labels. This represents the value of the j-th context label at time t, such as ambient temperature, rainfall intensity, water level change rate, etc. The contextual model is constructed using historical hydrological patterns and real-time external information sources, and is defined as follows: Where H represents local historical hydrological data; The context modeling function employs a combination of weighted moving average and hidden Markov model to capture the temporal dependence of environmental patterns.

[0053] Secondly, to quantify the value of power consumption regulation, this invention introduces a context-enhanced dynamic evaluation mechanism for power consumption value. Let the multi-dimensional operating status data of the device be... Where N is the number of status indicators, such as battery voltage, CPU utilization, communication load, etc. The power consumption value function is defined as: ;in, The power consumption value index For currently available energy, Total energy capacity Environmental risk level, The urgency of the task is denoted by α, β, and γ, which are weighting coefficients that satisfy the following conditions: .pass The power consumption control level is determined by comparing it with a preset threshold. :

[0054] ;

[0055] in, and The threshold parameter represents the high power consumption mode, the medium power consumption mode, and the low power consumption mode. Level 1 represents the high power consumption mode, Level 2 represents the medium power consumption mode, and Level 3 represents the low power consumption mode.

[0056] Third, to construct the power consumption topology, the internal functional modules of the device are abstracted into an energy consumption node graph. Here, V represents the set of nodes, such as sensors, processors, communication units, and storage units, and E represents the set of edges, indicating the energy consumption dependencies between modules. The goal of power consumption topology construction is to minimize total power consumption. At the same time, performance constraints are met: Where G is the constructed topology, For nodes power consumption, This is a binary variable, where 1 represents active and 0 represents dormant. Constraints include: ;in, For nodes Performance contribution, To meet minimum performance requirements, a set of power-saving solutions is generated using a greedy algorithm and constraint solving. Each of the schemes It corresponds to one topology configuration.

[0057] Finally, to assess the reliability of the solution group, a digital twin T of the equipment was constructed to simulate the behavior of the actual equipment under risk scenarios. System resilience indicators Defined as the ability of equipment to maintain its function under fault or stress conditions, the calculation formula is: ;in, This represents the actual power consumption. This is the nominal power consumption. This is the attenuation coefficient, reflecting the effect of time on toughness. By comparing the various schemes... Choose the optimal solution : This mechanism ensures that the control strategy is highly robust in complex environments.

[0058] The above theoretical framework provides a solid mathematical foundation for this invention, ensuring the accuracy, adaptability, and reliability of autonomous power consumption control. The specific implementation methods of this invention will be described in detail below.

[0059] Example 1;

[0060] Please see Figure 1 This illustrates an embodiment of the present invention providing a method for autonomous power consumption control of a water level monitoring device employing context awareness, the method comprising:

[0061] S100: Construct a multi-level context-aware layer and context model;

[0062] S200: Collects multi-dimensional operating data, assesses power consumption value, and determines control levels;

[0063] S300: Based on the control level, construct the power consumption topology and generate a power reduction scheme group;

[0064] S400: Construct a digital twin to assess resilience and select the optimal power reduction solution;

[0065] S500: Deploy the optimal solution, monitor and adaptively trigger control iterations.

[0066] The specific plan is as follows:

[0067] In a context-aware water level monitoring device power consumption autonomous control method, S100 achieves multi-source information fusion and contextual modeling of the macroscopic environmental background. A multi-level context-aware layer accesses external information sources via a low-power communication protocol and, combined with local historical hydrological patterns, forms a dynamically updated contextual model, providing environmental background support for subsequent power consumption value assessment and topology construction.

[0068] Please refer to Figure 2 The diagram illustrates a flowchart of an exemplary method for autonomous power consumption control of a water level monitoring device using a context-aware approach, S100, which includes:

[0069] S110: Low-power access to multiple external information sources to collect macroscopic environmental data.

[0070] The context-aware layer accesses external information sources via a low-power wide-area network to acquire macroscopic environmental data in real time. These external information sources include meteorological data, hydrological bulletins, topographic maps, and satellite remote sensing images, covering multi-dimensional indicators such as temperature, rainfall, evaporation, water level, and flow rate.

[0071] Specifically, external information access includes: meteorological data collection, hydrological data collection, geographic data collection, and remote sensing data collection.

[0072] In one alternative implementation, external information access employs edge gateway proxy technology, where data preprocessing and compression are performed at the local gateway, and only key feature values ​​are uploaded to reduce communication power consumption.

