Intelligent control system for island green comprehensive energy

Abstract

The invention provides an intelligent control system for island green comprehensive energy, and relates to the field of energy management and control, and the system comprises the steps: determining a distribution adjustment probability according to an energy consumption distribution parameter; according to the allocation environment information, determining the allocation congestion degree when the energy consumption equipment of the island green energy is to be adjusted, and performing matching prediction on the implicit association characteristics when the island green comprehensive energy is allocated according to the allocation congestion degree. Matching decision making is carried out on the energy distribution active quantity when the island green comprehensive energy is distributed through the dispatching distribution data segment; and determining a vacancy load instruction for island green comprehensive energy vacancy allocation according to the implicit association features after matching prediction and the energy allocation active quantity after matching decision, and performing centralized control on the island green comprehensive energy according to the vacancy load instruction. According to the invention, the overall efficiency and reliability of the island green integrated energy system can be improved under the condition that the influence of cooperative operation of each energy device cannot be accurately predicted and optimized in the energy distribution process.

Description

Technical Field

[0001] The present application relates to the field of energy management and control, and more specifically, to an intelligent control system for island green integrated energy. Background Art

[0002] Energy management and control refers to the comprehensive scheduling and optimization of energy production, distribution, consumption and other processes to achieve efficient and sustainable use of energy resources. Its core goal is to ensure that energy supply meets demand while maximizing energy efficiency, reducing energy waste and environmental pollution. In the green energy system, energy management and control uses real-time data monitoring, load forecasting, demand response and other technologies to intelligently schedule various energy equipment (such as wind power, solar energy, energy storage equipment, etc.) and balance the supply and demand relationship between different energy sources.

[0003] In the existing intelligent control systems for island green integrated energy, efficient energy management and scheduling are achieved by integrating a variety of advanced technologies, such as the Internet of Things (IoT), big data analysis, artificial intelligence (AI) and automated control. These systems first collect operating data from various energy devices (such as solar energy, wind energy, energy storage systems, etc.) in real time through sensors and transmit them to the central control platform. However, in the existing energy management systems, they usually only target a single energy type, lack the integrated management capabilities of multiple energy systems, and have limitations in data processing and prediction algorithms, making it impossible for the system to effectively coordinate the dynamic regulation and load balancing of different energy devices when dealing with complex island green integrated energy systems, resulting in the inability to accurately predict and optimize the coordinated operation of various energy devices during the energy distribution process, and may even lead to energy waste or mismatch between supply and demand, thereby reducing the overall efficiency and reliability of the system. Therefore, how to improve the overall efficiency and reliability of the island green integrated energy system under the influence of the inability to accurately predict and optimize the coordinated operation of various energy devices during the energy distribution process is a problem faced by the industry. Summary of the invention

[0004] The present application provides an intelligent control system for island green integrated energy, which can improve the overall efficiency and reliability of the island green integrated energy system under the influence of the inability to accurately predict and optimize the coordinated operation of various energy equipment during the energy distribution process.

[0005] The present application provides an intelligent control system for island green integrated energy, the intelligent control system comprising:

[0006] A sensor module is used to obtain the energy control sequence in the island green energy system through sensors;

[0007] A data processing module is used to screen the energy control sequence to obtain energy consumption distribution parameters for island green energy distribution control, and determine the distribution adjustment probability of green comprehensive energy when coordinated control with different characteristics is performed according to the energy consumption distribution parameters;

[0008] A prediction module is used to obtain the distribution environment information of the island green comprehensive energy control center, determine the distribution congestion of the island green energy energy-consuming equipment to be adjusted according to the distribution environment information, and then match and predict the implicit correlation characteristics of the island green comprehensive energy distribution according to the distribution congestion;

[0009] A decision-making module is used to obtain the supply status information of the island green comprehensive energy during cross-supply, determine the coordinated adjustment coefficient of the island green comprehensive energy during coordinated adjustment through the supply status information, determine the scheduling allocation data segment of the island green energy energy-consuming equipment to be adjusted through the coordinated adjustment coefficient and the distribution adjustment probability, and then make a matching decision on the energy allocation activity when the island green comprehensive energy is allocated based on the scheduling allocation data segment;

[0010] The execution module is used to determine the shortage load instruction of the island green comprehensive energy shortage allocation according to the implicit correlation characteristics after matching prediction and the energy allocation activity after matching decision, and centrally control the island green comprehensive energy according to the shortage load instruction.

[0011] In this embodiment, the energy management and control sequence represents a set of energy operation status data collected from the green energy system in chronological order, including key information such as power output, operation status, and environmental parameters of the equipment.

[0012] In this embodiment, the energy control sequence is screened to obtain energy consumption distribution parameters for island green energy distribution control, specifically including:

[0013] The energy control sequence is weighted to obtain an environmental weight vector for island green energy distribution control;

[0014] Mapping the environmental weight vector to the steady-state space of island green energy distribution control to obtain a steady-state allocation sample set;

[0015] The energy consumption distribution parameters for island green energy distribution control are determined based on the steady-state allocation sample set.

[0016] In this embodiment, the distribution adjustment probability represents the priority allocation probability of different energy sources in a collaborative control environment.

[0017] In this embodiment, the distribution environment information represents various real-time and predicted data that affect the energy distribution decision of the island green energy system.

[0018] In this embodiment, the allocation congestion degree represents a measure of whether the equipment faces excessive load during the energy scheduling process.

[0019] In this embodiment, the coordinated adjustment coefficient of the island green comprehensive energy when coordinated adjustment is determined by the supply status information specifically includes:

[0020] Determine the adjusted parameters when the island green comprehensive energy is coordinated and adjusted according to the supply status information;

[0021] Obtain the predicted target value of energy consumption when allocating green comprehensive energy on the island;

[0022] The coordinated adjustment coefficient when the island green comprehensive energy is coordinated is determined according to the adjusted parameter and the predicted target value.

