Multi-source energy storage self-power-supply method and system for iron tower, equipment and storage medium

Abstract

The invention provides a multi-source energy storage self-power supply method and system for an iron tower, equipment and a storage medium, and belongs to the technical field of iron tower power supply, and the method comprises the steps: inputting historical load data of the iron tower into a time sequence model, and obtaining a load demand of the iron tower; inputting meteorological data of the geographic position of the iron tower into the power prediction model to obtain wind power and photovoltaic power; determining a charging strategy of the energy storage battery based on the load demand, the wind power, the photovoltaic power and the charge state of the energy storage battery; and determining a self-power-supply control strategy according to the charging strategy of the energy storage battery, and selecting any one of a wind-solar power generation device, the energy storage battery or a power grid to supply power to the iron tower based on the self-power-supply control strategy. According to the multi-source energy storage self-powered method and system for the iron tower, the equipment and the storage medium, the overall operation cost of the iron tower is effectively reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of iron tower power supply, and more specifically, relates to a multi-source energy storage self-power supply method for an iron tower and its system, equipment, and storage medium. Background Art

[0002] In the construction of communications infrastructure, towers are key nodes for ensuring signal coverage and transmission. With the rapid growth of communications traffic, the demand for electricity from towers is also increasing. Traditional tower power supply methods rely primarily on the mains grid, a single power supply model with numerous drawbacks. Frequent power outages are common in remote areas or those with unstable power supply, which can easily lead to communication interruptions, severely impacting the quality of communication services and providing a poor user experience. Furthermore, with rising energy costs, long-distance power transmission not only requires high line laying costs but also subsequent maintenance costs, significantly increasing tower operating costs. Therefore, there is a need to develop a multi-source energy storage self-powered technology that can eliminate over-reliance on the mains grid, effectively reduce power supply costs, and be environmentally friendly and energy-saving. Summary of the Invention

[0003] The purpose of the present invention is to provide a multi-source energy storage self-power supply method and system, equipment, and storage medium for an iron tower, which effectively reduces the overall operating cost of the iron tower.

[0004] A first aspect of an embodiment of the present invention provides a method for self-powering a tower using multi-source energy storage, comprising: Input the tower's historical load data into the time series model to obtain the tower's load demand; The meteorological data of the tower's geographical location is input into the power prediction model to obtain wind power and photovoltaic power; 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; A self-power supply control strategy is determined according to the charging strategy of the energy storage battery, and based on the self-power supply control strategy, any one of wind and solar power generation equipment, energy storage battery or power grid is selected to power the tower.

[0005] A second aspect of an embodiment of the present invention provides a multi-source energy storage self-power supply system for an iron tower, comprising: The load demand forecasting module is used to predict the load demand of the tower based on the historical load data of the tower using a time series model; Energy power prediction module, used to obtain wind power and photovoltaic power based on meteorological data of the tower's geographical location; A charging strategy module 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; An execution module determines a self-power supply control strategy according to the charging strategy of the energy storage battery, and switches the wind and solar power generation equipment, the energy storage battery or the power grid to supply power to the tower based on the self-power supply control strategy.

[0006] According to a third aspect of an embodiment of the present invention, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the steps of the above-mentioned multi-source energy storage self-power supply method for an iron tower are implemented.

[0007] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method for self-powering a tower with multi-source energy storage are implemented.

[0008] The beneficial effects of the multi-source energy storage self-powering method, system, device, and storage medium for towers provided by the embodiments of the present invention are: Powering the tower through multiple energy sources avoids over-reliance on the mains power grid; the present invention predicts power generation power based on historical load data and accurate meteorological data, enabling advance judgment of the tower's power supply and demand. 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, and a power switching mechanism is selected, significantly improving the stability and reliability of the tower's power supply and effectively ensuring the quality of communication services. At the same time, the charging strategy for the energy storage battery is determined based on the charging strategy value, effectively extending the life of the energy storage battery and reducing the overall operating cost of the tower. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0010] Figure 1 A schematic flow chart of a multi-source energy storage self-power supply method for an iron tower provided in one embodiment of the present invention; Figure 2 A structural block diagram of a multi-source energy storage self-power supply system for an iron tower provided in one embodiment of the present invention; Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0011] In the following description, specific details such as particular system structures and techniques are provided for purposes of illustration, not limitation, to facilitate a thorough understanding of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

[0012] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below with reference to the accompanying drawings.

