Energy collaborative management system and method based on energy storage battery

Abstract

The invention relates to the technical field of ship energy management, particularly discloses an energy collaborative management system and method based on an energy storage battery, and is used for solving the problems that when an existing ship energy management system integrates energy storage battery information, it is difficult to accurately evaluate actual energy consumption requirements, and consequently energy waste and equipment overload risks are caused. The system comprises an energy storage system unit, a system monitoring unit, a data processing unit and an energy management system unit, and is characterized in that the system operation state is determined according to real-time data monitored by the system monitoring unit; by introducing an adaptive learning rate adjustment formula, dynamically adjusting a weight factor, optimizing an energy efficiency function, adjusting output power of an energy storage battery and a generator in real time, optimizing energy distribution, ensuring stable power supply, reducing overload of the generator and energy waste, improving stability and reliability of a ship electric power system especially in a complex navigation environment, and reducing energy consumption. The service life of equipment is prolonged and the overall operation cost of ships is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of ship energy management, and more specifically, to an energy collaborative management system and method based on energy storage batteries. Background Art

[0002] In the field of ships, energy management systems are crucial to the stable operation of ship power systems. With the increase in ship power demand and the introduction of new energy technologies, how to efficiently manage energy and avoid unnecessary energy waste has become a key issue. Energy storage battery systems have gradually become an important part of ship power systems, which can effectively reduce the workload of generators, improve the ability of ships to cope with sudden fluctuations in load demand and load shocks, and improve the overall energy utilization efficiency of the system, providing stable, safe and reliable energy supply guarantees for ship operations. However, the existing energy management system has some shortcomings in integrating energy storage battery information, making it difficult to accurately assess actual energy demand, resulting in energy waste and potential overload risks of equipment, which seriously hinders the stable, safe, reliable and sustainable operation of ships. The existing ship energy management systems are mainly divided into two categories: one is a system that uses only digital quantity interaction instructions, and the other is a system that combines digital quantity interaction instructions with analog quantity status information interaction. The former is limited to controlling the start and stop of energy-consuming equipment, but lacks effective restrictions and optimization on the power used by energy-consuming equipment, which can easily lead to generator overload or system downtime. Although the latter introduces analog information, allowing energy-consuming equipment to self-regulate according to the available power, it still does not fully consider the available power information of the energy storage battery and cannot achieve overall optimization of energy management. The existing system fails to fully consider the real-time status of the energy storage battery in energy management, resulting in the generator starting up unnecessarily, thus wasting energy. Since the existing system cannot accurately manage the power of energy-consuming equipment, the generator will overload in some cases, increasing the risk of equipment damage. The data collection of the existing system is not comprehensive enough, and it fails to make full use of key information such as the health status, charging and discharging status of the energy storage system to make intelligent management decisions. Summary of the invention

[0003] In order to overcome the above-mentioned defects of the prior art, the present invention provides an energy collaborative management system and method based on energy storage batteries, which optimizes energy distribution by adjusting the output power of energy storage batteries and generators in real time, ensures stable power supply, reduces generator overload and energy waste, and improves the stability and reliability of the ship's power system, extends the service life of equipment, and reduces the overall operating cost of the ship, especially in complex navigation environments.

[0004] In daily navigation, ships will encounter special application scenarios where multiple ships are sailing in parallel, especially when passing through busy waterways or ports. In this case, ships need to maintain close communication and coordination with other ships around them to ensure the safety and efficiency of navigation. However, the parallel navigation of multiple ships puts forward special requirements for the ship's energy management system. In particular, when frequent communication and positioning adjustments are made between ships, how to optimize energy distribution, avoid energy waste, and ensure the stable operation of key ship equipment has become a special and challenging technical problem. In this special situation of multiple ships sailing in parallel, high-energy-consuming equipment such as the ship's communication system, radar system, and navigation system need to maintain high-load operation for a long time to achieve real-time information exchange and accurate course adjustment with other ships. In addition, since ships need to frequently adjust their speed and course in busy waterways, the ship's propulsion system also needs to respond flexibly, which further increases energy consumption. In this scenario, it is difficult for existing ship energy management systems to accurately assess actual energy demand, especially when integrating energy storage battery information, which can easily lead to unreasonable energy distribution, thereby causing energy waste or equipment overload risks.

