CN114126019A - Forward-transmitting optical network dynamic resource mapping method and system based on energy efficiency optimization - Google Patents
Forward-transmitting optical network dynamic resource mapping method and system based on energy efficiency optimization Download PDFInfo
- Publication number
- CN114126019A CN114126019A CN202111444691.0A CN202111444691A CN114126019A CN 114126019 A CN114126019 A CN 114126019A CN 202111444691 A CN202111444691 A CN 202111444691A CN 114126019 A CN114126019 A CN 114126019A
- Authority
- CN
- China
- Prior art keywords
- baseband processing
- radio frequency
- energy consumption
- node
- remote radio
- 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
- 238000000034 method Methods 0.000 title claims abstract description 68
- 230000003287 optical effect Effects 0.000 title claims abstract description 58
- 238000013507 mapping Methods 0.000 title claims abstract description 41
- 238000005457 optimization Methods 0.000 title claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 132
- 238000005265 energy consumption Methods 0.000 claims abstract description 77
- 230000008569 process Effects 0.000 claims abstract description 34
- 230000006403 short-term memory Effects 0.000 claims abstract description 32
- 230000007787 long-term memory Effects 0.000 claims abstract description 30
- 238000012549 training Methods 0.000 claims abstract description 29
- 238000013135 deep learning Methods 0.000 claims abstract description 11
- 230000015654 memory Effects 0.000 claims description 19
- 238000007781 pre-processing Methods 0.000 claims description 16
- 230000003044 adaptive effect Effects 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000011478 gradient descent method Methods 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W52/00—Power management, e.g. TPC [Transmission Power Control], power saving or power classes
- H04W52/02—Power saving arrangements
- H04W52/0203—Power saving arrangements in the radio access network or backbone network of wireless communication networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
- H04B10/25—Arrangements specific to fibre transmission
- H04B10/2575—Radio-over-fibre, e.g. radio frequency signal modulated onto an optical carrier
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/50—Allocation or scheduling criteria for wireless resources
- H04W72/52—Allocation or scheduling criteria for wireless resources based on load
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Electromagnetism (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention relates to a method and a system for mapping dynamic resources of a fronthaul optical network based on energy efficiency optimization. The method comprises the following steps: collecting historical flow data of a remote radio frequency node; training a long-term and short-term memory network model in deep learning according to the historical traffic data, and predicting the traffic load condition of the next time node of each far-end radio frequency node; according to the flow load condition, aiming at minimizing the total energy consumption of the system, dynamically adjusting the connection relation of a fronthaul optical link between a baseband processing pool of a next time node and a remote radio frequency node; the minimum system total energy consumption comprises the inherent energy consumption of a baseband processing pool, the energy consumption generated in the process of executing baseband signal processing by the baseband processing pool and the energy consumption generated by switching. The invention can reduce the total energy consumption of the whole fronthaul optical link system and improve the resource utilization rate of the baseband processing pool.
Description
Technical Field
The invention relates to the technical field of mobile communication networks, in particular to a method and a system for mapping dynamic resources of a fronthaul optical network based on energy efficiency optimization.
Background
With the development of diversified network services and the large-scale popularization of intelligent terminal equipment, the data traffic of the mobile network increases exponentially, and higher requirements are put forward on the performances of the 5G mobile network in all aspects. How to reduce Capital Expenditure (CAPEX) and operational Expenditure (OPEX) of a network while satisfying the rapidly increasing wireless service requirements is a problem that operators need to pay a great deal of attention. The mobile Access Network architecture is developed from an integrated macro base station in the early 2G era to a distributed base station networking in the 3G era, and then the distributed base station networking is evolved towards a Centralized Radio Access Network (C-RAN) architecture in the 4G era, wherein the C-RAN mainly adopts the principle that a Remote Radio node (RRH)) and a user are reserved in a cell to establish connection, and Baseband processing units (Baseband Unit, BBU) in a traditional base station are concentrated together to form a BBU pool and are placed in a Central Office (CO) to uniformly schedule Baseband resources needing to be processed in the RRH. In the C-RAN, the BBU pool and the RRH perform data transfer by using an optical fiber link, and have high bandwidth and high reliability transmission capability, the link is called a Fronthaul (Fronthaul) optical link, and with the arrangement of intensive base stations, the RRH with a simple structure can greatly reduce the cost of the network arrangement and installation maintenance. And the BBU pool and the RRH establish forward connection through an optical fiber link. The C-RAN is gaining attention from a wide network operator in view of advantages in terms of reducing CAPEX and OPEX.
The fronthaul optical network is regarded as a novel optical access network scheme with great potential, and is also the key for the C-RAN to realize scale and industrialized deployment in 5G mobile communication. However, due to the mobility of users, mobile data traffic will continuously migrate with time and space, and traffic changes in a network service area have a significant tidal effect, that is, users tend to gather in a working area during the day, resulting in dense users in the working area, high base station load, large forward data traffic, and a relatively idle base station in a residential area. At night, most mobile users return to the residential area, and the base stations in the working area are idle. However, the existing access network structure does not have the capability of sensing the change of the network environment, and simultaneously lacks the uniform decision-making capability and intelligent control capability to schedule and distribute the network resources in time, so that the existing optical network still has a relatively fixed connection mode, the connection relationship of a front optical link cannot be adjusted in time according to the load change, the bandwidth resources and the processing capability of a BBU connected with a low-load RRH are not fully utilized, and the utilization rate of the whole resources of the BBU pool is low. It is clear that statically configured fronthaul optical networks do not take full advantage of the flexibility and intelligent management of the C-RAN architecture. With the deployment of densely populated cells in 5G, statically configured C-RANs can result in a huge waste of resources by BBU pools.
Disclosure of Invention
The invention aims to provide a fronthaul optical network dynamic resource mapping method and system based on energy efficiency optimization, so as to solve the problems of high system total energy consumption of the whole fronthaul optical link and low utilization rate of baseband processing pool resources.
