CN114995985A - Resource scheduling method, device and storage medium - Google Patents
Resource scheduling method, device and storage medium Download PDFInfo
- Publication number
- CN114995985A CN114995985A CN202210920761.3A CN202210920761A CN114995985A CN 114995985 A CN114995985 A CN 114995985A CN 202210920761 A CN202210920761 A CN 202210920761A CN 114995985 A CN114995985 A CN 114995985A
- Authority
- CN
- China
- Prior art keywords
- time
- data
- uploaded
- resource scheduling
- generation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
Abstract
The embodiment of the invention provides a resource scheduling method, equipment and a storage medium, wherein the method comprises the following steps: and predicting second generation time of the data to be uploaded according to the first generation time of the historical resource scheduling request. And further, determining a resource scheduling strategy meeting the preset time delay requirement according to the second generation time, and issuing the resource scheduling strategy and air interface resources to the terminal equipment. When the terminal device generates the data to be uploaded at the second generation time, the data may be uploaded by using the resource scheduling policy and the air interface resource. In the above process, the determination of the scheduling policy refers to the generation time of the data, so that the scheduling policy can control the uploading time of the data to be uploaded to meet the preset time delay requirement, and the data to be uploaded can be uploaded within a short time after being generated, thereby reducing the air interface time delay of the data to be uploaded.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a resource scheduling method, device, and storage medium.
Background
With the continuous development of the fifth Generation Mobile Communication Technology (5G), the 5G Communication system has been applied to various scenes, such as a live scene, an automatic driving scene, an industrial manufacturing scene, and the like.
In different application scenarios, for data to be uploaded generated by a terminal device, a base station may allocate an air interface resource to the terminal device according to a preset scheduling policy, so that the terminal device may be allocated the air interface resource to implement data uploading. Whether the scheduling policy is appropriate or not can directly influence the timeliness of uploading the data to be uploaded, and the timeliness can also be regarded as air interface delay of the data to be uploaded, namely the time difference between the generation time and the uploading time of the data to be uploaded.
Therefore, how to optimize the scheduling policy to reduce the air interface delay of the data to be uploaded becomes an urgent problem to be solved.
Disclosure of Invention
In view of this, embodiments of the present invention provide a resource scheduling method, a device, and a storage medium, so as to reduce an air interface delay of data to be uploaded.
In a first aspect, an embodiment of the present invention provides a resource scheduling method, including:
predicting second generation time of data to be uploaded according to the first generation time of the historical resource scheduling request;
determining a resource scheduling strategy meeting the requirement of preset time delay according to the second generation time;
and sending the resource scheduling strategy and the air interface resource so that the terminal equipment uploads the data to be uploaded according to the resource scheduling strategy and the air interface resource.
In a second aspect, an embodiment of the present invention provides a resource scheduling method, including:
predicting second generation time of the driving data to be uploaded according to the first generation time of the historical resource scheduling request;
determining a resource scheduling strategy meeting the requirement of preset time delay according to the second generation time;
and sending the resource scheduling strategy and the air interface resource so that the vehicle uploads the driving data to be uploaded according to the resource scheduling strategy and the air interface resource.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a processor and a memory, where the memory is configured to store one or more computer instructions, and when executed by the processor, the one or more computer instructions implement the resource scheduling method in the first aspect or the second aspect. The electronic device may also include a communication interface for communicating with other devices or a communication network.
In a fourth aspect, an embodiment of the present invention provides a non-transitory machine-readable storage medium having stored thereon executable code, which when executed by a processor of an electronic device, causes the processor to implement at least the resource scheduling method according to the first aspect or the second aspect.
In the resource scheduling method provided by the embodiment of the invention, the base station can predict the second generation time of the data to be uploaded according to the first generation time of the historical resource scheduling request. And further, determining a resource scheduling strategy meeting the preset time delay requirement according to the second generation time, and issuing the resource scheduling strategy and air interface resources to the terminal equipment. When the terminal device generates the data to be uploaded in the second generation time, the data can be uploaded by using the resource scheduling policy and the air interface resource. Compared with a fixed and unchangeable resource scheduling strategy, in the process, the scheduling strategy refers to the generation time of the data, so that the scheduling strategy can control the uploading time of the data to be uploaded to meet the preset delay requirement, the data to be uploaded can be uploaded in a short time after being generated, and the air interface delay of the data to be uploaded is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a flowchart of a resource scheduling method according to an embodiment of the present invention;
fig. 2 is a flowchart of another resource scheduling method according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a frame structure according to an embodiment of the present invention;
fig. 4 is a flowchart of another resource scheduling method according to an embodiment of the present invention;
FIG. 5 is a flowchart of a specific implementation manner of step S101 in the embodiment shown in FIG. 1;
FIG. 6 is a periodically generated periodic pattern of data to be uploaded;
fig. 7 is a flowchart of another resource scheduling method according to an embodiment of the present invention;
fig. 8 is a flowchart of another resource scheduling method according to an embodiment of the present invention;
fig. 9 is a schematic diagram of a resource scheduling method applied in an industrial manufacturing scenario according to an embodiment of the present invention;
fig. 10 is a schematic view of a resource scheduling method applied in an automatic driving scenario according to an embodiment of the present invention;
fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;
fig. 12 is a schematic structural diagram of another electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, and "a" and "an" generally include at least two, but do not exclude at least one, unless the context clearly dictates otherwise.
It should be understood that the term "and/or" as used herein is merely one type of association 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 "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
The words "if", as used herein, may be interpreted as "at … …" or "when … …" or "in response to a determination" or "in response to a recognition", depending on the context. Similarly, the phrases "if determined" or "if identified (a stated condition or event)" may be interpreted as "when determined" or "in response to a determination" or "when identified (a stated condition or event)" or "in response to an identification (a stated condition or event)", depending on the context.
It is also noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a good or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such good or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a commodity or system that includes the element.
Before describing the resource scheduling method provided by each embodiment of the present invention in detail, a basic resource scheduling process and a usage scenario of resource scheduling may also be explained first.
As mentioned in the background art, the data to be uploaded generated by the terminal device may be uploaded by the terminal device using the air interface resource allocated by the base station.