[0013] Please refer to Figure 1 , Figure 1 A schematic flow chart of a multi-source energy storage self-powering method for an iron tower provided in one embodiment of the present invention includes: S101: Input the historical load data of the tower into the time series model to obtain the load demand of the tower.

[0014] In this embodiment, the historical load data is information such as real-time power consumption and working hours of various electrical equipment of the tower in different seasons, different time periods, and different usage scenarios over a long period of time in the past.

[0015] Before entering the time series model, the collected historical load data is preprocessed. This preprocessing includes data cleaning to remove outliers caused by equipment failures, signal interference, etc., and data standardization to normalize load data of different magnitudes to a unified scale to improve data quality and usability.

[0016] The preprocessed historical load data is fed into a time series model. For example, the model deeply mines and learns the temporal trends and cyclical characteristics inherent in the data to predict the tower's load demand at different future time points (e.g., the next hour, six hours, or day). This model, in this embodiment, can accurately predict the tower's load demand by deeply mining and learning the temporal trends and cyclical characteristics inherent in the data.

[0017] S102: Inputting meteorological data of the geographical location of the tower into a power prediction model to obtain wind power and photovoltaic power.

[0018] In this embodiment, high-precision meteorological monitoring equipment is used to collect accurate meteorological data of the tower's geographical location, including but not limited to real-time wind speed, wind direction, temperature, humidity, light intensity, sunshine duration, etc., and the time interval for collecting meteorological data is ensured to be small enough to capture rapid changes in meteorological conditions.

[0019] 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, including: first, 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 moments in the future; wherein, the wind power prediction model is obtained by simulating the operating status and energy conversion process of the wind turbine, and combining it with historical wind power data for training and optimization.

[0020] In this embodiment, the meteorological data of the geographical location of the tower is input into the power prediction model to obtain the photovoltaic power, including: first, establishing a power prediction model of factors such as solar radiation intensity, photovoltaic panel tilt angle, and the impact of temperature on photovoltaic panel efficiency; secondly, inputting meteorological data such as light intensity, sunshine duration, ambient temperature, and technical parameters of the photovoltaic panel into the photovoltaic power prediction model to predict the future photovoltaic power, wherein the photovoltaic power prediction model is optimized through physical modeling of the photovoltaic panel power generation process and data-driven algorithm.

[0021] S103: Determine a 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.

[0022] In this embodiment, the state of charge (SOC) of the energy storage battery is monitored in real time to obtain the ratio of its current remaining charge to the total battery capacity. Based on the predicted tower load demand, wind power, photovoltaic power, and the energy storage battery's SOC, algorithms (such as particle swarm optimization and genetic algorithms) are used to determine the energy storage battery's charging strategy at different time points, while ensuring stable power supply to the tower load, with the goals of maximizing the utilization of wind and solar clean energy, extending the energy storage battery's service life, and reducing overall power supply costs. The charging strategy includes factors such as whether to charge, the charging power level, and the charging duration.

[0023] S104: Determine a self-power supply control strategy according to the charging strategy of the energy storage battery, and select any one of wind and solar power generation equipment, energy storage batteries or power grid to power the tower based on the self-power supply control strategy.

[0024] In this embodiment, a detailed self-power supply control strategy is further developed based on the determined energy storage battery charging strategy. This strategy specifies how to efficiently switch between wind and solar power generation equipment, energy storage batteries, or the grid to power the tower under different load demand, wind and solar power generation power, and energy storage battery charge state combinations. For example, when the sum of wind power and photovoltaic power is greater than the tower load demand and the state of charge of the energy storage battery is not fully charged, wind and solar power generation equipment will be used to power the tower first, and the excess electricity will be stored in the energy storage battery; when the sum of wind and solar power generation is less than the tower load demand but the state of charge of the energy storage battery is sufficient, the energy storage battery will provide additional power; when both wind and solar power generation and the power of the energy storage battery cannot meet the tower load demand, it will automatically switch to grid power supply to ensure the continuity and stability of the tower's power consumption; when wind power is greater than the tower load demand and the state of charge of the energy storage battery is not fully charged, wind and solar power generation equipment will be used to power the tower first; when photovoltaic power is greater than the tower load demand and the state of charge of the energy storage battery is not fully charged, photovoltaic power generation equipment will be used to power the tower first, and whether to charge will be determined based on the state of charge of the energy storage battery and the battery life.

[0025] Based on the self-power supply control strategy, the start and stop of wind and solar power generation equipment, power regulation, charge and discharge switching of energy storage batteries, and access and disconnection of power supply from the grid are monitored and automatically controlled in real time, realizing the intelligent and efficient operation of the multi-source energy storage self-power supply system for towers.

