CN115001057A

CN115001057A - Composite micro energy source system and energy control method, device and storage medium thereof

Info

Publication number: CN115001057A
Application number: CN202110230347.5A
Authority: CN
Inventors: 陈果; 张斌; 曾怀望; 康为; 张楚婷; 汪浩鹏
Original assignee: United Microelectronics Center Co Ltd
Current assignee: United Microelectronics Center Co Ltd
Priority date: 2021-03-02
Filing date: 2021-03-02
Publication date: 2022-09-02
Also published as: WO2022183568A1

Abstract

An energy control method and device of a composite micro energy system, a storage medium and the composite micro energy system are provided, wherein the composite micro energy system comprises a micro energy collection module, an energy storage module and a power supply module, and the method comprises the following steps: identifying characteristic information of each energy collected by the micro-energy collection module; inputting the characteristic information of each energy and the electric power required by the load into a decision tree model to obtain a decision label of each energy, wherein the decision label is used for indicating the trend of each energy; controlling a trend of each energy according to the decision tag to transmit at least a portion of each energy to the power supply module and/or energy storage module. By adopting the scheme of the invention, the trend of various energies in the composite micro-energy system can be accurately determined, and the energy utilization rate is improved.

Description

Composite micro energy source system and energy control method, device and storage medium thereof

Technical Field

The invention relates to the technical field of energy, in particular to a composite micro-energy system, an energy control method and device thereof, and a storage medium.

Background

A composite micro-energy system is a system that is capable of harvesting energy generated by a variety of micro-energy sources and storing and/or releasing the various energies (e.g., supplying power to an external load). In the prior art, a set of logic threshold value control strategy is artificially formulated to determine the trend of energy according to theoretical analysis and engineering experience for the energy collected by a composite micro-energy system.

It is understood that the environment is variable and the energy collected by the composite micro-energy system is generally greatly influenced by the environment, for example, seasonal variations and diurnal variations may cause the solar energy collected by the system to be constantly in change. Furthermore, the demand of users using complex micro-energy sources is also variable, for example, the energy required by external loads often varies greatly from case to case. Because the logic threshold value control strategy in the prior art is artificially established, and the cost for changing the logic threshold value control strategy is high, the artificially established logic threshold value control strategy is rarely changed once being determined, so the method in the prior art cannot adapt the trend of energy in the composite micro-energy system to different conditions such as variable external environment, actual requirements and the like.

Therefore, an energy control method for a composite micro-energy system is needed to accurately determine the trend of various energies in the composite micro-energy system under different conditions, so as to improve the energy utilization rate.

Disclosure of Invention

The technical problem to be solved by the invention is to provide an energy control method of a composite micro-energy system, which can more accurately determine the trend of various energies in the composite micro-energy system under different conditions and improve the energy utilization rate.

In order to solve the foregoing technical problem, an embodiment of the present invention provides an energy control method for a composite micro energy system, where the composite micro energy system includes a micro energy collecting module, an energy storage module, and a power supply module, the micro energy collecting module is configured to collect at least one type of energy, the energy storage module is configured to store electric energy obtained by converting the energy, and the power supply module is configured to supply power to a load, and the method includes: identifying characteristic information of each energy collected by the micro-energy collection module; inputting the characteristic information of each energy and the electric power required by the load into a decision tree model to obtain a decision label of each energy, wherein the decision label is used for indicating the trend of each energy; controlling the trend of each energy according to the decision tag so as to transmit at least one part of each energy to the power supply module and/or the energy storage module; wherein the decision tree model is generated by training using a plurality of first energy samples as training data.

Optionally, the feature information includes one or more of the following: the type of energy and the electrical power to which the energy can be converted.

Optionally, the method for obtaining the decision label of each energy further includes: and inputting the state of charge of the energy storage module, the characteristic information of each energy and the electric power required by the load into the decision tree model together to obtain a decision label of each energy.

Optionally, the method for generating the decision tree model includes: obtaining a plurality of first energy samples, wherein each first energy sample comprises electric power required by a load, at least one sample energy and characteristic information and a decision label thereof; and taking the plurality of first energy samples as the training data, and training to generate the decision tree model.

Optionally, before the training of the decision tree model by using the plurality of first energy samples as the training data, the method further includes: determining a range of possible values of the electric power required by the load and a range of possible values of the characteristic information for each sample energy; and screening the plurality of first energy samples according to the characteristic information of each sample energy in each first energy sample and the electric power required by the load corresponding to the first energy sample to obtain the first energy sample for generating the decision tree model.

Optionally, before inputting the characteristic information of each energy and the electric power required by the load into the decision tree model, the method further includes: obtaining a plurality of second energy samples, wherein each second energy sample comprises electric power required by the load, at least one sample energy and characteristic information thereof and a preset decision label, and the plurality of second energy samples and the plurality of first energy samples are independent from each other; inputting the characteristic information of each sample energy in each second energy sample and the electric power required by the load corresponding to the second energy sample into the decision tree model to obtain a model decision label of each sample energy in the second energy sample; comparing the model decision label of each sample energy in each second energy sample with the preset decision label, calculating the proportion of the number of second energy samples with the model decision label of each sample energy consistent with the preset decision label to the number of all second energy samples, and if the proportion is smaller than a first preset threshold value, performing pruning processing on the decision tree model to update the decision tree model.

Optionally, the energy storage module includes a plurality of energy storage elements, and the energy storage module is further configured to supply power to the load, and the method further includes: acquiring the charge states of a plurality of energy storage elements; obtaining the power supply proportion of the energy storage elements by adopting a fuzzy control algorithm according to the electric power required to be provided by the energy storage module and the charge states of the energy storage elements, wherein the electric power required to be provided by the energy storage module is the difference value of the electric power required by the load and the energy convertible electric power of the micro-energy collection module; and determining the output electric power of each energy storage element according to the power supply proportion and the electric power required by the load.

Optionally, the plurality of energy storage elements comprise super capacitors.

Optionally, obtaining the power supply proportion of the plurality of energy storage elements by using a fuzzy control algorithm according to the electric power required to be provided by the energy storage module and the charge states of the plurality of energy storage elements includes: determining a power range to which the electric power required to be provided by the energy storage module belongs according to the electric power required to be provided by the energy storage module, and determining a charge range to which the charge state of each energy storage element belongs according to the charge state of each energy storage element; inquiring the fuzzy control rule table according to the power range and the charge range of each energy storage element to determine the power supply proportion range of each energy storage element; defuzzification is carried out on the power supply proportion range of each energy storage element so as to obtain the power supply proportion of each energy storage element; the fuzzy control rule table is used for describing the mapping relation between the power range and the charge range and the power supply proportion range.

Optionally, the micro energy collecting module includes a plurality of micro energy collectors, and the method further includes: acquiring first feedback information, wherein the first feedback information is used for indicating whether the micro energy collector is replaced or not; judging whether the micro energy collectors are replaced or not according to the first feedback information, and if so, acquiring the energy convertible electric power of each replaced micro energy collector; comparing the energy-convertible electrical power of each replaced micro-energy collector with a second preset threshold; and if the energy-convertible electric power of any one replaced micro-energy collector does not exceed a second preset threshold, retraining to generate the decision tree model.

