Energy-saving mode optimization method for outdoor energy storage power supply

Abstract

The invention relates to the field of intelligent energy management, and discloses an energy-saving mode optimization method for an outdoor energy storage power supply, which comprises the following steps of: acquiring instantaneous current, voltage and power data of access equipment, and constructing a power consumption characteristic model of the equipment in combination with historical power consumption data; external environment parameters including temperature, humidity, illumination intensity, air pressure and wind speed are collected, environment data are subjected to fusion processing, and an environment change model is constructed; on the basis of the power consumption characteristic model and the environment change model, predicting a future equipment power demand through an AI algorithm, and calculating optimal output power; the output current and voltage of the energy storage power supply are dynamically adjusted according to the priority of the equipment, and meanwhile, a low-power-consumption standby strategy is executed on non-key equipment. Through a dynamic power distribution and environment adaptation mechanism, efficient energy utilization and equipment power supply stability are realized, and the operation efficiency and reliability of the energy storage power supply in a complex environment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent energy management, and in particular to a method for optimizing an energy-saving mode of an outdoor energy storage power supply. Background Art

[0002] With the growing demand for outdoor activities, energy storage power supplies play an indispensable role in emergency rescue, outdoor adventure, mobile office and other scenarios. The complexity of the outdoor environment places higher demands on the continuous power supply capability of the equipment. The energy storage power supply not only needs to provide efficient energy support, but also needs to maintain stable operation under dynamic conditions of multiple devices and multiple environments. Therefore, an optimization method for intelligent and energy-saving energy storage power supplies can adapt to complex scene requirements through precise power distribution and dynamic adjustment, providing users with more reliable outdoor power protection.

[0003] In the prior art, outdoor energy storage power supplies mainly manage power through fixed output power or simple preset modes. This type of technical solution shows certain stability and reliability in a single-device, low-dynamic change environment. For example, by presetting the power parameters of the device, it can ensure that the basic power supply needs are met while avoiding the waste of system resources caused by complex calculations. In addition, some energy storage power supplies have also introduced basic environmental monitoring functions, which can provide simple alarm information under extreme conditions, improving the user experience of the device in conventional scenarios.

[0004] However, existing technical solutions have exposed obvious shortcomings when facing dynamic multi-device power supply needs and complex external environments, mainly including the following problems: First, the fixed power allocation strategy cannot be dynamically adjusted according to real-time needs, which may easily cause key equipment to stop running due to insufficient power, while non-key equipment takes up too much power, resulting in low energy utilization efficiency; second, existing technologies are difficult to adapt to drastic changes in environmental parameters. For example, when the temperature drops suddenly or the light is insufficient, the lack of automatic power adjustment ability leads to unstable equipment operation; third, traditional energy storage power supplies fail to accurately predict the power demand of equipment, ignore the historical laws and periodic characteristics of equipment power consumption, and fail to reasonably plan energy allocation; fourth, when multiple devices are connected, the device priority cannot be distinguished, and the stable operation of high-priority devices cannot be guaranteed when energy is tight. Summary of the invention

[0005] In view of the deficiencies of the prior art, the present invention provides a method for optimizing the energy-saving mode of an outdoor energy storage power supply, which solves the problem in the prior art that the energy storage power supply cannot dynamically adjust power distribution according to the real-time power demand of the equipment and changes in the external environment.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for optimizing the energy-saving mode of an outdoor energy storage power supply, comprising the following steps: Collect instantaneous current, voltage and power data of connected devices, and build a power consumption characteristic model of the devices in combination with historical power consumption data; collect external environmental parameters, including temperature, humidity, light intensity, air pressure and wind speed, fuse and process environmental data and build an environmental change model; Based on the power consumption characteristic model and environmental change model, the AI ​​algorithm is used to predict the future power demand of the equipment and calculate the optimal output power; Dynamically adjust the output current and voltage of the energy storage power supply according to the device priority, and implement a low-power standby strategy for non-critical devices; When external environmental parameters change, the dynamic adaptation mechanism is triggered to adjust the power allocation strategy to ensure stable operation of the equipment.

[0007] Preferably, the construction of the power consumption characteristic model includes: Use the sliding window algorithm to analyze the power consumption data in segments and extract the periodic characteristics of device power consumption; Use long short-term memory networks to perform time series modeling on power consumption data and predict future power consumption trends of devices; The prediction accuracy of the power consumption model is optimized by combining the classification labels of the devices.