Specifically, in the uploading process, after the data to be uploaded is generated, the terminal device may send a Scheduling Request (SR for short) to the base station. The base station may further determine a resource scheduling policy in response to the request, where the resource scheduling policy may include a scheduling time of the scheduled air interface resource and a usage time of the air interface resource. The scheduling time is the sending time of the resource scheduling policy, and the using time is the uploading time for the terminal device to upload the data to be uploaded to the base station by using the air interface resource. The base station may send the usage time of the air interface resource to the terminal device when the scheduling time is reached, and simultaneously allocate the air interface resource to the terminal device, so that the terminal device may upload the data to be uploaded by using the allocated air interface resource when the usage time is reached. Therefore, the scheduling time and the using time in the resource scheduling strategy can influence the uploading of the data to be uploaded, namely, the interface time delay of the data to be uploaded.
In some specific scenes, such as automatic driving or industrial manufacturing scenes mentioned in the background art, the requirement for the air interface delay of the data is often higher, that is, a smaller air interface delay is required, and at this time, the resource scheduling method provided by the embodiments of the present invention can be used to schedule air interface resources, so as to reduce the air interface delay of the data to be uploaded, and ensure the timely uploading of the data.
In addition, before describing the resource scheduling method provided by the embodiments of the present invention in detail, the following concepts may be explained:
in the above data uploading process, when various data are transmitted between the terminal device and the base station, the minimum transmission unit may be called a timeslot, and a plurality of timeslots may form one frame. Any frame structure can be composed of an uplink time slot, a downlink time slot and a special time slot. And the frame structure, i.e., the number and arrangement order of various slots included in one frame, can be preset according to the requirements. The length of each slot in the preset frame structure may also be preset. The preset time slot length depends on that Sub-Carrier Spacing (SCS for short) is the same. The terminal device may upload data to the base station in an uplink timeslot in a frame, so as to implement uplink data transmission. In the following embodiments, the uplink data may include data to be uploaded or a resource scheduling request. The base station can issue control instructions and data packets to the terminal equipment in the downlink time slot and the special time slot to realize downlink data transmission. In various embodiments described below, the downlink control instructions may include scheduling policies and gapped resources.
For example, the frame structure may be represented as a DDSUU, DDDSU, DSUUU, or the like. The uplink time slot may be denoted as U, and the terminal device is configured to upload a resource scheduling request or data to be uploaded in the time slot. The downlink time slot may be denoted as D and the special time slot may be denoted as S. The special time slot S in the frame structure may also be used as a downlink time slot. That is, the base station can issue the resource scheduling policy in two time slots. The length of a slot in the frame structure, i.e. the preset slot length, may be 0.5 ms.
Based on the above description, some embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The features of the embodiments and examples described below may be combined with each other without conflict between the embodiments. In addition, the sequence of steps in each method embodiment described below is only an example and is not strictly limited.
Fig. 1 is a flowchart of a resource scheduling method according to an embodiment of the present invention. The resource scheduling method provided by the embodiment of the invention can be executed by a base station accessed with terminal equipment. The method reflects the process of resource scheduling. As shown in fig. 1, the method may include the steps of:
s101, predicting second generation time of data to be uploaded according to the first generation time of the historical resource scheduling request.
The base station may collect a plurality of historical resource scheduling requests generated by the terminal device within a historical period of time and a generation time of each request. The historical resource scheduling request can be generated after the terminal device generates the historical data to be uploaded. And then, the base station can also analyze the generation time of the historical resource scheduling request and predict the time for the terminal equipment to generate the data to be uploaded next time after the historical time period according to the analysis result. For clarity of the following description, the generation time of the historical resource scheduling request may be referred to as a first generation time, and the prediction result, that is, the time when the data to be uploaded is generated next time, may be referred to as a second generation time.
The reason why the second generation time prediction can be realized by analyzing the first generation time is as follows: the historical resource scheduling request and the historical data to be uploaded correspond to each other one by one, and the generation time of the historical resource scheduling request and the historical data to be uploaded is generally fixed time difference. For example, assuming that the first generation time of a historical resource scheduling request is T, the second generation time of the historical data to be uploaded corresponding to the scheduling request may be T +10 ms. Therefore, after the respective first generation times of the historical resource scheduling requests are analyzed as discrete time series data, if the first generation times are found to have periodicity, the generation time of the next resource scheduling request can be predicted according to the periodicity of the first generation times, and then the second generation time of the data to be uploaded can be predicted according to the time difference between the generation of the resource scheduling request and the generation of the data to be uploaded.
For the data to be uploaded generated by the terminal device, in the automatic driving scenario, the data may be driving data collected by a vehicle in an automatic driving mode. In an industrial manufacturing scene, the data to be uploaded can also be pressure value, temperature value and other sensing data generated by a mechanical arm on the production line.
And S102, determining a resource scheduling strategy meeting the preset time delay requirement according to the second generation time.
And S103, sending the resource scheduling strategy and the air interface resource so that the terminal equipment uploads the data to be uploaded according to the resource scheduling strategy and the air interface resource.
Then, the base station may determine, based on the predicted second generation time in the above step, a resource scheduling policy that meets a preset delay requirement, and send the resource scheduling policy that meets the requirement and the air interface resource one allocated to the terminal device. The terminal device may upload the data to be uploaded according to the resource scheduling policy and the allocated air interface resources. The resource scheduling policy may include a usage time and a scheduling time. The scheduling time may be separated from a second generation time of the data to be uploaded by a first preset duration, and the using time may be separated from the second generation time of the data to be uploaded by a second preset duration.
Alternatively, the predetermined delay requirement may be expressed as a specific length of time. The second predetermined duration is also the predetermined delay requirement. Therefore, the use time in the resource scheduling policy can control the uploading time of the data to be uploaded, so that the terminal device can upload the data according to the time required by the preset time delay, that is, the effect of controlling the uploading time of the data according to the preset time delay requirement is realized.
Alternatively, the resource scheduling policy and the empty resource may be sent by using a Physical Downlink Control Channel (PDCCH). The resource scheduling request and the data to be uploaded may be uploaded via a Physical Uplink Share Channel (PUSCH).
