CN113386611B

CN113386611B - Charging and discharging control method and device, computer equipment and storage medium

Info

Publication number: CN113386611B
Application number: CN202110690162.2A
Authority: CN
Inventors: 吴昊文; 罗洪江; 王翀; 周雨迪
Original assignee: Southern Power Grid Digital Grid Research Institute Co Ltd
Current assignee: China Southern Power Grid Digital Grid Technology Guangdong Co ltd
Priority date: 2021-06-22
Filing date: 2021-06-22
Publication date: 2023-01-20
Anticipated expiration: 2041-06-22
Also published as: CN113386611A

Abstract

The application relates to a charging and discharging control method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring battery charging and discharging information and vehicle driving travel information of a target vehicle; determining the charging and discharging probability of the target vehicle in a target time period according to the battery charging and discharging information and the vehicle driving travel information; acquiring the weather condition of the area where the charging pile is located and the energy supply and demand condition of the charging pile in the target time period, and performing fuzzy inference processing based on the weather condition, the energy supply and demand condition and the charging and discharging probability to obtain a fuzzy inference result; the fuzzy inference result comprises a target charging and discharging scheduling strategy in the target time period; and executing a vehicle charging and discharging control command corresponding to the target charging and discharging scheduling strategy. By adopting the method, the charging and discharging scheduling accuracy of the electric automobile can be improved.

Description

Charging and discharging control method and device, computer equipment and storage medium

Technical Field

The application relates to the technical field of new energy automobiles, in particular to a charge and discharge control method and device, computer equipment and a storage medium.

Background

Along with the increase of the number of electric automobiles, in some districts with higher utilization rate of the electric automobiles, if the charging time of users is concentrated, the problems of transformer overload, peak-valley difference increase and the like can occur, and the safe operation of a power distribution network is not facilitated. Therefore, the electric automobile needs to be orderly charged and participate in reverse power supply, so that a user can participate in charge and discharge scheduling according to requirements.

With the increase of the number of the electric automobiles, the problems of difficult charging, serious line loss, voltage reduction, peak-to-peak and the like of the electric automobiles can occur. The influence of various factors such as weather, energy supply and demand conditions, user habits and the like on the charging and discharging scheduling of the electric automobile is not considered in the existing method.

Therefore, the problem that the charging and discharging scheduling accuracy of the electric automobile is not high exists in the related technology.

Disclosure of Invention

In view of the above, it is necessary to provide a charging and discharging control method, device, computer device and storage medium capable of improving the accuracy of the charging and discharging schedule of the electric vehicle.

A charging and discharging control method of a charging pile is applied to the charging pile and comprises the following steps:

acquiring battery charging and discharging information and vehicle driving travel information of a target vehicle;

determining the charging and discharging probability of the target vehicle in a target time period according to the battery charging and discharging information and the vehicle driving travel information;

acquiring the weather condition of the area where the charging pile is located and the energy supply and demand condition of the charging pile in the target time period, and performing fuzzy inference processing based on the weather condition, the energy supply and demand condition and the charging and discharging probability to obtain a fuzzy inference result; the fuzzy inference result comprises a target charging and discharging scheduling strategy in the target time period;

and executing a vehicle charging and discharging control command corresponding to the target charging and discharging scheduling strategy.

In one embodiment, the determining the charging and discharging probability of the target vehicle in the target time period according to the battery charging and discharging information and the vehicle driving journey information includes:

inputting the battery charging and discharging information and the vehicle driving travel information into a charging and discharging probability prediction network to obtain the charging and discharging probability of the target vehicle in a target time period;

the charging and discharging probability prediction network is used for extracting battery charging and discharging characteristics in the battery charging and discharging information and the vehicle driving travel information and determining the charging and discharging probability of the target vehicle in the target time period according to the battery charging and discharging characteristics.

In one embodiment, the charging and discharging probability prediction network includes an input layer, a time cycle neural network node layer, a full connection layer, and an activation function layer, and the inputting the battery charging and discharging information and the vehicle driving travel information into the charging and discharging probability prediction network to obtain the charging and discharging probability of the target vehicle in the target time period includes:

receiving, through the input layer, the battery charge-discharge information and the vehicle driving travel information divided at a plurality of time steps;

performing feature extraction processing on the battery charging and discharging information and the vehicle driving travel information through the time cycle neural network node layer to generate charging and discharging feature vectors; the charge and discharge characteristic vector is used for representing the charge and discharge characteristics of the battery;

classifying the charge and discharge characteristic vectors through the full connection layer to obtain a characteristic classification result;

mapping, by the activation function layer, the feature classification result to a charging probability and a discharging probability of the target vehicle within the target time period.

In one embodiment, the performing fuzzy inference processing based on the weather condition, the energy supply and demand condition, and the charging and discharging probability to obtain a fuzzy inference result includes:

calculating the membership degree of the weather condition and each weather fuzzy evaluation grade through a preset weather condition membership function to obtain the weather membership degree;

calculating the membership degree of the energy supply and demand condition and each energy supply and demand fuzzy evaluation grade through a preset energy supply and demand condition membership function to obtain the energy supply and demand membership degree;

calculating the charge and discharge probability and the membership degree of each charge and discharge fuzzy evaluation grade through a preset charge and discharge membership function to obtain the charge and discharge membership degree;

and performing combined reasoning on the weather membership, the energy supply and demand membership and the charge and discharge membership by adopting a preset fuzzy reasoning rule to obtain the target charge and discharge scheduling strategy.