[0026] As can be seen from the above, the present invention avoids over-reliance on the mains power grid by powering the tower with multiple energy sources. By accurately predicting power generation based on historical load data and meteorological data, the present invention can predict the tower's power supply and demand in advance. The energy storage battery charging strategy is determined based on load demand, wind power, photovoltaic power, and the battery's state of charge, and a power supply switching mechanism is selected. This significantly improves the stability and reliability of the tower's power supply and effectively ensures the quality of communication services. Furthermore, the energy storage battery charging strategy is determined based on the charging strategy value, effectively extending the battery's lifespan and reducing the tower's overall operating costs.

[0027] In one embodiment of the present invention, the historical load data of the tower is input into a time series model to obtain the load demand of the tower, including: The external related data and the historical load data of the tower are integrated to obtain the target data, wherein the external related 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.

[0028] In this embodiment, the meteorological data of the externally associated data includes: temperature, humidity, air pressure, wind speed, precipitation, and other meteorological data for the area where the tower is located. Different meteorological conditions can affect the operating status of the equipment served by the tower. For example, high temperatures may increase the heat dissipation requirements of communication equipment, resulting in increased load; strong winds may affect the power consumption of some auxiliary equipment on the tower.

[0029] Holiday and weekday data in externally linked data includes weekdays, weekends, and statutory holidays. The traffic load and other loads carried by towers vary significantly depending on the date. For example, during weekday working hours, traffic may be concentrated on towers in commercial areas; while on holidays, tower loads in tourist areas may increase significantly.

[0030] Externally associated 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, thereby causing the communication load of the tower in the area to increase sharply.

[0031] In this embodiment, the external correlation data and the tower's historical load data need to be aligned temporally to ensure data accuracy. Methods for fusing the external correlation data and the tower's historical load data include weighted fusion and feature concatenation. Weighted fusion assigns different weights to the external correlation data and historical load data based on the degree to which different data elements in the external correlation data affect the tower's load demand. For example, weather data has a greater impact on load and can be assigned a higher weight, while holiday data has a relatively smaller impact and can be assigned a lower weight. Each data element is then multiplied by its corresponding weight and added together to produce the target data. Feature concatenation combines the various features of the external correlation data and historical load data to form a higher-dimensional dataset, serving as the target data. For example, features such as the power value of the historical load data, the temperature in the external correlation data, and whether it is a holiday, can be combined.

[0032] In this embodiment, a time series model (e.g., an autoregressive integrated moving average model, a seasonal autoregressive integrated moving average model, a 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 integrated moving average model is selected. If complex nonlinear relationships need to be processed, a long short-term memory network is selected.

[0033] 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, and the time series model is trained using the training set. During training, the model parameters are continuously adjusted to minimize prediction error. For example, for long-short-term memory networks, 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 and determine the load demand of the tower over a period of time. The prediction results can be either specific load power values or trends in load demand.

[0034] In one embodiment of the present invention, external correlation data and historical load data of the tower are fused to obtain target data, including: Time-align historical load data with external correlation data to construct a multi-dimensional feature vector; Calculate the weight of each dimension feature and historical load data in external correlation data based on the attention mechanism; The historical load data and the external associated data are fused according to the weight of each dimension feature in the external associated data and the historical load data to obtain the target data.

[0035] In this embodiment, before time-aligning the historical load data with the external associated data, the external associated data needs to be cleaned and standardized, and different data in the external associated data needs to be sorted according to timestamps to ensure that the time sequence of different data is correct.

[0036] In this embodiment, the time alignment method is to time-align externally associated data using the time dimension of historical load data as a benchmark. If historical load data is recorded hourly, the externally associated data is also organized and aggregated hourly. For data that cannot be accurately recorded at the same time granularity, appropriate methods can be used for approximate processing, such as allocating daily social activity data to each hour of the day.

[0037] In this embodiment, the multidimensional feature vector is constructed by combining the 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, whether it is a holiday, etc. At a certain time t, the feature vector can be expressed as x t =[P t , T t , H t ,⋯], where P t is the historical load power at that moment, T t is the temperature, H t It's humidity.

[0038] In this embodiment, external correlation data and historical tower load data are fused to generate target data. This involves: first, constructing a feature relationship graph, using historical load data and external correlation data as graph nodes. Edge weights between nodes are calculated using cosine similarity to form a feature relationship graph. Second, multi-head attention is used to calculate the weight distribution of different feature dimensions, with each head independently learning. Third, each weight is normalized using Layer Normalization to avoid the vanishing gradient problem. Finally, each weighted feature vector is passed through a fully connected layer for feature enhancement to generate the final target data.