In this embodiment, according to the first generation time of the historical resource scheduling request, the second generation time of the data to be uploaded is predicted. And further, determining a resource scheduling strategy meeting the preset time delay requirement according to the second generation time, and issuing the resource scheduling strategy and air interface resources to the terminal equipment. When the terminal device generates the data to be uploaded in the second generation time, the data can be uploaded by using the resource scheduling policy and the air interface resource. Compared with a fixed and unchangeable resource scheduling strategy, in the process, the scheduling strategy refers to the generation time of the data, so that the scheduling strategy can control the uploading time of the data to be uploaded to meet the preset time delay requirement, the data to be uploaded can be uploaded within a short time after being generated, and the air interface time delay of the data to be uploaded is reduced.
In addition, because the scheme of this embodiment can directly predict the second generation time of the data to be uploaded, and thus allocate an air interface resource to the terminal device directly according to the generation time, when this embodiment is used, the terminal device does not need to generate a resource scheduling request, so that the interaction flow between the terminal device and the base station is simplified, and the air interface delay caused by the interaction flow can be further reduced.
For the embodiment shown in fig. 1, for example, assuming that the current time is T0, the base station predicts that the terminal device will generate data to be uploaded at T2 according to the generation time of the historical resource scheduling request. By assuming that the preset delay requirement is 1ms, the base station may generate a resource scheduling policy according to the prediction result, where the scheduling time in the resource scheduling policy may be T1, and the usage time may be T2+1 ms. Wherein T0 is earlier than T1, and T1 is earlier than T2. The base station may send the air interface resource and the use time to the terminal device when T1 is reached, so that the terminal device uses the allocated air interface resource to achieve data uploading when T2+1ms is reached.
In practice, if the base station does not consider the generation time of the data to be uploaded but periodically allocates an air interface resource to the terminal device, when the uplink timeslot is reached, if the terminal device does not generate useful data to be uploaded, the terminal device may also upload invalid padding data (padding data) to the base station using the allocated air interface resource, thereby reducing the effective utilization rate of the air interface resource. In the embodiment shown in fig. 1, the base station starts determining the resource scheduling request and allocating the air interface resource after predicting that data to be uploaded will be generated, so that the terminal device transmits useful data using the allocated air interface resource, thereby improving the effective utilization rate of the air interface resource.
In the complete resource scheduling process, the resource scheduling policy, the issue of the air interface resource and the upload of the data to be uploaded can be realized by means of a preset frame structure. Therefore, the resource scheduling method of the embodiment shown in fig. 1 can also be described in conjunction with the frame structure and the time slot:
after predicting the second generation time, the base station may determine a target timeslot corresponding to the second generation time in the target frames, where the target timeslot may be any one of the target frames and the target frames have a preset frame structure. Then, the first preset duration may be converted into a first number of timeslots according to the preset timeslot length to determine a first number of downlink timeslots spaced from the target timeslot, where the downlink timeslots are before the target timeslot. And converting the second preset duration into a second number of time slots according to the preset time slot length so as to determine a second number of uplink time slots separated from the target time slot, wherein the uplink time slots are behind the target time slot. This second number may also be considered as another manifestation of the predetermined delay requirement, which is still expressed as a specific length of time.
After determining the uplink time slot and the downlink time slot according to the above manner, the base station may send the uplink time slot and the air interface resource to the terminal device when the downlink time slot is reached, and control the terminal device to upload data to be uploaded when the uplink time slot is reached. And according to the difference of the lengths of the first preset time length and the second preset time length, a plurality of time slots can be separated between the target time slot and the downlink time slot, and a plurality of time slots can also be separated between the target time slot and the uplink time slot.
It should be noted that there is no strict timing relationship between the uplink timeslot and the downlink timeslot, and the uplink timeslot and the downlink timeslot may be executed sequentially or simultaneously.
The above-mentioned process of implementing resource scheduling by means of frame structure and time slots can also be described in a flow manner, as shown in fig. 2. Fig. 2 is a flowchart of another resource scheduling method according to an embodiment of the present invention, where the method includes the following steps:
s201, predicting second generation time of data to be uploaded according to the first generation time of the historical resource scheduling request.
The specific execution process of step S201 may refer to the related description of step S101 in the embodiment shown in fig. 1, and is not described herein again.
S202, according to the preset time slot length, determining a target time slot corresponding to the second generation time, wherein the target time slot is contained in a target frame with a preset frame structure.
And S203, determining an uplink time slot after the target time slot according to the preset time delay requirement and the preset time slot length.
S204, the number of the time slots between the uplink time slot and the target time slot is determined as the time slot offset in the resource scheduling strategy.
The base station may determine a target time slot corresponding to the second generation time in the target frame according to the preset time slot length. And then, determining an uplink time slot after the target frame according to the preset time delay requirement and the preset time slot length. Wherein the uplink time slot and the target time slot are separated by a second number of time slots. This second number may also be considered as a slot offset, which may be denoted by K2 value, which corresponds to the time of use in the resource scheduling policy.
S205, according to the downlink time slot before the target time slot, determining the scheduling time of the hollow resource in the resource scheduling strategy.
And S206, when the scheduling time is reached, transmitting the air interface resource and the time offset, so that the terminal equipment determines the uplink time slot after the target time slot according to the time slot offset and the target time slot and uploads the data to be uploaded when the uplink time slot is reached.
Then, the base station may further determine a downlink time slot before the target time slot, where the downlink time slot corresponds to a scheduling time of the air interface resource in the resource scheduling policy. Wherein, the time slot of the first number is separated between the downlink time slot and the target time slot. At this time, the base station may issue the air interface resource and the slot offset to the terminal device when the scheduling time is reached, so that the terminal device calculates an uplink slot capable of uploading data according to the target slot and the slot offset, and uploads the data to be uploaded by using the allocated air interface resource when the uplink slot is reached.
In this embodiment, after predicting the second generation time, the base station may determine the target frame corresponding to the second generation time, the downlink time slot corresponding to the scheduling time in the resource scheduling policy, and the uplink time slot corresponding to the use time in sequence. The time slot quantity of the interval between the uplink time slot and the target time slot is determined according to the preset time delay requirement, so that the time interval between the second generation time of the data to be uploaded and the uploading time can be controlled to meet the preset time delay requirement by using the scheduling strategy, the data to be uploaded can be ensured to be uploaded in a short time after being generated, and the air interface time delay of the data to be uploaded is also reduced.