In one embodiment, the performing combined inference on the weather membership, the energy supply and demand membership, and the charge and discharge membership by using a preset fuzzy inference rule to obtain the target charge and discharge scheduling policy includes:

inputting the weather membership, the energy supply and demand membership and the charge and discharge membership into a fuzzy inference model; the fuzzy inference model is used for carrying out combined inference on the weather membership, the energy supply and demand membership and the charge and discharge membership to obtain a combined inference result; the combined reasoning system is also used for performing defuzzification operation on the combined reasoning result to obtain a fuzzy reasoning accurate value;

taking the charge-discharge scheduling strategy corresponding to the numerical range of the fuzzy inference accurate value as the target charge-discharge scheduling strategy; the charge-discharge scheduling decision comprises at least one of waiting for charge, urgently needing charge, waiting for discharge and urgently needing discharge.

In one embodiment, the acquiring the weather condition of the area where the charging pile is located and the energy supply and demand condition of the charging pile in the target time period includes:

acquiring the total energy supply quantity and the total power demand quantity of the charging pile in the target time period;

determining an energy supply and demand condition of the charging post over the target time period based on a difference between the total energy supply and the total power demand.

In one embodiment, the obtaining the total energy supply amount and the total power demand amount of the charging pile in the target time period comprises:

acquiring the available energy state of the target vehicle in the target time period, and acquiring a target charging level and a target discharging level of the target vehicle;

determining the total energy supply of the charging pile in the target time period according to the difference between the available energy state and the target discharge level;

determining a total power demand of the charging post over the target time period based on a difference between the target charge level and the available energy state.

A charge and discharge control apparatus for a charging pile, the apparatus comprising:

the acquisition module is used for acquiring battery charging and discharging information and vehicle driving travel information of a target vehicle;

the determining module is used for determining the charging and discharging probability of the target vehicle in a target time interval according to the battery charging and discharging information and the vehicle driving travel information;

the decision module is used for acquiring the weather condition of the area where the charging pile is located and the energy supply and demand condition of the charging pile in the target time period, and performing fuzzy inference processing on the charging and discharging scheduling strategy of the charging pile based on the weather condition, the energy supply and demand condition and the charging and discharging probability to obtain a fuzzy inference result; the fuzzy inference result comprises a target charging and discharging scheduling strategy in the target time period;

and the execution module is used for executing the vehicle charging and discharging control instruction corresponding to the target charging and discharging scheduling strategy.

A computer device comprising a memory storing a computer program and a processor implementing the steps of the method described above when executing the computer program.

A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method.

According to the charge and discharge control method, the charge and discharge control device, the computer equipment and the storage medium, the battery charge and discharge information and the vehicle driving travel information of the target vehicle are obtained; determining the charging and discharging probability of the target vehicle in the target time period according to the charging and discharging information of the battery and the driving travel information of the vehicle; acquiring the weather condition of the area where the charging pile is located and the energy supply and demand condition of the charging pile in a target time period, and performing fuzzy reasoning processing based on the weather condition, the energy supply and demand condition and the charging and discharging probability to obtain a target charging and discharging scheduling strategy in the target time period so as to execute a vehicle charging and discharging control instruction corresponding to the target charging and discharging scheduling strategy; therefore, on the premise of predicting the charging and discharging probability of the target vehicle in advance based on the battery charging and discharging information and the vehicle driving travel information, the energy supply and demand condition of the charging pile and the weather condition of the area where the charging pile is located are used as decision factors for determining the charging and discharging scheduling of the target vehicle by adopting the fuzzy reasoning technology, so that the weather condition and the energy supply and demand condition are integrated into the scheduling problem of the electric vehicle by adopting the fuzzy reasoning technology, more accurate and scientific charging and discharging scheduling control of the electric vehicle can be generated, the energy supply and demand balance of the electric vehicle during discharging is improved, and the feasibility and the effectiveness of large-scale application of the scheduling method are also improved.

Drawings

FIG. 1 is a diagram illustrating an exemplary embodiment of a charging/discharging control method;

fig. 2 is a schematic flow chart of a charging and discharging control method in one embodiment;

FIG. 3 is a diagram illustrating a membership function for charging and discharging probability according to an embodiment;

FIG. 4 is a diagram of a weather condition membership function in one embodiment;

FIG. 5 is a diagram illustrating membership functions for total energy supply and demand conditions of charging piles in accordance with an exemplary embodiment;

FIG. 6 is a diagram of decision output membership functions in one embodiment;

FIG. 7 is a block diagram of a charging and discharging probability prediction network in accordance with an embodiment;

FIG. 8 is a schematic flow chart illustrating a charging/discharging control method according to another embodiment;

fig. 9 is a block diagram showing a structure of a charge and discharge control apparatus according to an embodiment;

fig. 10 is an internal structural diagram of a computer device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.

The charge and discharge control method provided by the application can be applied to the application environment shown in fig. 1. In practice, the computer device 110 may be, but is not limited to, various personal computers, laptops, smart phones, tablets, and portable wearable devices.

In one embodiment, as shown in fig. 2, a charging and discharging control method is provided, which is described by taking the example that the method is applied to the computer device in fig. 1, and includes the following steps:

and step S210, acquiring the battery charging and discharging information and the vehicle driving travel information of the target vehicle.

Here, the target vehicle may refer to a vehicle having a charge and discharge function. In practical applications, the target vehicle may be an electric vehicle.

The battery charging/discharging information may refer to information such as a battery remaining capacity, a charging frequency, and a discharging frequency of the target vehicle.

The vehicle driving trip information may refer to a departure time and a return time of the target vehicle, among others.

In the concrete realization, when target vehicle is close to fill electric pile or with fill electric pile electricity and be connected, computer equipment can be used for the driving characteristic of sign target vehicle, user's the battery charge-discharge information and the vehicle driving stroke information of using the car custom through setting up the induction system collection that fills on electric pile.