[0005] In view of the above application scenarios, in order to achieve the above objectives, the present invention provides the following technical solutions:

[0006] An energy collaborative management system based on energy storage batteries includes an energy storage system unit, a system monitoring unit, a data processing unit and an energy management system unit. The energy storage system unit includes an isolating switch, an energy storage battery and a battery management system. The system monitoring unit includes a battery health monitoring module, a power supply busbar monitoring module and a system operation monitoring module. The data processing unit includes an energy collaborative management central processing module. The energy management system unit includes an energy-consuming equipment management module. The energy collaborative management central processing module dynamically adjusts the output power of the energy storage battery and the generator according to the real-time energy demand and power generation capacity, charges the energy storage battery during low-load periods, releases electric energy during high-load periods, balances the system load, automatically adjusts the energy distribution strategy through real-time monitoring and feedback, and adopts a multi-objective optimization strategy in combination with power generation cost, energy storage efficiency and system fluctuations, so that the system tends to the optimal operating state. The multi-objective optimization management formula is:

[0007]

[0008] Where: t is the current time, Z a (t) is the system operation status indicator at the current moment, T is the optimization window duration, which is set according to the requirements, and C fd (t) is the operating cost of the generator at time t, C cn(t) is the charging and discharging cost of the energy storage battery at the tth moment, R(t) is the volatility of the energy demand at the tth moment, α, β, and γ are the weight factors of power generation cost, energy storage cost, and energy demand volatility, respectively, which are dynamically adjusted through the weight factor optimization algorithm.

[0009] As a further solution of the present invention, the energy storage system unit is connected to the system monitoring unit to provide battery status information, and the system monitoring unit is connected to the data processing unit to perform real-time data monitoring and transmission. The data processing unit optimizes energy distribution through the energy collaborative management central processing module and controls the energy-consuming equipment management module in the energy management system unit to achieve efficient operation.

[0010] As a further solution of the present invention, in the energy collaborative management central processing module, the weight factor optimization algorithm dynamically adjusts the power generation cost, energy storage cost and energy demand volatility weight factors by balancing the learning rate, momentum and regularization, and gradually optimizing the energy efficiency function. The dynamic adjustment formula of the weight factor involved in the weight factor optimization algorithm is:

[0011]

[0012] Where: i is the weight factor index, when i=1, is the power generation cost weight factor α, when i=2, is the energy storage cost weight factor β, when i=3, is the energy demand volatility weight factor γ, Update the value for the weight factor, is the weight factor at the current moment, η(t) is the adaptive learning rate, which is dynamically adjusted according to the actual operating status of the system, and E is the energy efficiency function of the system. is the energy efficiency function with respect to the weight factor The first-order partial derivative of , μ is the momentum coefficient, equal to 0.99, is the difference between the weight factors at the previous and next moments.

[0013] As a further solution of the present invention, in the energy collaborative management central processing module, the adaptive learning rate is automatically adjusted as the gradient information accumulates. The formula of the adaptive learning rate is:

[0014]

[0015] Where: k is the index of the time step, η0 is the initial learning rate, is the basic step size when there is no historical gradient information, is 0.001, and ∈ is a constant to prevent the denominator from being zero.

[0016] As a further solution of the present invention, the energy storage system unit dynamically adjusts the charging and discharging strategy of the energy storage battery according to the current system operation status index and optimization results, balances the system load, minimizes the energy storage cost and smoothes the energy demand fluctuation. The energy storage battery charging and discharging power management formula is:

[0017] In P req (t) <P fd (t),

[0018] Where: P req (t) is the total energy demand of the system at time t, P fd (t) is the output power of the generator at the tth moment, P cn (t) is the charging and discharging power of the energy storage battery at the tth moment, P cd,max (t) is the maximum charging power of the energy storage battery at time t;

[0019] In P req (t)>P fd (t),

[0020] Where: P fd,max (t) is the maximum discharge power of the energy storage battery at moment t.

[0021] As a further solution of the present invention, in the system monitoring unit, according to the system operation state Z a (t) is fed back to adjust the monitoring voltage of the power supply busbar. The monitoring voltage adjustment formula of the power supply busbar is:

[0022]

[0023] Where: V mp (t) is the actual voltage of the power supply busbar at the tth moment, V bc It is the nominal voltage value of the power supply busbar.

[0024] As a further solution of the present invention, the energy management system unit is based on the system operation status indicator Z a (t) feedback to regulate the energy consumption of each energy-consuming device. The energy consumption adjustment formula of the energy-consuming device is:

[0025]

[0026] Where: j is the energy-consuming equipment index, P dev,j (t) is the energy consumption of the jth energy-consuming device at the tth time, P e,j is the rated power of the jth energy-consuming device, and n is the total number of energy-consuming devices that need to be adjusted in the system.

