Multi-source energy storage self-powering methods, systems, equipment, and storage media for iron towers

Abstract

This invention provides a method, system, device, and storage medium for multi-source energy storage self-powered supply for steel towers, belonging to the field of steel tower power supply technology. The method includes: inputting historical load data of the steel tower into a time series model to obtain the load demand of the tower; inputting meteorological data of the tower's geographical location into a power prediction model to obtain wind power and photovoltaic power; determining a charging strategy for the energy storage battery based on the load demand, wind power, photovoltaic power, and the state of charge of the energy storage battery; determining a self-powered supply control strategy based on the energy storage battery charging strategy; and selecting any one of wind and solar power generation equipment, energy storage battery, or the power grid to supply power to the tower based on the self-powered supply control strategy. The method, system, device, and storage medium for multi-source energy storage self-powered supply for steel towers provided by this invention effectively reduce the overall operating cost of steel towers.

Description

Technical Field

[0001] This invention belongs to the field of tower power supply technology, and more specifically, relates to a multi-source energy storage self-power supply method, system, equipment, and storage medium for towers. Background Technology

[0002] In telecommunications infrastructure construction, towers are crucial nodes for ensuring signal coverage and transmission. With the rapid growth of telecommunications services, the power demand for towers is also increasing. Traditional tower power supply mainly relies on the municipal power grid, a single-supply mode with numerous drawbacks. In remote areas or regions with unstable power supply, frequent power outages occur, easily leading to communication interruptions, severely impacting communication service quality, and providing users with a poor experience. Simultaneously, with the continuous rise in energy costs, long-distance power transmission not only requires high line laying costs but also incurrs high subsequent maintenance expenses, significantly increasing tower operating costs. Therefore, there is a need to develop a multi-source energy storage self-powering technology that can reduce over-reliance on the municipal power grid, effectively lower power supply costs, and is environmentally friendly and energy-saving. Summary of the Invention

[0003] The purpose of this invention is to provide a method, system, equipment, and storage medium for multi-source energy storage self-powered towers, which effectively reduces the overall operating cost of towers.

[0004] A first aspect of this invention provides a multi-source energy storage self-powering method for iron towers, comprising:

[0005] By inputting the historical load data of the towers into the time series model, the load demand of the towers can be obtained.

[0006] Meteorological data of the location of the tower is input into the power prediction model to obtain wind power and photovoltaic power;

[0007] The charging strategy for the energy storage battery is determined based on load demand, wind power, photovoltaic power, and the state of charge of the energy storage battery.

[0008] A self-powered control strategy is determined based on the charging strategy of the energy storage battery, and the tower is powered by any one of the following methods: wind and solar power generation equipment, energy storage battery, or power grid.

[0009] A second aspect of the present invention provides a multi-source energy storage self-powered system for iron towers, comprising:

[0010] The load demand forecasting module is used to predict the load demand of towers based on historical load data of towers using a time series model.

[0011] The energy power prediction module is used to obtain wind power and photovoltaic power based on meteorological data of the geographical location of the tower.

[0012] The charging strategy module is used to determine the charging strategy for the energy storage battery based on load demand, wind power, photovoltaic power, and the state of charge of the energy storage battery.

[0013] The execution module determines a self-powered control strategy based on the charging strategy of the energy storage battery, and switches the power supply to the tower from wind and solar power generation equipment, energy storage battery or grid based on the self-powered control strategy.

[0014] A third aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the above-described multi-source energy storage self-powering method for iron towers.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method for multi-source energy storage self-power supply for iron towers.

[0016] The beneficial effects of the multi-source energy storage self-powering method, system, equipment, and storage medium for iron towers provided in this invention are as follows: Powering the iron towers with multiple energy sources avoids excessive reliance on the mains power grid; this invention can predict the power supply and demand of the iron towers in advance by accurately predicting power generation based on historical load data and meteorological data. By determining the charging strategy of the energy storage battery based on load demand, wind power, photovoltaic power, and the state of charge of the energy storage battery, and selecting a power supply switching mechanism, the stability and reliability of the iron tower power supply are significantly improved, effectively ensuring the quality of communication services. Simultaneously, determining the charging strategy of the energy storage battery based on the charging strategy value effectively extends the lifespan of the energy storage battery and reduces the overall operating cost of the iron tower. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating a multi-source energy storage self-powering method for iron towers according to an embodiment of the present invention.

[0019] Figure 2 This is a structural block diagram of a multi-source energy storage self-powered system for iron towers provided in an embodiment of the present invention;

[0020] Figure 3This is a schematic block diagram of an electronic device provided according to an embodiment of the present invention. Detailed Implementation

[0021] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0022] To make the objectives, technical solutions, and advantages of the present invention clearer, specific embodiments will be described below in conjunction with the accompanying drawings.

[0023] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a multi-source energy storage self-powered supply method for iron towers according to an embodiment of the present invention. The method includes:

[0024] S101: Input the historical load data of the tower into the time series model to obtain the load demand of the tower.