In order to achieve the purpose, the invention provides the following scheme:
a method for mapping dynamic resources of a fronthaul optical network based on energy efficiency optimization comprises the following steps:
collecting historical flow data of a remote radio frequency node; the data types of the historical flow data comprise received and sent telephone service, short message service and Internet service; the historical traffic data represents the real traffic load conditions of a plurality of historical time nodes;
training a long-term and short-term memory network model in deep learning according to the historical traffic data, and predicting the traffic load condition of the next time node of each far-end radio frequency node;
according to the flow load condition, aiming at minimizing the total energy consumption of the system, dynamically adjusting the connection relation of a fronthaul optical link between a baseband processing pool of a next time node and a remote radio frequency node; the minimum system total energy consumption comprises the inherent energy consumption of a baseband processing pool, the energy consumption generated in the process of executing baseband signal processing by the baseband processing pool and the energy consumption generated by switching; the energy consumption generated by the switching comprises the energy consumption generated by switching the baseband processing units in the baseband processing pool between an activated state and a closed state and the energy consumption generated by switching the remote radio frequency node in different baseband processing units.
Optionally, the collecting historical traffic data of the remote radio frequency node further includes:
preprocessing the historical flow data to generate preprocessed historical flow data; the preprocessing comprises data normalization processing and data dimension increasing processing.
Optionally, the training, according to the historical traffic data, a long-term and short-term memory network model in deep learning, and predicting traffic load conditions of nodes at the next time of each remote radio frequency node specifically include:
training the long-short term memory network model by taking the real traffic load condition of a plurality of historical time nodes of each far-end radio frequency node as input and taking the traffic load condition of the next time node as output;
in each iteration process, comparing a predicted value corresponding to the predicted flow load condition with a real value corresponding to the real flow load condition, and adjusting the weight of the long-short term memory network model according to the error between the predicted value and the real value until the error requirement of training is met, thereby completing the trained long-short term memory network model;
and predicting the traffic load condition of the next time node of each remote radio frequency node by using the trained long-term and short-term memory network model.
Optionally, the energy consumption generated during the baseband processing performed by the baseband processing pool is generated by fully utilizing the resources of each activated baseband processing unit through the number of baseband processing units in the baseband processing pool that are in an activated state.
Optionally, the energy consumption generated by the switching is energy consumption generated by switching the baseband processing unit in the baseband processing pool between an active state and an inactive state, and energy consumption generated by switching the remote radio frequency node in different baseband processing units.
Optionally, the connection relationship of the fronthaul optical link between the baseband processing pool of the next time node and the remote radio frequency node is dynamically adjusted with the goal of minimizing the total energy consumption of the system according to the traffic load condition, and the dynamic adjustment method is regarded as a binning problem; the boxes represent the baseband processing units, the volume of each box is the maximum flow load which can be borne by each baseband processing unit, the size of each article is the load condition of each remote radio frequency node at the current moment, the size of each article changes along with time, and the boxing operation is to adjust the connection relation between the baseband processing units and the remote radio frequency nodes.
Optionally, the packing problem is solved by using a descending order first-time adaptive resource mapping algorithm based on the minimum switching number;
the step of the descending order first-time adaptive resource mapping algorithm based on the minimum switching number comprises the following steps:
according to the traffic load condition of the current remote radio frequency node, performing descending arrangement on the traffic load conditions of all the remote radio frequency nodes according to traffic load numerical values;
selecting the execution boxing operation with the maximum flow load in the unplanned remote radio frequency node;
judging whether a baseband processing unit connected with a last time node and the current far-end radio frequency node is in an activated state or not to obtain a first judgment result;
if the first judgment result is yes, judging whether the selected baseband processing unit has enough bandwidth resources to process the load flow of the current remote radio frequency node or not, and obtaining a second judgment result;
if the second judgment result is yes, maintaining the connection relationship between the selected baseband processing unit and the taken-out remote radio frequency node;
if the second judgment result is negative, traversing the rest activated baseband processing units, and judging whether enough bandwidth resources exist for processing the bandwidth resources of the taken-out remote radio frequency node to obtain a third judgment result;
if the third judgment result is yes, connecting the baseband processing unit with enough bandwidth resources encountered for the first time with the current remote radio frequency node in the traversal process;
if the third judgment result is negative, starting a new baseband processing unit, and connecting the new baseband processing unit with the taken-out remote radio frequency node;
if the first judgment result is negative, executing a third judgment process; the third judgment process is to traverse the rest activated baseband processing units and judge whether enough bandwidth resources exist to process the bandwidth resources of the taken-out remote radio frequency node to obtain a third judgment result;
and updating the working states and the load conditions of all the baseband processing units.
A fronthaul optical network dynamic resource mapping system based on energy efficiency optimization comprises:
the historical flow data collection module is used for collecting the historical flow data of the remote radio frequency node; the data types of the historical flow data comprise received and sent telephone service, short message service and Internet service; the historical traffic data represents the real traffic load conditions of a plurality of historical time nodes;
the traffic load condition prediction module is used for training a long-short term memory network model in deep learning according to the historical traffic data and predicting the traffic load condition of a next time node of each far-end radio frequency node;
the dynamic adjustment module is used for dynamically adjusting the connection relation of a fronthaul optical link between a baseband processing pool of a next time node and a remote radio frequency node according to the flow load condition by taking the minimization of the total energy consumption of the system as a target; the minimum system total energy consumption comprises the inherent energy consumption of a baseband processing pool, the energy consumption generated in the process of executing baseband signal processing by the baseband processing pool and the energy consumption generated by switching; the energy consumption generated by the switching comprises the energy consumption generated by switching the baseband processing units in the baseband processing pool between an activated state and a closed state and the energy consumption generated by switching the remote radio frequency node in different baseband processing units.
Optionally, the method further includes:
the preprocessing module is used for preprocessing the historical flow data to generate preprocessed historical flow data; the preprocessing comprises data normalization processing and data dimension increasing processing.