[0027] An energy collaborative management method based on energy storage batteries, using the above-mentioned energy collaborative management system based on energy storage batteries, comprises the following steps:

[0028] Step 1, system initialization and data collection: Initialize the energy collaborative management system, set initial parameters, start the system monitoring unit, collect data related to the energy storage battery status, power supply bus status, and system operation status in real time, start the data processing unit, receive and store monitoring data;

[0029] Step 2: Real-time energy demand evaluation and optimization: At each time step t, the data processing unit calculates the current energy demand P of the system based on the real-time collected data. req (t), charging and discharging power P of the energy storage battery cn (t) and generator output power P fd (t), the energy collaborative management central processing module evaluates the current system operation status indicator Z a (t), combined with the multi-objective optimization management formula, determine the weight factors α, β, γ of power generation cost, energy storage cost, and energy demand volatility, and optimize the energy allocation strategy;

[0030] Step 3: Charge and discharge management of energy storage batteries: According to the energy demand and generator output power, determine the working mode of the energy storage battery. In low load mode, i.e. P req (t) <P fd At (t), the energy storage battery is charged, and the charging power calculation formula is: In P req (t)>P fd At (t), the energy storage battery is discharged, and the discharge power calculation formula of the energy storage battery is:

[0031] Step 4: Dynamic adjustment of the power supply bus voltage: According to the system operation status indicator Z a (t) and energy demand volatility R(t), adjust the actual voltage of the power supply bus in real time, and the power supply bus monitoring module continuously monitors the adjustment results to ensure that the voltage is stable within a safe range;

[0032] Step 5: Control of energy consumption of energy-consuming equipment: Calculate the energy consumption adjustment formula of each energy-consuming equipment according to the current system operation status, and the energy-consuming equipment management module adjusts the operating parameters of each equipment to ensure that the total energy consumption is consistent with the system optimization target;

[0033] Step 6, system feedback and adaptive adjustment: The system monitoring unit feeds back the operating status and data of each module to the energy collaborative management central processing module in real time, dynamically adjusts the weight factor through the adaptive learning rate adjustment formula, optimizes the energy efficiency function, and adjusts the energy allocation strategy for subsequent time steps according to the optimization results. The system executes the above steps in a loop, continuously optimizes the energy management strategy, and ensures that the system maintains the best operating state under different load conditions.

[0034] For the above-mentioned application scenarios, the technical effects of the present invention are as follows: the present invention can dynamically adjust the output power of the energy storage battery and the generator according to the real-time energy demand and power generation capacity, ensuring that the excess power is fully utilized to charge the energy storage battery during low-load periods, and the energy storage power is released during high-load periods to balance the system load and reduce the risk of overload of the generator. Secondly, by optimizing the weight factors of power generation cost, energy storage cost and energy demand volatility, the system realizes the optimal decision of energy allocation, avoids energy waste and improves the overall energy utilization efficiency. In addition, the adaptive adjustment mechanism and real-time feedback function of the system ensure the voltage stability of the power supply busbar, and the energy consumption of the energy equipment is consistent with the system optimization goal. Especially in high dynamic environments such as multiple ships sailing in parallel, it can significantly improve the stability and reliability of the ship's power system, reduce the risk of equipment damage, extend the service life of the equipment, and reduce the overall operating cost of the ship. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 is a system block diagram of the present invention;

[0036] Figure 2 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the present invention to clearly and completely describe the technical solutions in the present invention. Obviously, the described content is only a part of the present invention, not all of it. Based on the content of the present invention, all other technical solutions obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0038] like Figure 1As shown, the present invention proposes an energy collaborative management system based on energy storage batteries, including an energy storage system unit, a system monitoring unit, a data processing unit and an energy management system unit. The energy storage system unit includes an isolating switch, an energy storage battery and a battery management system. The system monitoring unit includes a battery health monitoring module, a power supply busbar monitoring module and a system operation monitoring module. The data processing unit includes an energy collaborative management central processing module. The energy management system unit includes an energy-consuming equipment management module. The energy collaborative management central processing module dynamically adjusts the output power of the energy storage battery and the generator according to the real-time energy demand and power generation capacity, charges the energy storage battery during low-load periods, releases electric energy during high-load periods, balances the system load, and automatically adjusts the energy distribution strategy through real-time monitoring and feedback. In combination with power generation cost, energy storage efficiency and system fluctuations, a multi-objective optimization strategy is adopted to make the system tend to the optimal operating state. The multi-objective optimization management formula is:

[0039]

[0040] Where: t is the current time, Z a (t) is the system operation status indicator at the current moment, T is the optimization window duration, which is set according to the requirements, and C fd (t) is the operating cost of the generator at time t, C cn (t) is the charging and discharging cost of the energy storage battery at the tth moment, R(t) is the volatility of the energy demand at the tth moment, α, β, and γ are the weight factors of power generation cost, energy storage cost, and energy demand volatility, respectively, which are dynamically adjusted through the weight factor optimization algorithm.