[0008] Preferably, the construction of the environmental change model includes: The Kalman filter algorithm is used to filter and fuse the data collected by multi-modal sensors; Analyze the relationship between ambient temperature and humidity, light intensity, air pressure and wind speed and power demand, and establish mapping rules between environmental changes and power demand; Detect sudden changes in environmental parameters and trigger anomaly detection mechanisms.

[0009] Preferably, the step of predicting future device power requirements through an AI algorithm based on the power consumption characteristic model and the environment change model and calculating the optimal output power includes: Calculate output current and voltage based on power demand predicted by the power consumption characteristic model; Set dynamic adjustment thresholds. When the actual power demand deviates from the predicted value by more than the preset range, the power adjustment mechanism is triggered. Prioritize the power supply of key equipment and take measures such as delayed power supply or power restriction for non-key equipment. The device enters low-power standby mode when not in use for a long period of time.

[0010] Preferably, the dynamic adaptation mechanism includes: When the ambient temperature is lower than the preset threshold, the output current is adjusted to meet the power demand of the device when it starts; When the ambient temperature is higher than the preset threshold, the power output of non-critical equipment is reduced to protect the safety of the energy storage power supply; When the light intensity is lower than the preset value, the power supply to low-priority devices is reduced to ensure the stable operation of high-priority devices.

[0011] Preferably, the step of outputting current and voltage of the energy storage power supply includes: Prioritize power allocation to key equipment to ensure its normal operation; When the total power demand of the equipment exceeds the power output capacity, the power allocation of non-critical equipment is automatically reduced; The output voltage and current are adjusted in real time according to the changes in the actual power demand of the equipment to avoid energy waste.

[0012] Preferably, the step of executing the low power standby strategy for non-critical devices includes: Detect the operating status of non-critical equipment and reduce the output power to the standby level when the non-critical equipment has not been used for a long time; When non-critical equipment restarts, the system automatically resumes normal power output; Monitor device state changes during standby to ensure low-power modes do not affect the device's basic functionality.

[0013] Preferably, the step of adjusting the power allocation strategy includes: When a dramatic change in ambient temperature, light intensity, or other external parameters is detected, the power allocation scheme of the device is recalculated; Prioritize the allocation of stable power to devices that are sensitive to environmental changes to reduce equipment failures caused by environmental fluctuations; Dynamically adjust the output power according to the trend of environmental changes to optimize the energy utilization efficiency of the power supply.

[0014] Preferably, the step of predicting future equipment power requirements by using an AI algorithm includes: Analyze historical power consumption data, extract the periodic power consumption patterns of equipment, and establish a power consumption change prediction model; Combine real-time collected data and equipment classification labels to optimize the prediction accuracy of power demand; Adjust the power output curve of the energy storage power source based on the prediction results to reduce unnecessary power loss.

[0015] Preferably, the step of calculating the optimal output power comprises: Set the upper and lower limits of output power based on the matching of the actual power consumption requirements of the equipment with the power prediction model; For scenarios with multiple devices connected, the total output power is calculated based on device priority and power demand allocation ratio; By monitoring the fluctuations in equipment power demand in real time, the output power can be adjusted dynamically to ensure efficient use of energy.

[0016] The present invention provides an energy-saving mode optimization method for an outdoor energy storage power supply, which has the following beneficial effects: 1. The present invention adopts a technical solution based on the power consumption characteristic model and the environmental change model combined with the AI ​​algorithm, achieving the technical effect of accurately predicting the power demand of the equipment and dynamically adjusting the output power. Compared with the technical solution that only relies on fixed power allocation in the prior art, it solves the problems of inaccurate power allocation and energy waste in a dynamic environment, and at the same time improves the continuity and stability of equipment operation.

[0017] 2. The present invention achieves the technical effect of giving priority to the stable operation of key devices through the technical solution of device priority management and low-power standby strategy for non-key devices. Compared with the method of evenly distributing power to all devices in the prior art, it avoids the sudden power failure of devices when the power supply is tight, further prolongs the battery life, and is particularly suitable for complex scenarios where multiple devices are powered at the same time.

[0018] 3. The present invention adopts the technical solution of real-time collection and dynamic adaptation mechanism of external environmental parameters, achieving the technical effect of intelligently adjusting the power allocation strategy according to external conditions. It is difficult to cope with the impact of environmental changes on the power supply demand of equipment in the prior art. The present invention effectively solves the problem of power supply abnormality caused by drastic environmental changes, significantly enhances the adaptability and reliability of energy storage power supply, and is particularly suitable for the power supply demand of equipment under extreme climatic conditions.

