CN114816584B - Optimal carbon emission calculation unloading method and system for multi-energy supply edge system - Google Patents
Optimal carbon emission calculation unloading method and system for multi-energy supply edge system Download PDFInfo
- Publication number
- CN114816584B CN114816584B CN202210654463.4A CN202210654463A CN114816584B CN 114816584 B CN114816584 B CN 114816584B CN 202210654463 A CN202210654463 A CN 202210654463A CN 114816584 B CN114816584 B CN 114816584B
- Authority
- CN
- China
- Prior art keywords
- node
- unloading
- computing
- candidate
- task
- 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.)
- Active
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
- G06F9/44—Arrangements for executing specific programs
- G06F9/445—Program loading or initiating
- G06F9/44594—Unloading
-
- 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
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/502—Proximity
Abstract
The invention provides an optimal carbon emission calculation unloading method and system for a multi-energy supply edge system, wherein the method comprises the following steps: s1, collecting and updating the state parameters of all the computing nodes when each preset time slice starts; s2, polling whether the terminal equipment of the Internet of things has unloading requirements; s3 screening out a candidate unloading computing node set M according to the task data; s4 traversing the candidate unloading calculation node set M to calculate each candidate nodexWhen the calculation task is completed, the candidate nodexWith local computing nodesjTotal gain that can be achievedG(ii) a S5, selecting a computing node which enables the total profit to be maximum from the candidate set M as an unloading node; s6 sends the offload task to the corresponding offload node. According to the invention, by considering the influence of different energy supplies on the carbon emission of the edge computing system and cooperatively utilizing the difference of the carbon emission rates of the edge computing nodes with dispersed geographic positions, a simple and effective computing and unloading method is designed, so that the tasks are reasonably unloaded.
Description
Technical Field
The invention relates to the technical field of edge calculation, in particular to an optimal carbon emission calculation unloading method and system for a multi-energy supply edge system.
Background
With the rapid development of the internet of things, various computing-intensive applications need to be operated on terminals of the internet of things. However, the performance requirements of the applications are difficult to meet due to the shortness and weakness of the performance of the terminal of the internet of things. The computing offloading technology becomes one of effective solutions for solving the above problems, and by transmitting tasks related to the computing to an edge computing node near a terminal side of the internet of things, the terminal is helped to complete a complicated computing process, so that the problem that the terminal resource is limited is effectively solved.
However, conventional edge computing systems consume large amounts of fossil fuel-powered electrical energy when handling various types of computing tasks. With the increasingly prominent energy problems and global warming problems, sustainable low-carbon development is realized to serve as a global co-fighting target, and the energy supply mode is not adapted to the current low-carbon and environment-friendly development concept. The multi-energy-supply edge system is produced at the same time, and various clean energy sources such as solar energy, wind energy, natural gas and the like are introduced into the energy supply link of the edge system, so that the carbon emission can be effectively reduced, and the low-carbon benefit is remarkable.
From the spatial aspect, the multi-energy supply edge system can be divided into a cross-region multi-energy supply edge system and a regional multi-energy supply system. A trans-regional multi-energy supply system refers to the arrangement of edge computing nodes in areas of different geographical locations, each area being powered by multiple types of energy sources, such as: edge computing system for the entire city. The multi-energy supply edge system in the region refers to that edge computing nodes are arranged in a relatively small region, and various types of energy sources are coupled with each other to supply energy to the nodes, for example: an edge computing system within a community. In general, different edge computing systems may be deployed and operated by different operators.
Most of the current existing calculation unloading methods aim at energy consumption optimization, and the carbon emission constraint is less considered, so that the carbon emission is higher when the method is applied to a multi-energy supply edge system. Because minimizing energy consumption and carbon emissions is a more complex problem in multi-energy-supply edge systems, the differences in carbon emissions from different types of energy sources are large, and therefore may result in different carbon emissions even if the same energy source is consumed. As more and more countries start imposing carbon emission taxes (i.e. carbon taxes) and this tax will continue to increase in the coming years, it is essential for operators who possess a large number of edge nodes to mitigate the carbon taxes. Furthermore, the potential for reducing carbon emissions for geographically dispersed edge computing nodes has not been fully explored. The possibility of mutual cooperation exists between different edge computing nodes, and the difficulty exists in that different operators are likely not willing to participate in an unprofitable edge cooperation system. Therefore, how to design a reasonable calculation unloading method and a carbon trading strategy, cooperatively utilize edge calculation nodes with dispersed geographic positions, comprehensively consider different energy types and carbon emission rates, and reasonably allocate calculation tasks to realize optimal carbon emission is very important.