[0039] In this embodiment, the target data is obtained by fusing the data based on the weights calculated by the attention mechanism, including: First, the multidimensional feature vector is input into the linear transformation layer to map it into three different spaces: query, key, and value. Let the input feature vector be x, then: Q=W Q ×x,K=W K ×x,V=W V ×x; where W Q 、W K and W V is the learnable weight matrix.

[0040] Secondly, calculate the similarity score between the query vector Q and the key vector K; use the dot product operation, that is, ;in, is the query vector i elements, is the jth element of the key vector, and the superscript T means transpose.

[0041] Secondly, the similarity scores are normalized and the softmax function is used to obtain the attention weights; the weights of each dimension feature j in the external associated data and the historical load data are calculated. The weight calculation formula for historical load data is as follows:

[0042] Among them, n is the number of feature dimensions.

[0043] Finally, let the historical load data be P and the external related data be X , the corresponding weight is , then the fused target data Y is:

[0044] in, is the j-th dimension external related data, is the attention weight of the j-th dimension external correlation data and historical load data, belongs to [0,1], The larger the value, the more significant the impact of this dimension feature on load demand.

[0045] In this embodiment, the fused target data is used to input the time series model to predict the tower load demand. The tower's historical load data may include electricity consumption records in different time periods and scenarios. Historical load data only reflects past electricity consumption patterns, while external related 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 load factors through the attention mechanism. , so that the fused target data can highlight the key influencing factors. After being input into the time series model, it can more accurately calculate the load demand and provide a reliable basis for the subsequent power supply strategy formulation.

[0046] In one embodiment of the present invention, a charging strategy for an energy storage battery is determined based on load demand, wind power, photovoltaic power, and the state of charge of the energy storage battery, including: Based on load demand, wind power, photovoltaic power and the state of charge of the energy storage battery, an optimization model is constructed with the goal of minimizing the grid power supply cost. The charging strategy of the energy storage battery is determined according to the optimization model; among them, the constraint condition of the energy storage battery charging strategy is the state of charge of the energy storage battery.

[0047] In this embodiment, an optimization model is constructed with the goal of minimizing the grid power supply cost, including defining the objective function as:

[0048] in, is the power supply price of the power grid in period t, is the power supply obtained from the grid during period t, is the state of charge (SOC) balance coefficient, which is used to adjust the penalty weight for SOC deviation from the reference value; is the state of charge of the energy storage battery at time period t, is the reference state of charge of the energy storage battery, The total number of periods in the optimization time window (for example, 24 hours, with each period being 1 hour).

[0049] In this embodiment, the objective function is used to construct an optimization model with the goal of minimizing the grid power supply cost, and serves as the core objective function when determining the energy storage battery charging strategy. As the electricity purchase cost in period t, As the power obtained from the grid during period t, the product of the two It can be used to quantify the power purchase cost of the power grid in each period. On the basis of minimizing the power supply cost of the power grid, this embodiment also introduces This penalty term is used to penalize the battery's state of charge (SOC) when it deviates from its reference SOC. Specifically, the SOC refers to the ratio of the battery's current remaining charge to its total capacity. This penalty term helps minimize grid power costs while avoiding overcharging and discharging, thereby extending battery life. Furthermore, all parameters in this objective function are dimensionless.

[0050] The power balance constraint is:

[0051] is the tower load power demand in time period t (unit: kW); is the wind power generation power in time period t (unit: kW); is the photovoltaic power generation power in time period t (unit: kW); is the charge and discharge power of the energy storage battery in time period t (unit: kW, positive value indicates discharge, negative value indicates charge), is the grid power in period t.

[0052] In this embodiment, the objective function is calculated based on the purpose of minimizing the grid power supply cost. However, considering power balance, this embodiment establishes a power balance constraint formula as a core constraint in this process to ensure that the tower's load demand during time period t matches the output power of each power supply method. When determining charging and power supply control strategies, this power balance constraint formula verifies that the power distribution of wind and solar power generation, energy storage batteries, and the power grid meets the load demand. This is a fundamental constraint for achieving power supply stability. The power balance constraint ensures a balanced supply and demand of power at the tower, avoids power outages caused by power mismatches, and improves power supply reliability.