[0019] 4. The present invention achieves the technical effect of comprehensively improving the utilization efficiency of energy storage power sources through a dynamic power allocation model optimized by multiple objectives and combined with the predictive capability of a deep learning algorithm. Compared with the rough calculation method of power demand in the prior art, the present invention solves the problems of low power allocation efficiency and slow response speed, further optimizes the energy management level of energy storage equipment, and provides important technical guarantees for efficient energy saving. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a flow chart of the method of the present invention; DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Please see attached Figure 1 The embodiment of the present invention provides a method for optimizing an energy-saving mode of an outdoor energy storage power supply, comprising the following steps: S1. Collect instantaneous power data of connected devices and build a power consumption characteristic model: collect instantaneous current, voltage and power data of connected devices, and build a power consumption characteristic model of the devices in combination with historical power consumption data; Generally speaking, in outdoor energy storage equipment, the power consumption characteristics of the access equipment have obvious dynamic changes, and its power demand will fluctuate with time, equipment usage status and changes in the external environment. In order to realize the intelligent management of energy storage power supplies, the first step is to accurately grasp the power consumption characteristics of the access equipment. Therefore, this step collects the instantaneous current, voltage and power data of the access equipment, and combines it with the historical power consumption data to build a power consumption characteristic model of the equipment. This provides accurate data support for subsequent power regulation and dynamic adaptation mechanisms. Specifically, the construction of the power consumption characteristic model runs through the entire system operation process, and its accuracy directly determines the effect of the energy storage power supply optimization method.

[0023] In this embodiment, a technical solution combining real-time acquisition and offline modeling is adopted. Through the built-in power sensor, the system collects the instantaneous current I of the connected device in real time. t , voltage V t and power P t Among them, the instantaneous power P t The calculation formula is: P t =V t ×I t In the formula, V t Indicates the instantaneous voltage at the device access terminal, in volts (V); I t is the instantaneous current, in ampere (A); P t Indicates the instantaneous power of the device in watts (W). The time interval for data collection can be flexibly set according to the actual scenario requirements, such as 1 second or shorter, to ensure the real-time nature of the data.

[0024] In some embodiments, a sliding window algorithm is used to perform segmented analysis on the real-time collected data to extract the periodic power consumption characteristics of the device. Specifically, the sliding window size can be set to a dynamic time range between 5 minutes and 15 minutes, and gradually slide to update the real-time power consumption characteristics. The features extracted by the sliding window include but are not limited to: Maximum power consumption P max Minimum power consumption P min Average power consumption Power consumption fluctuation range ΔP=P max -P min .

[0025] As an option, in order to avoid the influence of noise data on the power consumption model, a low-pass filtering algorithm is used to pre-process the collected current and voltage data. Specifically, the cutoff frequency of the low-pass filter is set to the maximum frequency of the device power change, filtering out high-frequency noise while retaining the main characteristic signal of the power change.

[0026] In one implementation, in order to achieve regular modeling of device power consumption, the system introduces a long short-term memory network (LSTM) to model time series data. LSTM can effectively capture the time dependency in power consumption data, and is particularly suitable for modeling nonlinear and periodic power consumption characteristics. The input of the LSTM model is the power consumption data sequence {P t ,P t-1 ,…,P t-n}, the output is the power demand forecast for a period of time in the future Where n is the historical time step used by the model and k is the predicted time step.

[0027] In some embodiments, in order to further improve the prediction accuracy of the power consumption model, the system introduces device classification labels when training the LSTM model. For example, communication devices (such as mobile phones) usually exhibit low-power, stable power consumption characteristics; while thermal devices (such as portable heaters) exhibit high-power, periodically fluctuating power consumption characteristics. By classifying and training data from different device categories, the LSTM model can more accurately adapt to the power consumption patterns of various types of devices.

[0028] In addition, the training data of the power consumption model includes not only the data collected in real time, but also the historical power consumption data of the device. These historical data are stored in the local storage unit of the system or in the cloud database and can be used for offline model training. In general, historical data includes information such as the daily average power consumption curve of the device, the time distribution of power peak and trough values. For example, by analyzing the power consumption data of a device in the past 7 days, it can be found that its high power consumption range is from 8 pm to 11 pm every day. This regular information can significantly improve the predictive ability of the power consumption model.

[0029] As an extended technical solution, the system also introduces data enhancement technology in the modeling process. Specifically, more training samples are generated by randomly perturbing the original collected data. This method can enhance the adaptability of the power consumption model to non-ideal working conditions, such as sudden increases or decreases in the power demand of the device.