[0025] In this embodiment, historical load data refers to the real-time power consumption and operating time of various electrical devices on the tower over a relatively long period of time, under different seasons, time periods, and usage scenarios.

[0026] Before being input into the time series model, the historical load data is preprocessed. This preprocessing includes: data cleaning to remove outliers caused by equipment malfunctions, signal interference, etc.; and data standardization to normalize load data of different magnitudes to a uniform scale, thereby improving data quality and usability.

[0027] The preprocessed historical load data is input into a time series model. For example, the model performs in-depth analysis and learning of the time trends and periodic characteristics inherent in the data to predict the load demand of the towers at different future time points (such as the next hour, six hours, or one day). In this embodiment, the model's in-depth analysis and learning of the time trends and periodic characteristics inherent in the data enables accurate prediction of the tower load demand.

[0028] S102: Input the meteorological data of the geographical location of the tower into the power prediction model to obtain the wind power and photovoltaic power.

[0029] In this embodiment, high-precision meteorological monitoring equipment is used to collect accurate meteorological data of the geographical location of the tower, including but not limited to real-time wind speed, wind direction, temperature, humidity, light intensity, sunshine duration, etc., and the time interval between meteorological data collection is kept short enough to capture rapid changes in meteorological conditions.

[0030] In this embodiment, the meteorological data of the geographical location of the tower is input into the power prediction model to obtain the wind power. This includes: firstly, constructing a wind power prediction model based on the combination of aerodynamic principles and machine learning algorithms; secondly, inputting real-time wind speed, wind direction, wind turbine blade parameters, wind turbine tower height, and other information into the power prediction model to predict the wind power at different future times; wherein, the wind power prediction model is obtained by simulating the operating state and energy conversion process of the wind turbine and training and optimizing it in combination with historical wind power data.

[0031] In this embodiment, meteorological data of the geographical location of the tower is input into the power prediction model to obtain the photovoltaic power. This includes: firstly, establishing a power prediction model based on factors such as solar radiation intensity, photovoltaic panel tilt angle, and the influence of temperature on photovoltaic panel efficiency; secondly, inputting meteorological data such as light intensity, sunshine duration, and ambient temperature, as well as the technical parameters of the photovoltaic panel, into the photovoltaic power prediction model to predict the future photovoltaic power. The photovoltaic power prediction model is obtained through physical modeling of the photovoltaic panel power generation process and data-driven algorithm optimization.

[0032] S103: Determine the charging strategy for the energy storage battery based on load demand, wind power, photovoltaic power, and the state of charge of the energy storage battery.

[0033] In this embodiment, the State of Charge (SOC) of the energy storage battery is monitored in real time to obtain the proportion of its current remaining capacity to the total battery capacity. Based on the predicted tower load demand, wind power, photovoltaic power, and the SOC of the energy storage battery, algorithms (such as particle swarm optimization, genetic algorithms, etc.) are used to determine the charging strategy of the energy storage battery at different time points, with the goals of maximizing the utilization of clean wind and solar energy, extending the life of the energy storage battery, and reducing the overall power supply cost, while ensuring stable power supply to the tower load. The charging strategy includes: whether to charge, the charging power, and the charging duration.

[0034] S104: Determine a self-powered control strategy based on the charging strategy of the energy storage battery, and select any one of the following methods to power the tower: wind and solar power generation equipment, energy storage battery or power grid based on the self-powered control strategy.

[0035] In this embodiment, based on the determined energy storage battery charging strategy, a detailed self-powered control strategy is further formulated. This strategy clarifies how to efficiently switch between wind and solar power generation equipment, energy storage batteries, or the power grid to supply power to the tower under different combinations of load demand, wind and solar power generation capacity, and energy storage battery state of charge. For example, when the sum of wind and solar power exceeds the tower's load demand and the energy storage battery's state of charge is not fully charged, wind and solar power generation equipment is used to supply power to the tower first, and excess energy is stored in the energy storage battery; when the sum of wind and solar power generation is less than the tower's load demand but the energy storage battery's state of charge is sufficient, the energy storage battery supplements the power supply; when neither wind and solar power generation nor the energy storage battery's capacity can meet the tower's load demand, the system automatically switches to grid power supply to ensure the continuity and stability of the tower's power supply; when wind power exceeds the tower's load demand and the energy storage battery's state of charge is not fully charged, wind and solar power generation equipment is used to supply power to the tower first; when solar power exceeds the tower's load demand and the energy storage battery's state of charge is not fully charged, solar power generation equipment is used to supply power to the tower first, with charging determined based on the energy storage battery's state of charge and battery life.

[0036] Based on the self-powered control strategy, the system monitors and automatically controls the start-up and shutdown of wind and solar power generation equipment, power regulation, charging and discharging switching of energy storage batteries, and connection and disconnection of grid power supply in real time, thereby realizing the intelligent and efficient operation of the multi-source energy storage self-powered system for iron towers.