[0041] The present invention proposes an energy storage system unit, a system monitoring unit, a data processing unit, and an energy management system unit. The energy storage system unit includes an isolating switch, an energy storage battery, and a battery management system. The isolating switch is an electrical device / component that isolates and overcurrent protects the energy storage system. The energy storage battery includes several groups of energy storage battery packs. The battery management system is an integrated system for battery discharge control and monitoring, which receives energy storage battery charge and discharge control instructions sent from the data processing unit. The system monitoring unit includes battery health monitoring, power supply busbar monitoring, and system operation monitoring. Battery health monitoring is to connect data with the energy storage system through the bus communication module. The connected data includes the charge and discharge voltage and current, resistance, power, temperature, operating time, charge and discharge status, battery health status (historical records of system failures, maintenance and replacement, etc.) of the energy storage battery. Power supply busbar monitoring is to collect data and monitor the insulation and voltage conditions of the power supply busbar. System operation monitoring is to monitor the operating status of the energy consumption system, including system start and stop status and system failure status. The data processing unit includes an energy collaborative management central processing module, which is a central processing module / device that receives data from the system monitoring unit, the energy storage system unit, and the energy management system unit, and performs corresponding logical judgment and diagnosis. The logical judgment and diagnosis results of the energy collaborative management central processing module are communicated with the energy management system through the bus communication module to achieve the purpose of controlling the battery discharge inside the battery management system. The logical judgment and diagnosis results of the energy collaborative management central processing module exchange data with the energy management system through the bus communication module. The exchanged data includes sending energy demand power (kilowatts) and system startup request instructions to the energy management system. Among them, energy demand power = total system demand power - available power of energy storage system. The exchanged data also includes receiving available power (kilowatts) from the energy management system, energy consumption equipment energy consumption limit instructions, etc.

[0042] The present invention can dynamically adjust the output power of energy storage batteries and generators according to real-time energy demand and power generation capacity, ensuring that excess electricity is fully utilized to charge the energy storage batteries during low-load periods, and releasing the stored energy during high-load periods, balancing the system load, and reducing the risk of generator overload. Secondly, by optimizing the weight factors of power generation cost, energy storage cost and energy demand volatility, the system achieves the optimal decision for energy allocation, avoids energy waste, and improves overall energy utilization efficiency. In addition, the system's adaptive adjustment mechanism and real-time feedback function ensure the voltage stability of the power supply busbar, and the energy consumption of the energy-saving equipment is consistent with the system optimization goal. Especially in high-dynamic environments such as multiple ships sailing in parallel, it can significantly improve the stability and reliability of the ship's power system, reduce the risk of equipment damage, extend the service life of the equipment, and reduce the overall operating cost of the ship.

[0043] It should be noted that the energy storage system unit is connected to the system monitoring unit to provide battery status information, and the system monitoring unit is connected to the data processing unit to perform real-time data monitoring and transmission. The data processing unit optimizes energy distribution through the energy collaborative management central processing module and controls the energy-consuming equipment management module in the energy management system unit to achieve efficient operation.

[0044] By connecting the energy storage system unit to the system monitoring unit to obtain battery status information, and connecting the system monitoring unit to the data processing unit for real-time data monitoring and transmission, it is ensured that the charging and discharging process of the energy storage battery can be dynamically adjusted based on accurate and real-time status information. The data processing unit optimizes energy distribution through the energy collaborative management central processing module and controls the energy-consuming equipment management module in the energy management system unit to achieve consistency between energy consumption and system optimization goals. This efficient collaborative management significantly improves the overall energy efficiency of the system, reduces energy waste, and ensures the stable operation of the ship's power system under various load conditions, especially effectively reducing the risk of equipment overload and failure in complex navigation scenarios.