Disclosure of Invention
The invention aims to provide an optimal carbon emission calculation unloading method and system of a multi-energy supply edge system aiming at the defects of the prior art, which are used for filling or at least partially filling the technical problem that the carbon emission is higher due to the fact that multi-energy supply is not considered in the method in the prior art.
In order to achieve the above purpose, the invention provides a method for calculating and unloading optimal carbon emissions of a multi-energy supply edge system, which is characterized in that the method comprises the following steps:
s1 collects and updates the state parameters of all the compute nodes at the beginning of each preset time slice, including: calculating the residual amount of resources, the average running frequency of a CPU, various energy supply types, the proportion of each type of energy supply, the energy price, the carbon transaction price and the carbon emission quota amount;
s2, polling the terminal equipment of the Internet of things whether the unloading requirement exists: when connected to a local compute nodejOf an arbitrary terminaliWhen the unloading task is required, the unloading task data is collected, and the size of a task data packet is calculatedb i Maximum tolerated delayt i Type of computing resource requiredr i And resource sizes i ；
S3 screening out a candidate unloading computing node set M according to the task data;
s4 traversing the candidate unloading calculation node set M to calculate each candidate nodexWhen the calculation task is completed, the candidate nodexWith local computing nodesjTotal gain that can be achievedG；
S5, selecting the computing node which enables the total profit to be maximum from the candidate set M as an unloading node;
s6 sends the unloading task to the corresponding unloading node, and when the time slice is finished, the step returns to S1.
Preferably, each selected candidate computing node in step S3x，xE.g., M, satisfying the following three constraints:
1. candidate computing nodexSatisfies the resource type requirements of the task, i.e.r i ∈R x WhereinR x Representing a compute nodexComputing a set of resource types;
2. candidate computing nodexThe remaining amount of computing resources of (a) meets the resource size requirement of the task, i.e.s i ≤S x In whichS x Representing a compute nodexCalculating the residual quantity of resources;
3. candidate computing nodexIs at a distance that satisfies the maximum tolerated delay of the task, i.e.t i ≥T x In whichT x Representing task offloading to compute nodesxThe total time required to complete the task calculation and return the results.
Preferably, tasks are offloaded to compute nodesxThe total time required for completing the task calculation and returning the resultT x The method comprises the following steps:
T x =0.5*δ+0.1*Distance ix
wherein the content of the first and second substances,δrepresenting the network bandwidth characteristics, Distance, of the compute node ix Presentation terminaliAnd candidate computing nodexThe distance of (c).
Preferably, the terminaliAnd candidate computing nodexDistance of (3) ix The calculation method comprises the following steps:
Distance ix =R*cos -1 [sin(Mlat i )* sin(Mlat x )* cos(Mlon i - Mlon x )+
cos (Mlat i )* cos (Mlat x )*π÷180
wherein the content of the first and second substances,Rthe mean radius of the earth is represented, and pi is represented as a circumferential rate;Mlat i 、Mlat x respectively representing terminalsi、xIs calculated by the calculating unit (2) of (c),Mlon i 、Mlon x respectively representing terminalsi、xThe calculated longitude value of (1).
Preferably, the total profit in step S4GThe calculation method is obtained by the following formula:
G=αGx+βGj
wherein the content of the first and second substances,G x representing candidate nodesxThe gain of the gain to be obtained is,G j representing local compute nodesjα, β are control coefficients for adjusting the weight of each benefit.
Preferably, the local computing nodejGain of (2)G j Is obtained by the following formula:
G j =u i -γT x -C x total
wherein the content of the first and second substances,u i to complete the terminal equipmentiThe fixed yield of the task of (a),γis a weight parameter.
Preferably, earnings are capturedG x Is given by the following formula:
G x = C x total - C x engergy - C x trade
wherein the content of the first and second substances,C x total expressed as local computing node needs to pay each candidate nodexThe monetary cost of completing the computing task is,C x engergy computing node for executing tasksxThe energy consumption cost of (2) is low,C x trade to compute a nodexThe carbon transaction fee.