[0030] In practical applications, the power consumption characteristic model not only supports the power consumption prediction of a single device, but also supports the power demand analysis of multiple devices. For example, when the energy storage power supply is simultaneously powering a mobile phone, lighting equipment, and heater, the power consumption model can predict the power demand of each device separately, and then calculate the total power demand by superposition.total The calculation formula is: Among them, P i represents the power requirement of the ith device, and N is the total number of connected devices.

[0031] Specifically, when the power demand of the device suddenly increases, the present invention can predict in advance and quickly increase the output power to avoid device shutdown due to insufficient power. In addition, the model also provides support for low-power standby strategies. When the power consumption of the device is below a certain threshold for a long time, it can automatically enter standby mode to save power.

[0032] S2. Collect environmental parameters and build an environmental change model: Collect external environmental parameters, including temperature, humidity, light intensity, air pressure and wind speed, fuse the environmental data and build an environmental change model; In general, the operating performance of outdoor energy storage power supplies is significantly affected by external environmental conditions. For example, extremely high temperatures can easily cause the battery to overheat, thereby shortening its service life, while low temperature environments can easily increase the startup power consumption of the device or cause unstable operation. At the same time, changes in lighting conditions, air pressure, and wind speed will also have a multi-dimensional dynamic impact on the power output and operating efficiency of the device. Therefore, collecting external environmental parameters and fusing them to construct an environmental change model is an important basic part of the energy-saving mode optimization of the present invention.

[0033] In this embodiment, a multimodal sensor array is used to collect environmental parameters, including temperature, humidity, light intensity, air pressure and wind speed. The system uses standardized data fusion technology and multidimensional modeling methods to accurately describe the regularity and sudden characteristics of environmental changes, providing a basis for subsequent power regulation and dynamic adaptation mechanisms.

[0034] The temperature and humidity sensor uses a digital sensor with a measurement range of -40℃ to 80℃ and a humidity range of 0% to 100%. 2 C bus communicates with the main control unit and collects data once per second.

[0035] Photoresistors are used to detect light intensity and output the current light value (in lux) through analog signals. Photoresistors have a fast response time and are suitable for real-time detection of light changes.

[0036] The air pressure sensor is used to measure air pressure. Its measuring range is 300 to 1100hPa and its output accuracy reaches ±1hPa.

[0037] Wind speed sensors measure wind speed changes through the Hall effect or ultrasonic waves, with a measurement range of 0 to 30 m / s.

[0038] As an option, filtering is added to the acquisition process to ensure the accuracy of sensor data. Specifically, the Kalman filter algorithm is used to dynamically fuse environmental parameters to effectively remove data errors caused by instantaneous fluctuations or sensor noise. For example, when wind speed fluctuates violently in a short period of time, the Kalman filter algorithm can smooth these data and retain long-term stable trend information.

[0039] In one implementation, the construction of the environmental change model is based on multidimensional time series analysis. By analyzing the historical data and real-time data of each environmental parameter, its change law is extracted and a prediction model is established. The core of the environmental change model is the dynamic correlation between environmental parameters. For example There is a strong nonlinear correlation between temperature and humidity. When the humidity increases, the response speed of temperature changes tends to slow down.

[0040] Changes in light intensity and air pressure also show a certain correlation under certain weather conditions. For example, when air pressure drops rapidly, light intensity often decreases. In order to describe this correlation, the system uses a linear regression model combined with principal component analysis (PCA) to reduce the dimension and extract features of environmental parameters. The linear regression formula is as follows: y=β0+β1x1+β2x2+…+β n x n Among them, y represents the target variable; x1, x2, …, x n Respectively represent the environmental parameters; β0, β1,…, β n is the model coefficient; In some embodiments, in order to handle complex nonlinear relationships, the system introduces the support vector regression (SVR) method to build a prediction model. SVR maps the input space to a high-dimensional feature space through a kernel function to capture the implicit relationship between environmental parameters and power demand. For example, when the wind speed increases suddenly, the SVR model can predict that the output power needs to be reduced to ensure stable operation of the equipment.

[0041] Specifically, the application scenarios of environmental change models include: Under conditions of rapid air pressure drops, the system proactively reduces power supply to non-critical equipment by predicting based on the model that the cooling demand of the power supply will increase.

[0042] When the light intensity is lower than 100 lux, the environmental model triggers a policy adjustment to give priority to powering lighting and communication equipment.

[0043] In extreme weather with wind speeds exceeding 20m / s, the environmental model combines the historical patterns of wind speed and air pressure changes to predict that the stability of equipment operation is easily affected, thereby issuing early warning signals.