[0023] In this embodiment, the scheduling allocation data segment for determining the energy-consuming equipment of the island green energy to be adjusted by the coordinated adjustment coefficient and the distribution adjustment probability specifically includes:

[0024] The coordinated adjustment coefficient is used to determine the distribution energy consumption balance of the energy-consuming equipment of the island green energy when it is to be adjusted;

[0025] Determine the energy consumption control strategy of the energy-consuming equipment of the island green energy when it is to be adjusted according to the distribution adjustment probability;

[0026] The scheduling allocation data segment for the energy-consuming equipment of the island green energy to be adjusted is determined according to the allocated energy consumption balance amount and the energy consumption control strategy.

[0027] In this embodiment, the energy allocation activity refers to the degree of energy allocation of energy equipment (such as wind energy, solar energy, and energy storage equipment) within a specific time period during the scheduling process.

[0028] In this embodiment, determining the shortage load instruction of the shortage allocation of the island green comprehensive energy according to the implicit correlation characteristics after matching prediction and the energy allocation activity after matching decision specifically includes:

[0029] The adaptive compensation value of the shortage allocation of island green comprehensive energy is determined by matching the implicit correlation features after prediction;

[0030] Determine the load target information of island green comprehensive energy shortage allocation by matching the energy allocation activity after decision making;

[0031] The deficit load instruction for the deficit allocation of the island green comprehensive energy is determined by the adaptation compensation value and the load target information.

[0032] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0033] The energy control sequence in the island green energy system is obtained through sensors; the energy control sequence is screened to obtain the energy consumption distribution parameters of the island green energy distribution control, and the distribution adjustment probability of the green comprehensive energy when the characteristics are coordinated and controlled is determined according to the energy consumption distribution parameters; the distribution environment information of the island green comprehensive energy control center is obtained, and the distribution congestion of the island green energy energy-consuming equipment when it is to be adjusted is determined according to the distribution environment information, and then the implicit correlation characteristics of the island green comprehensive energy when it is distributed are matched and predicted by the distribution congestion; the supply status information of the island green comprehensive energy during cross supply is obtained, and the coordinated adjustment coefficient of the island green comprehensive energy when it is coordinated and adjusted is determined according to the supply status information, and the scheduling allocation data segment when the island green energy energy-consuming equipment is to be adjusted is determined according to the coordinated adjustment coefficient and the distribution adjustment probability, and then the energy distribution activity amount when the island green comprehensive energy is distributed is matched and decided by the scheduling allocation data segment; the shortage load instruction of the shortage allocation of the island green comprehensive energy is determined according to the implicit correlation characteristics after matching prediction and the energy distribution activity amount after matching decision, and the island green comprehensive energy is centrally controlled according to the shortage load instruction.

[0034] It can be seen from this that in this application, it is possible to achieve centralized control of island green comprehensive energy under the influence of the inability to accurately predict and optimize the coordinated operation of various energy devices during the energy distribution process; wherein, by real-time collection of the operating status and energy consumption data of each energy device, it is possible to provide the system with accurate real-time information, ensuring that the system can effectively perceive the fluctuations of energy supply and demand in a dynamically changing environment. This provides reliable data support for subsequent energy optimization and scheduling decisions, and helps to improve the response speed and accuracy of the system; the energy consumption distribution parameters can accurately reflect the operating characteristics of each energy device after screening, helping the system to understand the supply capacity and demand distribution of various energy sources, thereby providing a scientific basis for the reasonable allocation and scheduling of energy. This step reduces energy waste and optimizes energy utilization efficiency by accurately analyzing data; by accurately determining the distribution adjustment probability of each energy under different control conditions, it is possible to achieve intelligent scheduling and coordinated control of multiple energy devices, thereby balancing the output between different energy sources, avoiding overload or underload of a single energy device, and improving the stability and sustainability of the energy system; by analyzing the distribution environment information, it is possible to evaluate and predict the load and distribution pressure of each energy device, thereby avoiding excessive congestion or overload of the equipment. By predicting and adjusting the distribution congestion in advance, the smooth operation of equipment can be ensured, and system failures or energy shortages caused by equipment overload can be avoided, thereby improving system reliability; through intelligent matching decisions, the system can accurately identify and make up for deficiencies in energy distribution, reducing energy shortages caused by uneven distribution or prediction errors. Finally, centralized control combined with the shortage load instruction can accurately dispatch energy equipment, ensure the balance of energy supply, reduce energy waste, and improve the economy and stability of the system.

[0035] To sum up, the technical solution adopted in this application can improve the overall efficiency and reliability of the island green integrated energy system under the influence of the inability to accurately predict and optimize the coordinated operation of various energy equipment during the energy distribution process. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0037] Figure 1 It is a module structure diagram of an intelligent control system for island green integrated energy provided by this application;

[0038] Figure 2 is a schematic diagram of a flow chart for determining a distribution adjustment probability provided by the present application;

[0039] Figure 3 It is a flowchart of determining allocation congestion provided by this application. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0041] The embodiment of the present application provides an intelligent control system for island green integrated energy, the core of which is to obtain the energy control sequence in the island green energy system through sensors; screen the energy control sequence to obtain the energy consumption distribution parameters of the island green energy distribution control, and determine the distribution adjustment probability of the green integrated energy when the characteristics are different and coordinated according to the energy consumption distribution parameters; obtain the distribution environment information of the island green integrated energy control center, and determine the distribution congestion of the island green energy energy-consuming equipment to be adjusted according to the distribution environment information, and then match and predict the implicit correlation characteristics when the island green integrated energy is distributed according to the distribution congestion; Obtain the supply status information of the island green comprehensive energy during cross-supply, determine the coordinated adjustment coefficient of the island green comprehensive energy during coordinated adjustment through the supply status information, determine the scheduling allocation data segment of the island green energy energy-consuming equipment to be adjusted through the coordinated adjustment coefficient and the distribution adjustment probability, and then use the scheduling allocation data segment to make a matching decision on the energy allocation activity when the island green comprehensive energy is allocated; determine the shortage load instruction of the shortage allocation of the island green comprehensive energy according to the implicit correlation characteristics after the matching prediction and the energy allocation activity after the matching decision, and centrally control the island green comprehensive energy according to the shortage load instruction. The above scheme is adopted to improve the overall efficiency and reliability of the island green comprehensive energy system under the influence of the inability to accurately predict and optimize the coordinated operation of each energy equipment during the energy distribution process.

[0042] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 As shown, this figure is a module structure diagram of an intelligent control system for island green integrated energy according to this embodiment of the present application. The intelligent control system includes: a sensor module 100, a data processing module 200, a prediction module 300, a decision module 400 and an execution module 500, which are described as follows:

[0043] The sensor module 100 is used to obtain the energy management and control sequence in the island green energy system through sensors.

[0044] In the specific implementation, first, precision sensors are installed in various green energy facilities on the island (such as solar panels, wind turbines, and energy storage systems). These sensors can collect data in real time, including power output, voltage, current, equipment temperature, and environmental parameters (such as sunshine intensity and wind speed). Secondly, the sensors transmit the collected data to the data processing center through a wireless network or a low-power wide area network (such as LoRaWAN). This center receives and aggregates data in real time, sorts the energy status at different time points by timestamp, and forms a continuous time series. The data processing center uses edge computing technology to screen and preliminarily clean the data to filter out noise or outliers. In the end, the energy management and control sequence formed contains detailed energy consumption data and status information of each device at different times, which will not be repeated here.

[0045] It should be noted that, in this application, the energy management and control sequence refers to a set of energy operation status data collected from the green energy system in chronological order, including key information such as the power output, operating status, and environmental parameters of the equipment.

[0046] The data processing module 200 is used to screen the energy control sequence to obtain energy consumption distribution parameters for island green energy distribution control, and determine the distribution adjustment probability of green comprehensive energy when coordinated control is performed with different characteristics according to the energy consumption distribution parameters.

[0047] In this embodiment, the energy control sequence is screened to obtain energy consumption distribution parameters for island green energy distribution control, which can be achieved by the following steps:

[0048] The energy control sequence is weighted to obtain an environmental weight vector for island green energy distribution control;

[0049] Mapping the environmental weight vector to the steady-state space of island green energy distribution control to obtain a steady-state allocation sample set;

[0050] The energy consumption distribution parameters for island green energy distribution control are determined based on the steady-state allocation sample set.

[0051] In the specific implementation, first, each data in the energy management sequence (such as power, equipment status and environmental conditions) is weighted to reflect the importance of each parameter in the energy consumption distribution. For example, the weight of solar energy output on a sunny day may be higher than that on a cloudy day, and the weight of wind energy is higher in windy weather. By setting these weights, an environmental weight vector is generated to represent the contribution of different energy sources in different environments; then, the environmental weight vector is mapped to the steady-state space to obtain a stable energy consumption distribution sample of the system under different scenarios. The steady-state space is a space that characterizes the distribution of various energy sources under stable conditions of the system, reflecting the distribution of various energy sources during stable operation. By projecting the weight vector into this space, a steady-state distribution sample set can be constructed; finally, based on the steady-state distribution sample set, the average energy consumption and distribution characteristics of each energy source are calculated through statistical analysis or fitting algorithm, and the energy consumption distribution parameters of the system are finally determined. This parameter describes the consumption of different energy sources of the system under various typical environments, which will not be repeated here.

[0052] It should be noted that in this application, the environmental weight vector is a vector formed by assigning weights to different energy consumption parameters in the energy control sequence according to environmental conditions, which indicates the relative importance of each parameter to the system energy consumption under different environmental conditions; the steady-state distribution sample set represents a set of multiple energy consumption distribution data obtained by mapping the environmental weight vector under the stable operation conditions of the green energy system, which reflects the energy consumption characteristics and distribution ratio of the system under different environmental conditions; the energy consumption distribution parameter refers to a data set used to describe the energy consumption characteristics of various types of energy in the green energy system under different environments and operating conditions. It includes information such as the average energy consumption, consumption ratio, peak load, etc. of various types of energy, and can characterize the consumption trend and distribution characteristics of different energy sources.

[0053] Preferably, in this embodiment, the distribution adjustment probability of green comprehensive energy when coordinated control with different characteristics is determined according to the energy consumption distribution parameter, referring to Figure 2 The figure is a schematic diagram of a flow chart of determining the distribution adjustment probability in some embodiments of the present application. In this embodiment, determining the distribution adjustment probability can be implemented by the following steps:

[0054] In step S21, prediction parameters for green integrated energy when coordinated allocation of different characteristics is set;

[0055] In step S22, the control constraint amount of green comprehensive energy when coordinated control with different characteristics is determined according to the energy consumption distribution parameter;

[0056] In step S23, a reference value for the distribution correction of green comprehensive energy during the coordinated control of different characteristics is obtained;

[0057] In step S24, the distribution adjustment probability of the green comprehensive energy when the characteristics are coordinated and controlled is determined according to the prediction parameters, the control constraints and the allocation correction reference value.

[0058] In the specific implementation, first, for each type of energy in the green integrated energy system (such as solar energy, wind energy and energy storage system), a set of prediction models are trained based on historical energy consumption data and environmental data (such as wind speed, sunshine intensity, etc.), such as ARIMA time series prediction model or regression model in machine learning. These models receive historical and current input data and predict the energy supply and demand curve for a period of time in the future, including the power output and consumption requirements of each energy source. After the prediction is completed, the demand prediction results of different energy sources are integrated into a set of "prediction parameters" for allocation and scheduling decisions in subsequent steps. These parameters can include future load demand, expected supply capacity of each energy source, etc.; then, dynamic control constraints are set for each energy type. For example, the energy consumption distribution parameters can be converted into upper and lower limits of power output for each energy source through linear programming methods or constrained optimization algorithms. The control constraints not only consider the physical limits of each energy device (such as the maximum power of the generator), but also need to adapt to environmental changes (such as changes in wind power generation caused by changes in wind speed). In practice, the system regularly analyzes environmental data (such as wind speed, sunshine intensity, etc.) and current equipment status data (such as temperature, load rate), and adjusts the control constraints based on these inputs to ensure equipment stability and safety; then, based on the real-time collected sensor data (such as actual wind speed, sunshine intensity) and historical allocation records, obtains the real-time allocation correction reference value. This step usually relies on feedback control mechanisms or adaptive filtering algorithms, such as Kalman filtering, to dynamically adjust the gap between the predicted energy allocation and the actual demand. Specifically, the system inputs the current real-time data into the correction model, compares the initial set prediction parameters, and generates a corrected reference value. For example, if the actual wind speed is lower than the forecast, the system will reduce the reference value of wind energy allocation and adjust more allocation to other energy sources (such as solar energy or energy storage systems) to ensure that the system responds flexibly to environmental changes; finally, a probability distribution model (such as Bayesian network or Markov decision process) is applied to calculate the distribution adjustment probability of green integrated energy in collaborative control. The distribution regulation probability is a set of probability values ​​that reflect the priority of different energy sources. It is calculated by weighting the control constraints and the modified reference values ​​to ensure that the system can reasonably sort the allocation priorities of various energy sources under the current environmental conditions. It is assumed that the distribution regulation probability of wind energy increases when the wind speed is high, and the distribution regulation probability of solar energy increases when the sunshine is strong, so as to meet the optimal configuration of the current supply and demand dynamics.

[0059] It should be noted that in this application, the prediction parameters represent a set of energy supply and demand data for a period of time in the future predicted based on historical and environmental data; the control constraints are used to define the upper and lower limits of the power output of each energy in the system, and are dynamically adjusted based on system safety and environmental conditions to ensure equipment stability and system operation safety; the allocation correction reference value is used to correct the initial allocation plan of the energy system, so that the system can flexibly adjust resource allocation based on real-time environmental data to improve the adaptability and response speed of the system; the distribution adjustment probability represents the priority allocation probability of different energy sources in a collaborative control environment, and is dynamically adjusted based on environmental conditions and real-time demand to optimize the collaborative allocation of multiple energy sources and resource utilization efficiency.

[0060] The prediction module 300 is used to obtain the distribution environment information of the island green integrated energy control center, determine the distribution congestion of the island green energy energy-consuming equipment to be adjusted according to the distribution environment information, and then match and predict the implicit correlation characteristics when the island green integrated energy is distributed based on the distribution congestion.

[0061] In specific implementation, the distribution environment information of the island green integrated energy control center can be obtained in the following way, namely: first, rely on the sensor network to collect real-time data, including meteorological data (such as wind speed, temperature, sunshine intensity) and energy production data (such as solar panels, wind turbines and energy storage equipment power output). These data are cleaned, standardized and integrated through the integration platform to provide a basis for subsequent analysis. Then, the load forecasting model and the production capacity forecasting model are used to analyze future energy demand and supply conditions to generate distribution environment information. This information includes the expected energy supply capacity, the electricity demand of each region, and the impact of environmental conditions on energy production. On this basis, the energy control center adjusts the energy distribution plan in real time to ensure the stable operation of the system and optimize resource utilization. In other embodiments, other methods can also be used to determine the distribution environment information, which will not be repeated here.

[0062] It should be noted that, in the present application, the allocation environment information refers to various real-time and predicted data that affect the energy allocation decision of the island green energy system.

[0063] Preferably, in this embodiment, the distribution congestion of the energy-consuming equipment of the island green energy to be adjusted is determined according to the distribution environment information, referring to Figure 3 As described above, the figure is a schematic diagram of a process for determining allocation congestion in some embodiments of the present application. In this embodiment, determining allocation congestion can be implemented by the following steps:

[0064] In step S31, the operation balance amount in the operation environment of the energy-consuming equipment is extracted from the distribution environment information;

[0065] In step S32, extracting the distribution thermal response deviation from the distribution environment information;

[0066] In step S33, the adjustment feedback value of the energy-consuming equipment of the island green energy is determined when it is to be adjusted;

[0067] In step S34, the distribution congestion of the energy-consuming equipment of the island green energy to be adjusted is determined according to the operation balance amount, the operation balance amount and the distribution thermal response deviation.

[0068] In specific implementation, first, the real-time power consumption of each energy-consuming device, such as the power generation of the generator, the load of the motor, etc., the rated power or load limit of each device, the real-time amount of available energy, including the output of renewable energy (such as wind energy, solar energy) and the remaining capacity of the energy storage system, is calculated by comparing the current load of the device with the maximum load capacity, that is, the ratio of the current energy demand to the maximum load that the device can carry. For example, when the actual power of a wind turbine is close to its rated power, its load balance is low, which means that the device is close to saturation and needs to be adjusted; then, the temperature change of key equipment (for example, thermoelectric equipment or air-conditioning equipment) is monitored in real time, and the temperature response of the equipment is predicted based on historical data and environmental conditions (such as external temperature), and the actual temperature change of the equipment under the current environmental conditions is recorded. The deviation value is the difference between the actual response and the expected response. For example, if the external temperature rises, but the device fails to respond effectively and adjust the working state, the thermal response deviation value is large, indicating that the device has weak regulation ability; then, the load balance and thermal response deviation of each device are detected, and the regulation feedback value is calculated through the control algorithm based on the load and thermal response data. For example, when the load of the equipment is too high or the thermal response deviation is large, the system will send a "reduce load" or "enhance cooling" signal. The feedback value is generally a dynamic value, which is used to tell the control system whether a certain device needs to be adjusted immediately or preset. For example, when the feedback value exceeds a certain threshold, the system may trigger an adjustment strategy, such as reducing the load of a certain device, or increasing the energy supply to alleviate the overload situation. Finally, the operating balance, thermal response deviation and adjustment feedback value are weighted to obtain the comprehensive congestion index of each device. The comprehensive congestion of each device is compared with its current load status to identify the equipment that may be overloaded. For equipment with high allocation congestion, load adjustment or energy scheduling is prioritized to prevent the equipment from entering an overload state. For example, when a device has a low operating balance and a large thermal response deviation, it may be considered to be about to enter a congested state, so its allocation congestion is high and needs to be adjusted first.

[0069] It should be noted that in this application, the operating balance represents the relationship between the current load of the equipment and its maximum load-bearing capacity, and is used to evaluate the load status of the equipment. A lower operating balance means that the equipment load is close to the maximum load-bearing capacity and may need to be adjusted; the allocation thermal response deviation represents the difference between the actual thermal response and the expected thermal response of the equipment when responding to environmental changes (such as temperature changes). The larger the deviation value, the worse the adjustment ability of the equipment, and the operation may need to be adjusted; the adjustment feedback value represents the feedback signal generated by the control system based on the load and thermal response status of the equipment, which is used to indicate whether adjustment is needed to ensure that the equipment operates within a reasonable load range; the allocation congestion represents the degree to which the equipment faces excessive load during the energy scheduling process. A higher allocation congestion indicates that the equipment is at risk of resource shortage or overload, and energy allocation needs to be adjusted or optimized first.

[0070] In specific implementation, the matching prediction of the implicit correlation features when allocating the island green comprehensive energy by the distribution congestion can be achieved in the following way, namely: first, based on the calculated distribution congestion, the system needs to identify which energy-consuming devices have overload or competition risks when allocating resources. By analyzing the load status and energy demand of each device, the system extracts the "implicit correlation features" between devices. These features include the energy sharing relationship between devices, the time delay of load regulation, and the sensitivity of devices to environmental changes. For example, some devices may be more sensitive to external environmental changes (such as temperature fluctuations) when they are highly loaded, while other devices may show strong adaptability to the instability of energy supply. Next, based on these implicit correlation features, machine learning algorithms or prediction models (such as regression analysis, neural networks, etc.) are used for matching prediction. These algorithms are trained with historical data, learn the dynamic relationship between devices, and predict the regulation requirements under different load and environmental conditions. The prediction results provide data support for subsequent energy allocation, thereby achieving efficient and accurate scheduling. Ultimately, through this matching prediction, the system can adjust the energy allocation strategy in a timely manner when an imbalance in energy supply and demand occurs, ensuring the stability and efficiency of the system, which will not be elaborated here.

[0071] The decision module 400 is used to obtain the supply status information of the island green comprehensive energy during cross-supply, determine the coordinated adjustment coefficient of the island green comprehensive energy during coordinated adjustment through the supply status information, determine the scheduling allocation data segment of the island green energy energy-consuming equipment to be adjusted through the coordinated adjustment coefficient and the distribution adjustment probability, and then use the scheduling allocation data segment to make a matching decision on the energy allocation activity when the island green comprehensive energy is allocated.

[0072] In specific implementation, the supply status information of the island green comprehensive energy during cross-supply can be obtained in the following ways, namely: first, the system needs to monitor the output of multiple energy sources (such as solar energy, wind energy, energy storage system, etc.) in real time. These energy outputs are affected by factors such as climate, environment, and equipment status, so it is necessary to rely on sensor networks to collect real-time data, such as wind speed, solar radiation intensity, and the charging / discharging status of energy storage equipment. Secondly, the system needs to consider the concept of cross-supply, that is, the complementarity of different energy sources. For example, the supply of solar energy and wind energy often has time and seasonal differences, and may complement each other during certain periods. During the cross-supply process, the system will analyze the supply matching degree and load distribution between various energy sources and evaluate the maximum available supply capacity. Then, through data fusion and intelligent analysis technology, the supply data from each energy system is compared with the load demand of the island to calculate the coordination status between different energy supplies. For example, when the solar energy supply is sufficient, solar energy may be used first, and when the wind energy or energy storage system is insufficient, it will switch to other backup energy sources. Finally, by combining the meteorological forecast model and the equipment operating status, the changes in energy supply in the future are predicted, and real-time supply status information is generated to adjust the energy allocation strategy.

[0073] It should be noted that, in the present application, the supply status information refers to various data in the energy system that reflects in real time the energy supply capacity, the availability of energy sources, and the coordination status between various energy systems.

[0074] In this embodiment, the coordinated adjustment coefficient of the island green comprehensive energy for coordinated adjustment is determined by the supply status information and can be implemented by the following steps:

[0075] Determine the adjusted parameters when the island green comprehensive energy is coordinated and adjusted according to the supply status information;

[0076] Obtain the predicted target value of energy consumption when allocating green comprehensive energy on the island;

[0077] The coordinated adjustment coefficient when the island green comprehensive energy is coordinated is determined according to the adjusted parameter and the predicted target value.

[0078] In the specific implementation, first of all, real-time supply status information will be obtained from different energy devices, including the output data, operating status and load conditions of each energy source (such as solar energy, wind energy, and energy storage system). By analyzing this information, the system can identify the key parameters that need to be adjusted, that is, the adjusted parameters. For example, if the solar energy output is stable and the wind energy output is low, the proportion of wind energy generation may be adjusted, or the energy storage system may be started for charging. At this time, the wind energy output and the charging status of the energy storage device become the adjusted parameters; then, the system predicts the energy demand in the future period by using data analysis or machine learning models (such as time series prediction or regression analysis). First, obtain historical energy consumption data, weather forecast data, and system load demand information, use historical data to train the prediction model, generate an energy consumption prediction model, and use the model to calculate the energy consumption target for the future period, such as predicting the total energy consumption for a certain period of time or the whole day; finally, calculate the synergistic adjustment coefficient through a mathematical model (such as a weighted average or regression model). This coefficient indicates the degree to which each energy system (such as wind energy, solar energy, and energy storage) needs to be adjusted. For example, if the wind energy supply is insufficient, the energy storage system may need to increase its discharge capacity, and the synergy adjustment coefficient will reflect the proportion that the energy storage system should bear. For example, if the energy consumption forecast target is 1000kWh, and the wind energy output is expected to provide only 300kWh, the system may shift the target from wind energy to other energy sources and calculate the corresponding adjustment based on the synergy adjustment coefficient.

[0079] It should be noted that in this application, the adjusted parameters refer to the key variables that need to be adjusted in the energy allocation process, such as the power generation of each energy system, the charging / discharging status of the energy storage equipment, etc.; the predicted target value means the total energy consumption required by the island in a certain period of time in the future based on historical data, meteorological conditions and load demand; the coordinated adjustment coefficient represents the adjustment ratio between the systems when multiple energy systems are running in coordination. It quantifies the adjustment needs of different energy systems to ensure that the systems can coordinate and cooperate to improve overall efficiency while meeting the overall energy consumption target.

[0080] In this embodiment, the following steps can be used to determine the scheduling allocation data segment of the energy-consuming equipment of the island green energy to be adjusted by using the coordinated adjustment coefficient and the distribution adjustment probability:

[0081] The coordinated adjustment coefficient is used to determine the distribution energy consumption balance of the energy-consuming equipment of the island green energy when it is to be adjusted;

[0082] Determine the energy consumption control strategy of the energy-consuming equipment of the island green energy when it is to be adjusted according to the distribution adjustment probability;

[0083] The scheduling allocation data segment for the energy-consuming equipment of the island green energy to be adjusted is determined according to the allocated energy consumption balance amount and the energy consumption control strategy.

[0084] In the specific implementation, the coordinated adjustment coefficient calculated in the previous step will be obtained first. This coefficient quantifies the regulation demand of each energy system. According to the coordinated adjustment coefficient and the current energy supply capacity of each energy system, the system calculates the energy share that each energy should provide. For example, if the coordinated adjustment coefficient of the wind energy system is high, it means that wind energy needs to bear a larger part of the load in the dispatch, while the energy storage system may bear less load. The system determines the energy distribution ratio according to the output capacity of each system and the coordinated adjustment coefficient to ensure energy consumption balance. Finally, the obtained distribution energy consumption balance will reflect the regulation load that each energy device should bear; then, in a certain period of time, the distribution regulation probability of solar energy and wind energy may be high, while the regulation probability of the energy storage system is low, because its power is already in a low state. According to the distribution regulation probability, the system will formulate corresponding control strategies for each energy device. For example, when the solar energy output is high, solar energy may be used first, and when the solar energy is weak, the wind energy or energy storage system may be started as part of the regulation strategy. The system will combine the actual output capacity of the current energy system with the predicted future demand to generate an energy consumption control strategy for each device to ensure that the coordinated adjustment of each system meets the energy consumption target, that is, to obtain the energy consumption control strategy; finally, the allocated energy consumption balance will be combined with the energy consumption control strategy to determine the specific energy output of each energy system in the future scheduling cycle according to the adjustment needs and control strategies of different energy sources. This process involves scheduling each energy source (such as wind energy, solar energy, and energy storage) to ensure that the overall energy efficiency is maximized. Through comprehensive analysis, the system will create a scheduling allocation data segment based on the current and predicted load conditions, energy supply capacity, and control strategy. The data segment contains information such as load distribution and output power of each energy system during the scheduling cycle.

[0085] It should be noted that in this application, the allocation energy consumption balance refers to the energy allocation ratio that each system needs to bear when multiple energy systems operate in coordination. This measurement reflects how to balance the load of each energy system based on the coordinated adjustment coefficient and system capacity; the energy consumption control strategy represents the energy allocation and control scheme generated based on the distribution adjustment probability. It flexibly adjusts the operation mode of the energy system according to the real-time output and predicted demand of different energy systems to ensure the stability and efficiency of the system; the scheduling allocation data segment refers to the specific energy allocation scheme determined according to the allocation energy consumption balance and the energy consumption control strategy during the energy scheduling process. It describes the energy distribution of each energy system in a certain period of time and is used to guide actual scheduling and control.

[0086] In specific implementation, the energy distribution activity when the island green comprehensive energy is distributed by the scheduling and allocation data segment can be matched and decided in the following way, namely: by analyzing the scheduling and allocation data segment, the system will understand the expected output and load requirements of each energy device (such as wind energy, solar energy, energy storage, etc.). These data will help the system understand the amount of energy that each device needs to contribute and decide whether it is necessary to adjust the scheduling ratio of the device. For example, if the wind energy output is high and the demand is low in a certain period of time, the system may reduce the allocation activity of wind energy and increase the participation of energy storage equipment instead; the energy activity of each device is adjusted by establishing a matching model based on demand and supply. The model takes into account energy demand, the maximum output capacity of the equipment, the scheduling strategy and the real-time operating status. In this process, the system will dynamically adjust the activity of energy equipment according to the real-time output capacity and load demand of each device. For example, if the solar power generation capacity is too high and the demand is low, the system can avoid waste by reducing the allocation activity of solar energy and direct the remaining energy to other devices (such as energy storage) or time periods; matching decisions usually include optimizing the degree of equipment participation, adjusting the output ratio of equipment, and redistributing unused energy. For example, if an energy storage device fails to fully release the stored energy during a certain period of time, the system may forward this energy to devices or time periods with higher demand.

[0087] It should be noted that in this application, energy allocation activity refers to the degree of energy allocation of energy equipment (such as wind energy, solar energy, and energy storage equipment) in a specific time period during the scheduling process. The level of activity represents the enthusiasm of energy equipment to participate in energy supply during the period, which is usually affected by the supply status of energy equipment and demand response.

[0088] The execution module 500 is used to determine the shortage load instruction of the island green comprehensive energy shortage allocation according to the implicit correlation characteristics after matching prediction and the energy allocation activity after matching decision, and centrally control the island green comprehensive energy according to the shortage load instruction.

[0089] In this embodiment, the following steps can be used to determine the shortage load instruction of the island green comprehensive energy shortage allocation according to the implicit correlation characteristics after matching prediction and the energy allocation activity after matching decision:

[0090] The adaptive compensation value of the shortage allocation of island green comprehensive energy is determined by matching the implicit correlation features after prediction;

[0091] Determine the load target information of island green comprehensive energy shortage allocation by matching the energy allocation activity after decision making;

[0092] The deficit load instruction for the deficit allocation of the island green comprehensive energy is determined by the adaptation compensation value and the load target information.

[0093] In the specific implementation, the potential associations between different energy devices (such as solar energy, wind energy, and energy storage devices) in the island green energy system are first identified through historical data and machine learning models. For example, in past data, there is often a negative correlation between the output of solar energy and wind energy, that is, when the wind energy is strong, the solar power generation may be low, and vice versa. Through this association pattern, the system can predict that the output of certain energy devices may be insufficient in a certain period of time. The system calculates an "adaptive compensation value" based on these implicit association characteristics. This compensation value represents the missing energy, which needs to be supplemented by other devices. For example, assuming that the wind energy output is lower than expected and the solar power generation is in excess, the system adjusts the solar power generation through the adaptive compensation value to make up for the insufficient wind energy. The compensation value is dynamically adjusted. The system will monitor the output changes of energy equipment in real time, adjust the compensation value according to the real-time data, and ensure that the system can effectively respond to energy fluctuations; then, based on the above-mentioned distribution activity, the system generates load target information. This information defines the energy that each energy device needs to provide in a specific period of time. Assuming that the energy storage device is in a charging state, when demand increases, the load target information will indicate how much energy the energy storage device should release to make up for the shortfall. The load target information is not only based on the current device dispatch volume, but also takes into account changes in demand and device status. If some equipment has an excess supply during a period of time, the system will adjust the load target in a timely manner to avoid wasting resources; finally, the system will combine the adaptation compensation value with the load target information to generate a shortfall load instruction. By integrating the compensation value with the load target, the system generates a load instruction and dynamically optimizes it. For example, if solar power generation is more and wind power generation is insufficient, the system will instruct to increase the output of the energy storage device and reduce the dispatch of other equipment to ensure the optimal allocation of resources.

[0094] It should be noted that in this application, the adaptation compensation value represents the amount of compensation for insufficient or fluctuating output of energy equipment. The adaptation compensation value adjusts the equipment output in real time to ensure the balance of supply and demand by predicting the imbalance between demand and supply; the load target information represents the amount of energy that each device needs to provide within a specific period of time, based on the allocation activity and actual demand of each device in the energy allocation decision. It is the basis for scheduling decisions and is used to ensure the reasonable scheduling and efficient utilization of energy equipment; the shortfall load instruction is an instruction to each energy device to provide additional energy when the supply is insufficient. It ensures that when an energy gap occurs, it can be compensated in time by adjusting the equipment output to meet the overall system needs.

[0095] In specific implementation, the centralized control of the island green integrated energy according to the shortage load instruction can be implemented in the following way, namely: first, the system needs to determine the specific energy required to be provided by each energy device (such as wind energy, solar energy, energy storage system, etc.) according to the shortage load instruction, and combine the real-time status and capacity of the equipment to ensure that the scheduling of each device meets the demand. In specific implementation, the system will convert the shortage load instruction into a control instruction, and send it to each device and energy management system through the control center, wherein the control system assigns the corresponding load target to each device according to the shortage load instruction to ensure that each device provides supplementary energy within its maximum capacity. For example, if the energy storage system is instructed to release a certain amount of energy to make up for the lack of wind energy, the control system will adjust the output of the energy storage device in real time; the system will continuously monitor the operation of each device, and obtain the energy output, health status and environmental factors of the device through sensors and real-time data acquisition systems, such as temperature, humidity, etc. According to the monitoring data, the control center will adjust the execution of the instruction to cope with sudden load changes or equipment abnormalities; the system will adjust the scheduling strategy according to load demand and equipment feedback. For example, if the energy storage device is discharging rapidly, the control system may choose to dispatch other energy devices to avoid excessive discharge of the energy storage, which will not be discussed here.

[0096] It can be seen from this that in this application, it is possible to achieve centralized control of island green comprehensive energy under the influence of the inability to accurately predict and optimize the coordinated operation of various energy devices during the energy distribution process; wherein, by real-time collection of the operating status and energy consumption data of each energy device, it is possible to provide the system with accurate real-time information, ensuring that the system can effectively perceive the fluctuations of energy supply and demand in a dynamically changing environment. This provides reliable data support for subsequent energy optimization and scheduling decisions, and helps to improve the response speed and accuracy of the system; the energy consumption distribution parameters can accurately reflect the operating characteristics of each energy device after screening, helping the system to understand the supply capacity and demand distribution of various energy sources, thereby providing a scientific basis for the reasonable allocation and scheduling of energy. This step reduces energy waste and optimizes energy utilization efficiency by accurately analyzing data; by accurately determining the distribution adjustment probability of each energy under different control conditions, it is possible to achieve intelligent scheduling and coordinated control of multiple energy devices, thereby balancing the output between different energy sources, avoiding overload or underload of a single energy device, and improving the stability and sustainability of the energy system; by analyzing the distribution environment information, it is possible to evaluate and predict the load and distribution pressure of each energy device, thereby avoiding excessive congestion or overload of the equipment. By predicting and adjusting the distribution congestion in advance, the smooth operation of equipment can be ensured, and system failures or energy shortages caused by equipment overload can be avoided, thereby improving system reliability; through intelligent matching decisions, the system can accurately identify and make up for deficiencies in energy distribution, reducing energy shortages caused by uneven distribution or prediction errors. Finally, centralized control combined with the shortage load instruction can accurately dispatch energy equipment, ensure the balance of energy supply, reduce energy waste, and improve the economy and stability of the system.

[0097] To sum up, the technical solution adopted in this application can improve the overall efficiency and reliability of the island green integrated energy system under the influence of the inability to accurately predict and optimize the coordinated operation of various energy equipment during the energy distribution process.

[0098] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0099] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0100] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Claims

1. An intelligent control system for green integrated energy on islands, characterized in that: The intelligent control system comprises: A sensor module is used to obtain the energy control sequence in the island green energy system through sensors; A data processing module is used to screen the energy control sequence to obtain energy consumption distribution parameters for island green energy distribution control, and determine the distribution adjustment probability of green comprehensive energy when coordinated control with different characteristics is performed according to the energy consumption distribution parameters; A prediction module is used to obtain the distribution environment information of the island green comprehensive energy control center, determine the distribution congestion of the island green energy energy-consuming equipment to be adjusted according to the distribution environment information, and then match and predict the implicit correlation characteristics of the island green comprehensive energy distribution according to the distribution congestion; A decision-making module is used to obtain the supply status information of the island green comprehensive energy during cross-supply, determine the coordinated adjustment coefficient of the island green comprehensive energy during coordinated adjustment through the supply status information, determine the scheduling allocation data segment of the island green energy energy-consuming equipment to be adjusted through the coordinated adjustment coefficient and the distribution adjustment probability, and then make a matching decision on the energy allocation activity when the island green comprehensive energy is allocated based on the scheduling allocation data segment; The execution module is used to determine the shortage load instruction of the island green comprehensive energy shortage allocation according to the implicit correlation characteristics after matching prediction and the energy allocation activity after matching decision, and centrally control the island green comprehensive energy according to the shortage load instruction.

2. An intelligent control system for island green integrated energy as claimed in claim 1, characterized in that: The energy management and control sequence represents a set of energy operation status data collected from the green energy system in chronological order.

3. The intelligent control system for island green integrated energy according to claim 1, characterized in that: The energy control sequence is screened to obtain energy consumption distribution parameters for island green energy distribution control, including: The energy control sequence is weighted to obtain an environmental weight vector for island green energy distribution control; Mapping the environmental weight vector to the steady-state space of island green energy distribution control to obtain a steady-state allocation sample set; The energy consumption distribution parameters for island green energy distribution control are determined based on the steady-state allocation sample set.

4. The intelligent control system for island green integrated energy according to claim 1, characterized in that: The distribution adjustment probability represents the priority allocation probability of different energy sources in a collaborative control environment.

5. The intelligent control system for island green integrated energy according to claim 1, characterized in that: Allocation environment information represents various real-time and predicted data that affect energy allocation decisions in island green energy systems.

6. The intelligent control system for island green integrated energy according to claim 1, characterized in that: Dispatch congestion is a measure of the degree to which equipment faces excessive load during energy dispatch.

7. The intelligent control system for island green integrated energy according to claim 1, characterized in that: Determining the coordinated adjustment coefficient of the island green comprehensive energy for coordinated adjustment through the supply status information specifically includes: Determine the adjusted parameters when the island green comprehensive energy is coordinated and adjusted according to the supply status information; Obtain the predicted target value of energy consumption when allocating green comprehensive energy on the island; The coordinated adjustment coefficient when the island green comprehensive energy is coordinated is determined according to the adjusted parameter and the predicted target value.

8. The intelligent control system for island green integrated energy according to claim 1, characterized in that: The dispatching allocation data segment for determining the energy-consuming equipment of the island green energy to be adjusted by the coordinated adjustment coefficient and the distribution adjustment probability specifically includes: The coordinated adjustment coefficient is used to determine the distribution energy consumption balance of the energy-consuming equipment of the island green energy when it is to be adjusted; Determine the energy consumption control strategy of the energy-consuming equipment of the island green energy when it is to be adjusted according to the distribution adjustment probability; The scheduling allocation data segment for the energy-consuming equipment of the island green energy to be adjusted is determined according to the allocated energy consumption balance amount and the energy consumption control strategy.

9. The intelligent control system for island green integrated energy according to claim 1, characterized in that: Energy distribution activity refers to the degree of energy distribution of energy equipment (such as wind power, solar energy, and energy storage equipment) within a specific time period during the scheduling process.

10. The intelligent control system for island green integrated energy according to claim 1, characterized in that: According to the implicit correlation characteristics after matching prediction and the energy allocation activity after matching decision, the shortage load instructions for the shortage allocation of island green comprehensive energy are determined, including: The adaptive compensation value of the shortage allocation of island green comprehensive energy is determined by matching the implicit correlation features after prediction; Determine the load target information of island green comprehensive energy shortage allocation by matching the energy allocation activity after decision making; The deficit load instruction for the deficit allocation of the island green comprehensive energy is determined by the adaptation compensation value and the load target information.

Images