Preferably, the local computing node needs to pay each candidate nodexMonetary cost of completing computing taskC x total The calculation formula of (a) is as follows:
C x total = C x engergy +C x carbon
wherein, the first and the second end of the pipe are connected with each other, C x carbon representing a compute nodexCarbon emission cost of (a);C x engergy 、C x carbon the calculation formula of (a) is as follows:
C x engergy =e x *P x engergy
C x carbon =e x *K x * P x carbon
wherein, the first and the second end of the pipe are connected with each other,e x representing candidate nodesxEnergy consumption required for processing tasks;P x engergy represents the comprehensive price of various energy sources;K x representing candidate nodesxCarbon emission coefficient of (a);P x carbon represents the carbon trading price, which is typically determined by the market.
The invention provides a computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the optimal carbon emission calculation unloading method for the multi-energy supply edge system.
The invention also provides an optimal carbon emission calculation unloading system of the multi-energy supply edge system, which comprises a data acquisition module, a communication module, a target scheduling module and an unloading scheduling module;
the data acquisition module is configured to collect and update state parameters of all the computing nodes when each preset time slice starts, and includes: calculating the residual amount of resources, the average running frequency of a CPU, various energy supply types, the proportion of each type of energy supply, the energy price, the carbon transaction price and the carbon emission quota amount;
the communication module is used for polling the terminal equipment of the Internet of things whether to have an unloading requirement, acquiring unloading task data when any terminal connected to a local computing node has the requirement of unloading a task, computing the size of a task data packet, the maximum tolerance time delay, the type of required computing resources and the size of resources, and sending the data to the target scheduling module;
the target scheduling module is used for screening out candidate unloading computing nodes;
the unloading scheduling module is used for calculating the total benefit values of the candidate unloading computing nodes and the local computing nodes, selecting the computing node with the maximum total benefit as the unloading node, informing the communication module, and sending corresponding unloading node information to the terminal equipment.
Compared with the prior art, the invention has the following advantages:
1) the optimal carbon emission calculation unloading method and the optimal carbon emission calculation unloading system for the multi-energy supply edge system have the advantages that the calculation unloading method is small in calculation amount, low in calculation complexity, easy to realize and high in practicability;
2) according to the invention, the influence of different energy supplies on the carbon emission of the edge computing system is considered, and the difference of the carbon emission rates of the edge computing nodes with dispersed geographic positions is cooperatively utilized to design a simple and effective calculation unloading method, so that tasks are reasonably unloaded;
3) the invention effectively reduces the carbon emission of the edge system and reduces the cost of operators under the condition of ensuring that the tasks meet the delay constraint. The method has very important practical significance under the background that the current climate change problem is increasingly serious.
Drawings
Fig. 1 is a flowchart of an optimal carbon emission calculation unloading method of a multi-energy supply edge system according to an embodiment of the present invention.
Fig. 2 is a structural diagram of an optimal carbon emission calculation unloading system of a multi-energy supply edge system according to a second embodiment of the present invention.
Fig. 3 is a schematic diagram 1 illustrating data results comparing the method (Our) of the present invention with existing methods (e.g., reinforcement learning Q-learning, Random algorithm, and Greedy algorithm).
FIG. 4 is a schematic diagram 2 showing data results comparing the method (Our) of the present invention with conventional methods (reinforcement learning Q-learning, Random algorithm, and Greedy algorithm).
FIG. 5 is a schematic diagram 3 of data results comparing the method of the present invention (Our) with prior methods (reinforcement learning Q-learning, Random algorithm, and Greedy algorithm).
FIG. 6 is a schematic diagram 4 showing data results comparing the method (Our) of the present invention with conventional methods (reinforcement learning Q-learning, Random algorithm, and Greedy algorithm).
Detailed Description
In order to make the technical problems, technical solutions and advantages of the present invention more apparent, the following detailed description is given with reference to the accompanying drawings and specific examples, but the following examples are only illustrative, and the scope of the present invention is not limited by these examples.
Example one
The embodiment provides an optimal carbon emission calculation unloading method for a multi-energy supply edge system, as shown in fig. 1, the method includes the following steps:
s1: collecting and updating state parameters of all the computing nodes at the beginning of each preset time slice, wherein the state parameters comprise: the method comprises the following steps of calculating the surplus of various computing resources, the average running frequency of a CPU, various energy supply types, the proportion of each type of energy supply, the energy price, the carbon transaction price and the carbon emission quota consumption.