And step S220, determining the charging and discharging probability of the target vehicle in the target time period according to the battery charging and discharging information and the vehicle driving travel information.

The charging and discharging probability may include a charging probability and a discharging probability.

In specific implementation, after the computer device obtains the battery charging and discharging information and the vehicle driving travel information of the target vehicle, the computer device may perform normalization processing on the battery charging and discharging information and the vehicle driving travel information to obtain a normalized target feature vector. Then, the normalized target feature vector is input to a pre-trained charge and discharge probability prediction network (such as a pre-trained LSTM neural network) to output a charge and discharge probability vector for representing the charge and discharge probability of the target vehicle in the target time period.

The pre-trained LSTM neural network can be obtained by acquiring data such as driving characteristics of the electric automobile and vehicle using habits of a user based on the sensing device on the charging pile and training the data as a training sample. Wherein, the training sample can be denoted as EV = { EV = { EV ₁ ,EV ₂ ,···,EV _i ,···,EV _N }; wherein N represents the number of training samples, EV _i And the related data of the ith electric automobile in the training sample are represented, and the data comprises: EV (electric vehicle) _i ＝{x _i,1 ,x _i,2 ···,x _i,j ,···,x _i,q Q represents the number of the ith electric vehicle data types in the training sample, x _i,j And representing the value of the jth data type corresponding to the ith electric automobile in the training sample.

Step S230, acquiring weather conditions of an area where the charging pile is located and energy supply and demand conditions of the charging pile in a target time period, and performing fuzzy inference processing based on the weather conditions, the energy supply and demand conditions and the charging and discharging probability to obtain a fuzzy inference result;

and the fuzzy inference result comprises a target charging and discharging scheduling strategy in a target time period.

In the specific implementation, the computer device can select the energy supply and demand condition of the charging pile and the weather condition of the area where the charging pile is located as two decision factors, and the two decision factors and the existing charging and discharging probability distribution are used as the input of the electric vehicle charging and discharging problem model decision layer. Specifically, the computer device can acquire the weather conditions of the area where the charging pile is located, that is, the computer device can evaluate the influence degree of the weather conditions of the area where the charging pile is located, so as to obtain the influence degree P of the weather conditions of the area where the charging pile is located on the charging and discharging scheduling of the electric automobile _w . In practical application, the influence degree P of the weather condition of the charging pile area on the charging and discharging scheduling of the electric automobile _w Can be expressed as:

wherein, P _e The influence degree of the energy supply and demand condition of the charging pile on the charging and discharging scheduling of the electric automobile is represented; v. of _i Representing the weight corresponding to the ith factor, wherein the value range is 0-1; a. The _i The value of the ith influencing factor normalization processing is represented, and the value range is 0-1.

Meanwhile, the computer equipment can acquire the energy supply and demand conditions of the charging pile in a target time period, namely the computer equipment can evaluate the influence degree of the energy supply and demand conditions of the charging pile to obtain the influence degree P of the energy supply and demand conditions of the charging pile on the charging and discharging scheduling of the electric automobile _e . In practical application, the influence degree of the energy supply and demand condition of the charging pile on the charging and discharging scheduling of the electric automobile can be expressed as follows:

wherein, P _e The influence degree of the energy supply and demand conditions of the charging pile on the charging and discharging dispatching of the electric automobile is represented; v. of _i The weight corresponding to the ith factor is represented, and the value range is 0-1; a. The _i The value of the ith influence factor normalization processing is represented, and the value range is 0-1.

And then, the computer equipment performs fuzzy inference processing based on the weather condition, the energy supply and demand condition and the charging and discharging probability to obtain a fuzzy inference result comprising a target charging and discharging scheduling strategy in a target time period. Specifically, the computer device can input the characteristics representing the weather conditions, the energy supply and demand conditions and the charging and discharging probability into the fuzzy inference model, and perform fuzzy inference processing on the input quantity through the fuzzy inference model according to a preset fuzzy inference rule to obtain a fuzzy inference result including a target charging and discharging scheduling strategy in a target time period.

Specifically, the input quantity is fuzzified, the domain of discourse is U, the value range is uniform, the charging probability and the discharging probability are fuzzified into three fuzzy sets of positive small (PL), positive Middle (PM) and positive large (PH), and a triangular membership function is adopted, as shown in fig. 3. The weather conditions are blurred into two blur sets, good (PG) and bad (PB), respectively, as shown in fig. 4. The difference between the total energy supply status of the charging pile and the total power demand condition is fuzzy into two fuzzy sets, namely positive (PP) and negative (PM), as shown in fig. 5.

The output domain of the decision layer is also U, and the value range is blurred into 4 fuzzy sets, namely a discharging second Priority (PN), a discharging first Priority (PL), a charging second Priority (PM) and a charging first Priority (PH), and a triangular membership function is adopted, as shown in fig. 6.

The computer equipment adopts a Mamdani method (a fuzzy inference algorithm) and determines a fuzzy control rule according to the relation between actual input variables and the relation between the input variables and the output variables according to the establishment method of the fuzzy inference rule. Table 1 lists exemplary 5 fuzzy inference rules of which importance is based on the requirements of the actual detection system.

TABLE 1

If the charging probability fuzzy level is "PL", the discharging probability fuzzy level is also "PL", the weather condition fuzzy level is "PG", and the charging pile energy supply and demand condition fuzzy level is "PP", the decision output fuzzy level is "PM". I.e. when weather conditions are good and the energy supply of the charging post is greater than required, the decision "charge second priority (wait for charge)" needs to be issued even if the charging and discharging probabilities are low. Because the weather is good, the probability of using the electric vehicle is increased, and the energy supply is sufficient at this time, and therefore, the decision of "charge second priority (waiting for charging)" is finally issued.