[0044] This embodiment also supports the dynamic update function of the environmental change model. In general, environmental parameters have strong spatiotemporal dependence, and this dependence will change with the change of seasons or geographical location. To adapt to this dynamic characteristic, the environmental change model is retrained every 24 hours. The training data includes the latest collected data from the sensor and the operation feedback data of the equipment. For example, in the northern winter and the southern summer, the power demand of the equipment under the same temperature and humidity conditions will be significantly different. By dynamically updating the model, these regional characteristics can be included in the modeling scope.

[0045] In practical applications, the environmental change model can serve the power regulation of both single and multiple devices. For example, when the system detects that changes in temperature and humidity will cause the internal resistance of the battery to increase, the model will prioritize powering key devices while reducing the power allocation of low-priority devices.

[0046] S3. Predict device power demand and calculate optimal output power: Based on the power consumption characteristic model and environmental change model, the AI ​​algorithm is used to predict future device power demand and calculate the optimal output power. In general, the power demand of outdoor energy storage power supplies not only depends on the historical power consumption characteristics of the connected equipment, but is also dynamically affected by external environmental conditions. During the operation of the equipment, the power demand often presents complex nonlinear changes. Therefore, combining the power consumption characteristic model and the environmental change model, predicting future power demand and calculating the optimal output power through AI algorithms is an important part of realizing intelligent management of energy storage power supplies. This technical solution aims to dynamically respond to fluctuations in power demand and ensure efficient and stable operation of energy storage power supplies.

[0047] In this embodiment, through the collaborative calculation of the power consumption characteristic model and the environmental change model, a deep learning algorithm is used to achieve accurate prediction of future power demand, and the optimal output power is calculated in combination with an optimization strategy.

[0048] Specifically, the power consumption characteristic model provides the historical power demand trend of the device, and the environmental change model provides the parameters of the impact of the external environment on the operation of the device. The combination of the two forms a multivariate input for power prediction of the deep learning algorithm.

[0049] In some embodiments, the power prediction model uses a long short-term memory network (LSTM). The LSTM model is suitable for processing time series data and can capture the dynamic relationship between power consumption characteristics and environmental changes. The input data includes: The historical power data series of the equipment {P t-1 ,P t-2 ,…,P t-n}, where n is the historical time step; Current environment parameter data set {T t ,Ht ,L t ,G t ,W t},in: T t Indicates the current temperature (unit: °C); H t Indicates the current humidity (unit: %); L t Indicates the current light intensity (unit: lux); G t Indicates the current air pressure (unit: hPa); W t Indicates the current wind speed (unit: m / s).

[0050] The output of the model is the predicted value of the equipment power demand at the future time Where k is the prediction time step.

[0051] As an option, in order to improve the accuracy of the prediction model, the input data is normalized before entering the LSTM network. The normalization formula is: Among them, x i is the original data, μ is the mean of the data, σ is the standard deviation of the data, x i ′ is the standardized data.

[0052] In one implementation, the LSTM model contains a multi-layer structure, each layer contains a number of memory cells. The model optimizes the network weights through the error back propagation algorithm to minimize the error between the predicted results and the actual power demand. The optimization objective function uses the mean square error (MSE), and the formula is: in, is the predicted value, P i is the true value, and N is the number of samples.

[0053] In another embodiment, to further optimize the accuracy of power prediction, the model introduces equipment classification labels. Classification labels such as "lighting equipment" and "communication equipment" are used as auxiliary inputs to guide the model to distinguish the power demand characteristics of different equipment. For example, lighting equipment usually exhibits periodic changes, while communication equipment mainly operates stably with low power consumption. The introduction of classification labels can significantly improve the pertinence of predictions.

[0054] After the power prediction is completed, the calculation of the optimal output power depends on the multi-objective optimization method. The optimization objectives include: Maximize the satisfaction rate of equipment power requirements; Minimize battery energy consumption; Maintain the stability of system operation.

[0055] Specifically, the optimal output power P out The calculation formula is: Among them, w i is the weight coefficient of the ith device, is the power demand forecast for the device. The weight coefficient is assigned based on the device priority. For example, the weight coefficient of emergency communication equipment is set to a higher value, while the weight coefficient of non-essential equipment is relatively low.

[0056] As an extended technical solution, the weight coefficient w i The allocation can be adjusted dynamically based on real-time feedback. For example, when it is detected that the power consumption fluctuation range of a device has increased significantly, the system automatically increases its weight coefficient to ensure that its power demand is met first.

[0057] In some embodiments, the power optimization algorithm also takes into account the current state of the battery and environmental conditions. For example, when the remaining battery power is low, the system will reduce the power allocation of low-priority devices and extend the power supply time of high-priority devices.