[0045] It should be noted that in the energy collaborative management central processing module, the weight factor optimization algorithm dynamically adjusts the weight factors of power generation cost, energy storage cost and energy demand volatility by balancing learning rate, momentum and regularization, and gradually optimizing the energy efficiency function. The dynamic adjustment formula of the weight factor involved in the weight factor optimization algorithm is:

[0046]

[0047] Where: i is the weight factor index, when i=1, is the power generation cost weight factor α, when i=2, is the energy storage cost weight factor β, when i=3, is the energy demand volatility weight factor γ, Update the value for the weight factor, is the weight factor at the current moment, η(t) is the adaptive learning rate, which is dynamically adjusted according to the actual operating status of the system, and E is the energy efficiency function of the system. is the energy efficiency function with respect to the weight factor The first-order partial derivative of , μ is the momentum coefficient, equal to 0.99, is the difference between the weight factors at the previous and next moments.

[0048] By applying the weight factor optimization algorithm in the energy collaborative management central processing module and dynamically adjusting the weight factors of power generation cost, energy storage cost and energy demand volatility, the system can more effectively adapt to the complex and changing energy management environment. Specifically, the adaptive learning rate is used to dynamically adjust the step size according to the actual operating status of the system to ensure that the optimization process between power generation, energy storage and energy demand fluctuations is both fast and stable. By introducing the historical differences of momentum coefficients and weight factors, the algorithm can smooth the adjustment process and avoid over-adjustment or oscillation, thereby more accurately optimizing the energy efficiency function of the system. The introduction of regularization further prevents over-adjustment of weight factors and ensures the stability of the system in long-term operation. This optimization algorithm dynamically adjusts key weight factors, enabling the energy management system to respond to changes in actual energy demand and power generation capacity in real time, effectively reducing the risk of energy waste and equipment overload, and improving the overall energy utilization efficiency and operational stability of the system, especially under complex ship navigation conditions, ensuring that the system can maintain optimal operating conditions under various load and demand changes.

[0049] It should be noted that in the energy collaborative management central processing module, the adaptive learning rate is automatically adjusted as the gradient information accumulates. The formula for the adaptive learning rate is:

[0050]

[0051] Where: k is the index of the time step, η0 is the initial learning rate, is the basic step size when there is no historical gradient information, is 0.001, and ∈ is a constant to prevent the denominator from being zero.

[0052] In the energy collaborative management central processing module, an adaptive learning rate is introduced and dynamically adjusted through a formula, so that the system can automatically adjust the learning rate according to the cumulative changes in gradient information. As time goes by and the gradient changes accumulate, the system can adjust the optimization step in real time, so that the learning rate can dynamically adapt to the current optimization environment during the weight factor adjustment process. When the gradient is large, the learning rate automatically decreases to avoid oscillation or instability caused by excessive adjustment steps; when the gradient is small, the learning rate increases accordingly to speed up the system convergence. This adaptive mechanism ensures that the system can optimize the energy efficiency function in a stable and efficient manner when dealing with complex and dynamic energy management needs. In this way, the system avoids the problems of slow convergence or over-adjustment that may be caused by traditional fixed learning rates, improves the robustness and accuracy of the optimization algorithm, especially in the changeable ship navigation environment, so that the system can always maintain the best operating state under different load and demand conditions, reduce energy waste, and prevent equipment overload.

[0053] It should be noted that the energy storage system unit dynamically adjusts the charging and discharging strategy of the energy storage battery according to the current system operating status indicators and optimization results, balances the system load, minimizes the energy storage cost and smoothes the energy demand fluctuation. The energy storage battery charging and discharging power management formula is:

[0054] In P req (t) <P fd (t),

[0055] Where: P req (t) is the total energy demand of the system at time t, P fd (t) is the output power of the generator at the tth moment, P cn (t) is the charging and discharging power of the energy storage battery at the tth moment, P cd,max (t) is the maximum charging power of the energy storage battery at time t;

[0056] In P req (t)>P fd (t),

[0057] Where: P fd,max (t) is the maximum discharge power of the energy storage battery at moment t.

[0058] By dynamically adjusting the charging and discharging strategies of the energy storage battery according to the current system operating status indicators and optimization results, the system can effectively balance power supply and demand under different load conditions, minimize energy waste and reduce operating costs. During low-load periods, when the total energy demand of the system is less than the output power of the generator, the charging power of the energy storage battery is calculated according to the optimization formula to ensure that the charging process uses as much excess power as possible without exceeding the maximum charging capacity of the battery. During high-load periods, when P req (t)>P fd At (t), the energy storage battery discharge power is optimized according to the energy demand fluctuation and system operating status to ensure smooth energy demand fluctuations and avoid generator overload. This dynamic charge and discharge management strategy not only improves the efficiency of energy storage batteries, but also ensures the stability and efficient operation of the system under various complex working conditions by precisely controlling the charge and discharge process.