[0073] S120: Extract contextual tags to form standardized contextual tags.

[0074] Extract contextual labels representing the macro-environmental background from raw external information to form standardized contextual labels. Where M is the context label dimension, This represents the value of the j-th context label at time t.

[0075] In one possible implementation, contextual label extraction includes the following steps:

[0076] 1) Remove outliers and missing values, and use interpolation to complete the data;

[0077] 2) Map the original data to the [0,1] interval to eliminate the influence of dimensions;

[0078] 3) Based on domain knowledge, the continuous values ​​are discretized into situation levels. For example, rainfall intensity is divided into "no rain", "light rain", "moderate rain" and "heavy rain".

[0079] 4) Encode discrete labels into numerical vectors to facilitate model processing.

[0080] S130: Analyze local historical hydrological data to form a local hydrological pattern database.

[0081] By combining historical hydrological data from the equipment deployment sites, we analyze water level change patterns, seasonal characteristics, and the frequency of extreme events to form a local hydrological data database, namely, local historical hydrological data H. Historical hydrological data includes water level time series, flow records, flood events, and drought cycles.

[0082] S140: Constructing a scenario model using weighted moving average and hidden Markov model.

[0083] Context-based tags Construct a contextual model using local historical hydrological data H. The model employs a combination of weighted moving average and hidden Markov model to capture the temporal dependence of environmental patterns.

[0084] In one possible implementation, a contextual model for: ;in, A function for modeling the context.

[0085] Based on the above implementation method, the contextual model is calculated as follows:

[0086] For each context label Time series smoothing is performed, and the trend value is calculated using the weighted moving average method. ;

[0087] By combining local historical hydrological data H, the current environmental state is inferred using a hidden Markov model. The state space is defined as follows: The transition probability matrix is ​​obtained from historical hydrological events. The probability of being in each state at the current moment is calculated using a forward-backward algorithm, and the state with the highest probability is selected as the transition probability matrix. .

[0088] The contextual model outputs an enhanced state vector: ;

[0089] in State confidence.

[0090] In a context-aware method for autonomous power consumption control of water level monitoring equipment, the S200 performs a context-enhanced dynamic assessment of power consumption value based on real-time collected multi-dimensional operating status data and a contextual model. This assessment determines the appropriate power consumption control level that matches the monitoring stage and environmental risk level. This step deeply integrates the equipment's operating status with the environmental background, enabling precise decision-making in power consumption control.

[0091] Please refer to Figure 3 The diagram illustrates a flowchart of an exemplary method for autonomous power consumption control of a water level monitoring device using a context-aware approach, S200, which includes:

[0092] S210: Lightweight acquisition device for the operational status data of each module inside.

[0093] Real-time acquisition of operational status data from each module within the water level monitoring equipment to form a state vector. , where N is the number of status indicators.

[0094] Specifically, multidimensional operational status data includes: energy status data, computing status data, communication status data, and storage status data.

[0095] In one possible implementation, multidimensional operational status data acquisition employs a lightweight agent embedded in the device firmware, operating at a low sampling frequency to reduce its own power consumption.

[0096] S220: Analyze the coupling relationship between the context and the running data to form a coupling relationship matrix.

[0097] Enhanced state vector output from the contextual model built on S140 With equipment multidimensional operating status data , perform context-enhanced coupling analysis to form a coupling matrix R.

[0098] In one possible implementation, coupling analysis includes:

[0099] context labels Discrete environmental states Unified encoding as numerical feature vectors ,in This is an indicator function. The vector has a dimension of M+4.

[0100] For each state indicator Contextual features The correlation coefficient is obtained by using the Pearson correlation coefficient. .

[0101] Final formation 3D coupling matrix: .

[0102] The coupling matrix R quantifies the dynamic correlation strength between the internal operating state of the device and the external environmental context.

[0103] S230: Calculate the power consumption value index by combining the coupling relationship matrix.

[0104] The coupling matrix R is used to calculate the power consumption value index. This reflects the benefit-risk ratio of current power consumption usage. The power consumption value function is defined as: ;in, The power consumption value index For currently available energy, Total energy capacity Environmental risk level, The urgency of the task is denoted by α, β, and γ, which are weighting coefficients that satisfy the following conditions: .