[0058] In addition, to cope with the scenario of multiple device access, the calculation of the optimal output power also needs to consider the power allocation ratio between devices. Assuming there are N access devices, the system calculates the total output power P according to their power requirements and weight coefficients. total , the formula is: Then, P total Allocate to each device to ensure that the actual power demand of each device is met.

[0059] S4. Dynamically adjust output power according to device priority: Dynamically adjust the output current and voltage of the energy storage power supply according to device priority, and implement a low-power standby strategy for non-critical devices; In general, outdoor energy storage power supplies need to provide power to multiple devices at the same time, and the power requirements and priorities of different devices often vary significantly. For example, emergency communication equipment and medical equipment usually need to prioritize stable power supply, while portable fans or other non-critical devices can reduce power supply when power is insufficient. To this end, the present invention proposes a method for dynamically adjusting the output current and voltage of an energy storage power supply according to device priority, which optimizes energy utilization efficiency by flexibly allocating power resources, and implements a low-power standby strategy for non-critical devices to extend the overall battery life.

[0060] In this embodiment, the energy storage power supply dynamically adjusts the output current and voltage by analyzing the device priority and power demand to meet the actual operation requirements of different devices. The system assigns priority based on the importance of the device and determines the output parameters based on the real-time power demand.

[0061] Specifically, each access device is assigned a priority coefficient w i , with values ​​typically ranging from 0 to 1. The priority of a device is determined by the importance of its function, its power stability requirements, and its current power state. For example, emergency communication devices may be assigned a higher priority coefficient, while non-essential devices such as portable fans may have lower priority coefficients. In some embodiments, the priority coefficients may be dynamically adjusted based on user settings.

[0062] In practical applications, in order to achieve dynamic power regulation, the system needs to calculate the output current and voltage of each device in real time. Output current I out The calculation formula is: Among them, V out The output voltage of the energy storage power supply can be dynamically adjusted according to the voltage requirements of the device, usually in the range of 5V to 24V.

[0063] As an option, when the total power demand of the equipment exceeds the output capacity of the energy storage power supply, the system will automatically reduce the power allocation of non-critical equipment. Specific operations include reducing its output current or directly putting it into standby mode. In one implementation, the system determines whether it needs to enter low-power standby mode by monitoring the operating status of each device in real time.

[0064] In this embodiment, the low power standby strategy of non-critical devices is implemented by the following steps: When it is detected that the power demand of a device is below the set threshold for a long time, the system reduces its output power to the standby level, for example, only providing 1W of maintenance current.

[0065] Standby level output current I standby The calculation formula is: Among them, P standby The standby power setting is usually 1W or less.

[0066] When the device restarts, the system automatically resumes its normal power output to ensure the integrity of its functionality.

[0067] In some embodiments, to prevent the standby mode from affecting the operation of non-critical devices, the system will still periodically detect the state change of the device during the standby period. For example, every 10 seconds the system sends a small current pulse to the device to determine whether it has restarted. If it is detected that the device has restarted, the system will immediately increase its output power to ensure the normal operation of the device.

[0068] Specifically, the implementation process of dynamic adjustment and standby strategy is as follows: First, the system calculates the target output current and voltage for each device based on its priority coefficient and power requirements.

[0069] The energy storage power supply then adjusts the parameters of its output modules to prioritize providing sufficient current to high-priority devices while reducing or stopping power to non-critical devices.

[0070] Finally, for devices that spend extended periods of time in a low-power state, the system further conserves power by reducing their power allocation or entering standby mode.

[0071] In some extended application scenarios, this strategy can also adapt to the needs of complex connections of multiple devices. For example, when the energy storage power supply is simultaneously supplying power to communication equipment, lighting equipment, and portable heating equipment, the system will prioritize the distribution of stable power to communication equipment and lighting equipment, while the portable heating equipment will enter a low-power standby state during non-essential periods.

[0072] S5. Trigger the dynamic adaptation mechanism to adjust the power allocation strategy: When the external environmental parameters change, the dynamic adaptation mechanism is triggered to adjust the power allocation strategy to ensure stable operation of the equipment; In general, the operation of outdoor energy storage power supplies will be directly affected by environmental conditions, especially when parameters such as temperature, humidity, light intensity, air pressure or wind speed fluctuate violently, the stability of the equipment is easily threatened. For example, a sudden drop in temperature can easily lead to a decline in battery performance and insufficient power output; while a high temperature environment can easily cause the equipment to overheat or even be damaged. To this end, the present invention designs a dynamic adaptation mechanism to timely adjust the power allocation strategy when a significant change in external environmental parameters is detected to ensure the continuous and stable operation of the equipment.