Specifically, the preset time slice value may be set according to actual conditions, such as 100ms, 1s, and the like. The computing node related to the invention is not limited to the limitation of the traditional computer architecture, and all things with wireless transmission and computing capability can be regarded as the computing node, such as: unmanned aerial vehicle, intelligent automobile that possess computing power etc..
S2: polling whether the terminal equipment of the Internet of things has an unloading demand: when connected to a local compute nodejOf an arbitrary terminaliWhen the unloading task is required, the unloading task data is collected, and the size of a task data packet is calculatedb i Maximum tolerated delayt i Type of computing resource requiredr i And resource sizes i 。
S3: and screening out a candidate unloading computing node set M according to the task data. Specifically, each selected candidate compute nodex（xE.m) satisfies the following three constraints:
1. candidate computing nodexSatisfies the resource type requirements of the task, i.e.r i ∈R x WhereinR x Representing a compute nodexComputing a set of resource types;
2. candidate computing nodexThe remaining amount of computing resources of (a) meets the resource size requirement of the task, i.e.s i ≤S x In whichS x Representing a compute nodexThe remaining amount of resources is calculated.
3. Candidate computing nodexIs at a distance that satisfies the maximum tolerated delay of the task, i.e.t i ≥T x WhereinT x Representing task offloading to compute nodesxThe total time required to complete the task calculation and return the results.T x This can be calculated according to the following equation:
T x =0.5*δ+0.1*Distance ix
wherein the content of the first and second substances,δrepresenting a computational sectionNetwork bandwidth characteristics of points, Distance ix Presentation terminaliAnd candidate computing nodexCan be calculated by the following formula:
Distance ix =R*cos -1 [sin(Mlat i )*sin(Mlat x )*cos(Mlon i -Mlon x )+cos(Mlat i )*cos(Mlat x )*π÷180
wherein the content of the first and second substances,Rrepresenting the average radius of the earth, with a value of 6371.004km, and pi expressed as the circumference ratio;Mlat i 、Mlat x respectively representing terminalsi、xIf the geographic position is the northern hemisphere, then the latitude value is calculatedMlat i =90-lat i (ii) a If the geographic position is the southern hemisphere, thenMlat i =90+lat i ， lat i Is the true latitude value of terminal i, obtained from GPS data,Mlat x is calculated by the methodMlat i The consistency is achieved;
Mlon i 、Mlon x respectively representing terminalsi、xIf the geographic location is the east hemisphere, then the longitude value is calculatedMlon i =lon i ；If the geographic location is the western hemisphere, thenMlon i =-lon i ，lon i Is the true longitude value of terminal i, obtained from GPS data,Mlon x is calculated by the methodMlon i And (5) the consistency is achieved.
Specifically, corresponding constraint conditions may be constructed according to specific application situations, and in this embodiment, the resource type, the remaining number of resources, and the maximum tolerable delay are mainly considered.
Step S4: traversing the candidate unloading computing node set M, and firstly computing the local computing nodeThe point needs to pay each candidate nodexMonetary cost of completing computing taskC x total ：
C x total = C x engergy +C x carbon
Wherein the content of the first and second substances, C x carbon representing a compute nodexCarbon emission cost of (a);C x engergy 、C x carbon the calculation formula of (a) is as follows:
C x engergy =e x *P x engergy
C x carbon =e x *K x * P x carbon
wherein the content of the first and second substances,e x representing candidate nodesxEnergy consumption required for processing tasks;P x engergy represents the comprehensive price of various energy sources;K x representing candidate nodesxCarbon emission coefficient of (a);P x carbon represents the carbon trading price, which is typically determined by the market.
Energy consumptione x Can be calculated from the following formula:
e x = b i *f x *ρ+P x *e x,basic
wherein the content of the first and second substances,TDP x representing candidate nodesxThe thermal design power consumption value of the CPU, the specific numerical value can be obtained by the inquiry of a CPU manufacturer,f x,max representing candidate nodesxThe maximum frequency, specific numerical value of the CPU can be obtained by inquiring of a CPU manufacturer.
P x engergy 、K x Can be calculated by the following formula:
whereine k Representing candidate node energy typeskThe proportion of the energy supply of (2),p k as the type of energy sourcekThe market price of (a) is,c k is an energy source typekSpecific values of carbon emission coefficients for different energy types are shown in table 1. Wherein
Then, computing local computing nodesjGain of (2)G j The calculation method is obtained by the following formula:
G j =u i -γT x -C x total
wherein the content of the first and second substances,u i to complete the terminal equipmentiThe fixed yield of the task of (a),γin order to be a weight parameter, the weight parameter, T x representing task offloading to compute nodesxThe total time required to complete the task calculation for the returned results,T x see step S3.