[0037] As can be seen from the above, this invention avoids excessive reliance on the municipal power grid by supplying power to the towers through multiple energy sources. By accurately predicting power generation using historical load data and meteorological data, this invention can anticipate the power supply and demand situation of the towers in advance. Based on load demand, wind power, photovoltaic power, and the state of charge of the energy storage batteries, the charging strategy for the energy storage batteries is determined, and a power supply switching mechanism is selected, significantly improving the stability and reliability of the tower power supply and effectively guaranteeing the quality of communication services. Simultaneously, determining the charging strategy for the energy storage batteries based on the charging strategy values ​​effectively extends the lifespan of the energy storage batteries and reduces the overall operating cost of the towers.

[0038] In one embodiment of the present invention, historical load data of the tower is input into a time series model to obtain the load demand of the tower, including:

[0039] The target data is obtained by fusing external correlation data and historical load data of the tower. The external correlation data includes: meteorological data, holiday data and weekday data.

[0040] The target data is input into the time series model to obtain the load demand of the tower.

[0041] In this embodiment, the meteorological data of the external associated data includes: temperature, humidity, air pressure, wind speed, precipitation, and other meteorological data of the area where the tower is located. Different meteorological conditions will affect the operating status of the equipment served by the tower. For example, high temperatures may increase the heat dissipation demand of communication equipment, thereby leading to an increase in load; strong winds may affect the power consumption of some auxiliary equipment on the tower.

[0042] External data related to holidays and weekdays includes weekdays, weekends, and public holidays. The load on towers, such as communication traffic, varies significantly depending on the date type. For example, during weekday working hours, communication traffic may be concentrated on towers in commercial areas; while on holidays, the load on towers in tourist areas may increase dramatically.

[0043] External related data also includes social activity data; social activity data includes whether there are large-scale sports events, concerts, trade fairs and other social activities in the area around the tower; these activities will attract a large number of people to gather, which will cause the communication load of the tower in the area to rise sharply.

[0044] In this embodiment, it is necessary to align external correlation data and historical load data of the towers in the time dimension to ensure data accuracy. The method for fusing external correlation data and historical load data of the towers includes weighted fusion and feature stitching. Weighted fusion assigns different weights to external correlation data and historical load data based on the degree of influence of different data in the external correlation data on the tower load demand. For example, meteorological data has a greater impact on the load and can be assigned a higher weight; while holiday data has a relatively smaller impact and can be assigned a lower weight. Then, each data point is multiplied by its corresponding weight and summed to obtain the target data. Feature stitching combines various features from the external correlation data and historical load data to form a higher-dimensional dataset as the target data. For example, it combines features such as power values ​​from historical load data, temperature from external correlation data, and whether it is a holiday.

[0045] In this embodiment, a time series model (e.g., autoregressive integral moving average model, seasonal autoregressive integral moving average model, long short-term memory network, etc.) is selected based on the characteristics of the target data and the prediction requirements. If the target data has obvious seasonality and periodicity, the regression integral moving average model is selected; if it is necessary to handle complex nonlinear relationships, the long short-term memory network is selected.

[0046] In this embodiment, the time series model is trained using historical target data. During training, the historical target data is divided into a training set and a test set. The time series model is trained using the training set. During training, the model's parameters are continuously adjusted to minimize prediction error. For example, for a Long Short-Term Memory (LSTM) network, parameters such as the number of neurons, learning rate, and number of iterations need to be adjusted. The time series model is used to predict the target data to obtain the load demand of the tower over a future period. The prediction result can be a specific load power value or a trend in load demand.

[0047] In one embodiment of the present invention, external correlation data and historical load data of the tower are fused to obtain target data, including:

[0048] Historical load data is time-aligned with external correlated data to construct a multidimensional feature vector;

[0049] The weights of each feature dimension in the externally correlated data and the historical load data are calculated based on the attention mechanism.

[0050] The target data is obtained by fusing historical load data and external load data based on the weights of each feature in the external load data and the historical load data.

[0051] In this embodiment, before aligning historical load data with external related data in time, the external related data needs to be cleaned and standardized, and different data in the external related data are sorted according to timestamps to ensure that the time order of different data is correct.

[0052] In this embodiment, the time alignment method is as follows: based on the time dimension of historical load data, external related data is time-aligned. If the historical load data is recorded hourly, then the external related data is also organized and aggregated hourly. For some data that cannot be accurate to the same time granularity, appropriate methods can be used for approximation, such as distributing social activity data recorded daily into the various hours of each day.

[0053] In this embodiment, constructing a multidimensional feature vector involves combining time-aligned historical load data and external correlation data to obtain a multidimensional feature vector. Each time point corresponds to a feature vector, and each dimension of the vector represents a feature, such as historical load power, temperature, humidity, or whether it is a holiday. At a certain time t, the feature vector can be represented as x. t =[P t T t H t ,⋯], where P t It is the historical load power at that moment, T tIt is temperature, H t It's humidity.