Optionally, the traffic load condition prediction module specifically includes:
the training unit is used for training the long-term and short-term memory network model by taking the real traffic load condition of a plurality of historical time nodes of each far-end radio frequency node as input and taking the traffic load condition of the next time node as output;
the trained long and short term memory network model construction unit is used for comparing a predicted value corresponding to the predicted flow load condition with a real value corresponding to the real flow load condition in each iteration process, and adjusting the weight of the long and short term memory network model according to the error between the predicted value and the real value until the error requirement of training is met, so as to finish the trained long and short term memory network model;
and the traffic load condition prediction unit is used for predicting the traffic load condition of the next time node of each far-end radio frequency node by using the trained long and short term memory network model.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects: the invention provides a fronthaul optical network dynamic resource mapping method and system based on energy efficiency optimization, which are used for dynamically adjusting the connection relation between a baseband processing unit and a remote radio frequency node in a fronthaul optical network by acquiring the flow load condition of a next time node through a long-short term memory network and further aiming at minimizing the total energy consumption of the system, thereby greatly reducing the energy consumption of the whole system, improving the resource utilization rate of the fronthaul optical network and meeting the requirement of the deployment of large-scale intelligent equipment on the high energy efficiency of the fronthaul optical network.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
Fig. 1 is a flowchart of a method for mapping dynamic resources of a fronthaul optical network based on energy efficiency optimization according to the present invention;
fig. 2 is a schematic diagram illustrating the operation of predicting the traffic by using the long-term and short-term memory network in the energy efficiency optimization-based dynamic resource mapping method for the fronthaul optical network according to the present invention;
fig. 3 is a schematic flow diagram of a descending order first-time adaptive resource mapping algorithm based on a minimum switching number in the energy efficiency optimization-based fronthaul optical network dynamic resource mapping method provided by the present invention;
fig. 4 is a structural diagram of a dynamic resource mapping system of a fronthaul optical network based on energy efficiency optimization according to the present invention.
Detailed Description
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 only a part of the embodiments of the present invention, and not all of the embodiments. 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 invention aims to provide a fronthaul optical network dynamic resource mapping method and system based on energy efficiency optimization, which can reduce the total system energy consumption of the whole fronthaul optical link and improve the resource utilization rate of a baseband processing pool.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
With the C-RAN architecture and the development of Network Function Virtualization (NFV) technology, it is necessary to combine an artificial intelligence method and a Network control technology, plan Network resources in a comprehensive manner according to dynamic demands of services, construct an intelligent Network control strategy capable of responding to environmental changes in time, improve the utilization rate of spectrum resources, and further improve the performance of the whole system. Thus, the problem can be summarized as the following two sub-problems: 1) exploring the dynamic characteristics of the service requirements, for example, by predicting the resource requirements in the network, providing a reference for the on-demand allocation and dynamic adjustment of network resources; 2) a strategy for dynamically adjusting and migrating network resources needs to be designed according to the prediction result, so that the utilization rate of the network resources is maximized.
Fig. 1 is a flowchart of a method for mapping dynamic resources of a fronthaul optical network based on energy efficiency optimization according to the present invention, and as shown in fig. 1, the method for mapping dynamic resources of a fronthaul optical network based on energy efficiency optimization includes:
step 101: collecting historical flow data of a remote radio frequency node; the historical flow data is embodied by service interaction between a user and a base station in a longer time, and the data types of the historical flow data comprise received and sent data services such as telephone service, short message service, internet service and the like; the historical traffic data characterizes true traffic load conditions of a plurality of historical time nodes.
The step 101 further includes: preprocessing the historical flow data to generate preprocessed historical flow data; the preprocessing comprises data normalization processing and data dimension increasing processing.
In practical application, the collected historical flow data has different dimensions and measurement units, and the range of the eigenvalue is wide, so that when an optimal solution is solved by using a gradient descent method, the different ranges of the eigenvalue can cause non-optimal search directions of gradient directions in many positions. Therefore, when the long-term and short-term memory networks are used for flow prediction, data samples are preprocessed, and feature values of different dimensions are normalized to be in the same value range, so that the convergence speed can be improved.
Preprocessing the collected historical traffic data includes:
normalizing the flow data of the RRH nodes in the data set by using a scaling normalization method, and normalizing the value of each feature to be between [0 and 1], wherein the normalized feature x value can be expressed as:
according to the same for training dataThe ratio of (a) to (b) is normalized,
is a normalized characteristic x value, x(i)Raw traffic load data, max, collected for the networki(x(i)) And mini(x(i)) Respectively, a maximum value and a minimum value thereof.
In the training process of the long-short term memory network, the error between the predicted value and the actual value in the current iteration process needs to be judged, and the original traffic load change condition is a two-dimensional time-varying sequence, so that two-dimensional traffic time-varying data in an original data set needs to be converted into a three-dimensional time sequence data set. In the three-dimensional data, input data of the long-term and short-term memory network are two-dimensional data which represent the change condition of flow data along with time in a period of time, a target flow value corresponding to the two-dimensional array is flow data of a next time node after the continuous time sequence, and each two-dimensional training data group corresponds to a test value.
Step 102: and training a long-term and short-term memory network model in deep learning according to the historical traffic data, and predicting the traffic load condition of the next time node of each far-end radio frequency node.
The step 102 specifically includes: training the long-short term memory network model by taking the real traffic load condition of a plurality of historical time nodes of each far-end radio frequency node as input and taking the traffic load condition of the next time node as output; in each iteration process, comparing a predicted value corresponding to the predicted flow load condition with a real value corresponding to the real flow load condition, and adjusting the weight of the long-short term memory network model according to the error between the predicted value and the real value until the error requirement of training is met, thereby completing the trained long-short term memory network model; and predicting the traffic load condition of the next time node of each remote radio frequency node by using the trained long-term and short-term memory network model.
In practical application, the collected historical flow data has the characteristics of long time and large data volume.