For candidate nodexCarbon emission system due to the possibility of using various renewable energy sourcesThe number is low, so the carbon emission right can be traded, and the carbon trading process is divided into two stages: when the actual carbon emissions are less than the carbon emission quota, the carbon emission rights may be sold to obtain revenue; when the actual carbon emission is greater than the carbon emission quota, the cost is paid and the carbon emission rights are purchased. Therefore, the candidate nodexExecuting local compute nodesjCan obtain profit when migrating tasksG x The calculation is given by the following formula:
G x = C x total - C x engergy - C x trade
wherein the content of the first and second substances,C x total expressed as local computing node needs to pay each candidate nodexThe monetary cost of completing the computing task is,C x engergy computing node for executing tasksxThe energy consumption cost of (2) is low,C x trade to compute a nodexThe carbon transaction fee. Note that the carbon emission cost is distinguished from the carbon transaction cost, which is the cost charged by the compute node when performing the tasks of other node migration, and the carbon transaction cost, which is the compute node carbon transaction cost. Wherein the content of the first and second substances,C x trade is obtained by the following formula:
whereinE x Is a candidate nodexThe accumulated carbon emissions of the computing node, the data being collected by the computing node itself;Ethe carbon emission quota of the node is calculated and is regulated by relevant departments such as the government and the like;P x carbon is the carbon transaction price.
Finally, for the candidate nodexWith local computing nodesjIs weighted and expressed as a total profitGThe calculation method is obtained by the following formula：
G=αGx+βGj
Wherein, alpha and beta are control coefficients used for adjusting the weight occupied by each income.
Step S5: and selecting the computing node which can maximize the total income from the candidate set M as the unloading node. And if the plurality of computing nodes have the same maximum value, selecting the computing node closest to the terminal from the computing nodes as the unloading node.
Step S6: and sending the unloading task to the corresponding unloading node. When the time slice ends, the process returns to step S1.
Based on the same inventive concept, the application also provides a system corresponding to the optimal carbon emission calculation unloading method of the multi-energy supply edge system in the first embodiment, which is detailed in the second embodiment.
Example two
The embodiment provides an optimal carbon emission calculation unloading system of a multi-energy supply edge system, as shown in fig. 2, the system includes:
the data collection module 201 is configured to collect and update state parameters of all the computing nodes at the beginning of each preset time slice, and includes: the method comprises the following steps of calculating the surplus of various computing resources, the average running frequency of a CPU, various energy supply types, the proportion of each type of energy supply, the energy price, the carbon transaction price and the carbon emission quota consumption.
The communication module 202 is used for polling whether the terminal device of the internet of things has an unloading demand. When any terminal connected to the local computing node has the requirement of unloading tasks, the unloading task data is collected, the size of a task data packet, the maximum tolerance time delay, the type of required computing resources and the size of the resources are computed, and the data are sent to the target scheduling module.
And the target scheduling module 203 is used for screening out candidate unloading computing nodes.
And the unloading scheduling module 204 is configured to calculate a total benefit value of the candidate unloading computing nodes and the local computing node, and select a computing node with the maximum total benefit as the unloading node. The notification communication module 202 sends the corresponding offload node information to the terminal device.
In an embodiment, the target scheduling module 203 is specifically configured to perform the following steps:
and screening out a candidate unloading computing node set M according to the task data. Specifically, each selected candidate compute nodex（xE.m) satisfies the following three constraints:
1. candidate computing nodexSatisfies the resource type requirements of the task, i.e.r i ∈R x WhereinR x Representing a compute nodexComputing a set of resource types;
2. candidate computing nodexThe remaining amount of computing resources of (a) meets the resource size requirement of the task, i.e.s i ≤S x WhereinS x Representing a compute nodexThe remaining amount of resources is calculated.
3. Candidate computing nodexIs at a distance that satisfies the maximum tolerated delay of the task, i.e.t i ≥T x WhereinT x Representing task offloading to compute nodesxThe total time required to complete the task calculation and return the result.