[0053] The energy storage SOC constraint is:

[0054] in, The minimum state of charge allowed for the energy storage battery (e.g. 20%) to prevent over-discharge; The maximum state of charge allowed for the energy storage battery (e.g. 80%) to prevent overcharging.

[0055] Energy storage charging and discharging power limit:

[0056] in, It is the maximum charge and discharge power of the energy storage battery (unit: kW), which is determined by the battery specifications.

[0057] Upper limit of grid power supply:

[0058] in, The maximum power allowed to be drawn from the grid (unit: kW), set according to the grid agreement or device capacity.

[0059] 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 optimization models, such as maximizing the utilization rate of wind and solar power generation and extending the service life of energy storage batteries. These objectives can be weighted and combined to construct a multi-objective optimization model to integrate various factors. Constraints can also include energy storage battery charge and discharge power limits, charge and discharge frequency limits, and grid power supply capacity limits. These constraints are incorporated into the optimization model to ensure its feasibility and rationality. In this embodiment, a variety of optimization algorithms can be used to solve the optimization model, such as genetic algorithms, particle swarm optimization algorithms, and simulated annealing algorithms. The optimal optimization algorithm is selected by comparing the solution results and solution efficiency of different algorithms. Load demand, wind power, photovoltaic power, and the state of charge of the energy storage battery change in real time, necessitating real-time updates to the optimization model. The model is adjusted and optimized based on real-time data to ensure the real-time and accuracy of the charging strategy.

[0060] In one embodiment of the present invention, a charging strategy for an energy storage battery is determined based on load demand, wind power, photovoltaic power, and the state of charge of the energy storage battery, including: The load demand, wind power, photovoltaic power and state of charge of the energy storage battery are integrated to obtain a multi-dimensional feature vector. Calculate multiple matching degrees between the multidimensional feature vector and each charging strategy in the charging strategy library; the charging strategy library stores multiple charging strategies; The charging strategy of the energy storage battery is determined based on multiple matching degrees.

[0061] In this embodiment, in addition to the simple similarity calculation method mentioned above, other matching calculation methods can also be used, such as a matching calculation method based on fuzzy theory, a matching calculation method based on deep learning, etc.; these methods can better handle the uncertainty and ambiguity of the data and improve the accuracy of the matching calculation.

[0062] In this embodiment, when constructing a charging strategy library, various factors can be considered, such as different load demand scenarios, different wind and solar power generation conditions, and different energy storage battery states. By analyzing and mining historical data, a variety of different charging strategies are generated and stored in the charging strategy library. The charging strategy library can be continuously updated as actual operating conditions change. Based on real-time data and operating experience, the strategies in the charging strategy library can be adjusted and optimized to ensure the timeliness and effectiveness of the strategy library.

[0063] In this embodiment, when selecting a charging strategy based on the degree of matching, decision-making rules and expert experience can be incorporated. For example, when there are multiple strategies with a high degree of matching, the optimal strategy can be selected based on the decision-making rules and expert experience. Furthermore, a multi-attribute decision-making method can be used to comprehensively consider multiple factors when selecting a strategy.

[0064] In one embodiment of the present invention, a charging strategy for an energy storage battery is determined based on load demand, wind power, photovoltaic power, and the state of charge of the energy storage battery, including: Calculate wind power stability and photovoltaic stability; The target stability is obtained by weighted calculation based on wind power stability and photovoltaic stability; Obtaining a charging strategy value based on the state of charge and target stability of the energy storage battery; The charging strategy of the energy storage battery is determined according to the charging strategy value.

[0065] In this embodiment, the power supply stability calculation method is: The first step is to calculate the stability of renewable energy power (wind power, photovoltaic power); The calculation formula for wind power stability is:

[0066] The photovoltaic stability calculation formula is:

[0067] in, Indicates wind power stability, Indicates photovoltaic stability, are the standard deviations of wind power and photovoltaic power (reflecting volatility), respectively; , are the rated power of wind power and photovoltaic power respectively; ∈[0,1] ， ∈[0,1], the larger the value, the higher the stability.

[0068] In this embodiment, for the wind power stability calculation formula, Used to quantify the volatility of wind power. The larger the ratio, the stronger the volatility of wind power. This value is used to characterize the stability of wind power. A larger difference indicates greater wind power stability. The wind power stability calculation formula quantifies wind power stability into a value in the [0, 1] interval by calculating the ratio of the standard deviation of wind power to the rated power of the wind turbine. This provides a basis for charging strategies, such as prioritizing high-stability wind power for power supply or charging, improving power supply reliability and reducing grid dependence. Similarly, the photovoltaic stability calculation formula quantifies photovoltaic stability into a value in the [0, 1] interval by calculating the ratio of the standard deviation of photovoltaic power to the rated power of the photovoltaic module, providing a basis for charging strategies.