[0059] It should be noted that in the system monitoring unit, according to the system operation status Z a (t) is fed back to adjust the monitoring voltage of the power supply busbar. The monitoring voltage adjustment formula of the power supply busbar is:

[0060]

[0061] Where: V mp (t) is the actual voltage of the power supply busbar at the tth moment, Vbc It is the nominal voltage value of the power supply busbar.

[0062] By dynamically adjusting the monitoring voltage of the power supply busbar according to the feedback of the system operating status through the system monitoring unit, the system can respond more accurately to the volatility of energy demand and changes in power generation and energy storage costs. This adjustment ensures that the power supply busbar voltage is always maintained at an optimized level, avoiding equipment damage or system instability caused by excessively high or low voltage. Specifically, the formula introduces weight factors to comprehensively consider the impact of power generation costs, energy storage costs and demand fluctuations on voltage, thereby achieving precise voltage regulation. This method effectively improves the voltage stability and operational reliability of the system, reduces energy waste, and ensures the safe and efficient operation of the ship's power system in complex navigation environments, especially in scenarios where multiple ships are sailing in parallel and in busy waterways, significantly reducing the risks of power systems caused by voltage instability.

[0063] It should be noted that the energy management system unit is based on the system operation status indicator Z a (t) feedback to regulate the energy consumption of each energy-consuming device. The energy consumption adjustment formula of the energy-consuming device is:

[0064]

[0065] Where: j is the energy-consuming equipment index, P dev,j (t) is the energy consumption of the jth energy-consuming device at the tth time, P e,j is the rated power of the jth energy-consuming device, and n is the total number of energy-consuming devices that need to be adjusted in the system.

[0066] The system can achieve accurate energy distribution for energy-consuming equipment by regulating the energy consumption of each energy-consuming equipment according to the feedback of the system operation status indicators through the energy management system unit. Using this formula, the energy consumption of each device is dynamically adjusted to be associated with the power generation cost, energy storage cost and energy demand volatility. This ensures that the system effectively balances the energy consumption of each device under different operating conditions and avoids energy waste or equipment overload caused by unreasonable energy distribution. By optimizing the energy distribution between devices, the overall energy efficiency of the system is improved, ensuring efficient and stable operation in complex environments, while reducing the risk of equipment damage and unnecessary energy consumption.

[0067] like Figure 2 As shown, an energy collaborative management method based on energy storage batteries includes the following steps:

[0068] Step 1, system initialization and data collection: Initialize the energy collaborative management system, set initial parameters, start the system monitoring unit, collect data related to the energy storage battery status, power supply bus status, and system operation status in real time, start the data processing unit, receive and store monitoring data;

[0069] Step 2: Real-time energy demand evaluation and optimization: At each time step t, the data processing unit calculates the current energy demand P of the system based on the real-time collected data. req (t), charging and discharging power P of the energy storage battery cn (t) and generator output power P fd (t), the energy collaborative management central processing module evaluates the current system operation status indicator Z a (t), combined with the multi-objective optimization management formula, determine the weight factors α, β, γ of power generation cost, energy storage cost, and energy demand volatility, and optimize the energy allocation strategy;

[0070] Step 3: Charge and discharge management of energy storage batteries: According to the energy demand and generator output power, determine the working mode of the energy storage battery. In low load mode, i.e. P req (t) <P fd At (t), the energy storage battery is charged, and the charging power calculation formula is: In P req (t)>P fd At (t), the energy storage battery is discharged, and the discharge power calculation formula of the energy storage battery is:

[0071] Step 4: Dynamic adjustment of the power supply bus voltage: According to the system operation status indicator Z a (t) and energy demand volatility R(t), adjust the actual voltage of the power supply bus in real time, and the power supply bus monitoring module continuously monitors the adjustment results to ensure that the voltage is stable within a safe range;

[0072] Step 5: Control of energy consumption of energy-consuming equipment: Calculate the energy consumption adjustment formula of each energy-consuming equipment according to the current system operation status, and the energy-consuming equipment management module adjusts the operating parameters of each equipment to ensure that the total energy consumption is consistent with the system optimization target;

[0073] Step 6, system feedback and adaptive adjustment: The system monitoring unit feeds back the operating status and data of each module to the energy collaborative management central processing module in real time, dynamically adjusts the weight factor through the adaptive learning rate adjustment formula, optimizes the energy efficiency function, and adjusts the energy allocation strategy for subsequent time steps according to the optimization results. The system executes the above steps in a loop, continuously optimizes the energy management strategy, and ensures that the system maintains the best operating state under different load conditions.

[0074] By implementing this energy storage battery-based energy collaborative management method, the system can achieve highly optimized energy management in a dynamic and changeable navigation environment. First, through system initialization and data acquisition, key data is obtained and processed in real time, so that the system can accurately grasp the status of the energy storage battery, the power supply busbar and the system operation status. Real-time energy demand assessment and optimization steps enable the system to dynamically adjust the power generation and energy storage strategies to ensure the efficiency of energy distribution and avoid energy waste. The charge and discharge management strategy of the energy storage battery flexibly adjusts the charge and discharge power according to the actual energy demand, ensuring that the system stores energy at low load and releases energy at high load, effectively balancing the system load. The dynamic adjustment of the power supply busbar voltage ensures the stability of the voltage under various operating conditions and prevents the equipment from being damaged by voltage fluctuations. The precise regulation of the energy consumption of energy-consuming equipment further optimizes the energy utilization rate of each device in the system and ensures the overall energy efficiency of the system. Finally, through system feedback and adaptive adjustment, the system can continuously optimize and improve, adapt to different operating conditions, and always maintain the best operating state, effectively improving the stability, reliability and energy utilization efficiency of the ship's power system, and reducing the risk of equipment overload and failure.

[0075] The present invention combines the power supply busbar status information, energy storage system status information and energy management system to provide a more accurate energy management information matrix, which improves the utilization rate of available energy while also providing multi-dimensional and more accurate data support and control methods for the optimization of generator startup plans. At the same time, the system data collection of the present invention is more comprehensive and the monitoring range is wider, making the use of the energy system more scientific and reasonable, greatly improving the reliability and safety of the energy system.

[0076] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0077] Finally: The above description is only an explanation of the preferred implementation of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An energy collaborative management system based on energy storage batteries, characterized in that: It includes energy storage system unit, system monitoring unit, data processing unit and energy management system unit. The energy storage system unit includes disconnector, energy storage battery and battery management system. The system monitoring unit includes battery health monitoring module, power supply busbar monitoring module and system operation monitoring module. The data processing unit includes energy collaborative management central processing module. The energy management system unit includes energy consumption equipment management module. The energy collaborative management central processing module dynamically adjusts the output power of energy storage battery and generator according to real-time energy demand and power generation capacity, charges energy storage battery in low load period, releases electric energy in high load period, balances system load, automatically adjusts energy distribution strategy through real-time monitoring and feedback, and adopts multi-objective optimization strategy in combination with power generation cost, energy storage efficiency and system fluctuation, so that the system tends to the optimal operating state. The multi-objective optimization management formula is: Where: t is the current time, Z a (t) is the system operation status indicator at the current moment, T is the optimization window duration, which is set according to the requirements, and C fd (t) is the operating cost of the generator at time t, C cn (t) is the charging and discharging cost of the energy storage battery at the tth moment, R(t) is the volatility of the energy demand at the tth moment, α, β, and γ are the weight factors of power generation cost, energy storage cost, and energy demand volatility, respectively, which are dynamically adjusted through the weight factor optimization algorithm.

2. The energy collaborative management system based on energy storage battery according to claim 1 is characterized in that: The energy storage system unit is connected to the system monitoring unit to provide battery status information. The system monitoring unit is connected to the data processing unit for real-time data monitoring and transmission. The data processing unit optimizes energy distribution through the energy collaborative management central processing module and controls the energy-consuming equipment management module in the energy management system unit to achieve efficient operation.

3. The energy collaborative management system based on energy storage battery according to claim 1 is characterized in that: In the energy collaborative management central processing module, the weight factor optimization algorithm dynamically adjusts the weight factors of power generation cost, energy storage cost and energy demand volatility by balancing learning rate, momentum and regularization, and gradually optimizing the energy efficiency function. The dynamic adjustment formula of the weight factor involved in the weight factor optimization algorithm is: Where: i is the weight factor index, when i=1, is the power generation cost weight factor α, when i=2, is the energy storage cost weight factor β, when i=3, is the energy demand volatility weight factor γ, Update the value for the weight factor, is the weight factor at the current moment, η(t) is the adaptive learning rate, which is dynamically adjusted according to the actual operating status of the system, and E is the energy efficiency function of the system. is the energy efficiency function with respect to the weight factor The first-order partial derivative of , μ is the momentum coefficient, equal to 0.99, is the difference between the weight factors at the previous and next moments.