In this embodiment, the target scheduling module 204 is specifically configured to perform the following steps:
traversing the candidate unloading computing node set M, and computing the payment required by the local computing node to each candidate nodexMonetary cost of completing computing taskC x total . Candidate nodexExecuting local compute nodesjCan obtain profit when migrating tasksG x ，G x The calculating method comprises the following steps:
G x = C x total - C x engergy - C x trade
then, computing local computing nodesjGain of (2)G j ：
G j =u i -γT x -C x total
Finally according to
G=αGx+βGj
Calculating the total profitG。
The target scheduling module 204 selects the computing node from the candidate set M that maximizes the total profit as the offload node. And if the plurality of computing nodes have the same maximum value, selecting the computing node closest to the terminal from the computing nodes as the unloading node.
The target scheduling module 204 sends the offload tasks to the corresponding offload nodes.
Since the system described in the second embodiment of the present invention is a system for implementing the optimal carbon emission calculation and unloading method of the multi-energy supply edge system in the first embodiment of the present invention, based on the method described in the first embodiment of the present invention, those skilled in the art can understand the specific structure and deformation of the apparatus, and thus, details are not described herein. All the devices adopted in the method of the first embodiment of the present invention belong to the protection scope of the present invention.
The present invention has been described in terms of specific examples, which are provided to aid understanding of the invention and are not intended to be limiting. For a person skilled in the art to which the invention pertains, several simple deductions, modifications or substitutions may be made according to the idea of the invention. It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of this invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of this invention should be included within the scope of protection of this invention.
Details not described in this specification are within the skill of the art that are well known to those skilled in the art.
Claims (6)
1. An optimal carbon emission calculation unloading method of a multi-energy supply edge system is characterized by comprising the following steps: the method comprises the following steps:
s1 collects and updates the state parameters of all the compute nodes at the beginning of each preset time slice, including: surplus of various computing resourcesS x Maximum operating frequency of CPUf x max, Various types of energy supplykAnd the proportion of each type of energy supplye k And energy pricep k Carbon transaction priceP x carbon And carbon emission quota usageE；
S2, polling the terminal equipment of the Internet of things whether the unloading requirement exists: when connected to a local compute nodejOf the arbitrary terminaliWhen the unloading task is required, the unloading task data is collected, and the size of a task data packet is calculatedb i Maximum tolerated delayt i Type of computing resource requiredr i And resource sizes i ；
S3 screening out a candidate unloading computing node set M according to the task data;
s4 traversing the candidate unloading calculation node set M to calculate each candidate nodexWhen the calculation task is completed, the candidate nodexWith local computing nodesjTotal gain that can be achievedG；
Total profitGThe calculation method is obtained by the following formula:
G=αGx+βGj
wherein the content of the first and second substances,G x representing candidate nodesxThe gain of the gain to be obtained is,G j representing local compute nodesjα and β are control coefficients for adjusting the weight occupied by each benefit;
local computing nodejGain of (2)G j Is obtained by the following formula:
G j =u i -γT x -C x total
wherein the content of the first and second substances,u i to complete terminal equipmentiThe fixed yield of the task of (a),γin order to be a weight parameter, the weight parameter,T x representing task offloading to compute nodesxThe total time required to complete the task calculation of the backtransmission result,C x total expressed as local computing node needs to pay each candidate nodexMonetary cost of completing the computing task;
the local computing node needs to pay each candidate nodexMonetary cost of completing computing taskC x total The calculation formula of (a) is as follows:
C x total = C x engergy +C x carbon
wherein the content of the first and second substances, C x carbon representing a compute nodexCarbon emission cost of (a);C x engergy 、C x carbon the calculation formula of (a) is as follows:
C x engergy =e x *P x engergy
earningG x Is given by the following formula:
G x = C x total - C x engergy - C x trade
wherein the content of the first and second substances,C x engergy computing node for executing tasksxThe energy consumption cost of (2) is low,C x trade to compute a nodexA carbon transaction fee of (a);
C x carbon =e x *K x * P x carbon
wherein the content of the first and second substances,e x representing candidate nodesxEnergy consumption required for processing tasks;P x engergy represents the comprehensive price of various energy sources;K x representing candidate nodesxCarbon emission coefficient of (a);P x carbon representing a carbon transaction price;
s5, selecting the computing node which enables the total profit to be maximum from the candidate set M as an unloading node;
s6 sends the unloading task to the corresponding unloading node, and when the time slice is finished, the step returns to S1.