[0073] In this embodiment, by real-time monitoring of external environmental parameters, the system can quickly perceive dynamic changes in the environment. When it is detected that the parameters deviate from the preset normal range, the system will trigger a dynamic adaptation mechanism, reallocate power according to the current environment and device status, and take necessary protective measures.

[0074] Specifically, the monitoring of environmental parameters includes temperature T, humidity H, light intensity L, air pressure G, wind speed W, etc. These data are collected in real time by multimodal sensors. The amplitude of environmental parameter change ΔX can be calculated by the following formula: ΔX=X current -X baseline Among them, X current is the environmental parameter value currently collected, X baseline This is the default normal value for this parameter.

[0075] In some embodiments, when the parameter change amplitude |ΔX| exceeds the threshold ΔX threshold The dynamic adaptation mechanism is triggered. For example, when the ambient temperature T suddenly drops by more than 10°C (i.e. |ΔX|>10°C) or the wind speed W suddenly rises to more than 20m / s, the system will identify these changes as "abnormal conditions".

[0076] As an option, the dynamic adaptation mechanism will adopt different adjustment strategies according to the specific changes in environmental parameters. For example: In low temperature environments, the chemical reaction rate inside the battery decreases, resulting in insufficient power output. The system will prioritize increasing the current output of key devices while reducing the power allocation of non-key devices to ensure the stable operation of core devices.

[0077] In high temperature environments, to prevent the battery from overheating, the system will reduce the overall power output, especially the power supply to non-critical devices. At this time, the battery management module will also reduce heat accumulation through an active cooling mechanism.

[0078] When light intensity decreases significantly, the system reduces power supply to low-priority devices and switches the energy storage power supply to energy-saving mode to extend the operating time of high-priority devices.

[0079] In one implementation, the power allocation adjustment process relies on a multi-objective optimization model. The model takes the stability of device operation and power efficiency as optimization goals and determines the power ratio of each device through dynamic weight allocation. The optimization formula is as follows: in: P out,i is the actual power allocation of the i-th device; P demand,i is the power requirement of the i-th device; w i is the dynamic weight of the ith device, which is adjusted in real time based on device priority and environmental conditions; N is the total number of connected devices.

[0080] In some embodiments, the system also considers the indirect impact of environmental changes on the operating status of the device. For example, when the wind speed increases significantly, the communication device will increase its power consumption requirements due to signal attenuation. At this time, the dynamic adaptation mechanism not only adjusts the current power allocation, but also predicts subsequent power demand changes to provide more stable power support for the device.

[0081] Specifically, the adjustment process of the dynamic adaptation mechanism includes the following key links: First, when the system detects that an environmental parameter exceeds the normal range, it calculates the magnitude and trend of the parameter change and determines its potential impact on the power demand of the equipment. For example, when the humidity suddenly rises to more than 90%, the system predicts that this condition will cause the risk of short circuit of the equipment.

[0082] Secondly, according to the nature of environmental parameter changes, combined with device priority and current power status, the power allocation ratio of each device is dynamically adjusted. For high-priority devices, the system prioritizes the stability of their power requirements; for low-priority devices, the power is reduced or switched to low-power mode.

[0083] Finally, the adjustment effect is monitored in real time through the feedback control mechanism to ensure that the equipment operating status returns to a stable range.

[0084] In practical applications, the dynamic adaptation mechanism can effectively cope with extreme environmental conditions. For example, when the air pressure drops rapidly, the system will give priority to powering emergency communication equipment and medical equipment while reducing the power supply to lighting equipment. In addition, in a long-term low temperature environment, the system can prevent the battery performance from continuing to decline by adjusting the output parameters.

[0085] In other embodiments, the system can further optimize the power allocation strategy by combining the linkage changes of multiple environmental parameters. For example, when the temperature rises and the light intensity decreases, the system will predict a significant increase in the power demand of the device and allocate more power reserves in advance to ensure continuous power supply to the device.

[0086] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for optimizing energy-saving mode of an outdoor energy storage power supply, characterized in that: The following steps are involved: Collect instantaneous current, voltage and power data of connected devices, and build a power consumption characteristic model of the devices based on historical power consumption data; Collect external environmental parameters, including temperature, humidity, light intensity, air pressure and wind speed, fuse the environmental data and build an environmental change model; Based on the power consumption characteristic model and environmental change model, the AI ​​algorithm is used to predict the future power demand of the equipment and calculate the optimal output power; Dynamically adjust the output current and voltage of the energy storage power supply according to the device priority, and implement a low-power standby strategy for non-critical devices; When external environmental parameters change, the dynamic adaptation mechanism is triggered to adjust the power allocation strategy to ensure stable operation of the equipment.