If the charging probability fuzzy level is 'PM', the discharging probability fuzzy level is 'PL', the weather condition fuzzy level is 'PG', and the charging pile energy supply and demand condition fuzzy level is 'PP', the decision output fuzzy level is 'PH'. The rule is similar to the previous rule, but the fuzzy level of the charging probability detected by the rule is "PM", that is, the middle indicates that the electric vehicle has a charging requirement and needs to be charged, so that the decision of "charging first priority (urgent need to be charged)" is finally issued.

And if the charging probability fuzzy level is 'PH', the discharging probability fuzzy level is 'PL', the weather condition fuzzy level is 'PG' and the charging pile energy supply and demand condition fuzzy level is 'PP', the decision output fuzzy level is 'PH'. The rule is a successor of the last rule, the charging probability fuzzy level is already developed to be "PH", namely, is positive, which indicates that the electric vehicle is in urgent need of charging, and therefore, a decision of "charging first priority (urgent need of charging)" is finally issued.

If the charging probability fuzzy level is 'PL', the discharging probability fuzzy level is 'PL', the weather condition fuzzy level is 'PB', and the charging pile energy supply and demand condition fuzzy level is 'PM', the output fuzzy level is determined to be 'PN'. Due to bad weather conditions, the energy supply of the charging pile is smaller than the requirement, and the fuzzy levels of the charging probability and the discharging probability are both positive and small, so that a decision of discharging second priority (waiting for discharging) is output.

If the charging probability fuzzy level is "PL", the discharging probability fuzzy level is "PM", the weather condition fuzzy level is "PG", and the charging pile energy supply and demand condition fuzzy level is "PM", the output fuzzy level is determined to be "PL". When the discharge probability fuzzy grade is 'positive', it can be shown that the electric automobile needs to discharge, and at the moment, the energy supply of the charging pile is smaller than the demand, and even if the weather condition is better, in order to balance the supply and demand, a 'first priority (urgent discharge)' decision is sent out.

In step S240, a vehicle charge/discharge control command corresponding to the target charge/discharge scheduling policy is executed.

In the specific implementation, after the computer device determines the target charge and discharge scheduling policy within the target time period, the computer device may execute a vehicle charge and discharge control instruction corresponding to the target charge and discharge scheduling policy, so as to implement charge and discharge control on the target vehicle.

In the charge and discharge control method, the charge and discharge information of the battery of the target vehicle and the driving travel information of the vehicle are acquired; determining the charging and discharging probability of the target vehicle in the target time period according to the charging and discharging information of the battery and the driving travel information of the vehicle; acquiring the weather condition of the area where the charging pile is located and the energy supply and demand condition of the charging pile in a target time period, and performing fuzzy reasoning processing based on the weather condition, the energy supply and demand condition and the charging and discharging probability to obtain a target charging and discharging scheduling strategy in the target time period so as to execute a vehicle charging and discharging control instruction corresponding to the target charging and discharging scheduling strategy; therefore, on the premise of predicting the charging and discharging probability of the target vehicle in advance based on the battery charging and discharging information and the vehicle driving travel information, the energy supply and demand condition of the charging pile and the weather condition of the area where the charging pile is located are used as decision factors for determining the charging and discharging scheduling of the target vehicle by adopting the fuzzy reasoning technology, so that the weather condition and the energy supply and demand condition are integrated into the scheduling problem of the electric vehicle by adopting the fuzzy reasoning technology, more accurate and scientific charging and discharging scheduling control of the electric vehicle can be generated, the energy supply and demand balance of the electric vehicle during discharging is improved, and the feasibility and the effectiveness of large-scale application of the scheduling method are also improved.

In another embodiment, determining the charging and discharging probability of the target vehicle in the target time period according to the battery charging and discharging information and the vehicle driving travel information comprises: inputting the battery charging and discharging information and the vehicle driving travel information into a charging and discharging probability prediction network to obtain the charging and discharging probability of the target vehicle in a target time period; the charging and discharging probability prediction network is used for extracting battery charging and discharging characteristics in the battery charging and discharging information and the vehicle driving travel information, and determining the charging and discharging probability of the target vehicle in the target time period according to the battery charging and discharging characteristics.

The battery charging and discharging information comprises at least one of battery residual capacity, battery charging frequency and battery discharging frequency.

The vehicle driving travel information comprises at least one of the time when the target vehicle leaves the charging pile and the time when the target vehicle leaves the charging pile.

In specific implementation, in the process that the computer device determines the charging and discharging probability of the target vehicle in the target time period according to the battery charging and discharging information and the vehicle driving travel information, the computer device can input the battery charging and discharging information and the vehicle driving travel information into the charging and discharging probability prediction network to obtain the charging and discharging probability of the target vehicle in the target time period.

For example, the information of the electric vehicle contained in the data set includes the remaining battery capacity, the charging frequency, the discharging frequency, the leaving time and the returning time, data of a plurality of time steps are set as the input of the LSTM network, each group of data is a vector and is expressed as

Wherein the content of the first and second substances,

respectively corresponding to the battery residual capacity, the charging frequency, the discharging frequency, the leaving time and the returning time of one electric automobile after normalization processing.

According to the technical scheme of the embodiment, the charging and discharging probability of the target vehicle in the target time period is quickly determined by inputting the charging and discharging information of the battery and the driving travel information of the vehicle into the charging and discharging probability prediction network.