2. The method of claim 1, wherein the method further comprises: each of the selected candidate compute nodes in step S3x，xE.g., M, satisfying the following three constraints:
(1) candidate computing nodexSatisfies the resource type requirements of the task, i.e.r i ∈R x WhereinR x Representing a compute nodexComputing a set of resource types;
(2) candidate computing nodexThe remaining amount of computing resources of (a) meets the resource size requirement of the task, i.e.s i ≤S x WhereinS x Representing a compute nodexCalculating the residual quantity of resources;
(3) candidate computing nodexIs at a distance that satisfies the maximum tolerated delay of the task, i.e.t i ≥T x WhereinT x Representing task offloading to compute nodesxTo completionThe task calculates the total time required to return the result.
3. The method of claim 2, wherein the optimal carbon rejection calculation unloading method comprises: task offloading to compute nodesxTotal time required to complete task calculation and return resultT x The method comprises the following steps:
T x =0.5*δ+0.1*Distance ix
wherein the content of the first and second substances,δrepresenting the network bandwidth characteristics, Distance, of the compute node ix Presentation terminaliAnd candidate computing nodexThe distance of (c).
4. The method of claim 3, wherein the method further comprises: terminal deviceiAnd candidate computing nodexDistance of (2) ix The calculation method comprises the following steps:
Distance ix =R*cos -1 [sin(Mlat i )* sin(Mlat x )* cos(Mlon i - Mlon x )+
cos (Mlat i )* cos (Mlat x )*π÷180
wherein, the first and the second end of the pipe are connected with each other,Rthe mean radius of the earth is represented, and pi is represented as a circumferential rate;Mlat i 、Mlat x respectively representing terminalsi、xIs calculated by the calculating unit (2) of (c),Mlon i 、Mlon x respectively representing terminalsi、xThe calculated longitude value of (1).
5. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method of any one of claims 1 to 4.
6. An optimal carbon emission calculation unloading system of a multi-energy supply edge system, which is used for realizing the optimal carbon emission calculation unloading method of the multi-energy supply edge system as claimed in any one of claims 1-4, and is characterized in that: the system comprises a data acquisition module (201), a communication module (202), a target scheduling module (203) and an unloading scheduling module (204);
the data acquisition module (201) is configured to collect and update state parameters of all the computing nodes at the beginning of each preset time slice, and includes: calculating the residual amount of resources, the average running frequency of a CPU, various energy supply types, the proportion of each type of energy supply, the energy price, the carbon transaction price and the carbon emission quota amount;
the communication module (202) is used for polling the terminal equipment of the Internet of things whether to have an unloading requirement, acquiring unloading task data when any terminal connected to a local computing node has the requirement of an unloading task, computing the size of a task data packet, the maximum tolerance time delay, the type of required computing resources and the size of resources, and sending the data to the target scheduling module;
the target scheduling module (203) is used for screening out candidate unloading computing nodes;
the unloading scheduling module (204) is configured to calculate a total benefit value of the candidate unloading computing nodes and the local computing node, select a computing node with the maximum total benefit as an unloading node, notify the communication module (202), and send corresponding unloading node information to the terminal device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210654463.4A CN114816584B (en) | 2022-06-10 | 2022-06-10 | Optimal carbon emission calculation unloading method and system for multi-energy supply edge system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210654463.4A CN114816584B (en) | 2022-06-10 | 2022-06-10 | Optimal carbon emission calculation unloading method and system for multi-energy supply edge system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114816584A CN114816584A (en) | 2022-07-29 |
| CN114816584B true CN114816584B (en) | 2022-09-27 |
Family
ID=82521581
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210654463.4A Active CN114816584B (en) | 2022-06-10 | 2022-06-10 | Optimal carbon emission calculation unloading method and system for multi-energy supply edge system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114816584B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116321297B (en) * | 2023-03-13 | 2024-01-02 | 广州爱浦路网络技术有限公司 | Computing task unloading method and system based on new generation core network |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109814951A (en) * | 2019-01-22 | 2019-05-28 | 南京邮电大学 | The combined optimization method of task unloading and resource allocation in mobile edge calculations network |