4. The energy collaborative management system based on energy storage battery according to claim 3 is characterized in that: In the energy collaborative management central processing module, the adaptive learning rate is automatically adjusted as the gradient information accumulates. The formula for the adaptive learning rate is: Where: k is the index of the time step, η0 is the initial learning rate, is the basic step size when there is no historical gradient information, is 0.001, and ∈ is a constant to prevent the denominator from being zero.

5. The energy collaborative management system based on energy storage battery according to claim 4 is characterized in that: The energy storage system unit dynamically adjusts the charging and discharging strategy of the energy storage battery according to the current system operating status indicators and optimization results, balances the system load, minimizes the energy storage cost and smoothes the energy demand fluctuation. The energy storage battery charging and discharging power management formula is: In P req (t) <P fd (t), Where: P req (t) is the total energy demand of the system at time t, P fd (t) is the output power of the generator at the tth moment, P cn (t) is the charging and discharging power of the energy storage battery at the tth moment, P cd,max (t) is the maximum charging power of the energy storage battery at time t; In P req (t)>P fd (t), Where: P fd,max (t) is the maximum discharge power of the energy storage battery at moment t.

6. The energy collaborative management system based on energy storage battery according to claim 5 is characterized in that: In the system monitoring unit, according to the system operation status Z a (t) is fed back to adjust the monitoring voltage of the power supply busbar. The monitoring voltage adjustment formula of the power supply busbar is: Where: V mp (t) is the actual voltage of the power supply busbar at the tth moment, V bc It is the nominal voltage value of the power supply busbar.

7. The energy collaborative management system based on energy storage battery according to claim 6 is characterized in that: The energy management system unit is based on the system operation status indicator Z a (t) feedback to regulate the energy consumption of each energy-consuming device. The energy consumption adjustment formula of the energy-consuming device is: Where: j is the energy-consuming equipment index, P dev,j (t) is the energy consumption of the jth energy-consuming device at the tth time, P e,j is the rated power of the jth energy-consuming device, and n is the total number of energy-consuming devices that need to be adjusted in the system.

8. An energy collaborative management method based on energy storage batteries, used to implement an energy collaborative management system based on energy storage batteries as described in any one of claims 1 to 7, characterized in that: The steps include: Step 1, system initialization and data collection: Initialize the energy collaborative management system, set initial parameters, start the system monitoring unit, collect data related to the energy storage battery status, power supply bus status, and system operation status in real time, start the data processing unit, receive and store monitoring data; Step 2: Real-time energy demand evaluation and optimization: At each time step t, the data processing unit calculates the current energy demand P of the system based on the real-time collected data. req (t), charging and discharging power P of the energy storage battery cn (t) and generator output power P fd (t), the energy collaborative management central processing module evaluates the current system operation status indicator Z a (t), combined with the multi-objective optimization management formula, determine the weight factors α, β, γ of power generation cost, energy storage cost, and energy demand volatility, and optimize the energy allocation strategy; Step 3: Charge and discharge management of energy storage batteries: According to the energy demand and generator output power, determine the working mode of the energy storage battery. In low load mode, i.e. P req (t) <P fd At (t), the energy storage battery is charged, and the charging power calculation formula is: In P req (t)>P fd At (t), the energy storage battery is discharged, and the discharge power calculation formula of the energy storage battery is: Step 4: Dynamic adjustment of the power supply bus voltage: According to the system operation status indicator Z a (t) and energy demand volatility R(t), adjust the actual voltage of the power supply bus in real time, and the power supply bus monitoring module continuously monitors the adjustment results to ensure that the voltage is stable within a safe range; Step 5: Control of energy consumption of energy-consuming equipment: Calculate the energy consumption adjustment formula of each energy-consuming equipment according to the current system operation status, and the energy-consuming equipment management module adjusts the operating parameters of each equipment to ensure that the total energy consumption is consistent with the system optimization target; Step 6, system feedback and adaptive adjustment: The system monitoring unit feeds back the operating status and data of each module to the energy collaborative management central processing module in real time, dynamically adjusts the weight factor through the adaptive learning rate adjustment formula, optimizes the energy efficiency function, and adjusts the energy allocation strategy for subsequent time steps according to the optimization results. The system executes the above steps in a loop, continuously optimizes the energy management strategy, and ensures that the system maintains the best operating state under different load conditions.

Images