[0069] The second step is to calculate the target stability:

[0070] in, is the target stability, weight coefficient 、 Dynamic adjustment based on wind / solar installed capacity or real-time output ratio; In this embodiment, the charging strategy is formulated based on a combination of energy stability and energy storage status. Considering that both wind power and photovoltaic power are affected by natural conditions and have inherent volatility, this embodiment integrates the stability of wind power and photovoltaic power through a target stability formula to provide a comprehensive stability indicator for calculating the charging strategy value. The target stability formula incorporates wind and photovoltaic stability through dynamic weights γ and δ to provide a more comprehensive energy stability assessment, making the stability assessment more consistent with the actual energy mix and improving the adaptability of the charging strategy.

[0071] Step 3: Calculate the charging strategy value

[0072] Among them, SOC∈[0,1] is the current battery state of charge; CSV∈[0,1] is the charging strategy value, and the larger the value, the higher the charging demand. Step 4: Adjust the charging power according to CSV. The formula is:

[0073] in: To adjust the charging power, The maximum charging power of energy storage; Excess power from renewable energy sources; Energy storage battery SOC safety upper limit.

[0074] In this embodiment, for the charging strategy value calculation formula, It can reflect the impact of the state of charge (SOC) of the energy storage battery on the charging demand. When the SOC is lower, the larger (1-SOC) is, which means the battery is more depleted and the charging demand is more urgent. The larger the value, the higher the overall stability of the wind and solar hybrid energy, and the greater the reliability of charging using wind and solar energy. The larger the value, the higher the charging priority, indicating that the battery currently needs charging and the wind and solar energy is stable (suitable for charging). If only considering SOC when developing a charging strategy, forced charging may occur when wind and solar energy fluctuates drastically (low stability), resulting in unstable power supply. The charging strategy value calculation formula in this embodiment ensures that charging priority is increased only when charging is required and the energy source is stable, achieving a combination of on-demand charging and reliable charging.

[0075] In this embodiment, for the charging power adjustment formula, is the maximum allowable charging power calculated based on the charging strategy value. The more urgent the charging demand is and the higher the stability of wind and solar energy is, the higher the The larger the The larger the value, the higher the charging power. As the remaining power available for charging after deducting the load demand from wind and solar power generation, When the battery is not fully charged, the present embodiment and Taking the minimum value as the adjusted charging power can ensure that the charging power neither exceeds the battery hardware limitation nor exceeds the actual available excess energy, avoiding power consumption from the grid and reducing costs. Right now When the battery is fully charged, the charging power is set to 0, stopping charging to prevent overcharging and battery damage. This charging power adjustment formula dynamically adjusts the charging strategy, prioritizing excess, highly stable wind and solar energy for charging, reducing grid dependence, lowering costs, and extending battery life.

[0076] In this embodiment, wind / solar stability is quantified using standardized volatility (standard deviation / rated power). The closer the stability value is to 1, the more stable it is. This embodiment uses dynamic weighting to reflect the difference in wind / solar contributions to stability. The lower the SOC and the more stable the power supply system, the higher the charging demand. Charging is stopped when the SOC approaches the upper limit. This embodiment also adjusts the charging power based on excess power and charging strategy values to avoid overcharging.

[0077] In one embodiment of the present invention, determining a charging strategy for an energy storage battery based on multiple matching degrees includes: When the charging strategy matches multiple charging strategies in the preset strategy rule base, the multiple charging strategies are sorted according to the priority sorting preset in the strategy rule base to obtain a first sorting list, and the charging strategy is determined based on the first sorting list.

[0078] In this embodiment, priority is primarily determined based on the importance of system operation and cost-effectiveness. Strategies that play a significant role in ensuring stable system operation and reducing costs are given a higher priority. For example, prioritizing wind and solar power for charging can reduce grid reliance, lower energy costs, and benefit the environment. Therefore, such strategies are typically given a higher priority. While charging during off-peak hours can also reduce costs, the benefits are slightly lower compared to charging with wind and solar power, so they are given a moderate priority. Multiple matching charging strategies are ranked based on the priorities assigned to each strategy in the preset strategy rule base to generate a first ranked list. For example, if strategy A (high priority), strategy B (medium priority), and strategy C (low priority) are matched, the order of the first ranked list is strategy A, strategy B, strategy C. The charging strategy with the highest priority from the first ranked list is selected as the final charging strategy, prioritizing wind and solar power for charging the energy storage battery.