| CN110740459A (en) * | 2019-10-16 | 2020-01-31 | 杭州安恒信息技术股份有限公司 | uRLLC network slice generation device and generation method based on GPS |
| CN112363829A (en) * | 2020-11-03 | 2021-02-12 | 武汉理工大学 | Dynamic user resource allocation method based on elastic scale aggregation |
| CN113159539A (en) * | 2021-04-07 | 2021-07-23 | 中山大学 | Joint green energy scheduling and dynamic task allocation method in multilayer edge computing system |
| CN113156854A (en) * | 2021-04-02 | 2021-07-23 | 国网浙江慈溪市供电有限公司 | Enterprise comprehensive energy consumption assessment method based on digital twin technology |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210042160A1 (en) * | 2019-04-05 | 2021-02-11 | Mimik Technology Inc. | Method and system for distributed edge cloud computing |
| CN113037837B (en) * | 2021-03-05 | 2022-04-01 | 东北大学 | Intelligent terminal facing comprehensive energy system and based on edge calculation and control method thereof |
-
2022
- 2022-06-10 CN CN202210654463.4A patent/CN114816584B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109814951A (en) * | 2019-01-22 | 2019-05-28 | 南京邮电大学 | The combined optimization method of task unloading and resource allocation in mobile edge calculations network |
| CN110740459A (en) * | 2019-10-16 | 2020-01-31 | 杭州安恒信息技术股份有限公司 | uRLLC network slice generation device and generation method based on GPS |
| CN112363829A (en) * | 2020-11-03 | 2021-02-12 | 武汉理工大学 | Dynamic user resource allocation method based on elastic scale aggregation |
| CN113156854A (en) * | 2021-04-02 | 2021-07-23 | 国网浙江慈溪市供电有限公司 | Enterprise comprehensive energy consumption assessment method based on digital twin technology |
| CN113159539A (en) * | 2021-04-07 | 2021-07-23 | 中山大学 | Joint green energy scheduling and dynamic task allocation method in multilayer edge computing system |
Non-Patent Citations (2)
| Title |
|---|
| Enabling Green Mobile-Edge Computing for 5G-Based Healthcare Applications;P. K. Bishoyi;《IEEE Transactions on Green Communications and Networking》;20210930;第1623-1631页 * |
| 基于"端-边-云"架构的园区综合能源系统协调优化调度;李昊;《储能科学与技术》;20220228;第623-634页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114816584A (en) | 2022-07-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gao et al. | Truthful incentive mechanism for nondeterministic crowdsensing with vehicles | |
| Hassija et al. | Scheduling drone charging for multi-drone network based on consensus time-stamp and game theory | |
| US11238474B2 (en) | Distributed energy control | |
| Rigas et al. | Managing electric vehicles in the smart grid using artificial intelligence: A survey | |
| US20210402889A1 (en) | Method and apparatus for charging a battery using local power grid topology information | |
| JP6963397B2 (en) | Aggregation control system, aggregation control method and control device | |
| Zhou et al. | A truthful online mechanism for location-aware tasks in mobile crowd sensing | |
| Janko et al. | Scalable multi-agent microgrid negotiations for a transactive energy market | |
| CN108200610B (en) | Crowd sensing resource allocation method adopting distributed game | |
| Mehrabi et al. | Decentralized greedy-based algorithm for smart energy management in plug-in electric vehicle energy distribution systems | |
| CN110503396B (en) | Multi-skill-based complex space crowdsourcing task allocation method | |
| Ma et al. | A time and location correlation incentive scheme for deep data gathering in crowdsourcing networks | |
| CN114816584B (en) | Optimal carbon emission calculation unloading method and system for multi-energy supply edge system | |
| JPWO2019182038A1 (en) | Energy systems, energy management servers, energy management methods, and programs | |
| JP7053795B2 (en) | Condition determination device, program and condition determination method | |
| Wei et al. | A novel distributed algorithm for power loss minimizing in smart grid | |
| JP6945723B2 (en) | Power interchange device, program and power interchange method | |
| CN111008463A (en) | Capacity allocation optimization method, device and equipment considering energy storage at power generation side | |
| Doan et al. | Optimal peer-to-peer energy trading under load uncertainty incorporating carbon emission and transaction cost for grid-connected prosumers | |
| US20220305942A1 (en) | System and method for scheduling electric charging for vehicles | |
| Etesami et al. | Smart routing in smart grids | |
| CN113383351A (en) | Transportation method and device | |
| CN115641174A (en) | Electricity charge determining method and device, storage medium and electronic equipment | |
| Rahman et al. | On efficient operation of a V2G-enabled virtual power plant: when solar power meets bidirectional electric vehicle charging | |
| Umoren et al. | Combined economic emission based resource allocation for electric vehicle enabled microgrids |
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 |