[0105] In one possible implementation, the step of dynamically evaluating the power consumption value using a power consumption value function includes:

[0106] 1) Obtain , , , ;in, and Read from the battery management unit; It is a contextual model Environmental status , mapped to risk value (01); Obtained based on the priority and timing requirements of the monitoring tasks;

[0107] 2) Dynamically adjust α, β, and γ based on the coupling matrix R; for example, increase β when the environmental risk is high.

[0108] 3) Real-time calculation using power consumption value function .

[0109] S240: Compare power consumption value index to determine power consumption control level.

[0110] According to the power consumption value index The power consumption control level is determined by comparing it with a preset threshold. : ;in, and The threshold parameter represents the high power consumption mode, the medium power consumption mode, and the low power consumption mode. Level 1 represents the high power consumption mode, Level 2 represents the medium power consumption mode, and Level 3 represents the low power consumption mode.

[0111] In a context-aware autonomous power consumption control method for water level monitoring equipment, the S300, based on the power consumption control level and the current context model, treats sensors, processors, communication units, and storage units as flexibly combinable energy-consuming nodes, constructs the power consumption topology of the internal functional modules of the equipment, and generates a set of power consumption reduction schemes. This step achieves refined power consumption management through topology optimization.

[0112] Please refer to Figure 4 The diagram illustrates a flowchart of an exemplary method for autonomous power consumption control of a water level monitoring device using a context-aware approach, S300, which includes:

[0113] S310: Abstract the device functional modules into an energy consumption node diagram.

[0114] Abstracting the internal functional modules of the equipment into an energy consumption node diagram Where V is the node set, including sensor nodes, processor nodes, communication nodes, and storage nodes; E is the edge set, representing the energy consumption dependencies between nodes, such as data flow and control flow.

[0115] S320: Defines the power consumption topology objective function and performance constraints.

[0116] Energy consumption node graph of power consumption topology Internal node attribute definition, that is, defining each node in the node set V. Related power consumption Performance contribution State variables ,in, Represents activation. It represents hibernation.

[0117] The goal of power consumption topology is to minimize total power consumption. While satisfying performance constraints, this is based on an energy consumption node graph. The defined objective function is: The constraints include: ;in, The minimum performance requirement is determined by the monitoring task.

[0118] S330: Uses a greedy algorithm to generate a group of power reduction schemes that satisfy the constraints.

[0119] A greedy algorithm and constraint solver are used to generate topology configurations that satisfy the constraints. The algorithm construction considers power consumption control levels. and contextual model To adapt to different environments.

[0120] In one possible implementation, the algorithm construction steps include:

[0121] 1) Based on the current power consumption topology, randomly generate several feasible solutions;

[0122] 2) A greedy search algorithm is used, starting from the initial solution and gradually adjusting the node state to reduce power consumption;

[0123] 3) Verify whether each solution satisfies the constraints;

[0124] 4) Generate a set of solutions to reduce power consumption. Each plan It corresponds to one topology configuration.

[0125] In a context-aware method for autonomous power consumption control of water level monitoring equipment, the S400 constructs a digital twin of the equipment based on a contextual model and real-time operational data. It then loads a group of power-saving solutions and determines the optimal solution by quantitatively evaluating the system resilience of the solution group under risk scenarios. This step achieves controllable verification of the solutions through digital twin technology.

[0126] Please refer to Figure 5 It illustrates a flowchart of an exemplary method for autonomous power consumption control of a water level monitoring device using a context-aware approach, S400, which includes:

[0127] S410: Construct a digital twin based on device parameters and context model.

[0128] A high-fidelity digital twin T is constructed based on the device's physical model, operational logic, and contextual model. The digital twin simulates the dynamic behavior of the actual device, including power consumption, performance, and fault modes.

[0129] In one possible implementation, digital twin construction includes:

[0130] 1) Extract parameters from the actual equipment, such as battery capacity, CPU frequency, and communication protocol;

[0131] 2) Contextual Model Injecting a twin to simulate a real environment;

[0132] 3) By simulating discrete events or using system dynamics models, the operation of equipment is simulated to form a digital twin.

[0133] S420: Load scenario group simulation and collect data under risk scenarios.

[0134] The selected solution group Loaded into a digital twin, the simulation demonstrates the effectiveness of various scenarios under risk conditions, including extreme weather, hardware failures, and network outages. During the simulation, power consumption, performance, and failure events are recorded, and simulation data is collected for resilience index calculation.

[0135] S430: Calculate system resilience index based on simulation data.

[0136] Based on simulation data, calculate each scheme System resilience index This reflects the resilience of a system under pressure. The resilience index is defined as: ;in, The actual power consumption at time t. This is the nominal power consumption. The attenuation coefficient is... and This represents the start and end times of the simulation.

[0137] S440: Compare resilience metrics to determine the optimal power reduction scheme.

[0138] Comparing the resilience indicators of each scheme ,according to Sort the solutions in descending order and select the optimal solution. ,Right now: .

[0139] In a context-aware method for autonomous power consumption control of water level monitoring equipment, step S500 deploys the optimal power reduction scheme to each node in the actual water level monitoring network and continuously monitors environmental changes and the effectiveness of the strategy execution. When a change in the environmental mode or a decrease in strategy effectiveness is detected, step S100 is automatically triggered and returned to the execution step. This step achieves control and long-term adaptation.

[0140] Please refer to Figure 6The diagram illustrates a flowchart of an exemplary method for autonomous power consumption control of a water level monitoring device using a context-aware approach, S500, which includes:

[0141] S510: Transforms the optimal solution into command deployment and monitors execution from multiple dimensions.

[0142] The optimal power reduction solution verified by the digital twin. It is converted into executable instructions and a multi-dimensional monitoring system is established.

[0143] First, the optimal power reduction solution will be... The commands are converted into a set of control instructions that the devices can recognize, including specific operations such as adjusting sensor sampling frequency, switching processor operating modes, reconstructing communication protocol stacks, and updating storage strategies. The deployment process adopts a tiered approach, prioritizing command verification at the edge gateway nodes before distributing them to terminal devices in batches via the LoRaWAN / NBIoT network. To ensure deployment reliability, a digital signature and rollback mechanism are introduced, automatically reverting to the previous stable version when command verification failure is detected.

[0144] At the device level during the policy execution phase, power consumption data of each functional module is collected in real time to obtain actual power saving rates. At the network level during the policy execution phase, link quality index and packet delivery rate are collected through the SDN controller to evaluate the optimal power reduction scheme. Execution Results. At the platform level, during the strategy execution phase, a streaming pipeline was built based on Apache Flink to perform real-time aggregation and analysis of 12 core indicators, including device health, task completion rate, and environmental adaptability. Specifically, for extreme scenarios such as torrential rain and floods, an LSTM-based anomaly detection module was implemented. When the water level change rate exceeds a threshold... When necessary, an emergency sampling mode is automatically triggered to ensure data integrity while maintaining controllable power consumption.

[0145] S520: Multi-condition triggering backtracking enables strategy optimization.

[0146] By constructing a multi-condition triggering mechanism and a knowledge evolution system, the autonomous iterative optimization of the control strategy can be achieved.

[0147] In one possible implementation, a triggering and judgment process based on multi-dimensional perception is established, and the backtracking process is immediately initiated when any of the following conditions are met simultaneously:

[0148] 1) The environmental model has undergone a fundamental shift, manifested in the environmental state within the contextual situation model. transition probability Below the historical mean by 2 standard deviations;

[0149] 2) The effectiveness of the strategy continues to decline, that is, the power saving rate is less than 25% for three consecutive monitoring cycles.

[0150] When the triggering condition is met, the system automatically reverts to S100 for reinitialization.

[0151] This invention has been fully validated in the Yangtze River Basin water level monitoring network, which includes 200 monitoring nodes, and the monitoring indicators include water level, flow rate, rainfall, and temperature. The specific configuration adopted during implementation is as follows:

[0152] Context-aware layer: Accesses publicly available data from the China Meteorological Administration and the Ministry of Water Resources, uses LoRaW for transmission, and samples at a frequency of 1 time per minute;

[0153] Data processing layer: Configure edge servers, perform context modeling and value assessment, using Python and TensorFlow Lite;

[0154] Digital twin layer: The twin is built based on AWS IoT Greengrass, and the simulation software is AnyLogic;

[0155] Policy execution layer: Integrates Huawei OceanConnect IoT platform, supporting remote deployment and monitoring.

[0156] During the testing phase, 10 risk scenarios, including heavy rain, drought, and equipment failure, were simulated, with each scenario repeated 15 times. Test results showed that:

[0157] The average power saving rate is 35.7%, and up to 50% in low-risk scenarios;

[0158] The system's resilience index improved by 42.3%, and the equipment's continuous operating time in extreme environments increased by 60%.