In another embodiment, inputting the battery charging and discharging information and the vehicle driving travel information into a charging and discharging probability prediction network to obtain the charging and discharging probability of the target vehicle in a target time period includes: receiving battery charge-discharge information and vehicle driving travel information which are obtained by dividing at a plurality of time steps through an input layer; performing feature extraction processing on battery charge and discharge information and vehicle driving travel information through a time cycle neural network node layer to generate charge and discharge feature vectors; the charge and discharge characteristic vector is used for representing the charge and discharge characteristics of the battery; classifying the charge and discharge characteristic vectors through a full connection layer to obtain a characteristic classification result; and mapping the characteristic classification result into a charging probability and a discharging probability of the target vehicle in a target time period by activating the function layer.

The charge and discharge probability prediction network comprises an input layer, a time cycle neural network node layer (such as an LSTM layer), a full connection layer (such as a Dense layer) and an activation function layer (such as a Softmax layer). To facilitate understanding by those skilled in the art, fig. 7 exemplarily provides a block diagram of a charging and discharging probability prediction network.

The charge and discharge probability prediction network may be a pre-trained LSTM neural network. Wherein, the LSTM neural network comprises four layers: the first layer is an input layer, and time series data M are input; the second layer is an LSTM layer, and the number of the neurons is a; the third layer is a Dense layer, and the output classification length is n; the fourth layer is a Softmax layer, and in practical application, the activation function layer can be expressed as:

wherein z is _j Represents the output of the fully connected layer and n represents the classification number.

Error back propagation and updating of LSTM neural network parameters are performed using the following equations:

h _t ＝tanh(Wh _t-1 +Ux _t )；

wherein, the network loss function of the t-th time sequence is represented, U is the network sharing parameter of the input layer, and W is the network sharing parameter of the hidden layer.

The computer equipment can receive battery charging and discharging information and vehicle driving travel information which are obtained by dividing at a plurality of time steps through an input layer; then, the computer equipment can perform feature extraction processing on the battery charging and discharging information and the vehicle driving travel information through a time cycle neural network node layer to generate charging and discharging feature vectors; the charge and discharge characteristic vector is used for representing the charge and discharge characteristics of the battery; then, the computer equipment can classify the charge and discharge characteristic vectors through the full connection layer to obtain a characteristic classification result; and mapping the characteristic classification result into a charging probability and a discharging probability of the target vehicle in a target time period by activating the function layer. For example, the computer device may input the extracted charging and discharging-related characteristics into the full connection layer for classification after passing the electric vehicle-related data through the LSTM network, and then output the corresponding charging and discharging probabilities of the electric vehicle through the Softmax function.

According to the technical scheme of the embodiment, battery charging and discharging information and vehicle driving travel information which are obtained by dividing a plurality of time steps are received through an input layer; performing feature extraction processing on battery charge and discharge information and vehicle driving travel information through a time cycle neural network node layer to generate charge and discharge feature vectors; the charge and discharge characteristic vector is used for representing the charge and discharge characteristics of the battery; through the full connection layer, the charging and discharging characteristic vectors are rapidly classified to obtain a characteristic classification result; by activating the function layer, the feature classification result is accurately mapped to the charging probability and the discharging probability of the target vehicle in the target time period.

In another embodiment, the fuzzy inference processing is performed based on weather conditions, energy supply and demand conditions and charging and discharging probabilities to obtain a fuzzy inference result, and the fuzzy inference result comprises: calculating the membership degree of the weather condition and each weather fuzzy evaluation grade through a preset weather condition membership function to obtain the weather membership degree; calculating the membership degree of the energy supply and demand condition and each energy supply and demand fuzzy evaluation grade through a preset energy supply and demand condition membership function to obtain the energy supply and demand membership degree; calculating the charge and discharge probability and the membership degree of each charge and discharge fuzzy evaluation grade through a preset charge and discharge membership function to obtain the charge and discharge membership degree; and performing combined reasoning on the weather membership, the energy supply and demand membership and the charge and discharge membership by adopting a preset fuzzy reasoning rule to obtain a target charge and discharge scheduling strategy.

The weather fuzziness evaluation level may include, among others, good weather (PG) and bad weather (PB).

The fuzzy evaluation level of energy supply and demand can comprise positive (PP) and negative (PM).

The charge and discharge blur evaluation level may include positive small (PL), positive Middle (PM), and positive large (PH).

In specific implementation, the computer device performs fuzzy inference processing based on weather conditions, energy supply and demand conditions and charging and discharging probabilities to obtain a fuzzy inference result, and the fuzzy inference result comprises the following steps: the computer equipment can calculate the membership degree of the weather condition and each weather fuzzy evaluation grade through a preset weather condition membership function to obtain the weather membership degree; calculating the membership degree of the energy supply and demand condition and each energy supply and demand fuzzy evaluation grade through a preset energy supply and demand condition membership function to obtain the energy supply and demand membership degree; calculating the charge and discharge probability and the membership degree of each charge and discharge fuzzy evaluation grade through a preset charge and discharge membership function to obtain the charge and discharge membership degree; and performing combined reasoning on the weather membership, the energy supply and demand membership and the charge and discharge membership by adopting a preset fuzzy reasoning rule to obtain a target charge and discharge scheduling strategy.

According to the technical scheme, the energy supply and demand condition of the charging pile and the weather condition of the area where the charging pile is located are used as decision factors for determining the charging and discharging scheduling of the target vehicle by adopting the fuzzy reasoning technology, so that the weather condition and the energy supply and demand condition are integrated into the scheduling problem of the electric vehicle by adopting the fuzzy reasoning technology, more accurate and scientific charging and discharging scheduling control of the electric vehicle can be generated, the energy supply and demand balance of the electric vehicle during discharging is improved, and the feasibility and effectiveness of large-scale application of the scheduling method are also improved.

In another embodiment, a preset fuzzy inference rule is adopted to perform combined inference on the weather membership, the energy supply and demand membership and the charging and discharging membership to obtain a target charging and discharging scheduling strategy, which includes: inputting the weather membership, the energy supply and demand membership and the charge and discharge membership into a fuzzy inference model; the fuzzy inference model is used for carrying out combined inference on the weather membership, the energy supply and demand membership and the charge and discharge membership to obtain a combined inference result; the fuzzy inference engine is also used for performing defuzzification operation on the combined inference result to obtain a fuzzy inference accurate value; taking the charge-discharge scheduling strategy corresponding to the numerical range of the fuzzy inference accurate value as a target charge-discharge scheduling strategy; the charge and discharge scheduling decision comprises at least one of waiting for charge, urgently needing charge, waiting for discharge and urgently needing discharge.

In the specific implementation, the computer device can input the weather membership, the energy supply and demand membership and the charge and discharge membership to the fuzzy inference model in the process of obtaining the target charge and discharge scheduling strategy by performing combined inference on the weather membership, the energy supply and demand membership and the charge and discharge membership by adopting a preset fuzzy inference rule. Performing combined reasoning on the weather membership, the energy supply and demand membership and the charge and discharge membership through the fuzzy reasoning model to obtain a combined reasoning result; the fuzzy inference method is also used for carrying out defuzzification operation on the combined inference result to obtain a fuzzy inference accurate value; taking the charge-discharge scheduling strategy corresponding to the numerical range of the fuzzy inference accurate value as a target charge-discharge scheduling strategy; the charge and discharge scheduling decision comprises at least one of waiting for charge, charging urgently needed, waiting for discharge and discharging urgently needed.

For example, the blurring result obtained is deblurred, and the center of gravity method is adopted as the deblurring method. After obtaining the accurate value subjected to the defuzzification operation, judging the result of which the output value is less than 0.25 as a discharging second priority (waiting for discharging); the result with the output value between 0.25 and 0.5 is judged as the first priority of discharging (emergency discharging) "; the result with an output value between 0.5 and 0.75 is decided as "charge second priority (wait for charge)"; the result of the output value being greater than 0.75 is decided as "charge first priority (urgent need for charge)".

According to the technical scheme of the embodiment, the weather membership, the energy supply and demand membership and the charge and discharge membership are subjected to combined reasoning to obtain a combined reasoning result, and the combined reasoning result is subjected to defuzzification operation to obtain a fuzzy reasoning accurate value; and taking the charge and discharge scheduling strategy corresponding to the numerical range of the fuzzy inference accurate value as a target charge and discharge scheduling strategy, thereby fully integrating the influence factors such as weather, energy supply and demand, vehicle charge and discharge and the like and accurately determining the charge and discharge scheduling strategy.

In another embodiment, acquiring weather conditions of an area where the charging pile is located and energy supply and demand conditions of the charging pile in a target time period comprises the following steps: acquiring total energy supply quantity and total power demand quantity of a charging pile in a target time period; and determining the energy supply and demand condition of the charging pile in the target time period based on the difference between the total energy supply amount and the total power demand amount.

In the specific implementation, in the process that the computer equipment acquires the weather condition of an area where the charging pile is located and the energy supply and demand condition of the charging pile in a target time period, the computer equipment can acquire the total energy supply quantity and the total power demand quantity of the charging pile in the target time period; finally, the computer device determines the energy supply and demand condition of the charging pile in the target time period based on the difference between the total energy supply amount and the total power demand amount.

According to the technical scheme, the total energy supply quantity and the total power demand quantity of the charging pile in the target time period are obtained, and the energy supply and demand condition of the charging pile in the target time period is accurately determined based on the difference between the total energy supply quantity and the total power demand quantity.

In another embodiment, obtaining the total energy supply and the total power demand of the charging piles within the target time period comprises: acquiring the available energy state of the target vehicle in a target time period, and acquiring a target charging level and a target discharging level of the target vehicle; determining the total energy supply amount of the charging pile in a target time period according to the difference between the available energy state and the target discharge level; and determining the total power demand of the charging pile in the target time period according to the difference between the target charging level and the available energy state.

In the specific implementation, in the process that the computer device obtains the total energy supply amount and the total power demand amount of the charging pile in the target time period, the computer device can obtain the available energy state of the target vehicle in the target time period, and obtain the target charging level and the target discharging level of the target vehicle.

The computer device may then determine a total energy supply of the charging post over the target time period based on a difference between the available energy state and the target discharge level.

In practical application, the total energy supply amount of the charging pile in the target time period can be expressed as follows:

wherein, the first and the second end of the pipe are connected with each other,

representing the total energy supply of the charging post during the t-th time period;

indicating the discharge energy supply of the ith electric vehicle in the t-th period,

which indicates the target level of the discharge,

indicating the available energy state.

Additionally, the computer device may determine a total power demand of the charging post over the target time period based on a difference between the target charge level and the available energy state.

In practical application, the total power demand of the charging pile in the target time period can be expressed as:

wherein the content of the first and second substances,

represents the charging energy demand of the ith electric vehicle in the t period,

indicates the expected target level of charge of the battery,

indicating the available energy state.

According to the technical scheme of the embodiment, the available energy state of the target vehicle in the target time period is obtained, and the target charging level and the target discharging level of the target vehicle are obtained; according to the difference between the available energy state and the target discharge level, the total energy supply amount of the charging pile in the target time period is accurately determined; and according to the difference between the target charging level and the available energy state, accurately determining the total power demand of the charging pile in the target time period.

In another embodiment, as shown in fig. 8, a charging and discharging control method is provided, which is described by taking the method as an example applied to the computer device in fig. 1, and includes the following steps:

step S810, acquiring battery charging and discharging information and vehicle driving travel information of a target vehicle; the battery charging and discharging information comprises at least one of battery residual capacity, battery charging frequency and battery discharging frequency, and the vehicle driving journey information comprises at least one of time when the target vehicle drives away from the charging pile and time when the target vehicle drives to the charging pile.

Step S820, inputting the battery charging and discharging information and the vehicle driving travel information into a charging and discharging probability prediction network to obtain the charging and discharging probability of the target vehicle in a target time period; the charging and discharging probability prediction network is used for extracting battery charging and discharging characteristics in the battery charging and discharging information and the vehicle driving travel information and determining the charging and discharging probability of the target vehicle in the target time period according to the battery charging and discharging characteristics;

step S830, acquiring the weather condition of the area where the charging pile is located; acquiring the total energy supply quantity and the total power demand quantity of the charging pile in the target time period;

step 840, determining the energy supply and demand condition of the charging pile in the target time period based on the difference between the total energy supply amount and the total power demand amount;

step S850, calculating the membership degree of the weather condition and each weather fuzzy evaluation grade through a preset weather condition membership function to obtain the weather membership degree;

step S860, calculating the membership degree of the energy supply and demand condition and each energy supply and demand fuzzy evaluation grade through a preset energy supply and demand condition membership function to obtain the energy supply and demand membership degree;

step S870, calculating the charge and discharge probability and the membership degree of each charge and discharge fuzzy evaluation grade through a preset charge and discharge membership function to obtain the charge and discharge membership degree;

step S880, performing combined inference on the weather membership degree, the energy supply and demand membership degree and the charge and discharge membership degree by adopting a preset fuzzy inference rule to obtain a target charge and discharge scheduling strategy;

and step S890, executing a vehicle charging and discharging control command corresponding to the target charging and discharging scheduling strategy.

For the specific limitations of the above steps, reference may be made to the above specific limitations of a charge and discharge control method.

It should be understood that although the steps in the flowcharts of fig. 2 and 8 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not limited to being performed in the exact order illustrated and, unless explicitly stated herein, may be performed in other orders. Moreover, at least a portion of the steps in fig. 2 and 8 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a portion of the steps or stages in other steps.

In one embodiment, as shown in fig. 9, there is provided a charge and discharge control device including:

an obtaining module 910, configured to obtain battery charging and discharging information of a target vehicle and vehicle driving route information;

the determining module 920 is configured to determine, according to the battery charging and discharging information and the vehicle driving route information, a charging and discharging probability of the target vehicle within a target time period;

a decision module 930, configured to obtain a weather condition of an area where the charging pile is located and an energy supply and demand condition of the charging pile in the target time period, and perform fuzzy inference processing on a charging and discharging scheduling policy of the charging pile based on the weather condition, the energy supply and demand condition, and the charging and discharging probability to obtain a fuzzy inference result; the fuzzy inference result comprises a target charging and discharging scheduling strategy in the target time period;

and an executing module 940, configured to execute the vehicle charging and discharging control instruction corresponding to the target charging and discharging scheduling policy.

In one embodiment, the battery charging and discharging information includes at least one of a battery remaining capacity, a battery charging frequency, and a battery discharging frequency, the vehicle driving trip information includes at least one of a time when the target vehicle drives away from the charging pile and a time when the target vehicle drives to the charging pile, and the determining module 920 is specifically configured to input the battery charging and discharging information and the vehicle driving trip information into a charging and discharging probability prediction network to obtain a charging and discharging probability of the target vehicle in a target time period; the charging and discharging probability prediction network is used for extracting battery charging and discharging characteristics in the battery charging and discharging information and the vehicle driving travel information and determining the charging and discharging probability of the target vehicle in the target time period according to the battery charging and discharging characteristics.

In one embodiment, the charge and discharge probability prediction network includes an input layer, a time-cycle neural network node layer, a full connection layer, and an activation function layer, and the determining module 920 is specifically configured to receive, through the input layer, the battery charge and discharge information and the vehicle driving route information which are obtained by dividing at a plurality of time steps; performing feature extraction processing on the battery charge and discharge information and the vehicle driving travel information through the time cycle neural network node layer to generate charge and discharge feature vectors; the charge and discharge characteristic vector is used for representing the charge and discharge characteristics of the battery; classifying the charge and discharge characteristic vectors through the full connection layer to obtain a characteristic classification result; mapping, by the activation function layer, the feature classification result to a charging probability and a discharging probability of the target vehicle within the target time period.

In one embodiment, the decision module 930 is specifically configured to calculate membership degrees of the weather conditions and each weather fuzzy evaluation level through a preset weather condition membership function to obtain weather membership degrees; calculating the membership degree of the energy supply and demand condition and each energy supply and demand fuzzy evaluation grade through a preset energy supply and demand condition membership function to obtain the energy supply and demand membership degree; calculating the charge and discharge probability and the membership degree of each charge and discharge fuzzy evaluation grade through a preset charge and discharge membership function to obtain the charge and discharge membership degree; and performing combined reasoning on the weather membership, the energy supply and demand membership and the charge and discharge membership by adopting a preset fuzzy reasoning rule to obtain the target charge and discharge scheduling strategy.

In one embodiment, the decision module 930 is specifically configured to input the weather membership, the energy supply and demand membership, and the charge and discharge membership to a fuzzy inference model; the fuzzy inference model is used for carrying out combined inference on the weather membership degree, the energy supply and demand membership degree and the charge and discharge membership degree to obtain a combined inference result; the combined reasoning system is also used for performing defuzzification operation on the combined reasoning result to obtain a fuzzy reasoning accurate value; taking the charge-discharge scheduling strategy corresponding to the numerical range of the fuzzy inference accurate value as the target charge-discharge scheduling strategy; the charge and discharge scheduling decision comprises at least one of waiting for charge, charging urgently needed, waiting for discharge and discharging urgently needed.

In one embodiment, the decision module 930 is specifically configured to obtain a total energy supply amount and a total power demand amount of the charging pile in the target time period; and determining the energy supply and demand condition of the charging pile in the target time period based on the difference between the total energy supply amount and the total power demand amount.

In one embodiment, the decision module 930 is specifically configured to obtain an available energy state of the target vehicle in the target time period, and obtain a target charging level and a target discharging level of the target vehicle; determining the total energy supply of the charging pile in the target time period according to the difference between the available energy state and the target discharge level; determining a total power demand of the charging post over the target time period based on a difference between the target charge level and the available energy state.

For specific limitations of the charge and discharge control device, reference may be made to the limitations of the charge and discharge control method above, and details are not repeated here. All or part of the modules in the charge and discharge control device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 10. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program to run on the non-volatile storage medium. The database of the computer device is used for storing charge and discharge control data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a charging and discharging control method.

Those skilled in the art will appreciate that the architecture shown in fig. 10 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, the computer program, when executed by the processor, causing the processor to perform the steps of a charging and discharging control method as described above. The steps of a charge and discharge control method herein may be the steps in one of the charge and discharge control methods of the respective embodiments described above.

In one embodiment, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, causes the processor to execute the steps of one of the charge and discharge control methods described above. The steps of a charge and discharge control method herein may be the steps in a charge and discharge control method of the above-described respective embodiments.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is specific and detailed, but not to be understood as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A charge and discharge control method, characterized by comprising:

acquiring the weather condition of an area where the charging pile is located and the energy supply and demand condition of the charging pile in the target time period, and performing fuzzy inference processing based on the weather condition, the energy supply and demand condition and the charging and discharging probability to obtain a fuzzy inference result; the fuzzy inference result comprises a target charging and discharging scheduling strategy in the target time period; calculating the membership degree of the weather condition and each weather fuzzy evaluation grade through a preset weather condition membership function to obtain the weather membership degree; calculating the membership degree of the energy supply and demand condition and each energy supply and demand fuzzy evaluation grade through a preset energy supply and demand condition membership function to obtain the energy supply and demand membership degree; calculating the charge and discharge probability and the membership degree of each charge and discharge fuzzy evaluation grade through a preset charge and discharge membership function to obtain the charge and discharge membership degree; performing combined inference on the weather membership degree, the energy supply and demand membership degree and the charge and discharge membership degree by adopting a preset fuzzy inference rule to obtain the target charge and discharge scheduling strategy;

2. The method of claim 1, wherein the battery charging and discharging information comprises at least one of a battery residual capacity, a battery charging frequency and a battery discharging frequency, the vehicle driving trip information comprises at least one of a time when the target vehicle is driven away from the charging pile and a time when the target vehicle is driven to the charging pile, and the determining the charging and discharging probability of the target vehicle in a target time period according to the battery charging and discharging information and the vehicle driving trip information comprises:

3. The method according to claim 2, wherein the charging and discharging probability prediction network comprises an input layer, a time cycle neural network node layer, a full connection layer and an activation function layer, and the step of inputting the battery charging and discharging information and the vehicle driving travel information into the charging and discharging probability prediction network to obtain the charging and discharging probability of the target vehicle in the target time period comprises the following steps:

4. The method according to claim 1, wherein the combined inference of the weather membership, the energy supply and demand membership, and the charge and discharge membership using a preset fuzzy inference rule to obtain the target charge and discharge scheduling policy comprises:

inputting the weather membership, the energy supply and demand membership and the charge and discharge membership into a fuzzy inference model; the fuzzy inference model is used for carrying out combined inference on the weather membership degree, the energy supply and demand membership degree and the charge and discharge membership degree to obtain a combined inference result; the combined reasoning system is also used for performing defuzzification operation on the combined reasoning result to obtain a fuzzy reasoning accurate value;

taking the charge-discharge scheduling strategy corresponding to the numerical range of the fuzzy inference accurate value as the target charge-discharge scheduling strategy; the charge and discharge scheduling strategy comprises at least one of waiting for charge, charging urgently needed, waiting for discharge and discharging urgently needed.

5. The method of claim 1, wherein the obtaining of the weather conditions of the area where the charging pile is located and the energy supply and demand conditions of the charging pile in the target time period comprises:

and determining the energy supply and demand condition of the charging pile in the target time period based on the difference between the total energy supply amount and the total power demand amount.

6. The method of claim 5, wherein the obtaining the total energy supply and the total power demand of the charging post over the target time period comprises:

7. A charge-discharge control device, characterized by comprising:

the decision module is used for acquiring the weather condition of an area where the charging pile is located and the energy supply and demand condition of the charging pile in the target time period, and performing fuzzy inference processing on the charging and discharging scheduling strategy of the charging pile based on the weather condition, the energy supply and demand condition and the charging and discharging probability to obtain a fuzzy inference result; the fuzzy inference result comprises a target charging and discharging scheduling strategy in the target time period; calculating the membership degree of the weather condition and each weather fuzzy evaluation grade through a preset weather condition membership function to obtain the weather membership degree; calculating the membership degree of the energy supply and demand condition and each energy supply and demand fuzzy evaluation grade through a preset energy supply and demand condition membership function to obtain the energy supply and demand membership degree; calculating the charge and discharge probability and the membership degree of each charge and discharge fuzzy evaluation grade through a preset charge and discharge membership function to obtain the charge and discharge membership degree; adopting a preset fuzzy reasoning rule to carry out combined reasoning on the weather membership degree, the energy supply and demand membership degree and the charge and discharge membership degree to obtain the target charge and discharge scheduling strategy;

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.