[0054] In this embodiment, the target data is obtained by fusing external correlation data and historical load data of the tower. This includes: first, constructing a feature relationship graph, using historical load data and external correlation data as graph nodes, and calculating edge weights between nodes using cosine similarity to form a feature correlation graph; second, using multi-head attention to calculate the weight distribution of different feature dimensions independently learned by each head; third, normalizing each weight by using Layer Normalization to standardize the attention weights to avoid the gradient vanishing problem; and finally, enhancing the weighted feature vectors through a fully connected layer to generate the final target data.

[0055] In this embodiment, the process of fusing data based on attention mechanisms to calculate weights to obtain target data includes:

[0056] First, the multidimensional feature vector is input into the linear transformation layer, which maps it to three different spaces: query, key, and value.

[0057] Let the input feature vector be x, then we have: Q = W Q ×x, K=W K ×x, V=W V ×x; where W Q W K and W V This is a learnable weight matrix.

[0058] Secondly, the similarity score between the query vector Q and the key vector K is calculated; this is done using the dot product operation, i.e. ;in, It is the first of the query vectors i One element, It is the j-th element of the key vector, and the superscript T is the transpose.

[0059] Secondly, the similarity scores are normalized, and the attention weights are obtained using the softmax function; the weights for each feature j in the external correlation data and the historical load data are then calculated. The weighting formula for historical load data is as follows:

[0060]

[0061] Where n is the number of dimensions of the feature.

[0062] Finally, let the historical load data be P and the external correlation data be X. The corresponding weight is Then the fused target data Y is:

[0063]

[0064] in, For the j-th dimension of external related data, The attention weights for the j-th dimension external correlation data and historical load data are given. Belongs to [0,1] The larger the value, the more significant the impact of that dimension feature on load demand.

[0065] In this embodiment, the fused target data is used as input to a time series model to predict tower load demand. Historical tower load data can include electricity consumption records from different time periods and scenarios. Historical load data only reflects past electricity consumption patterns, while external correlation data directly affects load changes. The fused target data can more comprehensively characterize load influencing factors, thereby improving prediction accuracy. Specifically, this embodiment can dynamically allocate attention mechanisms. This allows the fused target data to highlight key influencing factors, enabling more accurate calculation of load demand when subsequently input into a time series model, thus providing a reliable basis for formulating subsequent power supply strategies.

[0066] In one embodiment of the present invention, a charging strategy for the energy storage battery is determined based on load demand, wind power, photovoltaic power, and the state of charge of the energy storage battery, including:

[0067] Based on load demand, wind power, photovoltaic power, and the state of charge of energy storage batteries, an optimization model is constructed with the goal of minimizing grid power supply costs. The charging strategy for energy storage batteries is determined according to the optimization model. The constraint condition of the charging strategy for energy storage batteries is the state of charge of the energy storage batteries.

[0068] In this embodiment, an optimization model is constructed with the objective of minimizing the cost of grid power supply, including: defining the objective function as:

[0069]

[0070] in, The electricity price supplied by the grid during time period t. The power supplied from the grid during time period t. This is the State of Charge (SOC) balance coefficient, used to adjust the penalty weight for SOC deviation from the reference value; The state of charge of the energy storage battery during time period t. This serves as the reference state of charge for the energy storage battery. To optimize the total number of time periods in the time window (e.g., 24 hours, with each period being 1 hour).

[0071] In this embodiment, the objective function is used to construct an optimization model aimed at minimizing the cost of grid power supply, and serves as the core objective function when determining the energy storage battery charging strategy. As the electricity purchase cost for time period t, The product of the two is the power obtained from the grid during time period t. This can be used to quantify the cost of purchasing electricity from the grid in different time periods. In addition to minimizing the cost of grid power supply, this embodiment also introduces... This penalty term, applied to address deviations of the energy storage battery's state of charge (SOC) from its reference SOC, refers to the percentage of the battery's current remaining charge relative to its total capacity. This penalty term ensures that the objective function, while minimizing grid supply costs, avoids overcharging and over-discharging of the energy storage battery, thus extending its lifespan. Furthermore, all parameters in this objective function are calculated using dimensionless parameters.

[0072] The power balance constraint is:

[0073]

[0074] The tower load demand power (unit: kW) for time period t. The wind power generation capacity during time period t (unit: kW); The photovoltaic power generation during time period t (unit: kW); The charging and discharging power of the energy storage battery during time period t (unit: kW, positive value indicates discharging, negative value indicates charging). Let be the grid power during time period t.

[0075] In this embodiment, the objective function is calculated based on minimizing the cost of grid power supply. However, considering power balance factors, this embodiment sets a power balance constraint formula as the core constraint condition in this process to ensure that the load demand of the tower in time period t matches the output power of each power supply method. When determining the charging strategy and power supply control strategy, this power balance constraint formula can be used to verify whether the power distribution of wind and solar power generation, energy storage batteries, and the power grid meets the load demand, which is a fundamental constraint for achieving power supply stability. The power balance constraint ensures the balance of power supply and demand for the tower, avoids power outages caused by power mismatch, and improves power supply reliability.