The Long Short-Term Memory Network (LSTM) is a typical Recurrent Neural Network (RNN), and when a deep learning method is used to handle a problem of a continuous time sequence, RNN is a more common model because RNN calculates the content of a current time node while considering information of a previous time node, that is, when a current time node t performs data operation, the output of a hidden node of the previous time node t-1 is used as the input of the current time node. However, in the RNN operation process, there is a problem of "long-term dependence", and after a number of time nodes are operated, characteristics of the previous longer time nodes are forgotten, so that when the gradient is calculated by using an error back propagation method, there is a problem that the gradient disappears, and the solution is easily trapped in a local optimal solution. Due to the unique structure of the LSTM network, a plurality of tasks which cannot be solved by the RNN learning algorithm of the conventional recurrent neural network can be solved, and the LSTM network has a very good effect on predicting events with long time intervals.
The concept of a long short term memory network incorporating a gate (gate) is used to control the proportion of eigenvalue passes. As shown in fig. 2, the long-short term memory network comprises three gates: an Input Gate (Input Gate), an Output Gate (Output Gate), and a forgetting Gate (Forget Gate). To solve the problem of early memory forgetting encountered by RNN, the long-short term memory network not only includes the short-term memory value h generated by each hidden layertA chain of cellular states throughout the network is also added to store long term memory.
The first step of the long-short term memory network is to use a forgetting gate ftControlling the proportion of information that is forgotten in the cells of the current hidden layer can be expressed as:
ft＝σ(Wf[ht-1,xt]+bf)
wherein h ist-1And xtRespectively representing the output value of the previous hidden layer and the newly input information of the current hidden layer, WfAnd bfRespectively representing the weight matrix and the Bayes vector of the forgetting gate, sigma representing a Sigmoid function,the forgetting gate gives a [0,1] based on the contents of the two pieces of information]The numerical values between the above indicate the ratio of the forgotten contents. The next step is to determine how the newly entered information is added to the cell state, which includes two aspects, first, the "input gate" itDetermining a method for updating the input value; secondly, candidate vector value C is calculated by utilizing tanh functiontRespectively expressed as:
it＝σ(Wi[ht-1,xt]+bi)
Ct＝tanh(WC[ht-1,xt]+bc)
wherein, Wi,biAnd WC,bcRespectively representing the weight matrix and the Bayes vector when inputting the gate and calculating the candidate vector value.
Based on the previous steps, the state of the cells at time t is represented by Ct-1Is updated to CtExpressed as:
Ct＝ft*Ct-1+it*Ct
output gate otThe result used to compute each hidden layer output can be expressed as:
ot＝σ(Wo[ht-1,xt]+bo)
wherein, WoAnd boRespectively representing the weight matrix and the Bayes vector of the output gate.
The output result is determined by the output gate and the cell state of the current hidden layer together:
ht＝ot*tanh(Ct)
further, training the long-term and short-term memory network, updating the weight matrix W and the Bayes variable b, starting to update the network weight by error back transmission if the output result of the output layer is different from the target result in the training process, and updating the weight of each hidden layer by a gradient descent method:
W＝W-η▽Ep(W)
where, η represents the step size of the update,
when a sample p is input, the output deviation is the partial derivative of a certain hidden layer weight, namely, the weight is updated every time a new sample is input. And in the training process, the weight value is continuously adjusted until the error is reduced to an acceptable degree.
Step 103: according to the flow load condition, aiming at minimizing the total energy consumption of the system, dynamically adjusting the connection relation of a fronthaul optical link between a baseband processing pool of a next time node and a remote radio frequency node; the minimum system total energy consumption comprises the inherent energy consumption of a baseband processing pool, the energy consumption generated in the process of executing baseband signal processing by the baseband processing pool and the energy consumption generated by switching; the energy consumption generated by the switching comprises the energy consumption generated by switching the baseband processing units in the baseband processing pool between an activated state and a closed state and the energy consumption generated by switching the remote radio frequency node in different baseband processing units.
The energy consumption generated in the process of executing baseband signal processing by the baseband processing pool is generated by fully utilizing the resource of each activated baseband processing unit through the number of the baseband processing units in the activated state in the baseband processing pool.
The energy consumption generated by the switching is the energy consumption generated by switching the baseband processing unit in the baseband processing pool between the activated state and the closed state and the energy consumption generated by switching the remote radio frequency node in different baseband processing units.
The invention can be explained as a boxing problem, the boxes represent baseband processing units, the volume of each box is the maximum flow load which can be borne by each baseband processing unit, the size of each article is the load condition of each remote radio frequency node at the current moment, the size of each article changes along with time, and the boxing operation represents the adjustment of the connection relation between the baseband processing units and the remote radio frequency nodes.
Compared with the classical boxing problem, the problem of dynamic resource mapping between the baseband processing unit and the remote radio frequency node, which needs to be solved by the invention, is to generate switching energy consumption as less as possible, thereby minimizing the energy consumption of the whole system. If a common approximate algorithm for solving the boxing problem is directly adopted to solve the problem, namely a First-time-reduction (FFD) algorithm is used to determine which baseband processing units are activated and deactivated without considering the connection condition between the baseband processing unit of the previous time node and the far-end radio frequency node, excessive extra energy consumption may be generated due to too frequent switching. Therefore, the invention provides a descending order first-time adaptive resource mapping algorithm (MS-FFD) based on Minimum switching number (MS) based on the thought of the descending order first-time adaptive algorithm.
Referring to fig. 3, fig. 3 is a schematic flow chart of a descending order first-time adaptive resource mapping algorithm based on a minimum switching number in the energy efficiency optimization-based dynamic resource mapping method of the fronthaul optical network provided by the present invention, and the specific steps are as follows:
s301, according to the flow prediction results of the remote radio frequency nodes, the flow loads of all the remote radio frequency nodes are arranged in a descending order according to the numerical values.
S302, taking out the execution boxing operation with the maximum flow load in the unplanned remote radio frequency node.