2. The energy-saving mode optimization method of an outdoor energy storage power supply according to claim 1, characterized in that: The construction of the power consumption characteristic model includes: Use the sliding window algorithm to analyze the power consumption data in segments and extract the periodic characteristics of device power consumption; Use long short-term memory networks to perform time series modeling on power consumption data and predict future power consumption trends of devices; The prediction accuracy of the power consumption model is optimized by combining the classification labels of the devices.

3. The energy-saving mode optimization method of an outdoor energy storage power supply according to claim 1, characterized in that: The construction of the environmental change model includes: The Kalman filter algorithm is used to filter and fuse the data collected by multi-modal sensors; Analyze the relationship between ambient temperature and humidity, light intensity, air pressure and wind speed and power demand, and establish mapping rules between environmental changes and power demand; Detect sudden changes in environmental parameters and trigger anomaly detection mechanisms.

4. The energy-saving mode optimization method of an outdoor energy storage power supply according to claim 1, characterized in that: The steps of predicting future device power requirements and calculating optimal output power by using an AI algorithm based on the power consumption characteristic model and the environment change model include: Calculate output current and voltage based on power demand predicted by the power consumption characteristic model; Set a dynamic adjustment threshold. When the deviation between the actual power demand and the predicted value exceeds the preset range, the power adjustment mechanism is triggered. Prioritize power supply to critical equipment and delay power supply or limit power supply to non-critical equipment; The device enters low-power standby mode when not in use for a long period of time.

5. The energy-saving mode optimization method of an outdoor energy storage power supply according to claim 1, characterized in that: The dynamic adaptation mechanism includes: When the ambient temperature is lower than the preset threshold, the output current is adjusted to meet the power demand of the device when it starts; When the ambient temperature is higher than the preset threshold, the power output of non-critical equipment is reduced to protect the safety of the energy storage power supply; When the light intensity is lower than the preset value, the power supply to low-priority devices is reduced to ensure the stable operation of high-priority devices.

6. The energy-saving mode optimization method of an outdoor energy storage power supply according to claim 1, characterized in that: The step of outputting current and voltage of the energy storage power supply comprises: Prioritize power allocation to key equipment to ensure its normal operation; When the total power demand of the equipment exceeds the power output capacity, the power allocation of non-critical equipment is automatically reduced; The output voltage and current are adjusted in real time according to the changes in the actual power demand of the equipment to avoid energy waste.

7. The energy-saving mode optimization method of an outdoor energy storage power supply according to claim 1, characterized in that: The step of executing the low power standby strategy for non-critical devices includes: Detect the operating status of non-critical equipment and reduce the output power to the standby level when the non-critical equipment has not been used for a long time; When non-critical equipment restarts, the system automatically resumes normal power output; Monitor device state changes during standby to ensure low-power modes do not affect the device's basic functionality.

8. The energy-saving mode optimization method of an outdoor energy storage power supply according to claim 1, characterized in that: The step of adjusting the power allocation strategy comprises: When a dramatic change in ambient temperature, light intensity, or other external parameters is detected, the power allocation scheme of the device is recalculated; Prioritize the allocation of stable power to devices that are sensitive to environmental changes to reduce equipment failures caused by environmental fluctuations; Dynamically adjust the output power according to the trend of environmental changes to optimize the energy utilization efficiency of the power supply.

9. The energy-saving mode optimization method of an outdoor energy storage power supply according to claim 1, characterized in that: The steps of predicting future device power requirements by using an AI algorithm include: Analyze historical power consumption data, extract the periodic power consumption patterns of equipment, and establish a power consumption change prediction model; Combine real-time collected data and equipment classification labels to optimize the prediction accuracy of power demand; Adjust the power output curve of the energy storage power source based on the prediction results to reduce unnecessary power loss.

10. The energy-saving mode optimization method of an outdoor energy storage power supply according to claim 1, characterized in that: The step of calculating the optimal output power comprises: Set the upper and lower limits of output power based on the matching of the actual power consumption requirements of the equipment with the power prediction model; For scenarios with multiple devices connected, the total output power is calculated based on device priority and power demand allocation ratio; By monitoring the fluctuations in equipment power demand in real time, the output power can be adjusted dynamically to ensure efficient use of energy.

Images