[0076] The energy storage SOC constraint is:

[0077]

[0078] in, To prevent over-discharge of the energy storage battery, it is set to the minimum permissible state of charge (e.g., 20%). To prevent overcharging, the maximum state of charge (e.g., 80%) allowed for the energy storage battery.

[0079] Energy storage charging and discharging power limitations:

[0080]

[0081] in, The maximum charge and discharge power of the energy storage battery (unit: kW) is determined by the battery specifications.

[0082] Maximum power supply capacity of the power grid:

[0083]

[0084] in, The maximum power supply (in kW) allowed to be obtained from the grid is set according to the grid agreement or equipment capacity.

[0085] In this embodiment, an optimization model is constructed with the goal of minimizing grid power supply costs. Other objectives can also be used to construct the optimization model, such as maximizing the utilization rate of wind and solar power generation and extending the lifespan of energy storage batteries. These objectives can be weighted and combined to construct a multi-objective optimization model that integrates various factors. Constraints may also include limitations on the charging and discharging power of the energy storage battery, limits on the number of charge and discharge cycles, and limitations on the grid's power supply capacity. These constraints are incorporated into the construction of the optimization model to ensure its feasibility and rationality. This embodiment can employ various optimization algorithms to solve the optimization model, such as genetic algorithms, particle swarm optimization, and simulated annealing. The optimal optimization algorithm is selected by comparing the solution results and efficiency of different algorithms. Since load demand, wind power, photovoltaic power, and the state of charge of the energy storage battery change in real time, the optimization model needs to be updated in real time. The model is adjusted and optimized based on real-time data to ensure the real-time performance and accuracy of the charging strategy.

[0086] In one embodiment of the present invention, a charging strategy for the energy storage battery is determined based on load demand, wind power and photovoltaic power, and the state of charge of the energy storage battery, including:

[0087] The load demand, wind power, photovoltaic power, and state of charge of energy storage batteries are fused to obtain a multi-dimensional feature vector.

[0088] Calculate multiple matching degrees between the multidimensional feature vector and each charging strategy in the charging strategy library; the charging strategy library contains a variety of charging strategies.

[0089] The charging strategy for the energy storage battery is determined based on multiple matching degrees.

[0090] In this embodiment, in addition to the simple similarity calculation method described above, other matching degree calculation methods can also be used, such as matching degree calculation methods based on fuzzy theory, matching degree calculation methods based on deep learning, etc. These methods can better handle the uncertainty and fuzziness of data and improve the accuracy of matching degree calculation.

[0091] In this embodiment, when constructing the charging strategy library, multiple factors can be considered, such as different load demand scenarios, different wind and solar power generation conditions, and different energy storage battery states. Through analysis and mining of historical data, various charging strategies are generated and stored in the charging strategy library. The charging strategy library needs continuous updating as actual operating conditions change. Based on real-time data and operational experience, the strategies in the charging strategy library can be adjusted and optimized to ensure its timeliness and effectiveness.

[0092] In this embodiment, when selecting a charging strategy based on the matching degree, decision rules and expert experience can be introduced; for example, when there are multiple strategies with high matching degrees, the optimal strategy is selected based on decision rules and expert experience. Furthermore, a multi-attribute decision-making method can be used to comprehensively consider multiple factors in strategy selection.

[0093] In one embodiment of the present invention, a charging strategy for the energy storage battery is determined based on load demand, wind power and photovoltaic power, and the state of charge of the energy storage battery, including:

[0094] Calculate the stability of wind power and photovoltaic power;

[0095] The target stability is obtained by weighted calculation of wind power stability and photovoltaic stability.

[0096] The charging strategy value is obtained based on the state of charge and target stability of the energy storage battery;

[0097] The charging strategy for the energy storage battery is determined based on the charging strategy value.

[0098] In this embodiment, the power supply stability calculation method is as follows:

[0099] The first step is to calculate the stability of renewable energy power (wind power, photovoltaic power);

[0100] The formula for calculating wind power stability is as follows:

[0101]

[0102] The formula for calculating photovoltaic stability is:

[0103]

[0104] in, Indicates wind power stability. Indicates photovoltaic stability. These are the standard deviations of wind power and photovoltaic power (reflecting volatility), respectively. , These are the rated power of wind power and solar power, respectively; ∈[0,1] ， ∈[0,1], the larger the value, the higher the stability.

[0105] In this embodiment, for the wind power stability calculation formula, where, Used to quantify the volatility of wind power output; the larger this ratio, the stronger the volatility of wind power output. 1- The standard deviation of wind power is used to characterize the stability of wind power output; the larger the difference, the stronger the stability. The wind power stability calculation formula quantifies wind power stability into a value within the [0,1] range by using the ratio of the standard deviation of wind power output to the rated power of the wind turbine. This provides a basis for charging strategies, such as prioritizing the use of highly stable wind power for supply or charging, improving power supply reliability, and reducing grid dependence. Similarly, the photovoltaic (PV) stability calculation formula quantifies PV stability into a value within the [0,1] range by using the ratio of the standard deviation of PV power output to the rated power of the PV module, providing a basis for charging strategies.