S303, determining whether the baseband processing unit connected to the previous time node and the remote rf node is in an active state, if so, executing step 304. If not, go to step 306.
S304, determining whether the baseband processing unit selected in S303 has enough bandwidth resources to process the load traffic of the current remote rf node, if yes, performing step S305, and if no, performing step 306.
And S305, maintaining the connection relationship between the baseband processing unit selected in the S303 and the far-end radio frequency node extracted in the S302.
S306, traversing other activated baseband processing units, and determining whether there is enough bandwidth resource to process the bandwidth resource of the remote rf node extracted in S302, if yes, executing step S307, and if not, executing step S308.
And S307, connecting the baseband processing unit with enough bandwidth resources encountered for the first time with the remote radio frequency node in the traversal process.
And S308, starting a new baseband processing unit, and connecting the new baseband processing unit with the remote radio frequency node extracted in the S302.
And S309, updating the working states and the load conditions of all the baseband processing units.
The invention relates to a fronthaul optical network dynamic resource mapping method based on energy efficiency optimization, which can greatly reduce the energy consumption in a baseband processing pool and improve the utilization rate of baseband resources in the fronthaul optical network by adopting an active fronthaul optical network resource dynamic adjustment mode. In addition, a long-short term memory network in deep learning is introduced into a resource mapping process of a 5G-oriented fronthaul optical network, and reference and ideas are provided for the application of future artificial intelligence technology in the industrialization of a cloud wireless access network.
Correspondingly, the invention also provides a fronthaul optical network dynamic resource mapping system based on energy efficiency optimization, which can realize all the processes of the fronthaul optical network dynamic resource mapping method based on energy efficiency optimization.
Fig. 4 is a structural diagram of a dynamic resource mapping system of a fronthaul optical network based on energy efficiency optimization, and as shown in fig. 4, a dynamic resource mapping system of a fronthaul optical network based on energy efficiency optimization includes:
a historical traffic data collection module 401, configured to collect historical traffic data of a remote radio frequency node; the data types of the historical flow data comprise received and sent telephone service, short message service and Internet service; the historical traffic data characterizes true traffic load conditions of a plurality of historical time nodes.
A traffic load condition prediction module 402, configured to train a long-term and short-term memory network model in deep learning according to the historical traffic data, and predict a traffic load condition of a next time node of each remote radio frequency node.
A dynamic adjustment module 403, configured to dynamically adjust a connection relationship of a fronthaul optical link between a baseband processing pool of a next time node and a remote radio frequency node, with a goal of minimizing total system energy consumption according to the traffic load condition; the minimum system total energy consumption comprises the inherent energy consumption of a baseband processing pool, the energy consumption generated in the process of executing baseband signal processing by the baseband processing pool and the energy consumption generated by switching; the energy consumption generated by the switching comprises the energy consumption generated by switching the baseband processing units in the baseband processing pool between an activated state and a closed state and the energy consumption generated by switching the remote radio frequency node in different baseband processing units.
The invention also includes: the preprocessing module is used for preprocessing the historical flow data to generate preprocessed historical flow data; the preprocessing comprises data normalization processing and data dimension increasing processing.
The traffic load condition predicting module 402 specifically includes: the training unit is used for training the long-term and short-term memory network model by taking the real traffic load condition of a plurality of historical time nodes of each far-end radio frequency node as input and taking the traffic load condition of the next time node as output; the trained long and short term memory network model construction unit is used for comparing a predicted value corresponding to the predicted flow load condition with a real value corresponding to the real flow load condition in each iteration process, and adjusting the weight of the long and short term memory network model according to the error between the predicted value and the real value until the error requirement of training is met, so as to finish the trained long and short term memory network model; and the traffic load condition prediction unit is used for predicting the traffic load condition of the next time node of each far-end radio frequency node by using the trained long and short term memory network model.
The energy efficiency optimization-based dynamic resource mapping system of the fronthaul optical network can collect long-time historical flow data of the remote radio frequency node, train the long-term and short-term memory network by using the historical flow data, obtain the flow prediction result of the next time node by using the trained model, and further dynamically adjust the connection relation between the baseband processing unit and the remote radio frequency node in the fronthaul optical network, thereby realizing more efficient resource allocation, reducing the energy consumption of the whole system, improving the resource utilization rate of the fronthaul optical network and meeting the access requirements of mass users.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (10)
1. A method for mapping dynamic resources of a fronthaul optical network based on energy efficiency optimization is characterized by comprising the following steps:
collecting historical flow data of a remote radio frequency node; the data types of the historical flow data comprise received and sent telephone service, short message service and Internet service; the historical traffic data represents the real traffic load conditions of a plurality of historical time nodes;
training a long-term and short-term memory network model in deep learning according to the historical traffic data, and predicting the traffic load condition of the next time node of each far-end radio frequency node;
according to the flow load condition, aiming at minimizing the total energy consumption of the system, dynamically adjusting the connection relation of a fronthaul optical link between a baseband processing pool of a next time node and a remote radio frequency node; the total energy consumption of the system comprises the inherent energy consumption of a baseband processing pool, the energy consumption generated in the process of executing baseband signal processing by the baseband processing pool and the energy consumption generated by switching; the energy consumption generated by the switching comprises the energy consumption generated by switching the baseband processing units in the baseband processing pool between an activated state and a closed state and the energy consumption generated by switching the remote radio frequency node in different baseband processing units.
2. The energy-efficiency optimization-based dynamic resource mapping method for the fronthaul optical network according to claim 1, wherein the collecting historical traffic data of the remote radio frequency node further comprises:
preprocessing the historical flow data to generate preprocessed historical flow data; the preprocessing comprises data normalization processing and data dimension increasing processing.