[0079] 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, such as changes in the energy storage battery's state of charge and load demand. If the system's operating status changes during execution, rendering the current strategy no longer applicable, the matching, sorting, and strategy selection processes are re-performed to ensure that the energy storage battery charging strategy always adapts to the system's actual operating conditions.

[0080] Corresponding to the above embodiment of the multi-source energy storage self-power supply method for the iron tower, Figure 2 This is a structural block diagram of a multi-source energy storage self-power supply system for a tower provided by an embodiment of the present invention. For ease of explanation, only the parts related to the embodiment of the present invention are shown. Figure 2 The multi-source energy storage self-power supply 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.

[0081] 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; Energy power prediction module 22, used to obtain wind power and photovoltaic power based on meteorological data of the tower's geographical location; A charging strategy module 23 is configured to determine a 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 24 determines a self-power supply control strategy according to the charging strategy of the energy storage battery, and switches the wind and solar power generation equipment, the energy storage battery or the power grid to supply power to the tower based on the self-power supply control strategy.

[0082] In one embodiment of the present invention, the load demand forecasting module 21 is specifically configured to: The target data is obtained by fusing external related data with the tower's historical load data. The external related data includes: meteorological data, holiday and weekday data; The target data is input into the time series model to predict the load demand of the tower.

[0083] In one embodiment of the present invention, the load demand forecasting module 21 is specifically configured to: Time-align historical load data with external correlation data to construct a multi-dimensional feature vector; Calculate the weight of each dimension feature and historical load data in external correlation data based on the attention mechanism; The historical load data and the external associated data are fused according to the weight of each dimension feature in the external associated data and the historical load data to obtain the target data.

[0084] In one embodiment of the present invention, the charging strategy module 23 is specifically configured to: 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, including: Based on load demand, wind power, photovoltaic power and the state of charge of the energy storage battery, an optimization model is constructed with the goal of minimizing the grid power supply cost. The charging strategy of the energy storage battery is determined according to the optimization model; among them, the constraint condition of the energy storage battery charging strategy is the state of charge of the energy storage battery.

[0085] In one embodiment of the present invention, the charging strategy module 23 is specifically configured to: 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, including: The load demand, wind power, photovoltaic power and state of charge of the energy storage battery are integrated to obtain a multi-dimensional feature vector. Calculate multiple matching degrees between the multidimensional feature vector and each charging strategy in the charging strategy library; the charging strategy library stores multiple charging strategies; The charging strategy of the energy storage battery is determined based on multiple matching degrees.

[0086] In one embodiment of the present invention, the charging strategy module 23 is specifically configured to: 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, including: Calculate wind power stability and photovoltaic stability; The target stability is obtained by weighted calculation based on wind power stability and photovoltaic stability; Obtaining a charging strategy value based on the state of charge and target stability of the energy storage battery; The charging strategy of the energy storage battery is determined according to the charging strategy value.

[0087] In one embodiment of the present invention, the charging strategy module 23 is specifically configured to: Determine the charging strategy for the energy storage battery based on multiple matching degrees, including: When the charging strategy matches multiple charging strategies in the preset strategy rule base, the multiple charging strategies are sorted according to the priority sorting preset in the strategy rule base to obtain a first sorting list, and the charging strategy is determined based on the first sorting list.

[0088] The multi-source energy storage self-powering method, system, device, and storage medium provided by the embodiments of the present invention offer the following advantages: by predicting power generation based on historical load data and accurate meteorological data, the tower's power supply and demand can be predicted in advance. 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, and a power supply switching mechanism is selected. This significantly improves the stability and reliability of the tower's power supply and effectively ensures the quality of communication services. Furthermore, the charging strategy for the energy storage battery is determined based on the charging strategy value, effectively extending the battery life and reducing the tower's overall operating costs.

[0089] See also Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided by an embodiment of the present invention. Figure 3 The electronic device 300 in the embodiment shown 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 memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of the modules in the above-mentioned device embodiments, such as Figure 2 The functions of the load demand prediction module 21, the energy power prediction module 22, the charging strategy module 23 and the execution module 24 are shown.