Optionally, the energy storage module includes a plurality of energy storage elements, and the method further includes: acquiring second feedback information, wherein the second feedback information is used for indicating whether the energy storage element is replaced or not; judging whether the energy storage elements are replaced or not according to the second feedback information, and if so, acquiring the charge state of each replaced energy storage element; comparing the upper limit of the state of charge of each replaced energy storage element with a third preset threshold; and if the upper limit of the charge state of any replaced energy storage element does not exceed the third preset threshold, retraining to generate the decision tree model.

In order to solve the above technical problem, an embodiment of the present invention further provides an energy control device of a composite micro energy system, where the composite micro energy system includes a micro energy collecting module, an energy storage module, and a power supply module, the micro energy collecting module is configured to collect at least one type of energy, the energy storage module is configured to store electric energy converted from the energy, and the power supply module is configured to supply power to a load, and the device includes: the identification module is used for identifying the characteristic information of each energy collected by the micro-energy collection module; the classification module is used for inputting the characteristic information of each energy and the electric power required by the load into a decision tree model to obtain a decision label of each energy, and the decision label is used for indicating the trend of each energy; the transmission control module is used for controlling the trend of each energy according to the decision tag so as to transmit at least one part of each energy to the power supply module and/or the energy storage module; wherein the decision tree model is generated by training using a plurality of first energy samples as training data.

The embodiment of the present invention further provides a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the energy control method of the composite micro energy system are executed.

An embodiment of the present invention further provides a composite micro energy system, where the system includes: the micro-energy collection module is used for collecting at least one type of energy; the energy storage module is used for storing the electric energy after the energy conversion; the power supply module is used for supplying power to a load; and the controller is used for executing the steps of the energy control method of the composite micro-energy source system.

Compared with the prior art, the technical scheme of the embodiment of the invention has the following beneficial effects:

in the scheme of the embodiment of the invention, the decision tree model is generated by training a plurality of first energy samples, and the decision tree model generated by training can learn the relation and the rule among the characteristic information of the energy in the first energy samples, the power required by the load and the decision label of the energy. The recognized characteristic information of each energy and the load required electric power are input into a decision tree model generated by training, a decision label of each energy can be determined according to the current characteristic information of each energy and the load required electric power, and then the trend of each energy is controlled according to the decision label, so that the trend of the energy can be controlled according to the characteristic information of each energy and the load required electric power. By the method, the trend of the energy can be adapted to the characteristic information of the energy currently collected by the micro energy collection module and the condition of electric power required by the load, so that the trend of the energy can be determined more accurately, and the utilization rate of the energy is improved.

Further, in the scheme of the embodiment of the present invention, before the decision tree model is trained and generated, the plurality of first energy samples are screened according to the determined available value range of the characteristic information and the available value range of the electric power required by the load to obtain the first energy samples used for generating the decision tree model, so that the accuracy of the first energy samples as training data can be ensured, and the decision tree model generated by training is more accurate.

Further, in the scheme of the embodiment of the present invention, before the user uses the decision tree model to perform energy trend control, the decision tree model generated by training is tested by using the second energy sample that is independent from the first energy sample, and when the ratio of the number of the second energy samples in which the model decision labels of each sample energy obtained by the test are consistent with the preset decision labels to the number of all the second energy samples is smaller than the first preset threshold, the decision tree model is pruned to calibrate the decision tree model, so that the decision tree model can adapt to the current actual demand, thereby more accurately determining the energy trend.

Further, in the scheme of the embodiment of the invention, based on a fuzzy control algorithm, the power supply proportion of each energy storage element is determined according to the electric power required to be provided by the energy storage module and the charge state of each energy storage element, so that the power supply module can be prevented from being powered by repeatedly using individual energy storage elements, and the problems of premature aging, loss and the like caused by repeated charge and discharge of the individual energy storage elements are avoided as much as possible.

Drawings

Fig. 1 is a schematic structural diagram of a hybrid micro energy system according to an embodiment of the present invention.

Fig. 2 is a schematic flow chart of a first method for controlling energy of the hybrid micro energy system according to an embodiment of the present invention.

FIG. 3 is a schematic structural diagram of a decision tree model according to an embodiment of the present invention.

Fig. 4 is a flowchart illustrating an energy control method of a second hybrid micro energy system according to an embodiment of the present invention.

Fig. 5 is a flowchart illustrating an energy control method of a third hybrid micro energy system according to an embodiment of the present invention.

Fig. 6 is a schematic structural diagram of an energy control device of a hybrid micro energy system according to an embodiment of the present invention.

Detailed Description

As described in the background art, there is a need for an energy control method for a hybrid micro energy system, which can accurately determine the trend of various energies in the hybrid micro energy system under different conditions, and improve the energy utilization rate.

As described above, the inventors of the present invention have found through research that, in the prior art, a set of logic threshold control strategies is artificially established to determine the trend of energy for the energy collected by the composite micro-energy system, usually according to theoretical analysis and engineering experience. It is understood that the environment is variable and the energy collected by the composite micro-energy system is generally greatly influenced by the environment, for example, seasonal variations and diurnal variations may cause the solar energy collected by the system to be constantly in change. Furthermore, the demand of users using complex micro-energy sources is also variable, for example, the energy required by external loads often varies greatly from case to case. Because the logic threshold value control strategy in the prior art is artificially established, and the cost for changing the logic threshold value control strategy is high, the artificially established logic threshold value control strategy is rarely changed once being determined, and the method in the prior art cannot adapt the trend of energy in the composite micro-energy system to different conditions such as variable external environment, actual requirements and the like.

In order to solve the above technical problem, an embodiment of the present invention provides a control method for a hybrid micro energy system, and in a scheme of the embodiment of the present invention, since a decision tree model is generated by training a plurality of first energy samples, the decision tree model generated by training can learn a relationship and a rule between feature information of energy in the first energy samples, power required by a load, and a decision label of the energy. And inputting the identified characteristic information of each energy and the load required electric power into a decision tree model generated by training, determining a decision label of each energy according to the current characteristic information of each energy and the load required electric power, and controlling the trend of each energy according to the decision label, so that the trend of the energy can be controlled according to the characteristic information of each energy and the load required electric power. By the method, the trend of the energy can be adapted to the characteristic information of the energy currently collected by the micro energy collection module and the condition of electric power required by the load, so that the trend of the energy can be accurately determined, and the utilization rate of the energy is improved.

In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.

Referring to fig. 1, fig. 1 is a schematic structural diagram of a hybrid micro energy system according to an embodiment of the present invention. A composite micro energy system suitable for use in the embodiments of the present invention is described below with reference to fig. 1.

The hybrid micro energy system shown in fig. 1 may include: the micro-energy collection module 11, the energy storage module 12, the power supply module 13 and the controller 14.

The micro energy harvesting module 11 is used to harvest at least one energy, which may be any kind of energy. The energy may be electric energy, or any energy that can be converted into electric energy, such as solar energy, electromagnetic energy, vibration energy, and the like, but is not limited thereto.

The micro energy collecting module 11 may include a plurality of micro energy collectors, and the micro energy collectors may be used to collect various types of energy and convert the collected various types of energy into electric energy.

In particular, the types of energy vary, and the micro-energy collectors typically vary. For example, the micro-power harvester can include a solar energy harvester (e.g., a solar panel), a vibration energy harvester, a radio frequency energy harvester, and the like. The solar energy collector is a micro energy collector for collecting solar energy, the vibration energy collector is a micro energy collector for collecting vibration energy, and the radio frequency energy collector is a micro energy collector for collecting electromagnetic energy, but not limited thereto.

The micro-energy collection module 11 may be coupled to the energy storage module 12 to transmit the collected energy (or the converted electric energy) to the energy storage module 12, and may also be coupled to the power supply module 13 to transmit the collected energy (or the converted electric energy) to the power supply module 13, but is not limited thereto.

The energy storage module 12 is used for storing the electric energy after the energy conversion. Specifically, the energy collected by the micro energy collecting module 11 is converted into electric energy, and then the electric energy can be transmitted to the energy storage module 12 for storage. It should be noted that the energy stored in the energy storage module 12 is usually electric energy.

The energy storage module 12 may include a plurality of energy storage elements, which may refer to elements for storing electric energy, such as, but not limited to, a lithium battery and/or a super capacitor. The number and the type of the energy storage elements are not limited in any way in the embodiments of the present invention.

The energy storage module 12 may be coupled to the power supply module 13, and may transmit the stored electric energy to the power supply module 13.

The power supply module 13 is configured to be coupled to an external load and supply power to the external load. The electric energy obtained by the power supply module 13 may come from the micro-energy collecting module 11, may come from the energy storage module 12, or may come from both of them. In other words, the power obtained by the power supply module 13 may be only from the micro power collecting module 11, only from the energy storage module 12, or may be both from the micro power collecting module 11 and from the energy storage module 12, but is not limited thereto.

The controller 14 may be used to control the direction of the energy collected by the micro energy harvesting modules in the composite micro energy system.

Specifically, the controller 14 may be coupled to the micro energy collecting module 11 and configured to control the direction of each energy collected by the micro energy collecting module 11, and more specifically, the controller 14 may be configured to control whether the energy collected by the micro energy collecting module 11 is transmitted to the energy storage module 12, the power supply module 13, or both.

Further, the controller 14 may also be coupled to the energy storage module 12 and configured to control whether the electric energy stored in the energy storage module 12 needs to be transmitted to the power supply module 13. More specifically, the controller 14 may be further coupled to each energy storage element in the energy storage module 12 and configured to control the power transmitted from each energy storage element to the power supply module 13.

Further, the controller 14 may also be coupled to the power supply module 13 to obtain the current power supply requirement, which refers to the electric power that the composite micro-energy source system currently needs to provide to the outside, and may be the electric power required by the load, for example.

The composite micro energy system may further include a monitoring module 15, and the monitoring module 15 may be coupled to the micro energy collecting module 11 to monitor whether there is an abnormality in the micro energy collecting module 11. More specifically, the monitoring module 15 may be used to monitor whether each micro energy collector is abnormal, for example, whether various parameters (such as peak power of output energy) of the micro energy collector are abnormal, whether the micro energy collector itself has problems of cracking, breaking, being blocked, and the like.

Further, the monitoring module 15 may also be coupled to the energy storage module 12 to monitor the energy storage module 12 for anomalies. More specifically, the monitoring module 15 may be used to monitor the presence of anomalies in the various energy storage elements of the energy storage module 12, such as: whether or not various parameters of the energy storage element (for example, parameters such as an upper limit of stored energy) are abnormal, the energy storage element itself is aged, and the like.

Referring to fig. 2, fig. 2 is a schematic flow chart illustrating an energy control method of a hybrid micro energy system according to an embodiment of the present invention. The energy control method may be performed by a controller, which may be any suitable terminal having data receiving and processing capabilities, such as, but not limited to, a computer, a sensing analyzer, and the like. The controller can be arranged inside the composite micro energy system and is coupled with each device in the composite micro energy system; alternatively, the controller may be located external to the hybrid micro energy system and remotely coupled to the various devices in the hybrid micro energy system, but is not limited thereto. The hybrid micro energy system may be a system capable of collecting energy generated by a plurality of micro energy sources and storing and/or releasing various kinds of energy, and may include a micro energy collecting module, an energy storage module and a power supply module, but is not limited thereto. In one non-limiting embodiment of the present invention, the hybrid micro energy system is the hybrid micro energy system shown in fig. 1.

The energy control method of the hybrid micro energy system shown in fig. 2 may include the steps of:

step S201: identifying characteristic information of each energy collected by the micro-energy collection module;

step S202: inputting the characteristic information of each energy and the electric power required by the load into a decision tree model to obtain a decision label of each energy, wherein the decision label is used for indicating the trend of each energy; wherein the decision tree model is generated by training using a plurality of first energy samples as training data.

Step S203: controlling a trend of each energy according to the decision tag to transmit at least a portion of each energy to the power supply module and/or energy storage module.

In a specific implementation of step S201, the characteristic information of each energy collected by the micro energy collecting module may be acquired and identified according to a preset time interval, where the preset time interval may be configured in advance. Wherein the characteristic information refers to a characteristic for describing one or more aspects of the energy. For example, the characteristic information may include, but is not limited to, a type of energy and an energy-convertible electric power.

In particular, the micro energy harvesting module may include a plurality of micro energy harvesters that differ in the type of energy, and thus the type of energy may be determined from the micro energy harvester from which each type of energy originates. More specifically, each micro energy collector may have an energy identifier, micro energy collectors that collect the same kind of energy may have the same energy identifier, and the kind of energy may be determined by identifying the energy identifiers of the respective micro energy collectors.

Further, the convertible electrical power of each energy in the micro energy harvesting module can also be obtained. The convertible electrical power of energy refers to the efficiency with which energy can be converted into electrical energy. Specifically, the convertible electrical power of each energy in the micro energy harvesting module can be obtained by a sensor or the like mounted to the micro energy harvesting module. More specifically, the electrical power convertible in energy in each micro-energy collector can also be obtained.

In the specific implementation of step S202, the electric power required by the external load may be obtained at preset time intervals, and the characteristic information of each energy and the electric power required by the load are input into the decision tree model to obtain the decision label of each energy.

The decision tag may be used to indicate the trend of energy, for example, to a power supply module and/or to an energy storage module. In one non-limiting embodiment of the invention, the energy storage elements in the energy storage module include lithium batteries and super capacitors, and the energy profile may include one or more of the following: the power is transmitted to the power supply module, the lithium battery and the super capacitor.

It should be noted that the correlation between the characteristic information of the energy, the electric power required by the load, and the decision label is time-dependent, and the correlation may change with time. Specifically, the characteristic information of the energy and the electric power required by the load may belong to the same time interval, and the obtained decision label is the trend of the energy in the time interval. That is, at every time interval, the current characteristic information of each energy and the required electric power of the load are used to obtain the current decision labels of various energies.

In one non-limiting embodiment of the invention, the state of charge of the energy storage module can be input to the decision tree model along with the characteristic information of each energy and the electric power required by the load to obtain the decision label of each energy. In other words, the decision label of each energy is determined according to the state of charge of the energy storage module, the characteristic information of the energy and the electric power required by the load. The state of charge of the energy storage module is also in time-related association with the characteristic information of energy, the electric power required by the load and the decision tag. Compared with the scheme of determining the decision tag of each energy according to the characteristic information of each energy and the electric power required by the load, the scheme of inputting the charge state of the energy storage module, the characteristic information of each energy and the electric power required by the load into the decision tree model together to obtain the decision tag of the category tag of each energy can enable the trend of the energy to better meet the actual requirement of the composite micro-energy system and improve the utilization rate of the energy.

More specifically, the state of charge of each energy storage element in the energy storage module may be input into the decision tree model together with the characteristic information of the energy and the electric power required by the load. That is, the decision label of the energy may be determined by the characteristic information of the energy, the electric power required by the load, and the state of charge of each energy storage element, which have a time-dependent correlation therewith.

Further, the decision tree model is generated by training using a plurality of first energy samples as training data. Wherein each first energy sample may comprise the electrical power required by the load, at least one sample energy, and characteristic information and a decision tag for each sample energy. The sample energy may be selected from the energy collected by the micro-energy collection module, for example, solar energy, vibrational energy, electromagnetic energy, etc., but is not limited thereto. Wherein, each sample energy has characteristic information and decision label, and the characteristic information and decision label of different sample energies can be different.

It should be noted that each first energy sample includes a time-dependent relationship between the electric power required by the load and the first energy sample. More specifically, the electrical power required by the load has a time-dependent relationship with each of the first energy samples.

In one non-limiting embodiment of the present invention, each first energy sample may further comprise a state of charge of the energy storage module. The state of charge of the energy storage module may also be correlated with the first energy sample in a time-dependent manner. More specifically, the state of charge of the energy storage module may comprise the state of charge of a plurality of energy storage elements. It should be noted that the specific content of the first energy sample depends on the input data of the decision tree model.

Further, for each combination of sample energies, all possible trends of each energy in the combination need to be included in the plurality of first energy samples. The combination mode refers to the type of the sample energy in each first energy sample. Taking this combination of solar energy and vibration energy as an example, in the first energy samples with sample energy of solar energy and vibration energy, it is required that the decision labels including solar energy are the first energy samples of all selectable decision labels, respectively, and the decision labels of vibration energy are the first energy samples of all selectable decision labels, respectively.

In one non-limiting embodiment of the present invention, considering that part of the first energy samples may be obtained in the presence of an anomaly in the composite micro-energy system, in order to ensure the accuracy of the decision tree model, a plurality of first energy samples need to be screened.

Specifically, an available value range of the characteristic information of each sample energy and an available value range of the electric power required by the load may be determined first. The above-mentioned available value range may be received from the outside or may be stored in the controller in advance. The range of values of the characteristic information of each sample energy may be the range of values of the energy identifier, or the range of values of the energy-convertible electric power of each energy, but is not limited thereto.

Further, whether the characteristic information of each first energy sample meets the available value range of the characteristic information or not is judged, whether the load required electric power corresponding to each first energy sample meets the available value range of the load required electric power or not is judged, and if both the two conditions are met, the first energy sample can be judged to be used for training the spanning decision tree model.

In a non-limiting embodiment of the present invention, a state of charge range of the energy storage module may also be determined, and the plurality of first energy samples are screened according to the state of charge of the energy storage module corresponding to the first energy sample, so as to obtain the first energy sample for generating the decision tree model.

Therefore, a plurality of first energy samples can be screened by setting the range of the acquirable value of the characteristic information and the range of the acquirable value of the electric power required by the load, the accuracy of training data is improved, and the decision tree model is more accurate.

Further, the method for generating the decision Tree model by training the plurality of first energy samples may be any suitable existing algorithm, for example, a Classification and Regression Tree (CART) algorithm, that is, the decision Tree model may be recursively constructed according to the principle of minimization of a kini (Gini) index.

Referring to fig. 3, fig. 3 is a schematic diagram of a decision tree model according to an embodiment of the present invention. The decision tree model shown in fig. 3 comprises nodes and directed edges, wherein the nodes comprise inner nodes 31 and leaf nodes 32. The internal node 31 represents a plurality of preset attributes, which can be determined according to the input of the decision tree model. For example: the type of energy, the convertible electrical power of the energy and the electrical power required by the load, etc. The leaf nodes 32 may represent a plurality of decision labels.

Each internal node 31 corresponds to an attribute test, and each internal node 31 includes a plurality of first energy samples divided into sub-nodes of the internal node 31 according to the result of the attribute test. Starting from the uppermost internal node of the internal nodes 31, the plurality of first energy samples included in each internal node 31 are recursively classified until a preset condition position for stopping recursion is reached, so as to obtain a plurality of leaf nodes 32. The preset condition for stopping the recursion may be, but is not limited to, that the number of the plurality of first energy samples in each internal node 31 is less than a preset number, or that the kuni index of the plurality of first energy samples included in each internal node 31 is less than a preset index.

Specifically, for a sample set D contained by each internal node 31, the sample set D including a plurality of first energy samples, the sample set D having K sample subsets, the following formula is used to calculate the kini index of the sample set D:

where Gini (D) is the Kini index of the sample set D, K is the number of children of the internal node 31,

is the division of the first energy sample in the sample set D into the sample subset D _k The probability of (c).

Further, there are multiple possible values of the attribute a corresponding to each internal node 31, and for each possible value a, the sample set D is divided into the sample subsets D according to whether the test result of each first energy sample on the attribute a is yes or no ₁ And sample subset D ₂ And calculating the kini index of the sample set D when A is a by adopting the following formula:

wherein Gini (D, a) is a kini index when the attribute a of the internal node 31 takes a value, and Gini (D, a) ₁ ) As a subset of samples D ₁ Gini (D) is a Gini index ₂ ) As a subset of samples D ₂ The index of the degree of damping of (a),

dividing first energy samples in sample set D into sample subset D ₁ The probability of (a) of (b) being,

dividing first energy samples in sample set D into sample subset D ₂ The probability of (c). The kini index Gini (D, a) may represent an uncertainty when the sample set D is segmented according to the attribute a of the first energy sample taking the value a, and the larger the kini index Gini (D, a), the larger the uncertainty of such a segmentation manner.

For different values a of the attribute a, corresponding Gini indexes are respectively calculated, the value a with the minimum Gini index is selected, and the first energy sample of the internal node 31 is divided into sample sets of two sub-nodes according to the value a.

Further, the steps are recursively called for the two sub-nodes until a preset condition for stopping recursion is met, so that a decision tree model is generated.

Further, in the solution of the embodiment of the present invention, after the decision tree model is trained and generated, the obtained decision tree model may be tested, and the testing method may be any appropriate method that can be used for testing the accuracy of the generated decision tree model, for example, a method of S-fold cross validation may be used for testing, but is not limited thereto.

Specifically, before training the decision tree model, the plurality of first energy samples may be divided into a training sample set and a test sample set, and after the decision tree model is generated by training with the first energy samples in the training sample set, the electric power required by the load and the characteristic information of each sample energy in the test sample set are input into the decision tree model to obtain the model decision label of each sample energy in the first energy samples. And comparing the model decision label of each sample energy in each first energy sample with the decision label of the sample energy, and calculating the proportion of the number of the first energy samples with the consistent model decision label and decision label of each sample energy to the number of all the first energy samples. If the ratio is smaller than the preset ratio, it is determined that the decision tree model is inaccurate, and the decision tree model needs to be processed to improve the accuracy of the decision tree model.

In one non-limiting embodiment of the invention, the decision tree model may also be calibrated before inputting the characteristic information of the energy and the electric power required by the load to the decision tree model. In particular, the decision tree model is calibrated using second energy samples that are independent of the first energy samples. Here, "independent" means that there is no correlation between the first energy sample and the second energy sample, for example, the first energy sample is a sample taken during training of the decision tree model, and the second energy sample is a sample taken during calibration before the decision tree model is actually used. More specifically, in different usage scenarios, the difference between the electric powers required by the loads is large, and the training data of the decision tree model cannot cover the electric powers required by the loads in all the scenarios, so before the trend of the energy is controlled by actually using the decision tree model, a second energy sample can be selected according to the actual usage scenario to calibrate the decision tree model.

Specifically, a plurality of second energy samples may be obtained, each second energy sample comprising the electrical power required by the load and at least one sample energy and its characteristic information and a preset decision tag. Further description of the second energy samples can refer to the above description related to the first energy samples, and will not be repeated herein.

Further, the characteristic information of each sample energy in each second energy sample and the electric power required by the load corresponding to the second energy sample can be input into the decision tree model to obtain a model decision tag of each sample energy in the second energy sample. It should be noted that, if the input of the decision tree model further includes the state of charge of the energy storage module, the state of charge of the energy storage module corresponding to each second energy sample needs to be input into the decision tree model together.

Further, comparing a model decision tag of each sample energy in each second energy sample with the preset decision tag, calculating a ratio of the number of second energy samples with the model decision tag of each sample energy consistent with the preset decision tag to the number of all second energy samples, and if the ratio is smaller than a first preset threshold, performing pruning processing on the decision tree model to update the decision tree model. Wherein the first preset threshold may be preconfigured. The pruning treatment may be performed by any appropriate method.

Therefore, in the scheme of the embodiment of the invention, before the user uses the decision tree model to control the trend of the energy, the decision tree model is pruned to calibrate the decision tree model, so that the decision tree model can adapt to the current actual demand, and the trend of the energy can be determined more accurately.

With continued reference to fig. 2, in an implementation of step S203, after obtaining the decision tag of each energy, the trend of each energy may be controlled according to the decision tag of the energy, so as to transmit at least a portion of each energy to the power supply module and/or the energy storage module.

Particularly, controllable paths can be arranged between the micro-energy collection module and the power supply module and between the micro-energy collection module and the energy storage module. The corresponding control signal can be generated according to the decision tag of each energy, and the control signal can be used for setting the connection or disconnection of a path between the micro energy collecting module and the power supply module, and also can be used for setting the connection or disconnection of a path between the micro energy collecting module and the energy storage module. More specifically, the control signal may be used to set the path between each micro-energy collector and the power supply module to be turned on or off, and may also be used to set the path between each energy storage element and the power supply module to be turned on or off.

Therefore, in the scheme of the embodiment of the invention, the identified characteristic information of each energy and the electric power required by the load are input into the trained decision tree model, the decision label of each energy can be determined according to the current characteristic information of each energy and the electric power required by the load, and then the trend of each energy is controlled according to the decision label, so that the trend of each energy can be controlled according to the current characteristic information of each energy and the electric power required by the load. The control process can be executed once every preset time, and the trend of the energy can be adapted to the characteristic information of the energy currently collected by the micro energy collection module and the condition of the electric power required by the load through the method, so that the trend of the energy can be accurately determined, various energies can be fully utilized, and the utilization rate of the energy is improved.

Referring to fig. 4, fig. 4 illustrates a second method for controlling energy of the hybrid micro energy system according to an embodiment of the present invention. The method is used for controlling the power supply proportion of each energy storage element in the energy storage module to the power supply module. It should be noted that the energy storage module may also be used for transmitting electric energy to the power supply module.

Preferably, when the power supply module supplies power to the load, the electric energy collected by the micro energy collection module may be transmitted to the power supply module first, and when the convertible electric power of the energy in the micro energy collection module is lower than the electric power threshold, the micro energy collection module does not transmit electric energy to the power supply module any more, and at this time, the energy storage module may continue to transmit electric energy to the power supply module. The method that the micro energy collection module supplies power firstly and then the energy storage module supplies power can avoid the problems of rapid aging and the like caused by frequent charging and discharging of the energy storage element in the energy storage module.

The energy control method of the hybrid micro energy source system shown in fig. 4 may include the steps of:

step S401: acquiring the charge states of a plurality of energy storage elements;

step S402: obtaining the power supply proportion of the energy storage elements by adopting a fuzzy control algorithm according to the electric power required to be provided by the energy storage module and the charge states of the energy storage elements, wherein the electric power required to be provided by the energy storage module is the difference value of the electric power required by the load and the energy convertible electric power of the micro-energy collection module;

step S403: and determining the output electric power of each energy storage element according to the power supply proportion and the electric power to be supplied by the energy storage module.

In the specific implementation of step S401, a State of Charge (SoC) of each energy storage element in the energy storage module may be obtained. Preferably, the energy storage element may include a super capacitor, and the super capacitor has an advantage of rapid charging and discharging. It can be understood that the lithium battery repeatedly charges and discharges with large current for a long time to lead to the lithium battery to age fast, compares in the scheme that energy storage element only includes the lithium battery, adopts super capacitor as energy storage element, can make super capacitor and lithium battery can effectively cooperate.

In the specific implementation of step S402, the electric power to be provided by the energy storage module and the state of charge of each energy storage element are respectively blurred. Specifically, the power range to which the electric power required to be provided by the energy storage module belongs may be determined according to the electric power required to be provided by the energy storage module, and the charge range to which the charge state of each energy storage element belongs may be determined according to the charge state of the energy storage element.

The fuzzification of the electric power to be provided by the energy storage module and the state of charge of the individual energy storage elements may be any suitable algorithm. Preferably, the fuzzification can be performed by using a membership value method.

Specifically, the respective membership functions of the electric power to be provided by the energy storage module and the states of charge of the energy storage elements may be determined, and the intervals of the membership functions may be uniform or non-uniform. The membership function may be a dual sigmoid membership function, a triangular membership function, a gaussian membership function, a sigmoid membership function, a trapezoidal membership function, etc., but is not limited thereto. And then determining a power range according to the electric power required to be provided by the energy storage module and the corresponding membership function thereof, and determining a charge range corresponding to each energy storage element according to the charge state of each energy storage element and the membership function thereof.

It should be noted that the electric power required to be provided by the energy storage module is the difference between the electric power required by the load and the energy-convertible electric power of the micro energy collecting module. More specifically, when the convertible electric power of the energy in the micro energy collection module is lower than the electric power threshold, the micro energy collection module does not transmit electric energy to the power supply module any more, and in order to extend the service life of the device in the micro energy collection module, etc., the convertible electric power of the energy in the micro energy collection module may be subtracted by a preset fixed value, and then the subtracted electric power may be used to calculate the electric power required to be provided by the energy storage module, where the preset fixed value may be the electric power threshold.

Further, the fuzzy control rule table is inquired according to the power range and the charge range of each energy storage element so as to determine the power supply proportion range of each energy storage element. The fuzzy control rule table may be preconfigured and is used for describing a mapping relationship between the power range and the charge range and the power supply proportion range. The fuzzy control rule table may include a set of fuzzy condition statements of if-then structure to query the corresponding range of supply proportions from the input power range and the charge range.

Further, the power supply proportion range of each energy storage element is defuzzified to obtain the power supply proportion of each energy storage element. In other words, the power supply proportion of each energy storage element is determined according to the power supply proportion range of the energy storage element. The defuzzification method may be any suitable algorithm, such as, but not limited to, maximum membership method, weighted average method, center of gravity method, etc. Preferably, an adaptive method can be selected according to the requirements or the actual operation condition of the composite micro-energy system, so that the fuzzy power supply proportion range is converted into the accurate power supply proportion. More specifically, the defuzzification method may be selected according to the performance requirement of the composite micro energy system, for example, when the requirement of the composite micro energy system on the calculation speed for determining the power supply proportion is high, the maximum membership method, the weighted average method may be selected; when the composite micro energy system has a high demand for calculation accuracy of determining the power supply ratio, the center of gravity method may be selected, but is not limited thereto. In one non-limiting embodiment of the present invention, the range of the power supply proportion of each energy storage element is defuzzified by using a gravity center method to obtain the power supply proportion of each energy storage element.

In the specific implementation of step S403, the output electric power of each energy storage element may be determined by calculation according to the power supply ratio of each energy storage element and the electric power to be provided by the negative energy storage module, and the power supply module may be powered according to the output electric power of each energy storage element. Therefore, in the scheme of the embodiment of the invention, the purpose of prolonging the service life of the system can be achieved while meeting the power supply requirement of the load.

Referring to fig. 5, fig. 5 illustrates an energy control method of a third hybrid micro energy system according to an embodiment of the present invention. Compared to the energy control method of the hybrid micro energy source system shown in fig. 2, the energy control method of the hybrid micro energy source system shown in fig. 5 may further include the steps of:

step S204: acquiring first feedback information, wherein the first feedback information is used for indicating whether the micro energy collector is replaced or not;

step S205: judging whether the micro energy collectors are replaced or not according to the first feedback information, and if so, acquiring the energy convertible electric power of each replaced micro energy collector;

step S206: and comparing the energy convertible electric power of each replaced micro-energy device collector with the second preset threshold, and if the energy convertible electric power of any replaced micro-energy device collector does not exceed the second preset threshold, retraining to generate the decision tree model.

In the specific implementation of step S204, the energy-convertible electric power in each micro-energy collector may be obtained, and the energy-convertible electric power in each micro-energy collector may be compared with a preset second preset threshold, and when the energy-convertible electric power in any one micro-energy collector does not exceed the second preset threshold, it may be determined that the micro-energy collector is abnormal. More specifically, when the duration of the energy-convertible electric power in any one of the micro energy collectors does not exceed the second preset threshold exceeds a first preset time, it may be judged that there is an abnormality in the micro energy collector. The second preset threshold and the first preset time may be preconfigured.

Further, when the micro energy collecting device is judged to be abnormal, first alarm information can be sent out, and the first alarm information can indicate the abnormal micro energy collecting device, so that a user can replace the abnormal micro energy collecting device.

Further, first feedback information may be received from the outside, and the first feedback information may be used to indicate whether the user replaces the micro energy collector.

In an implementation of step S205, it may be determined whether the micro energy collector is replaced according to the received first feedback information. In addition, if the first feedback information is not acquired after the second preset time, it can be determined that the micro energy collector is not replaced.

Further, after the micro energy collector is determined to be replaced, the energy convertible electric power of the replaced micro energy collector can be obtained. Specifically, the upper limit of the energy-convertible electrical power within the first preset time after the micro-energy collector is replaced may be obtained.

In the specific implementation of step S206, the energy convertible electric power of the replaced micro energy collector may be compared with a second preset threshold, and if the energy convertible electric power of any one replaced micro energy collector does not exceed the second preset threshold, the decision tree model may be retrained and generated, so that the decision tree model can adapt to the composite micro energy system after the replacement of the micro energy collector, and the self-correction of the decision tree model is realized.

Therefore, in the scheme of the embodiment of the invention, the decision tree model is not necessarily retrained after the micro energy collector is replaced, but the energy convertible electric power is compared with the second preset threshold value again to judge whether the abnormal condition still exists after the replacement, if the abnormal condition disappears after the micro energy collector is replaced, the decision tree model does not need to be retrained, and compared with the decision tree model which is retrained every time the micro energy collector is replaced, the scheme of the embodiment of the invention has higher efficiency.

In addition, compared with the situation that the decision tree model is not generated again after the micro energy collector is replaced, the scheme provided by the embodiment of the invention monitors the replaced micro energy collector again, so that whether the replaced micro energy collector is abnormal or not can be found in time, and the normal operation of the composite micro energy system can be ensured.

In a non-limiting embodiment of the present invention, if it is determined that the micro energy collector is not replaced according to the first feedback information, the decision tree model may be retrained, so that the decision tree model can adapt to the abnormal condition of the micro energy collector, thereby implementing self-correction of the decision tree model.

Specifically, a plurality of third energy samples may be obtained and the spanning decision tree model retrained with the third energy samples. Wherein each third energy sample may comprise power required by the load, at least one sample energy and its characteristic information and a decision tag. And the characteristic information of the sample energy in each third energy sample meets the characteristic requirement of the energy collected by the micro energy collector when the micro energy collector is abnormal. For example, the energy-convertible electrical power of the sample energy in each third energy sample does not exceed a second preset threshold. For more details on the retraining of the spanning tree model with the third energy sample, reference may be made to the above description on the training of the spanning tree model with the first energy sample, and details are not repeated here.

In another non-limiting embodiment of the present invention, in consideration of the fact that the type, etc. of the micro energy collector may change before and after the replacement, which results in that the original decision tree model is not suitable for the replaced micro energy collector, a difference between the energy convertible electric power of each replaced micro energy collector and the standard value of the energy convertible electric power of the micro energy collector may be calculated, and the difference is compared with a preset first difference threshold, if the difference is greater than the first difference threshold, it may be determined that the replaced micro energy collector has a larger difference from the micro energy collector before the replacement, and at this time, the decision tree model may be retrained and generated.

Wherein the standard value of the energy-convertible electrical power may be determined according to a micro-energy harvester. The standard values for the energy-convertible electrical power of the different micro-energy collectors may be different. More specifically, the standard values of the energy-convertible electrical power of different models of micro-energy collectors may be different. For the replaced micro-energy collector, the standard value of the energy convertible electric power can be calculated according to the energy convertible electric power of the micro-energy collector in a third preset time before the replacement. For example, the intermediate value of the energy-convertible electric power within the third preset time may be taken as the standard value of the energy-convertible electric power, but is not limited thereto.

In another non-limiting embodiment of the present invention, the charge state of each energy storage element may be obtained, and the charge state of each energy storage element is compared with a preset third preset threshold, and when the charge state of any one energy storage element does not exceed the third preset threshold, it may be determined that the energy storage element is abnormal. More specifically, when the time that the state of charge of any one energy storage element does not exceed the third preset threshold continuously exceeds the first preset time, it may be determined that the energy storage element is abnormal. The third preset threshold may be preconfigured.

Further, when judging that the energy storage element is abnormal, second alarm information can be sent out, and the second alarm information can indicate the abnormal energy storage element, so that a user can replace the abnormal energy storage element.

Further, second feedback information may be received from the outside, which may be used to indicate to a user whether to replace the energy storage element.

Further, whether the energy storage element is replaced or not can be determined according to the received second feedback information. In addition, if the second feedback information is not acquired after the second preset time, it can be determined that the energy storage element is not replaced.

Further, after the energy storage element is determined to be replaced, the state of charge of the replaced energy storage element can be obtained. Specifically, the upper limit of the state of charge in the first preset time after the energy storage element is replaced can be obtained. More specifically, an upper limit of the state of charge of the energy storage element within a first preset time may be obtained.

Further, the state of charge of each replaced energy storage element may be compared with the third preset threshold, and if the state of charge of any replaced energy storage element does not exceed the third preset threshold, the decision tree model may be generated by retraining.

In a non-limiting embodiment of the present invention, in consideration of the fact that the type, and the like of the energy storage element may change before and after replacement, which results in that the original decision tree model is not suitable for the replaced energy storage element, a difference between the charge state of each energy storage element after replacement and a standard value of the charge state of the energy storage element may be calculated, and the difference is compared with a preset second difference threshold, if the difference is greater than the second difference threshold, it may be determined that the energy storage element after replacement and the energy storage element before replacement have a large difference, and at this time, the decision tree model may be generated by retraining.

Wherein the standard value of the state of charge may be determined according to an energy storage element. The standard values of the states of charge of the different energy storage elements may be different. More specifically, the standard values of the states of charge of the energy storage elements of different models may be different. For the replaced energy storage element, the standard value of the state of charge of the energy storage element may be calculated according to the state of charge of the energy storage element in a third preset time before the replacement, for example, an intermediate value of the state of charge in the third preset time may be taken as the standard value of the state of charge, but the method is not limited thereto.

For more details about whether to retrain the spanning decision tree model according to the second feedback information, reference may be made to the above description about fig. 5, which is not repeated herein.

Referring to fig. 6, fig. 6 is a diagram illustrating an energy control apparatus of a hybrid micro energy system according to an embodiment of the present invention, the apparatus may include:

an identification module 61 for identifying the characteristic information of each energy collected by the micro energy collection module;

a classification module 62, configured to input the characteristic information of each energy and the electric power required by the load into a decision tree model to obtain a decision label of each energy, where the decision label is used to indicate a trend of each energy;

a transmission control module 63, configured to control a trend of each energy according to the decision tag, so as to transmit at least a portion of each energy to the power supply module and/or the energy storage module;

the decision tree model is generated by training by using a plurality of first energy samples as training data.

For the principle, the operation mode and the beneficial effects of the energy control apparatus of the hybrid micro energy system in the embodiment of the present invention, reference is made to the foregoing description of the energy control method of the hybrid micro energy system, and details are not repeated herein.

Referring to fig. 1, an embodiment of the present invention further provides a composite micro energy system, which may include: a micro-energy collection module 11 for collecting at least one energy; the energy storage module 12 is used for storing the electric energy converted by the energy; a power supply module 13 for supplying power to a load; and the controller 14 is used for executing the steps of the energy control method of the composite micro-energy source system.

The controller may be coupled to a memory storing a computer program, and the controller may read the computer program in the memory and execute the steps of the energy control method of the composite micro energy system by running the computer program. The controller may be a processor independent from the memory, or may be a terminal integrating the memory and the processor, but is not limited thereto.

For the principle, structure, operation mode and beneficial effects of the composite micro energy system in the embodiment of the present invention, please refer to the related description of the energy control method of the composite micro energy system, which is not repeated herein.

The embodiment of the invention also discloses a storage medium which is a computer readable storage medium and is stored with a computer program, and the computer program can execute the steps of the method when running. The storage medium may include ROM, RAM, magnetic or optical disks, etc. The storage medium may further include a non-volatile memory (non-volatile) or a non-transitory memory (non-transient), and the like.

The processor may be a Central Processing Unit (CPU), or may be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

It is noted that the controller may also include memory, which may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read-only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. Volatile memory can be Random Access Memory (RAM) which acts as external cache memory. By way of example and not limitation, many forms of Random Access Memory (RAM) are available, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double data rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and Direct rambus RAM (DR RAM).

The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. The procedures or functions according to the embodiments of the present application are wholly or partially generated when the computer instructions or the computer program are loaded or executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire or wirelessly. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more collections of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.

It should be understood that, in the various embodiments of the present application, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

In the several embodiments provided in the present application, it should be understood that the disclosed method, apparatus and system may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative; for example, the division of the unit is only a logic function division, and there may be another division manner in actual implementation; for example, various elements or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be physically included alone, or two or more units may be integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.

The integrated unit implemented in the form of a software functional unit may be stored in a computer-readable storage medium. The software functional unit is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

It should be understood that the term "and/or" herein is merely one type of association relationship that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" in this document indicates that the former and latter related objects are in an "or" relationship.

The "plurality" appearing in the embodiments of the present application means two or more.

The descriptions of the first, second, etc. appearing in the embodiments of the present application are only for the purpose of illustrating and differentiating the description objects, and do not represent any particular limitation to the number of devices in the embodiments of the present application, and cannot constitute any limitation to the embodiments of the present application.

The term "connection" in the embodiment of the present application refers to various connection manners such as direct connection or indirect connection, so as to implement communication between devices, which is not limited in this embodiment of the present application.

Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.

Claims

1. An energy control method of a hybrid micro energy system, the hybrid micro energy system comprising a micro energy collecting module, an energy storage module and a power supply module, the micro energy collecting module is configured to collect at least one type of energy, the energy storage module is configured to store electric energy converted from the energy, and the power supply module is configured to supply power to a load, the method comprising:

identifying characteristic information of each energy collected by the micro-energy collection module;

inputting the characteristic information of each energy and the electric power required by the load into a decision tree model to obtain a decision label of each energy, wherein the decision label is used for indicating the trend of each energy;

controlling the trend of each energy according to the decision tag so as to transmit at least one part of each energy to the power supply module and/or the energy storage module;

wherein the decision tree model is generated by training using a plurality of first energy samples as training data.

2. The method of energy control for a hybrid micro energy system according to claim 1, wherein the characteristic information comprises one or more of: the type of energy and the electrical power to which the energy can be converted.

3. The energy control method of the hybrid micro energy system according to claim 1, wherein the method of obtaining the decision label for each energy further comprises:

and inputting the state of charge of the energy storage module, the characteristic information of each energy and the electric power required by the load into the decision tree model together to obtain a decision label of each energy.

4. The energy control method of the hybrid micro energy system according to claim 1, wherein the method for generating the decision tree model comprises:

acquiring a plurality of first energy samples, wherein each first energy sample comprises electric power required by a load, at least one sample energy and characteristic information thereof and a decision tag;

and taking the plurality of first energy samples as the training data, and training to generate the decision tree model.

5. The energy control method of a hybrid micro energy system according to claim 4, wherein before training the decision tree model using the plurality of first energy samples as the training data, the method further comprises:

determining a range of possible values of electric power required by the load and a range of possible values of the characteristic information for each sample energy;

and screening the plurality of first energy samples according to the characteristic information of each sample energy in each first energy sample and the electric power required by the load corresponding to the first energy sample to obtain the first energy sample for generating the decision tree model.

6. The energy control method of the hybrid micro energy system according to claim 1, wherein before inputting the characteristic information of each energy and the electric power required by the load to the decision tree model, the method further comprises:

obtaining a plurality of second energy samples, wherein each second energy sample comprises electric power required by the load, at least one sample energy and characteristic information thereof and a preset decision label, and the plurality of second energy samples and the plurality of first energy samples are independent from each other;

inputting the characteristic information of the electric power required by the load and the energy of each sample in each second energy sample into the decision tree model to obtain a model decision label of the energy of each sample in the second energy sample;

comparing the model decision label of each sample energy in each second energy sample with the preset decision label, calculating the proportion of the number of second energy samples with the model decision label of each sample energy consistent with the preset decision label to the number of all second energy samples, and if the proportion is smaller than a first preset threshold value, performing pruning processing on the decision tree model to update the decision tree model.

7. The method of energy control for a hybrid micro energy system according to claim 1, wherein said energy storage module comprises a plurality of energy storage elements, said energy storage module further configured to supply power to said load, said method further comprising:

acquiring the charge states of a plurality of energy storage elements;

obtaining the power supply proportion of the energy storage elements by adopting a fuzzy control algorithm according to the electric power required to be provided by the energy storage module and the charge states of the energy storage elements, wherein the electric power required to be provided by the energy storage module is the difference value of the electric power required by the load and the energy convertible electric power of the micro-energy collection module;

and determining the output electric power of each energy storage element according to the power supply proportion and the electric power to be provided by the energy storage module.

8. The method according to claim 7, wherein the plurality of energy storage elements comprise super capacitors.

9. The energy control method of the hybrid micro energy system according to claim 7, wherein obtaining the power supply ratio of the plurality of energy storage elements by using a fuzzy control algorithm according to the electric power to be supplied by the energy storage module and the states of charge of the plurality of energy storage elements comprises:

determining a power range to which the electric power required to be provided by the energy storage module belongs according to the electric power required to be provided by the energy storage module, and determining a charge range to which the charge state of each energy storage element belongs according to the charge state of each energy storage element;

inquiring a fuzzy control rule table according to the power range and the charge range of each energy storage element to determine the power supply proportion range of each energy storage element;

defuzzification is carried out on the power supply proportion range of each energy storage element so as to obtain the power supply proportion of each energy storage element;

the fuzzy control rule table is used for describing the mapping relation between the power range and the charge range and the power supply proportion range.

10. The method of energy control of a hybrid micro energy source system of claim 1, wherein said micro energy harvesting module comprises a plurality of micro energy harvesters, the method further comprising:

acquiring first feedback information, wherein the first feedback information is used for indicating whether the micro energy collector is replaced or not;

judging whether the micro energy collectors are replaced or not according to the first feedback information, and if so, acquiring the energy convertible electric power of each replaced micro energy collector;

and comparing the energy convertible electric power of each replaced micro-energy collector with a second preset threshold, and if the energy convertible electric power of any replaced micro-energy collector does not exceed the second preset threshold, retraining to generate the decision tree model.

11. The method of energy control of a hybrid micro energy system of claim 1, wherein said energy storage module comprises a plurality of energy storage elements, said method further comprising:

acquiring second feedback information, wherein the second feedback information is used for indicating whether the energy storage element is replaced or not;

judging whether the energy storage elements are replaced or not according to the second feedback information, and if so, acquiring the charge state of each replaced energy storage element;

comparing the upper limit of the state of charge of each replaced energy storage element with a third preset threshold;

and if the upper limit of the state of charge of any replaced energy storage element does not exceed the third preset threshold, retraining to generate the decision tree model.

12. An energy control device of a hybrid micro energy system, the hybrid micro energy system comprising a micro energy collecting module, an energy storage module and a power supply module, the micro energy collecting module is configured to collect at least one type of energy, the energy storage module is configured to store electric energy converted from the energy, and the power supply module is configured to supply power to a load, the device comprising:

the identification module is used for identifying the characteristic information of each energy collected by the micro-energy collection module;

the classification module is used for inputting the characteristic information of each energy and the electric power required by the load into a decision tree model to obtain a decision label of each energy, and the decision label is used for indicating the trend of each energy;

the transmission control module is used for controlling the trend of each energy according to the decision tag so as to transmit at least one part of each energy to the power supply module and/or the energy storage module;

13. A storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, performs the steps of the energy control method of the hybrid micro energy system of any one of claims 1 to 11.

14. A composite micro energy system, the system comprising:

the micro-energy collection module is used for collecting at least one type of energy;

the energy storage module is used for storing the electric energy after the energy conversion;

the power supply module is used for supplying power to a load;

a controller for performing the steps of the energy control method of the hybrid micro energy system of any one of claims 1 to 11.