For the embodiment shown in fig. 2, continuing to bear the example in the embodiment shown in fig. 1, assuming that the current time is T0, the base station predicts that the terminal device will generate data to be uploaded at T2, and the preset delay is required to be 2 ms. It is also assumed that a target frame with a predetermined frame structure is shown in fig. 3, the frame structure is DSUUU, and the length of each slot is 0.5 ms. And the frame structure may be transformed into DSU1U2U3 for clarity of description.
The base station may determine that the time corresponds to the U1 slot (i.e., the target slot) in the target frame according to the predicted second generation time, determine that the downlink slot is the D slot before the U1 slot, and determine that the U3 slot after the U1 slot in the uplink slot, where the slot offset of the U3 slot with respect to the U1 slot is K2= 4. The base station may send the air interface resource and the time slot offset when the D time slot is reached, so that the terminal device uses the allocated air interface resource time slot to upload data in the U3 time slot.
It should be noted that, in the above example, the target timeslot, the uplink timeslot, and the downlink timeslot are all located in the same frame. However, in practice, the target timeslot, the uplink timeslot, and the downlink timeslot may be located in different frames due to different requirements of the target timeslot, the frame structure, and the delay.
In the above embodiments, the predetermined delay requirement may represent a value, that is, a specific delay length. In practice, in order to further reduce the air interface delay of the data to be uploaded, optionally, the preset delay requirement may also be embodied as a principle: after the data to be uploaded is generated, the data can be uploaded in the shortest time.
For such a delay requirement, the uplink timeslot determined in the embodiment shown in fig. 2 for implementing data upload may be an uplink timeslot adjacent to the target timeslot. For example, as shown in fig. 3, the target timeslot is U1 timeslot in the target frame, and the uplink timeslot is U2 timeslot adjacent to U1 timeslot.
The base station may determine the uplink time slot and also may determine a downlink time slot for issuing a resource scheduling policy, and in order to ensure the reasonability of air interface resource scheduling, the downlink time slot for issuing the resource may also be a downlink time slot before the target time slot and closest to the target time slot. For example, as shown in fig. 3, the target timeslot is U1 timeslot in the target frame, and the downlink timeslot is S timeslot adjacent to U1 timeslot. The resource scheduling and data upload process described above can be understood in connection with fig. 4.
It should be noted that, considering the difference between the target timeslot, the frame structure and the delay requirement, the uplink timeslot and the target timeslot may not be located in the same frame, but the timeslot is an uplink timeslot that is after the target timeslot and is closest to the target timeslot. Similar to the uplink timeslot, the uplink timeslot and the target timeslot may be located in the same or different frame.
As described in the embodiment shown in fig. 1, the base station may analyze the first generation time and predict the second generation time using the analysis result. In practice, when the terminal device can periodically generate data to be uploaded, optionally, fig. 5 is a method for predicting generation time provided by the present invention, that is, an optional implementation manner of step S101. As shown in fig. 5, the method may include the steps of:
s1011, determining a generation period of the data to be uploaded according to the first generation time of the historical resource scheduling request.
And S1012, predicting second generation time of the data to be uploaded according to the generation period.
The base station may first determine whether there is periodicity in the generation of the historical resource scheduling request according to a first generation time of the historical resource request. As described in the embodiment shown in fig. 1, the historical resource scheduling request and the historical data to be uploaded correspond to each other one to one, and a pair of the historical resource scheduling request and the historical data to be uploaded having a corresponding relationship generally have a fixed time difference between their generation times. Therefore, if the generation of the historical resource scheduling request is periodic, and it can be considered that the generation of the data to be uploaded is also periodic, the generation period of the data to be uploaded can be further determined according to the generation period of the request, and then the second generation time of the data to be uploaded is predicted according to the generation period of the data to be uploaded. Since the data to be uploaded is periodically generated, the second generation time predicted by the base station may be optionally multiple.
As for the generation cycle of the data to be uploaded, it may be a single layer cycle as shown in (a) in fig. 6, or may be a nested cycle as shown in (b) in fig. 6. In fig. 6 (a), T is a generation period of data to be uploaded; in (b) in fig. 6, a period T1 is nested in the period T2.
In this embodiment, for the periodically generated data to be uploaded, it may be determined whether the generation of the data is periodic according to the first generation time. And if the data generation has periodicity, predicting second generation time of the data to be uploaded according to the generation period of the data to be uploaded.
As can be seen from the description in the embodiment shown in fig. 5, the generation cycle prediction of the data to be uploaded specifically includes two stages, namely, a stage of determining whether there is periodicity and a stage of predicting the generation cycle.
Alternatively, the time distribution rule of the first generation time may be analyzed to determine whether the first generation time has periodicity and predict the generation period. And in practice the analysis of the first generation time may be carried out using different methods.
The base station may alternatively implement the above-described decision phase and prediction phase using either the first analysis method alone or the second analysis method alone.
In order to ensure the accuracy of the judgment and the prediction, two analysis methods can be used to judge whether the periodicity exists and predict the generation period.
In order to ensure the accuracy of judgment and prediction, in yet another alternative way, different analysis methods may be respectively adopted to perform periodic judgment and generation period prediction. That is, the first analysis method may be used to analyze the first generation time of the historical resource scheduling request to determine whether the generation of the historical resource scheduling request is periodic, that is, to determine whether the generation of the data to be uploaded is periodic. Meanwhile, a second analysis method is used for determining the generation period of the data to be uploaded.
Since the first analysis method is a lightweight method, periodic rapid identification can be achieved. And the second analysis method may be an algorithm more suitable for generating the period prediction. Therefore, the first analysis method is used for periodic judgment, the second analysis method is used for predicting the generation period, and the accuracy of generation period prediction can be guaranteed while the rapid recognition of the periodicity is guaranteed.