[0106] The second step is to calculate the target stability:

[0107]

[0108] in, For target stability, weighting coefficients , Dynamically adjust based on wind / solar installed capacity or real-time output ratio;

[0109] In this embodiment, the charging strategy is formulated by combining energy stability and energy storage status. Considering that both wind and solar power are affected by natural conditions and have inherent volatility, this embodiment uses a target stability formula to integrate the stability of wind and solar power, providing a comprehensive stability index for calculating the charging strategy value. Specifically, the target stability formula integrates wind and solar stability through dynamic weights γ and δ to obtain a more comprehensive energy stability assessment, making the stability assessment more consistent with the actual energy composition and improving the adaptability of the charging strategy.

[0110] The third step is to calculate the charging strategy value.

[0111]

[0112] Where SOC∈[0,1] represents the current battery state of charge; CSV∈[0,1] represents the charging strategy value, with a larger value indicating a higher charging demand.

[0113] Step 4: Adjust the charging power according to the CSV, using the following formula:

[0114]

[0115] in: To adjust the charging power, This represents the maximum charging power for energy storage. Excess power from renewable energy sources; Safety limit of SOC for energy storage batteries.

[0116] In this embodiment, the formula for calculating the charging strategy value is as follows: This can reflect the impact of the state of charge (SOC) of the energy storage battery on charging demand. The lower the SOC, the larger (1−SOC), indicating a higher degree of battery depletion and a more urgent need for charging. The target stability... The larger the value, the higher the overall stability of the wind-solar hybrid energy system, and the more reliable the charging process using wind and solar energy. Multiplying the two values ​​yields... The higher the SOC (State of Charge), the more stable the wind and solar energy (suitable for charging), and thus the higher the charging priority. If only SOC is considered when formulating a charging strategy, there may be instances where charging is forced when wind and solar energy fluctuates drastically (low stability), leading to unstable power supply. The charging strategy value calculation formula in this embodiment ensures that charging priority is increased only when charging is needed and energy is stable, achieving a combination of on-demand charging and reliable charging.

[0117] In this embodiment, for the charging power adjustment formula, where, The maximum allowable charging power is calculated based on the charging strategy value. The more urgent the charging demand and the higher the stability of wind and solar energy, the greater the power output. The larger, the better The larger the value, the higher the charging power. As the surplus power generated by wind and solar power after deducting load demand, which can be used for charging, when When, that is, when the battery is not fully charged, this embodiment starts from... and Taking the minimum value as the adjusted charging power ensures that the charging power does not exceed the battery hardware limitations or the actual available excess energy, thus avoiding drawing power from the grid and reducing costs. Right now In other words, when the battery is fully charged, the charging power is set to 0, and charging is stopped to prevent overcharging from damaging the battery. The charging power adjustment formula can realize dynamic adjustment of the charging strategy, giving priority to using surplus, highly stable wind and solar energy for charging, reducing grid dependence, lowering costs, and extending battery life.

[0118] In this embodiment, wind / solar stability is quantified by standardized volatility (standard deviation / rated power), with a stability value closer to 1 indicating greater stability. This embodiment uses dynamic weights to reflect the difference in contribution of wind and solar power to stability; the lower the SOC and the more stable the power supply system, the higher the charging demand; charging stops when the SOC approaches its upper limit; this embodiment can also adjust the charging power based on excess power and charging strategy values ​​to avoid overcharging.

[0119] In one embodiment of the present invention, a charging strategy for the energy storage battery is determined based on multiple matching degrees, including:

[0120] When a charging strategy matches multiple charging strategies in a preset strategy rule base, the multiple charging strategies are sorted according to the preset priority order in the strategy rule base to obtain a first sorted list, and the charging strategy is determined based on the first sorted list.

[0121] In this embodiment, the priority setting is mainly based on considerations of the importance to system operation and cost-effectiveness. Strategies that play a crucial role in ensuring stable system operation and reducing costs are assigned higher priority. For example, prioritizing wind and solar power charging can reduce dependence on the grid, lower energy costs, and benefit environmental protection; therefore, such strategies usually have a high priority. While charging during off-peak electricity pricing periods can also reduce costs, the benefits are slightly lower than those of wind and solar power charging, so these strategies have a moderate priority. Based on the priority assigned to each strategy in the preset strategy rule base, the matched charging strategies are sorted to generate a first sorted list. For example, if strategy A (high priority), strategy B (medium priority), and strategy C (low priority) are matched, the order of the first sorted list is strategy A, strategy B, strategy C. The charging strategy with the highest priority from the first sorted list is selected as the final charging strategy, i.e., prioritizing wind and solar power charging of the energy storage battery.

[0122] In this embodiment, the charging and discharging process of the energy storage battery is controlled according to a determined charging strategy. Simultaneously, the system's operating status is continuously monitored, including changes in the energy storage battery's state of charge and load demand. If, during execution, the system's operating status changes, rendering the current strategy inapplicable, a new matching, sorting, and strategy selection process is performed to ensure that the energy storage battery's charging strategy always adapts to the system's actual operating conditions.

[0123] Corresponding to the multi-source energy storage self-powering method for iron towers in the above embodiment, Figure 2 This is a structural block diagram of a multi-source energy storage self-powered system for iron towers according to an embodiment of the present invention. For ease of explanation, only the parts relevant to the embodiment of the present invention are shown. (See references) Figure 2The multi-source energy storage self-powered system 20 for the iron tower includes: a load demand prediction module 21, an energy power prediction module 22, a charging strategy module 23, and an execution module 24.

[0124] Among them, the load demand prediction module 21 is used to predict the load demand of the tower based on the historical load data of the tower using a time series model.

[0125] The energy power prediction module 22 is used to obtain wind power and photovoltaic power based on meteorological data of the geographical location of the tower.

[0126] The charging strategy module 23 is used to determine the charging strategy of the energy storage battery based on load demand, wind power, photovoltaic power and the state of charge of the energy storage battery.

[0127] The execution module 24 determines the self-power supply control strategy based on the charging strategy of the energy storage battery, and switches the power supply to the tower from the wind and solar power generation equipment, energy storage battery or grid based on the self-power supply control strategy.

[0128] In one embodiment of the present invention, the load demand prediction module 21 is specifically used for:

[0129] The target data is obtained by fusing external correlation data and historical load data of the tower. External correlation data includes: meteorological data, holiday data and weekday data.

[0130] By inputting the target data into a time series model, the load demand of the towers can be predicted.

[0131] In one embodiment of the present invention, the load demand prediction module 21 is specifically used for:

[0132] Historical load data is time-aligned with external correlated data to construct a multidimensional feature vector;

[0133] The weights of each feature dimension in the externally correlated data and the historical load data are calculated based on the attention mechanism.

[0134] The target data is obtained by fusing historical load data and external load data based on the weights of each feature in the external load data and the historical load data.

[0135] In one embodiment of the present invention, the charging strategy module 23 is specifically used for:

[0136] The charging strategy for energy storage batteries is determined based on load demand, wind power, photovoltaic power, and the state of charge of the energy storage batteries, including:

[0137] Based on load demand, wind power, photovoltaic power, and the state of charge of energy storage batteries, an optimization model is constructed with the goal of minimizing grid power supply costs. The charging strategy for energy storage batteries is determined according to the optimization model. The constraint condition of the charging strategy for energy storage batteries is the state of charge of the energy storage batteries.

[0138] In one embodiment of the present invention, the charging strategy module 23 is specifically used for:

[0139] The charging strategy for the energy storage battery is determined based on load demand, wind power and photovoltaic power, and the state of charge of the energy storage battery, including:

[0140] The load demand, wind power, photovoltaic power, and state of charge of energy storage batteries are fused to obtain a multi-dimensional feature vector.

[0141] Calculate multiple matching degrees between the multidimensional feature vector and each charging strategy in the charging strategy library; the charging strategy library contains a variety of charging strategies.

[0142] The charging strategy for the energy storage battery is determined based on multiple matching degrees.

[0143] In one embodiment of the present invention, the charging strategy module 23 is specifically used for:

[0144] The charging strategy for the energy storage battery is determined based on load demand, wind power and photovoltaic power, and the state of charge of the energy storage battery, including:

[0145] Calculate the stability of wind power and photovoltaic power;

[0146] The target stability is obtained by weighted calculation of wind power stability and photovoltaic stability.

[0147] The charging strategy value is obtained based on the state of charge and target stability of the energy storage battery;

[0148] The charging strategy for the energy storage battery is determined based on the charging strategy value.

[0149] In one embodiment of the present invention, the charging strategy module 23 is specifically used for:

[0150] Based on multiple matching degrees, the charging strategy for the energy storage battery is determined, including:

[0151] When a charging strategy matches multiple charging strategies in a preset strategy rule base, the multiple charging strategies are sorted according to the preset priority order in the strategy rule base to obtain a first sorted list, and the charging strategy is determined based on the first sorted list.

[0152] The beneficial effects of the multi-source energy storage self-powered method, system, equipment, and storage medium for iron towers provided in this invention are as follows: By accurately predicting power generation based on historical load data and meteorological data, the power supply and demand situation of the iron tower can be predicted in advance. Based on load demand, wind power, photovoltaic power, and the state of charge of the energy storage battery, the charging strategy of the energy storage battery is determined, and a power supply switching mechanism is selected, significantly improving the stability and reliability of the iron tower's power supply and effectively ensuring the quality of communication services. Simultaneously, determining the charging strategy of the energy storage battery according to the charging strategy value effectively extends the lifespan of the energy storage battery and reduces the overall operating cost of the iron tower.