3. The energy efficiency optimization-based dynamic resource mapping method for the fronthaul optical network according to claim 1, wherein the training of a deep-learning long-short term memory network model according to the historical traffic data to predict the traffic load condition of the next time node of each remote radio frequency node specifically comprises:
training the long-short term memory network model by taking the real traffic load condition of a plurality of historical time nodes of each far-end radio frequency node as input and taking the traffic load condition of the next time node as output;
in each iteration process, comparing a predicted value corresponding to the predicted flow load condition with a real value corresponding to the real flow load condition, and adjusting the weight of the long-short term memory network model according to the error between the predicted value and the real value until the error requirement of training is met, thereby completing the trained long-short term memory network model;
and predicting the traffic load condition of the next time node of each remote radio frequency node by using the trained long-term and short-term memory network model.
4. The energy-efficiency-optimization-based dynamic resource mapping method for the fronthaul optical network according to claim 1, wherein the energy consumption generated during the baseband processing pool performing baseband signal processing is generated by fully utilizing the resources of each activated baseband processing unit according to the number of activated baseband processing units in the baseband processing pool.
5. The energy-efficiency-optimization-based dynamic resource mapping method for the fronthaul optical network according to claim 1, wherein the energy consumption generated by the switching is energy consumption generated by switching the baseband processing units in the baseband processing pool between an active state and a closed state and energy consumption generated by switching the remote radio frequency node in different baseband processing units.
6. The energy-efficiency-optimization-based dynamic resource mapping method for the fronthaul optical network according to any one of claims 1 to 5, wherein the dynamic adjustment method is regarded as a binning problem by dynamically adjusting the connection relationship of the fronthaul optical link between the baseband processing pool of the next time node and the remote radio frequency node with the goal of minimizing the total energy consumption of the system according to the traffic load condition; the boxes represent the baseband processing units, the volume of each box is the maximum flow load which can be borne by each baseband processing unit, the size of each article is the load condition of each remote radio frequency node at the current moment, the size of each article changes along with time, and the boxing operation is to adjust the connection relation between the baseband processing units and the remote radio frequency nodes.
7. The energy efficiency optimization-based dynamic resource mapping method for the fronthaul optical network according to claim 6, wherein the binning problem is solved by using a descending order first-time adaptive resource mapping algorithm based on a minimum switching number;
the step of the descending order first-time adaptive resource mapping algorithm based on the minimum switching number comprises the following steps:
according to the traffic load condition of the current remote radio frequency node, performing descending arrangement on the traffic load conditions of all the remote radio frequency nodes according to traffic load numerical values;
selecting the execution boxing operation with the maximum flow load in the unplanned remote radio frequency node;
judging whether a baseband processing unit connected with a last time node and the current far-end radio frequency node is in an activated state or not to obtain a first judgment result;
if the first judgment result is yes, judging whether the selected baseband processing unit has enough bandwidth resources to process the load flow of the current remote radio frequency node or not, and obtaining a second judgment result;
if the second judgment result is yes, maintaining the connection relationship between the selected baseband processing unit and the taken-out remote radio frequency node;
if the second judgment result is negative, traversing the rest activated baseband processing units, and judging whether enough bandwidth resources exist for processing the bandwidth resources of the taken-out remote radio frequency node to obtain a third judgment result;
if the third judgment result is yes, connecting the baseband processing unit with enough bandwidth resources encountered for the first time with the current remote radio frequency node in the traversal process;
if the third judgment result is negative, starting a new baseband processing unit, and connecting the new baseband processing unit with the taken-out remote radio frequency node;
if the first judgment result is negative, executing a third judgment process; the third judgment process is to traverse the rest activated baseband processing units and judge whether enough bandwidth resources exist to process the bandwidth resources of the taken-out remote radio frequency node to obtain a third judgment result;
and updating the working states and the load conditions of all the baseband processing units.
8. A fronthaul optical network dynamic resource mapping system based on energy efficiency optimization is characterized by comprising the following components:
the historical flow data collection module is used for collecting the historical flow data of the remote radio frequency node; the data types of the historical flow data comprise received and sent telephone service, short message service and Internet service; the historical traffic data represents the real traffic load conditions of a plurality of historical time nodes;
the traffic load condition prediction module is used for training a long-short term memory network model in deep learning according to the historical traffic data and predicting the traffic load condition of a next time node of each far-end radio frequency node;
the dynamic adjustment module is used for dynamically adjusting the connection relation of a fronthaul optical link between a baseband processing pool of a next time node and a remote radio frequency node according to the flow load condition by taking the minimization of the total energy consumption of the system as a target; the minimum system total energy consumption comprises the inherent energy consumption of a baseband processing pool, the energy consumption generated in the process of executing baseband signal processing by the baseband processing pool and the energy consumption generated by switching; the energy consumption generated by the switching comprises the energy consumption generated by switching the baseband processing units in the baseband processing pool between an activated state and a closed state and the energy consumption generated by switching the remote radio frequency node in different baseband processing units.
9. The energy-efficient optimization-based dynamic resource mapping system for a fronthaul optical network according to claim 8, further comprising:
the preprocessing module is used for preprocessing the historical flow data to generate preprocessed historical flow data; the preprocessing comprises data normalization processing and data dimension increasing processing.