Alternatively, the first analysis method described above may include various methods of performing discrete analysis using the first generation time as discrete-time data, such as fourier transform, polynomial fitting, autoregressive moving average, time series decomposition, and the like. The following illustrates how discrete data analysis is performed on a first generation time using a first analysis algorithm to achieve periodic judgments and predictions of generation periods:
one way, the first generation time as time-series data is converted into frequency-domain data by fourier transform. If the values of the frequency domain data are all smaller than a given threshold value, judging that the first generation time has no periodicity; if there is frequency domain data greater than the threshold, then the first generation time may be deemed periodic. And determining a target frequency corresponding to a non-0 wave crest with the highest amplitude in the frequency domain data, wherein a quotient obtained by dividing the number of the historical resource scheduling requests by the target frequency is a generation period of the data to be uploaded.
In another mode, the first generation time of the plurality of historical scheduling resource requests is used as discrete data to perform curve fitting, and whether periodicity exists and a generation period are determined according to the positions of peaks and troughs in a fitting curve.
In another embodiment, a time series including a first generation time is decomposed, and if a seasonal variation can be decomposed in addition to a long-term trend, a cyclic fluctuation, and an irregular wave, whether or not periodicity exists is determined, and a generation period is predicted from the decomposed seasonal variation.
Alternatively, the second analysis method described above may include a network model prediction method. The first generation time of the historical resource scheduling request is input into a pre-trained network model, so that whether the terminal equipment periodically generates the data to be uploaded is judged by the network model, and the generation period of the data to be uploaded is predicted by the network model. Alternatively, the same or different models may be used for the models that implement the periodicity judgment and generate the periodicity prediction. Alternatively, the prediction model may include a Support Vector Machine (SVM) model, various Neural Network models such as a Convolutional Neural Network (CNN) model, a Recurrent Neural Network (RNN) model, and the like.
The above embodiments describe in detail the manner of predicting the second generation time and the manner of generating the resource scheduling policy, respectively. In the foregoing embodiments, the size of the air interface resource allocated by the base station to the terminal device is not limited. In practice, if a fixed size of air interface resource is allocated to the terminal device, a situation may occur that the size of the air interface resource is not matched with the size of the data to be uploaded, at this time, the terminal device may not successfully upload the data using the allocated air interface resource, or waste of the air interface resource may be caused.
In order to improve the above problem, fig. 7 is a flowchart of another resource scheduling method provided by the embodiment of the present invention, which may include the following steps, and the following steps may be executed after step S102 and step S205.
S301, the size of data corresponding to the historical resource scheduling request is obtained.
S302, inputting the size of the historical data to be uploaded into a network model so as to predict the size of the data to be uploaded by the network model.
And S303, determining air interface resources according to the size of the data to be uploaded.
The base station may also obtain the size of the historical data to be uploaded corresponding to each historical resource scheduling request while obtaining the historical resource scheduling request to perform the second generation time prediction, and input the size of the historical data to be uploaded into the prediction model, so that the prediction model predicts the size of the data to be uploaded generated at the second generation time, and the base station may allocate an air interface resource suitable for the size of the data to the terminal device. Alternatively, the prediction model for predicting the size of the data to be uploaded may be the same as or different from the prediction generation period and the network model for determining whether periodicity exists.
In this embodiment, the allocation of the air interface resources takes into account the size of the data to be uploaded, so that the allocation of the air interface resources is more reasonable, and the waste of the air interface resources is improved.
According to the embodiments, the determination of whether periodicity exists, the prediction of the generation period, and the prediction of the size of the data to be uploaded can be performed by the same or different network models.
For the training of the network model, the historical resource scheduling request generated in a historical period can be used as a training sample, and whether the training sample has periodicity and a periodicity value is artificially marked. The collected training samples are input into a network model, and the artificial marking information of each training sample is used as supervision information to train the network model, so that the trained network model can judge whether the terminal equipment periodically generates data to be uploaded, and can predict the generation period of the data to be uploaded.
In addition, assuming that the historical time period includes historical scheduling resource requests generated from time T1 to time T10 and the size of the historical data to be uploaded corresponding to each request, the size of the historical data to be uploaded corresponding to the historical resource scheduling requests generated from time T1 to time T9 may be input into the network model, and the size of the historical data to be uploaded corresponding to the historical resource scheduling requests generated from time T10 is predicted by the network model, so that the predicted size is obtained. And then, calculating a loss value between the predicted size and the actual size of the historical data to be uploaded corresponding to the historical resource scheduling request generated at the time T10, and optimizing network model parameters according to the loss value, so that training of a network model is realized, and the network model can predict the size of the data to be uploaded.
As can be seen from the above description, for the data to be uploaded generated by the terminal device, in the automatic driving scenario, it may be the driving data collected by the vehicle in the automatic driving mode. In this scenario, fig. 8 is a flowchart of another resource scheduling method provided in an embodiment of the present invention, which may include the following steps,
s401, predicting second generation time of the driving data to be uploaded according to the first generation time of the historical resource scheduling request.
S402, determining a resource scheduling strategy meeting the preset time delay requirement according to the second generation time.
And S403, sending the resource scheduling strategy and the air interface resource so that the vehicle uploads the driving data to be uploaded according to the resource scheduling strategy and the air interface resource.
The base station may obtain a first generation time of a historical resource scheduling request sent by the vehicle and predict a second generation time of the vehicle generating the travel data to be uploaded. The base station may determine a resource scheduling policy meeting the preset delay requirement according to the predicted second generation time, and send the air interface resource and the resource scheduling policy to the vehicle, so that the vehicle uses the allocated air interface resource, and the driving data to be uploaded is uploaded to the base station in time according to the resource scheduling policy. Alternatively, the travel data may include a travel speed, a travel time period, a travel route, sensor data of an important component in the vehicle, and the like.
The specific process of generating the time prediction and determining the resource scheduling policy may be referred to in the above description of the embodiments. In addition, the contents and the technical effects that are not described in detail in this embodiment can be referred to the related description in the above embodiments, and are not described again here.
For ease of understanding, specific implementation procedures of the resource scheduling method provided above may be exemplified in connection with an industrial manufacturing scenario. The following can be understood in conjunction with fig. 9.
In an industrial manufacturing scenario, a robot arm on an industrial production line may periodically generate sensing data (i.e., data to be uploaded in the above embodiments), where the sensing data may be a pressure value, a temperature value, and the like. The mechanical arm can upload the sensing data to the base station, and then the sensing data is forwarded to the server through the base station. The server can judge the working state of the mechanical arm according to the sensing data, namely whether the mechanical arm is abnormal or not.