[0090] It should be understood that in the embodiment of the present invention, the processor 301 may be a central processing unit (CPU), and may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0091] The input device 302 may include a touchpad, a fingerprint collection sensor (for collecting user fingerprint information and fingerprint direction information), a microphone, etc. The output device 303 may include a display (LCD, etc.), a speaker, etc.

[0092] The memory 304 may include a read-only memory and a random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store device type information.

[0093] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiment of the present invention can execute the implementation methods described in the first and second embodiments of the multi-source energy storage self-power supply method for the iron tower provided by the embodiment of the present invention, and can also execute the implementation methods of the electronic device described in the embodiment of the present invention, which will not be repeated here.

[0094] In another embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program. The computer program includes program instructions. When executed by a processor, the program instructions implement all or part of the process of the method in the above-mentioned embodiment. The computer program can also be used to instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. Computer-readable media can include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium.

[0095] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the aforementioned 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, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Furthermore, the computer-readable storage medium can include both an internal storage unit of the electronic device and an external storage 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 is about to be output.

[0096] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0097] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0098] 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 schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or can be an electrical, mechanical or other form of connection.

[0099] Units described as separate components may or may not be physically separate, and 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 these units may be selected based on actual needs to achieve the objectives of the embodiments of the present invention.

[0100] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0101] 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 such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A multi-source energy storage self-powering method for an iron tower, characterized in that: include: Input the tower's historical load data into the time series model to obtain the tower's load demand; The meteorological data of the tower's geographical location is input into the power prediction model to obtain wind power and photovoltaic power; 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; A self-power supply control strategy is determined according to the charging strategy of the energy storage battery, and based on the self-power supply control strategy, any one of wind and solar power generation equipment, energy storage battery or power grid is selected to power the tower.

2. The multi-source energy storage self-power supply method for an iron tower according to claim 1, characterized in that: The process of inputting the historical load data of the tower into the time series model to obtain the load demand of the tower includes: The external related data and the historical load data of the tower are integrated to obtain the target data, wherein the external related 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-power supply method for an iron tower according to claim 2, characterized in that: The external correlation data and the historical load data of the tower are integrated to obtain the target data, including: Time-align historical load data with external correlation data to construct a multi-dimensional feature vector; Calculate the weight of each dimension feature and historical load data in external correlation data based on the attention mechanism; The historical load data and the external associated data are fused according to the weight of each dimensional feature in the external associated data and the historical load data to obtain target data.

4. The multi-source energy storage self-power supply method for an iron tower according to claim 1, characterized in that: The method of 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 includes: Based on load demand, wind power, photovoltaic power, and the state of charge of the energy storage battery, an optimization model is constructed with the goal of minimizing the grid power supply cost. The charging strategy of the energy storage battery is determined based on the optimization model; wherein the constraint condition of the energy storage battery charging strategy is the state of charge of the energy storage battery.

5. The multi-source energy storage self-power supply method for an iron tower according to claim 1, characterized in that: 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, including: The load demand, wind power, photovoltaic power and state of charge of the energy storage battery are integrated to obtain a multidimensional feature vector; Calculating multiple matching degrees between the multidimensional feature vector and each charging strategy in a charging strategy library; the charging strategy library stores multiple charging strategies; A charging strategy for the energy storage battery is determined based on the multiple matching degrees.

6. The multi-source energy storage self-power supply method for an iron tower according to claim 5, characterized in that: Determining a charging strategy for the energy storage battery based on the multiple matching degrees includes: When the charging strategy matches multiple charging strategies in a preset strategy rule base, the multiple charging strategies are sorted according to a priority sorting preset in the strategy rule base to obtain a first sorting list, and the charging strategy is determined based on the first sorting list.

7. The multi-source energy storage self-power supply method for an iron tower according to claim 1, characterized in that: 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, including: Calculate wind power stability and photovoltaic stability; Obtaining target stability by weighted calculation based on the wind power stability and the photovoltaic stability; Obtaining a charging strategy value according to the state of charge of the energy storage battery and the target stability; A charging strategy for the energy storage battery is determined according to the charging strategy value.

8. A multi-source energy storage self-power supply system for an iron tower, characterized in that: include: The load demand forecasting module is used to predict the load demand of the tower based on the historical load data of the tower using a time series model; Energy power prediction module, used to obtain wind power and photovoltaic power based on meteorological data of the tower's geographical location; A charging strategy module 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; An execution module determines a self-power supply control strategy according to the charging strategy of the energy storage battery, and switches the wind and solar power generation equipment, the energy storage battery or the power grid to supply power to the tower based on the self-power supply control strategy.

9. 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, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images