[0153] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of the present invention. Figure 3 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of the modules in the aforementioned device embodiments, for example... Figure 2 The functions of the load demand prediction module 21, energy power prediction module 22, charging strategy module 23, and execution module 24 are shown.

[0154] It should be understood that, in this embodiment of the invention, the processor 301 may be a Central Processing Unit (CPU), but it may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0155] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0156] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store device type information.

[0157] In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of the present invention can execute the implementation methods described in the first and second embodiments of the multi-source energy storage self-powered method for iron towers provided in the embodiments of the present invention, or they can execute the implementation methods of the electronic devices described in the embodiments of the present invention, which will not be repeated here.

[0158] In another embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to implement these processes. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0159] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0160] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0161] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0162] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces or units, or it may be an electrical, mechanical, or other form of connection.

[0163] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.

[0164] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0165] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for multi-source energy storage self-powered transmission for iron towers, characterized in that, include: By inputting the historical load data of the towers into the time series model, the load demand of the towers can be obtained. Meteorological data of the location of the tower is input into the power prediction model to obtain wind power and photovoltaic power; The charging strategy for the energy storage battery is determined based on load demand, wind power, photovoltaic power, and the state of charge of the energy storage battery. A self-powered control strategy is determined based on the charging strategy of the energy storage battery, and the tower is powered by any one of the following methods: wind and solar power generation equipment, energy storage battery or power grid. The charging strategy for energy storage batteries is determined based on load demand, wind power, photovoltaic power, and the state of charge of the energy storage batteries, including: Calculate the stability of wind power and photovoltaic power; The target stability is obtained by weighted calculation based on the wind power stability and the photovoltaic stability. The charging strategy value is obtained based on the state of charge of the energy storage battery and the target stability. The charging strategy for the energy storage battery is determined based on the charging strategy value. The charging strategy value is calculated using the following formula: Where SOC∈[0,1] represents the current battery state of charge; CSV∈[0,1] represents the charging strategy value, with a larger value indicating a higher charging demand. , For target stability, weighting coefficients , Dynamically adjust based on wind / solar installed capacity or real-time output ratio. , , For wind power stability, For photovoltaic stability, These are the standard deviations of wind power and photovoltaic power, respectively. , These are the rated power of wind power and solar power, respectively; ∈[0,1], ∈[0,1], the larger the value, the higher the stability; Adjust the charging power based on the CSV, using the following formula: in, This represents the maximum charging power for energy storage. For excess power from renewable energy sources; This represents the upper limit of the SOC (State of Charge) for energy storage batteries.

2. The multi-source energy storage self-powering method for iron towers as described in claim 1, characterized in that, The step of inputting historical load data of the towers into a time series model to obtain the load demand of the towers includes: The target data is obtained by fusing external correlation data and historical load data of the tower. The external correlation data includes: meteorological data, holiday data and weekday data. The target data is input into the time series model to obtain the load demand of the tower.

3. The multi-source energy storage self-powering method for iron towers as described in claim 2, characterized in that, The process of fusing external correlation data and historical load data of the towers to obtain target data includes: Historical load data is time-aligned with external correlated data to construct a multidimensional feature vector; The weights of each feature dimension in the externally correlated data and the historical load data are calculated based on the attention mechanism. Based on the weights of each feature dimension in the external associated data and the historical load data, the historical load data and the external associated data are fused to obtain the target data.

4. A multi-source energy storage self-powered system for iron towers, characterized in that, include: The load demand forecasting module is used to predict the load demand of towers based on historical load data of towers using a time series model. The energy power prediction module is used to obtain wind power and photovoltaic power based on meteorological data of the geographical location of the tower. The charging strategy module is used to determine the charging strategy for the energy storage battery based on load demand, wind power, photovoltaic power, and the state of charge of the energy storage battery. The execution module determines a self-powered control strategy based on the charging strategy of the energy storage battery, and switches the power supply to the tower from the wind and solar power generation equipment, the energy storage battery, or the power grid based on the self-powered control strategy. The charging strategy module is specifically used to calculate wind power stability and photovoltaic stability. The target stability is obtained by weighted calculation based on the wind power stability and the photovoltaic stability. The charging strategy value is obtained based on the state of charge of the energy storage battery and the target stability. The charging strategy for the energy storage battery is determined based on the charging strategy value. The charging strategy value is calculated using the following formula: Where SOC∈[0,1] represents the current battery state of charge; CSV∈[0,1] represents the charging strategy value, with a larger value indicating a higher charging demand. , For target stability, weighting coefficients , Dynamically adjust based on wind / solar installed capacity or real-time output ratio. , , For wind power stability, For photovoltaic stability, These are the standard deviations of wind power and photovoltaic power, respectively. , These are the rated power of wind power and solar power, respectively; ∈[0,1], ∈[0,1], the larger the value, the higher the stability; Adjust the charging power based on the CSV, using the following formula: in, This represents the maximum charging power for energy storage. For excess power from renewable energy sources; This represents the upper limit of the SOC (State of Charge) for energy storage batteries.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 3.

6. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 3.

Images