In the historical time period, when the mechanical arm collects the sensing data, the resource scheduling requests can be generated to the base station, and then the base station can obtain the resource scheduling requests generated by the mechanical arm in the historical time period and the first generation time of each scheduling request. The base station may analyze the first generation time, and if the first generation time is determined to be periodic, the robot arm may be determined to periodically generate the sensing data. After this historical period of time, the base station may further determine the period of time the robotic arm produced the sensory data and the time of generation of the sensory data. And determining a resource scheduling strategy of air interface resources for the mechanical arm according to the generation time of the sensing data and a preset time delay requirement, so that the mechanical arm can upload the sensing data to the base station in time according to the resource scheduling strategy. In addition, since the robot generates the sensing data periodically, the base station can directly predict the generation time of the plurality of sensing data.
Assume that the same structure as that shown in fig. 3, the preset frame structure used in the resource scheduling process is DSUUU, and the preset time slot length of each time slot is 0.5 ms. For clarity of description, two adjacent frames may be transformed into D1S1U 2U 3D 2S2U4U5U 6. Assume again that the predetermined delay requirement is: after the data to be uploaded is generated, the data can be uploaded in the shortest time. The base station can predict that the period for the robot arm to generate the sensing data is 3ms, and can also predict that the sensing data can be generated at the U1 time slot and the U5 time slot.
For the sensing data generated in the U1 timeslot, the base station may further determine the following resource scheduling policy according to the prediction result and the preset delay requirement: the scheduling time of the resource scheduling policy corresponds to S1 slots with a slot offset K2= 2. Based on the resource scheduling policy, the base station may send air interface resources and a time slot offset to the robot arm when reaching the downlink time slot S1 closest to the U1 time slot. The mechanical arm may calculate, according to K2=2 in the resource scheduling policy, that the uploading time of the sensor data (i.e., the use time of the air interface resource) is the uplink timeslot U2 timeslot closest to the U1 timeslot, and when the time slot reaches the U2 timeslot, the air interface resource allocated to the mechanical arm by the base station is used to upload the sensor data.
The resource scheduling strategy obtained according to the above manner can ensure that the sensing data can be uploaded in time after being generated, thereby reducing the air interface delay of the sensing data. And the base station can predict the generation time of the sensing data, so that the mechanical arm does not need to generate a resource scheduling request, the interaction process between the mechanical arm and the base station is simplified, and the air interface delay of the sensing data can be reduced.
In addition, the base station can predict the sizes of the sensing data generated in the two time slots when the mechanical arm generates the sensing data in the U1 time slot and the U5 time slot, and allocate air interface resources with different sizes to the mechanical arm according to the sizes of the sensing data, so that the use efficiency of the air interface resources is improved.
Similarly, for the sensing data generated at the U5 time slot, the base station may determine the following resource scheduling policy: the scheduling time of the resource scheduling policy corresponds to S2 slots with a slot offset K2= 3. The base station may send the air interface resources and the slot offset to the robot arm when reaching the downlink slot S2 slot closest to the U5 slot. The mechanical arm may calculate, according to K2=3 in the resource scheduling policy, that the uploading time of the sensor data (i.e., the use time of the air interface resource) is an uplink timeslot U6 timeslot closest to the U5 timeslot, and when the time slot reaches the U6 timeslot, the air interface resource allocated to the mechanical arm by the base station is used to upload the sensor data.
In the above process, for the sensing data generated at different time slots, the resource scheduling policies determined by the base station may be different, so that the sensing data can be uploaded in time, and the air interface delay is reduced.
In addition, in the foregoing process, the prediction process of the generation time of the sensing data and the prediction process of the size of the air interface resource may all participate in the relevant description in the foregoing embodiments, and details are not described here.
The resource scheduling method provided by each embodiment of the present invention may also be applied to an automatic driving scenario, and a specific execution flow may be as described in the embodiment shown in fig. 8.
In this scenario, the vehicle may periodically generate the driving data, and transmit the driving data to the base station in time according to the preset time delay requirement, and then the driving data is forwarded to the server by the base station. The server can judge the driving state of the vehicle according to the driving data and determine the navigation data corresponding to the vehicle according to the driving state, so that the vehicle can realize automatic driving according to the navigation data. In this scenario, the specific uploading process of the driving data can also be understood in conjunction with fig. 10.
During the historical time period, the base station may receive resource scheduling requests generated by the vehicle during the time period to obtain a first generation time of each scheduling request. When the base station analyzes the first generation time, the generation period of the vehicle generated running data can be determined. Then after this historical period of time, the base station may further predict when the vehicle will produce travel data the next or several times based on the generation cycle of the travel data. The base station can determine a resource scheduling strategy of the air interface resource for the vehicle according to the prediction result of the generation time and the preset time delay requirement, so that the vehicle can upload the sensing data to the base station in time according to the resource scheduling strategy.
It is assumed that in the automatic driving scenario, the frame structure, the preset slot length, and the preset delay requirement are the same as those in the embodiment shown in fig. 9. The vehicle may also upload the driving data generated at the U1 time slot at the U2 time slot, wherein the resource scheduling policy and the air interface resource may be transmitted at the S1 time slot before the U1 time slot. The vehicle can also upload the driving data generated in the U5 time slot in the U6 time slot, wherein the resource scheduling strategy and air interface resources can be transmitted in the S2 time slot before the U5 time slot.
In the above process, for the sensing data generated at different time slots, the resource scheduling policies determined by the base station may be different, so that the sensing data can be uploaded in time, and the air interface delay is reduced. In addition, in the foregoing process, the prediction process of the generation time of the sensing data and the prediction process of the size of the air interface resource may all participate in the relevant description in the foregoing embodiments, and details are not described here.
In a possible design, the resource scheduling method provided in the foregoing embodiments may be applied in an electronic device, as shown in fig. 11, where the electronic device may include: a processor 21 and a memory 22. The memory 22 is used for storing a program that supports the electronic device to execute the resource scheduling method provided in the embodiments shown in fig. 1 to fig. 7, and the processor 21 is configured to execute the program stored in the memory 22.