10. The energy-efficiency-optimization-based dynamic resource mapping system for the fronthaul optical network according to claim 8, wherein the traffic load condition prediction module specifically comprises:
the training unit is used for training the long-term and short-term memory network model by taking the real traffic load condition of a plurality of historical time nodes of each far-end radio frequency node as input and taking the traffic load condition of the next time node as output;
the trained long and short term memory network model construction unit is used for comparing a predicted value corresponding to the predicted flow load condition with a real value corresponding to the real flow load condition in each iteration process, and adjusting the weight of the long and short term memory network model according to the error between the predicted value and the real value until the error requirement of training is met, so as to finish the trained long and short term memory network model;
and the traffic load condition prediction unit is used for predicting the traffic load condition of the next time node of each far-end radio frequency node by using the trained long and short term memory network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111444691.0A CN114126019B (en) | 2021-11-30 | 2021-11-30 | Energy efficiency optimization-based dynamic resource mapping method and system for forward optical network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111444691.0A CN114126019B (en) | 2021-11-30 | 2021-11-30 | Energy efficiency optimization-based dynamic resource mapping method and system for forward optical network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114126019A true CN114126019A (en) | 2022-03-01 |
| CN114126019B CN114126019B (en) | 2024-04-23 |
Family
ID=80368721
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111444691.0A Active CN114126019B (en) | 2021-11-30 | 2021-11-30 | Energy efficiency optimization-based dynamic resource mapping method and system for forward optical network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114126019B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116390165A (en) * | 2023-03-09 | 2023-07-04 | 中南大学 | Dynamic management method and system for data-driven cellular base station |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103945548A (en) * | 2014-04-29 | 2014-07-23 | 西安电子科技大学 | Resource distribution system and task/service scheduling method in C-RAN |
| CN105050170A (en) * | 2015-06-30 | 2015-11-11 | 东南大学 | Base station dormancy method based on flow prediction in heterogeneous network |
| US20160219602A1 (en) * | 2013-09-26 | 2016-07-28 | Nec Corporation | Radio base station apparatus and resource allocation method |
| CN106374996A (en) * | 2016-08-29 | 2017-02-01 | 北京邮电大学 | Optical network fault handling method and apparatus |
| CN106793045A (en) * | 2017-03-01 | 2017-05-31 | 安徽工程大学 | Cloud wirelessly networking system and its Energy dissipation method |
| US20170237495A1 (en) * | 2016-02-15 | 2017-08-17 | Hfr, Inc. | Method and system for compensating for latency difference due to switchover in fronthaul in ring topology form |
| US20180138957A1 (en) * | 2015-12-21 | 2018-05-17 | Huawei Technologies Co., Ltd. | Data transmission method, remote radio unit rru, and baseband unit bbu |
| WO2018093301A1 (en) * | 2016-11-16 | 2018-05-24 | Telefonaktiebolaget Lm Ericsson (Publ) | Methods and devices for adapting load on a fronthaul network |
| WO2018113797A1 (en) * | 2016-12-23 | 2018-06-28 | 中国移动通信有限公司研究院 | Front-haul transport network, data transmission method, apparatus and computer storage medium |
| CN109639470A (en) * | 2018-11-30 | 2019-04-16 | 四川安迪科技实业有限公司 | VSAT satellite communication system bandwidth distribution method based on star-like networking |
| CN109831808A (en) * | 2019-02-25 | 2019-05-31 | 重庆邮电大学 | A kind of resource allocation methods of the hybrid power supply C-RAN based on machine learning |
| WO2019137513A1 (en) * | 2018-01-15 | 2019-07-18 | Huawei Technologies Co., Ltd. | Method and apparatus for front-haul network dependent wireless network control |
| CN110839184A (en) * | 2019-10-15 | 2020-02-25 | 北京邮电大学 | Method and device for adjusting bandwidth of mobile fronthaul optical network based on flow prediction |
| CN110915251A (en) * | 2017-06-30 | 2020-03-24 | 意大利电信股份公司 | Forward-flow congestion control in mobile communication network |
| US20200137201A1 (en) * | 2018-10-31 | 2020-04-30 | At&T Intellectual Property I, L.P. | Adaptive fixed point mapping for uplink and downlink fronthaul |
| CN111586502A (en) * | 2020-03-26 | 2020-08-25 | 北京邮电大学 | Resource allocation method and system in elastic optical network |
| WO2020206705A1 (en) * | 2019-04-10 | 2020-10-15 | 山东科技大学 | Cluster node load state prediction-based job scheduling method |
| WO2020248574A1 (en) * | 2019-06-12 | 2020-12-17 | 苏州大学 | Energy consumption optimization method and system for wireless access spectrum flexible optical network |
| CN112584386A (en) * | 2020-11-17 | 2021-03-30 | 国网安徽省电力有限公司信息通信分公司 | 5G C-RAN resource prediction and allocation method and system |
| US20210133569A1 (en) * | 2019-11-04 | 2021-05-06 | Tsinghua University | Methods, computing devices, and storage media for predicting traffic matrix |
-
2021
- 2021-11-30 CN CN202111444691.0A patent/CN114126019B/en active Active
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160219602A1 (en) * | 2013-09-26 | 2016-07-28 | Nec Corporation | Radio base station apparatus and resource allocation method |
| CN103945548A (en) * | 2014-04-29 | 2014-07-23 | 西安电子科技大学 | Resource distribution system and task/service scheduling method in C-RAN |
| CN105050170A (en) * | 2015-06-30 | 2015-11-11 | 东南大学 | Base station dormancy method based on flow prediction in heterogeneous network |
| US20180138957A1 (en) * | 2015-12-21 | 2018-05-17 | Huawei Technologies Co., Ltd. | Data transmission method, remote radio unit rru, and baseband unit bbu |
| US20170237495A1 (en) * | 2016-02-15 | 2017-08-17 | Hfr, Inc. | Method and system for compensating for latency difference due to switchover in fronthaul in ring topology form |
| CN106374996A (en) * | 2016-08-29 | 2017-02-01 | 北京邮电大学 | Optical network fault handling method and apparatus |
| WO2018093301A1 (en) * | 2016-11-16 | 2018-05-24 | Telefonaktiebolaget Lm Ericsson (Publ) | Methods and devices for adapting load on a fronthaul network |
| WO2018113797A1 (en) * | 2016-12-23 | 2018-06-28 | 中国移动通信有限公司研究院 | Front-haul transport network, data transmission method, apparatus and computer storage medium |
| CN106793045A (en) * | 2017-03-01 | 2017-05-31 | 安徽工程大学 | Cloud wirelessly networking system and its Energy dissipation method |
| CN110915251A (en) * | 2017-06-30 | 2020-03-24 | 意大利电信股份公司 | Forward-flow congestion control in mobile communication network |
| WO2019137513A1 (en) * | 2018-01-15 | 2019-07-18 | Huawei Technologies Co., Ltd. | Method and apparatus for front-haul network dependent wireless network control |
| US20200137201A1 (en) * | 2018-10-31 | 2020-04-30 | At&T Intellectual Property I, L.P. | Adaptive fixed point mapping for uplink and downlink fronthaul |
| CN109639470A (en) * | 2018-11-30 | 2019-04-16 | 四川安迪科技实业有限公司 | VSAT satellite communication system bandwidth distribution method based on star-like networking |
| CN109831808A (en) * | 2019-02-25 | 2019-05-31 | 重庆邮电大学 | A kind of resource allocation methods of the hybrid power supply C-RAN based on machine learning |
| WO2020206705A1 (en) * | 2019-04-10 | 2020-10-15 | 山东科技大学 | Cluster node load state prediction-based job scheduling method |
| WO2020248574A1 (en) * | 2019-06-12 | 2020-12-17 | 苏州大学 | Energy consumption optimization method and system for wireless access spectrum flexible optical network |
| CN110839184A (en) * | 2019-10-15 | 2020-02-25 | 北京邮电大学 | Method and device for adjusting bandwidth of mobile fronthaul optical network based on flow prediction |
| US20210133569A1 (en) * | 2019-11-04 | 2021-05-06 | Tsinghua University | Methods, computing devices, and storage media for predicting traffic matrix |
| CN111586502A (en) * | 2020-03-26 | 2020-08-25 | 北京邮电大学 | Resource allocation method and system in elastic optical network |
| CN112584386A (en) * | 2020-11-17 | 2021-03-30 | 国网安徽省电力有限公司信息通信分公司 | 5G C-RAN resource prediction and allocation method and system |
Non-Patent Citations (6)
| Title |
|---|
| BO TIAN; QI ZHANG; XIANGJUN XIN; QINGHUA TIAN; XIANGYU WU; YING TAO; YUFEI SHEN; GUIXING CAO; NAIJIN LIU: "Recursive_Neural_Network_Based_RRH_to_BBU_Resource_Allocation_in_5G_Fronthaul_Network", RECURSIVE_NEURAL_NETWORK_BASED_RRH_TO_BBU_RESOURCE_ALLOCATION_IN_5G_FRONTHAUL_NETWORK * |
| FU WANG; HAIPENG YAO; QI ZHANG; JINGJING WANG; RAN GAO; DONG GUO; MOHSEN GUIZANI: "Dynamic Distributed Multi-Path Aided Load Balancing for Optical Data Center Networks", IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT * |
| 及睿，忻向军，张琦: "光通信中的新型复用形式", 新型工业化, no. 08 * |
| 李隆胜;毕美华;胡卫生;: "云化移动接入网中前传链路负载自适应技术", 聊城大学学报(自然科学版), no. 02 * |
| 纪越峰;张佳玮;: "5G前传光网络:关键问题、重要特征与发展目标", 中国科学:信息科学, no. 10 * |
| 龙恳;胡渝纺;: "一种基于C-RAN架构下资源负载预测方法", 科学技术与工程, no. 33 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116390165A (en) * | 2023-03-09 | 2023-07-04 | 中南大学 | Dynamic management method and system for data-driven cellular base station |
| CN116390165B (en) * | 2023-03-09 | 2023-11-14 | 中南大学 | Dynamic management method and system for data-driven cellular base station |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114126019B (en) | 2024-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109447275B (en) | Switching method based on machine learning in UDN | |
| CN111988796B (en) | Dual-mode communication-based system and method for optimizing platform information acquisition service bandwidth | |
| CN111641681A (en) | Internet of things service unloading decision method based on edge calculation and deep reinforcement learning | |
| Hu et al. | Edge intelligence for real-time data analytics in an IoT-based smart metering system | |
| CN106793031A (en) | Based on the smart mobile phone energy consumption optimization method for gathering competing excellent algorithm | |
| Gao et al. | Accurate load prediction algorithms assisted with machine learning for network traffic | |
| CN114885388B (en) | Multi-service type self-adaptive switching judgment method combining RSS prediction | |
| CN114126019B (en) | Energy efficiency optimization-based dynamic resource mapping method and system for forward optical network | |
| CN115622603A (en) | Age minimization optimization method for auxiliary transmission information | |
| Yi et al. | DMADRL: A distributed multi-agent deep reinforcement learning algorithm for cognitive offloading in dynamic MEC networks | |
| Yang et al. | A scheme of terminal mobility prediction of ultra dense network based on SVM | |
| Zhang et al. | Edge computing resource allocation method for mining 5G communication system | |
| Tan et al. | Uav control in smart city based on space-air-ground integrated network | |
| CN106954268A (en) | Access network resource distribution method under a kind of SDN frameworks | |
| CN116488344A (en) | Dynamic resource scheduling method for measurement data of multi-type power grid equipment | |
| Lu et al. | Distributed task offloading for large-scale vec systems: A multi-agent deep reinforcement learning method | |
| He et al. | Traffic Processing Model of Big Data Base Station Based on Hybrid Improved CNN Algorithm and K-Centroids Clustering Algorithm | |
| Shao | Based on Two Swarm Optimized Algorithm of Neural Network to Prediction the Switch's Traffic of Coal | |
| Peng et al. | Edge-cloud collaborative computation offloading for federated learning in smart city | |
| Yu et al. | Research on dynamic spectrum allocation algorithm based on cyclic neural network | |
| Huang et al. | Research on Application of Computer Big Data Technology in 5G Communication Network | |
| Zhang et al. | Cellular traffic forecasting based on inverted transformer for mobile perception dual-level base station sleep control | |
| Zhong et al. | Traffic prediction of converged network for smart gird based on GNN and LSTM | |
| CN117580107B (en) | GNN base station association method and system for green wireless mesh network traffic field | |
| Yang et al. | Traffic-Aware Transmission Strategy of Fog Cell in Green Industrial Internet |
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 |