[0159] The average response time for regulatory decisions is 8 seconds, which meets the real-time requirements;

[0160] The adaptive mechanism reduces long-term operation and maintenance costs by 28%.

[0161] Specifically, in a real-world rainstorm event, this invention successfully predicted the rising water level and switched to a low-power mode in advance, extending battery life by 72 hours and preventing data loss. Digital twin assessment showed a system resilience index of 0.89 with a confidence level of 96.8%, verifying the reliability of the control system.

[0162] Example 2;

[0163] A context-aware water level monitoring device power consumption autonomous control system includes:

[0164] The context awareness and modeling module is used to build a multi-level context awareness layer. It accesses external information sources in a low-power manner, extracts contextual labels that represent the macro-environmental background, and combines them with local historical hydrological patterns to form a contextual model.

[0165] The dynamic assessment and decision-making module is used to collect multi-dimensional operating status data in real time. Based on the coupling relationship between the multi-dimensional operating status data and the contextual model, it performs a context-enhanced dynamic assessment of power consumption value and determines the power consumption control level that matches the monitoring stage of the device and the environmental risk level.

[0166] The power consumption scheme generation module is used to construct the power consumption topology of the internal functional modules of the water level monitoring equipment, based on the power consumption control level and the current context scenario model, treating the sensor, processor, communication unit and storage unit as energy consumption nodes that can be flexibly combined. According to the different power consumption topology requirements under different scenarios, it generates a group of schemes to reduce power consumption.

[0167] The digital twin and optimization module is used to build a digital twin of the water level monitoring equipment based on the contextual model and real-time operating data, load a group of power reduction solutions, and determine the optimal power reduction solution by quantitatively evaluating the system resilience index of the solution group under risk scenarios.

[0168] The strategy execution and feedback module is used to deploy the optimal power reduction scheme to each node in the actual water level monitoring network and continuously monitor environmental changes and strategy execution effects. When a change in environmental mode or a decrease in strategy performance is detected, the context awareness and modeling module is automatically triggered to restart.

[0169] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0170] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0171] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for autonomous power consumption control of water level monitoring equipment with context awareness, characterized in that: include: S100: Constructs a multi-level context awareness layer, accesses external information sources in a low-power manner, extracts context labels that represent the macro-environmental background, and combines them with local historical hydrological patterns to form a context model. S200: Real-time acquisition of multi-dimensional operating status data; based on the coupling relationship between multi-dimensional operating status data and contextual model, perform context-enhanced dynamic power consumption value assessment to determine the power consumption control level that matches the monitoring stage of the device and the environmental risk level. S300: Based on the power consumption control level and the current context scenario model, the sensor, processor, communication unit and storage unit are regarded as energy consumption nodes that can be flexibly combined. The power consumption topology of the internal functional modules of the water level monitoring equipment is constructed. According to the differences in the power consumption topology requirements under different scenarios, a group of schemes to reduce power consumption is generated. S400: Based on the contextual model and real-time operating data, a digital twin of the water level monitoring equipment is built, a group of power reduction solutions are loaded, and the optimal power reduction solution is determined by quantitatively evaluating the system resilience index of the solution group under risk scenarios. S500: Deploy the optimal power reduction scheme to each node in the actual water level monitoring network and continuously monitor environmental changes and policy execution effects. When a change in environmental mode or a decrease in policy performance is detected, it automatically triggers and returns to the execution step S100.

2. The method for autonomous power consumption control of water level monitoring equipment using context-awareness as described in claim 1, characterized in that, In step S100, the contextual model is: ;in, Modeling functions for the context For contextual models, For contextual labels, H represents local historical hydrological data.

3. The method for autonomous power consumption control of water level monitoring equipment using context-awareness as described in claim 2, characterized in that, In step S100, the contextual modeling formation step includes: Contextual labels are constructed based on multi-source external information. It also integrates local historical hydrological data H; where the contextual label is... Where M is the context label dimension, This represents the value of the j-th context label at time t; A weighted moving average method is used to smooth the context labels over time in order to extract trend values. ; Inferring the current environmental state using hidden Markov models The state space is Environmental conditions The probability of being in each state at the current moment is calculated using a forward-backward algorithm, and the state with the highest probability is selected as the [state name]. ; The contextual context model outputs an enhanced state vector containing contextual trends, environmental states, and state confidence. The enhanced state vector output by the contextual context model is as follows: ;in State confidence.

4. The method for autonomous power consumption control of water level monitoring equipment using context-awareness as described in claim 1, characterized in that, In step S200, the context-enhanced power consumption value dynamic assessment includes: Based on the enhanced state vector output by the contextual model and the multi-dimensional operating state data of the device, a context-enhanced coupling relationship analysis is performed to form a coupling relationship matrix R; The power consumption value index is calculated using the power consumption value function, where the power consumption value function is defined as follows: ;in, The power consumption value index For currently available energy, Total energy capacity Environmental risk level, Let α, β, and γ represent the task urgency, and let them be weighting coefficients, satisfying the following condition: ; The power consumption control level is determined by comparing the power consumption value index with a preset threshold.

5. The method for autonomous power consumption control of water level monitoring equipment using context-awareness as described in claim 4, characterized in that, The context-enhanced coupling analysis includes: context labels With environmental conditions Unified encoding as numerical feature vectors ,in For indicator functions, It is a numerical feature vector. State confidence; numerical feature vector The dimension is M+4; For each state indicator Contextual features The correlation coefficient is obtained by using the Pearson correlation coefficient. ; form 3D coupling matrix: .

6. The method for autonomous power consumption control of water level monitoring equipment using context-awareness as described in claim 4, characterized in that, The power consumption control level : ;in, and This is the threshold parameter.

7. The method for autonomous power consumption control of water level monitoring equipment using context-awareness as described in claim 1, characterized in that, In step S300, the power consumption topology of the internal functional modules of the constructed water level monitoring device includes: The internal functional modules of the device are abstracted into an energy consumption node graph, where the node set includes sensor nodes, processor nodes, communication nodes and storage nodes, and the edge set represents the energy consumption dependency relationship between nodes; Define a power consumption topology objective function to minimize total power consumption while satisfying performance constraints. The objective function is: The constraints include: ;in, To minimize total power consumption, As the minimum performance requirement, G is the energy consumption node diagram, i.e. Where V is the set of nodes and E is the set of edges. , , Each node in the node set V represents a node. Related power consumption, performance contribution, and state variables.

8. The method for autonomous power consumption control of water level monitoring equipment using context-awareness as described in claim 7, characterized in that, In step S300, the generation of the power-reducing scheme group is performed using a greedy algorithm and a constraint solver, specifically including: Based on the current power consumption topology, several feasible solutions are randomly generated; A greedy search algorithm is used to gradually adjust the node states starting from the initial solution in order to reduce power consumption. Verify that each solution satisfies the constraints; Generate a set of solutions to reduce power consumption Each plan It corresponds to one topology configuration.

9. The method for autonomous power consumption control of water level monitoring equipment using context-awareness as described in claim 1, characterized in that, In step S400, the system resilience index is quantified using the following formula: ;in, The actual power consumption at time t. This is the nominal power consumption. The attenuation coefficient is... and The simulation start and end times; By comparing the resilience indicators of each scheme, the optimal scheme is selected in descending order.

10. A control system employing a context-aware autonomous power consumption control method for water level monitoring equipment according to any one of claims 1-9, characterized in that, include: The context awareness and modeling module is used to build a multi-level context awareness layer. It accesses external information sources in a low-power manner, extracts contextual labels that represent the macro-environmental background, and combines them with local historical hydrological patterns to form a contextual model. The dynamic assessment and decision-making module is used to collect multi-dimensional operating status data in real time. Based on the coupling relationship between the multi-dimensional operating status data and the contextual model, it performs a context-enhanced dynamic assessment of power consumption value and determines the power consumption control level that matches the monitoring stage of the device and the environmental risk level. The power consumption scheme generation module is used to construct the power consumption topology of the internal functional modules of the water level monitoring equipment, based on the power consumption control level and the current context scenario model, treating the sensor, processor, communication unit and storage unit as energy consumption nodes that can be flexibly combined. According to the different power consumption topology requirements under different scenarios, it generates a group of schemes to reduce power consumption. The digital twin and optimization module is used to build a digital twin of the water level monitoring equipment based on the contextual model and real-time operating data, load a group of power reduction solutions, and determine the optimal power reduction solution by quantitatively evaluating the system resilience index of the solution group under risk scenarios. The strategy execution and feedback module is used to deploy the optimal power reduction scheme to each node in the actual water level monitoring network and continuously monitor environmental changes and strategy execution effects. When a change in environmental mode or a decrease in strategy performance is detected, the context awareness and modeling module is automatically triggered to restart.

Images