The program comprises one or more computer instructions which, when executed by the processor 21, are capable of performing the steps of:
predicting second generation time of data to be uploaded according to the first generation time of the historical resource scheduling request;
determining a resource scheduling strategy meeting the preset time delay requirement according to the second generation time;
and sending the resource scheduling strategy and the air interface resource so that the terminal equipment uploads the data to be uploaded according to the resource scheduling strategy and the air interface resource.
Optionally, the processor 21 is further configured to perform all or part of the steps in the embodiments shown in fig. 1 to 7.
The electronic device may further include a communication interface 23 for communicating with other devices or a communication network.
In one possible design, the resource scheduling method provided by the foregoing embodiments may be applied in an electronic device, as shown in fig. 12, where the electronic device may include: a processor 31 and a memory 32. Wherein the memory 32 is used for storing a program for supporting the electronic device to execute the resource scheduling method provided in the embodiment shown in fig. 8, and the processor 31 is configured to execute the program stored in the memory 32.
The program comprises one or more computer instructions which, when executed by the processor 31, are capable of performing the steps of:
predicting second generation time of the driving data to be uploaded according to the first generation time of the historical resource scheduling request;
determining a resource scheduling strategy meeting a preset time delay requirement according to the second generation time;
and sending the resource scheduling strategy and the air interface resource so that the vehicle uploads the driving data to be uploaded according to the resource scheduling strategy and the air interface resource.
Optionally, the processor 31 is further configured to perform all or part of the steps in the foregoing embodiment shown in fig. 8.
The electronic device may further include a communication interface 33 for communicating with other devices or a communication network.
In addition, an embodiment of the present invention provides a computer storage medium for storing computer software instructions for the electronic device, which includes a program for executing the resource scheduling method according to the embodiment of the method shown in fig. 1 to 8.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (13)
1. A method for scheduling resources, comprising:
predicting second generation time of data to be uploaded according to the first generation time of the historical resource scheduling request;
determining a resource scheduling strategy meeting a preset time delay requirement according to the second generation time;
and sending the resource scheduling strategy and the air interface resource so that the terminal equipment uploads the data to be uploaded according to the resource scheduling strategy and the air interface resource.
2. The method of claim 1, wherein the determining a resource scheduling policy that meets a preset delay requirement according to the second generation time comprises:
determining a target time slot corresponding to the second generation time according to a preset time slot length, wherein the target time slot is contained in a target frame with a preset frame structure;
determining an uplink time slot after the target time slot according to the preset time delay requirement and the preset time slot length;
determining the number of the time slots at intervals between the uplink time slots and the target time slots as the time slot offset in the resource scheduling strategy;
and determining the scheduling time of the hollow resource in the resource scheduling strategy according to the downlink time slot before the target time slot.
3. The method of claim 2, wherein the sending the resource scheduling policy and air interface resources comprises:
when the scheduling time is reached, sending the air interface resource and the time slot offset;
the uploading, by the terminal device, the data to be uploaded according to the resource scheduling policy and the air interface resource includes:
determining an uplink time slot after the target time slot according to the time slot offset and the target time slot;
and uploading the data to be uploaded when the uplink time slot is reached.
4. The method of claim 2, wherein the downlink timeslot is adjacent to the target timeslot; the uplink time slot is adjacent to the target time slot.
5. The method of claim 2, wherein the sending the resource scheduling policy and air interface resources comprises:
when the downlink time slot is reached, a downlink physical control channel is used for sending the resource scheduling strategy and the air interface resource;
the uploading, by the terminal device, the data to be uploaded according to the resource scheduling policy and the air interface resource includes:
and when the uplink time slot is reached, uploading the data to be uploaded by using an uplink physical shared channel.
6. The method of claim 1, wherein before the sending the resource scheduling policy and the air interface resource, the method further comprises:
acquiring the size of historical data to be uploaded corresponding to the historical resource scheduling request;
inputting the size of the historical data to be uploaded into a network model so as to predict the size of the data to be uploaded by the network model;
and determining the air interface resource according to the size of the data to be uploaded.
7. The method of claim 1, wherein predicting a second generation time of data to be uploaded based on a first generation time of a historical resource scheduling request comprises:
determining a generation period of the data to be uploaded according to the first generation time;
and predicting the second generation time according to the generation period.
8. The method according to claim 7, wherein determining the generation period of the data to be uploaded according to the first generation time comprises:
and analyzing a time distribution rule of the first generation time to determine whether periodicity exists in the generation of the data to be uploaded and the generation period.
9. The method of claim 8, wherein analyzing the time distribution law of the first generation time comprises:
performing discrete data analysis on the first generation time;
and/or inputting the first generation time into a network model to output the generation period by the network model.
10. The method of claim 8, wherein analyzing the time distribution law of the first generation time to determine whether periodicity exists in the generation of the data to be uploaded and the generation period comprises:
performing discrete data analysis on the first generation time to determine whether periodicity exists in the generation of the data to be uploaded;
inputting the first generation time into a network model to output the generation period by the network model.
11. A method for scheduling resources, comprising:
predicting second generation time of the driving data to be uploaded according to the first generation time of the historical resource scheduling request;
determining a resource scheduling strategy meeting a preset time delay requirement according to the second generation time;
and sending the resource scheduling strategy and the air interface resource so that the vehicle uploads the driving data to be uploaded according to the resource scheduling strategy and the air interface resource.
12. An electronic device, comprising: a memory, a processor; wherein the memory has stored thereon executable code which, when executed by the processor, causes the processor to perform the method of resource scheduling according to any of claims 1 to 11.
13. A non-transitory machine-readable storage medium having stored thereon executable code, which when executed by a processor of an electronic device, causes the processor to perform the resource scheduling method of any one of claims 1-11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210920761.3A CN114995985B (en) | 2022-08-02 | 2022-08-02 | Resource scheduling method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210920761.3A CN114995985B (en) | 2022-08-02 | 2022-08-02 | Resource scheduling method, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114995985A true CN114995985A (en) | 2022-09-02 |
| CN114995985B CN114995985B (en) | 2023-01-17 |
Family
ID=83022345
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210920761.3A Active CN114995985B (en) | 2022-08-02 | 2022-08-02 | Resource scheduling method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114995985B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102300324A (en) * | 2010-06-23 | 2011-12-28 | 大唐移动通信设备有限公司 | resource authorization and scheduling information sending method, system and device |
| CN108513359A (en) * | 2018-02-09 | 2018-09-07 | 京信通信系统（中国）有限公司 | A kind of interface-free resources distribution method and device |
| CN109788571A (en) * | 2017-11-14 | 2019-05-21 | 大唐移动通信设备有限公司 | A kind of data processing method and device |
| WO2019115225A2 (en) * | 2017-12-13 | 2019-06-20 | Nokia Technologies Oy | Methods and devices for resource scheduling in communication system |
| CN110621072A (en) * | 2019-09-29 | 2019-12-27 | 京信通信系统（中国）有限公司 | Resource scheduling method, device, base station equipment and storage medium |
| CN111143070A (en) * | 2019-12-27 | 2020-05-12 | 北京奇艺世纪科技有限公司 | Resource scheduling method and device |
| CN112312536A (en) * | 2019-08-01 | 2021-02-02 | 华为技术有限公司 | Transmission control method and device |
| CN112544101A (en) * | 2019-01-08 | 2021-03-23 | 华为技术有限公司 | Scheduling method, scheduling device, storage medium and communication system |
| CN113543332A (en) * | 2020-12-24 | 2021-10-22 | 中兴通讯股份有限公司 | Configuration method and device of frame structure, electronic equipment and readable storage medium |
| CN114499773A (en) * | 2022-03-28 | 2022-05-13 | 阿里巴巴达摩院(杭州)科技有限公司 | Data transmission method, electronic device, and storage medium |
| CN114630422A (en) * | 2020-12-10 | 2022-06-14 | 上海华为技术有限公司 | Sending method and device |
-
2022
- 2022-08-02 CN CN202210920761.3A patent/CN114995985B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102300324A (en) * | 2010-06-23 | 2011-12-28 | 大唐移动通信设备有限公司 | resource authorization and scheduling information sending method, system and device |
| CN109788571A (en) * | 2017-11-14 | 2019-05-21 | 大唐移动通信设备有限公司 | A kind of data processing method and device |
| WO2019115225A2 (en) * | 2017-12-13 | 2019-06-20 | Nokia Technologies Oy | Methods and devices for resource scheduling in communication system |
| CN108513359A (en) * | 2018-02-09 | 2018-09-07 | 京信通信系统（中国）有限公司 | A kind of interface-free resources distribution method and device |
| CN112544101A (en) * | 2019-01-08 | 2021-03-23 | 华为技术有限公司 | Scheduling method, scheduling device, storage medium and communication system |
| CN112312536A (en) * | 2019-08-01 | 2021-02-02 | 华为技术有限公司 | Transmission control method and device |
| CN110621072A (en) * | 2019-09-29 | 2019-12-27 | 京信通信系统（中国）有限公司 | Resource scheduling method, device, base station equipment and storage medium |
| CN111143070A (en) * | 2019-12-27 | 2020-05-12 | 北京奇艺世纪科技有限公司 | Resource scheduling method and device |
| CN114630422A (en) * | 2020-12-10 | 2022-06-14 | 上海华为技术有限公司 | Sending method and device |
| CN113543332A (en) * | 2020-12-24 | 2021-10-22 | 中兴通讯股份有限公司 | Configuration method and device of frame structure, electronic equipment and readable storage medium |
| CN114499773A (en) * | 2022-03-28 | 2022-05-13 | 阿里巴巴达摩院(杭州)科技有限公司 | Data transmission method, electronic device, and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 王汝言等: "C-RAN回传网络中下行资源调度策略", 《工程科学学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114995985B (en) | 2023-01-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Artificial intelligence inspired transmission scheduling in cognitive vehicular communications and networks | |
| Prathiba et al. | Federated learning empowered computation offloading and resource management in 6G-V2X | |
| Abiko et al. | Flexible resource block allocation to multiple slices for radio access network slicing using deep reinforcement learning | |
| CN109669768B (en) | Resource allocation and task scheduling method for edge cloud combined architecture | |
| Hazra et al. | Cooperative transmission scheduling and computation offloading with collaboration of fog and cloud for industrial IoT applications | |
| CN112055329B (en) | Edge Internet of vehicles task unloading method suitable for RSU coverage switching | |
| Sen et al. | Machine learning based timeliness-guaranteed and energy-efficient task assignment in edge computing systems | |
| Rodoplu et al. | A multiscale algorithm for joint forecasting–scheduling to solve the massive access problem of IoT | |
| JP2022104776A (en) | Resource allocation method and device for network access device | |
| Karadag et al. | QoS-constrained semi-persistent scheduling of machine-type communications in cellular networks | |
| Xia et al. | Control and scheduling codesign: flexible resource management in real-time control systems | |
| Naghshtabrizi et al. | Implementation considerations for wireless networked control systems | |
| Rodoplu et al. | Multi-channel joint forecasting-scheduling for the Internet of Things | |
| CN115002123B (en) | System and method for rapidly adapting task offloading based on mobile edge computation | |
| Wu et al. | Deep reinforcement learning for scheduling in an edge computing-based industrial internet of things | |
| Eisen et al. | Scheduling low latency traffic for wireless control systems in 5G networks | |
| Cecchinato et al. | Elastic and predictive allocation of computing tasks in energy harvesting IoT edge networks | |
| CN114995985B (en) | Resource scheduling method, device and storage medium | |
| CN113242304B (en) | Edge side multi-energy data acquisition scheduling control method, device, equipment and medium | |
| CN114185674A (en) | CPU task real-time scheduling method, device, equipment and storage medium | |
| Che et al. | Deep reinforcement learning in M2M communication for resource scheduling | |
| CN114138453B (en) | Resource optimization allocation method and system suitable for edge computing environment | |
| CN116599028A (en) | Multi-source data fusion-based method and system for autonomous and cooperative control of edge of platform | |
| CN113271221B (en) | Network capacity opening method and system and electronic equipment | |
| Zhao et al. | Optimizing allocation and scheduling of connected vehicle service requests in cloud/edge computing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |