Architecture of the edge computing network.

Architecture of the edge computing network.

Source publication
Article
Full-text available
For the edge computing network, whether the end-to-end delay satisfies the delay constraint of the task is critical, especially for delay-sensitive tasks. Virtual machine (VM) migration improves the robustness of the network, whereas it also causes service downtime and increases the end-to-end delay. To study the influence of failure, migration, an...

Contexts in source publication

Context 1
... depicted by Figure 1, the edge computing network is composed of four partssensor nodes, the edge server, the cloud gateway, and the cloud server. The task data generated by sensors are transmitted to the edge server for necessary processing by VMs, including pre-processing, analysis, compression, and encryption, over Bluetooth Low Energy, or Wi-Fi. ...
Context 2
... depicted by Figure 1, the edge computing network is composed of four partssensor nodes, the edge server, the cloud gateway, and the cloud server. The task data generated by sensors are transmitted to the edge server for necessary processing by VMs, including pre-processing, analysis, compression, and encryption, over Bluetooth Low Energy, or Wi-Fi. ...
Context 3
... a crossroads, the edge computing network for traffic monitoring consists of several sensors, an edge server, a cloud gateway, and a cloud server. The architecture of this network is depicted in Figure 1. To monitor the traffic at this crossroads, the sensors collect task data in real-time and transmit the tasks to the edge server, where the tasks are processed by VMs. ...
Context 4
... compare the simulation results and the numerical results of ETR when the failure rate í µí¼ƒ equals to 0.0002, 0.0006, and 0.001 with different numbers of sensors. The comparisons are shown in Figure 10, where the bars' heights represent the relative errors of the numerical results. The relative errors are all less than 2%. ...
Context 5
... compare the simulation results and the numerical results of ETR when the failure rate θ equals to 0.0002, 0.0006, and 0.001 with different numbers of sensors. The comparisons are shown in Figure 10, where the bars' heights represent the relative errors of the numerical results. The relative errors are all less than 2%. ...
Context 6
... is observed in Figures 11 and 12 that VTR is a monotonic function of the failure rate, migration rate, and reboot rate of VM. Comparing Figure 11a with Figure 11b, we find VTR is more sensitive to the failure rate when the reboot rate and migration rate are smaller since the VMs spend more time to migrate and recover when the reboot rate and migration rate are smaller. ...
Context 7
... is observed in Figures 11 and 12 that VTR is a monotonic function of the failure rate, migration rate, and reboot rate of VM. Comparing Figure 11a with Figure 11b, we find VTR is more sensitive to the failure rate when the reboot rate and migration rate are smaller since the VMs spend more time to migrate and recover when the reboot rate and migration rate are smaller. Thus, if the migration time and reboot time are quite short, the designers do not need to be very rigid on the reliability of VMs. ...
Context 8
... is observed in Figures 11 and 12 that VTR is a monotonic function of the failure rate, migration rate, and reboot rate of VM. Comparing Figure 11a with Figure 11b, we find VTR is more sensitive to the failure rate when the reboot rate and migration rate are smaller since the VMs spend more time to migrate and recover when the reboot rate and migration rate are smaller. Thus, if the migration time and reboot time are quite short, the designers do not need to be very rigid on the reliability of VMs. ...
Context 9
... is observed in Figures 11 and 12 that VTR is a monotonic function of the failure rate, migration rate, and reboot rate of VM. Comparing Figure 11a with Figure 11b, we find VTR is more sensitive to the failure rate when the reboot rate and migration rate are smaller since the VMs spend more time to migrate and recover when the reboot rate and migration rate are smaller. ...
Context 10
... is observed in Figures 11 and 12 that VTR is a monotonic function of the failure rate, migration rate, and reboot rate of VM. Comparing Figure 11a with Figure 11b, we find VTR is more sensitive to the failure rate when the reboot rate and migration rate are smaller since the VMs spend more time to migrate and recover when the reboot rate and migration rate are smaller. Thus, if the migration time and reboot time are quite short, the designers do not need to be very rigid on the reliability of VMs. ...
Context 11
... is observed in Figures 11 and 12 that VTR is a monotonic function of the failure rate, migration rate, and reboot rate of VM. Comparing Figure 11a with Figure 11b, we find VTR is more sensitive to the failure rate when the reboot rate and migration rate are smaller since the VMs spend more time to migrate and recover when the reboot rate and migration rate are smaller. Thus, if the migration time and reboot time are quite short, the designers do not need to be very rigid on the reliability of VMs. ...
Context 12
... is observed in Figures 11 and 12 that VTR is a monotonic function of the failure rate, migration rate, and reboot rate of VM. Comparing Figure 11a with Figure 11b, we find VTR is more sensitive to the failure rate when the reboot rate and migration rate are smaller since the VMs spend more time to migrate and recover when the reboot rate and migration rate are smaller. ...
Context 13
... is observed in Figures 11 and 12 that VTR is a monotonic function of the failure rate, migration rate, and reboot rate of VM. Comparing Figure 11a with Figure 11b, we find VTR is more sensitive to the failure rate when the reboot rate and migration rate are smaller since the VMs spend more time to migrate and recover when the reboot rate and migration rate are smaller. Thus, if the migration time and reboot time are quite short, the designers do not need to be very rigid on the reliability of VMs. ...
Context 14
... is observed in Figures 11 and 12 that VTR is a monotonic function of the failure rate, migration rate, and reboot rate of VM. Comparing Figure 11a with Figure 11b, we find VTR is more sensitive to the failure rate when the reboot rate and migration rate are smaller since the VMs spend more time to migrate and recover when the reboot rate and migration rate are smaller. Thus, if the migration time and reboot time are quite short, the designers do not need to be very rigid on the reliability of VMs. ...
Context 15
... number of TVMs and BVMs are also influential factors of VTR. Results in Figure 13a show that VTR is higher with the increase in the number of TVMs when the failure rate is high. The reason is that more VMs mean the server can process more tasks at the same time. ...
Context 16
... reason is that more VMs mean the server can process more tasks at the same time. However, when the failure rate is low, we have an interesting finding that VTR monotonically decreases as the number of TVMs grows, such as the cases when the failure rate equals 0.0002 or 0.0004 in Figure 13a. In fact, the increase in the number of TVMs influences VTR by two means, i.e., (1) reducing the end-to-end delay by processing more tasks at the same time and (2) increasing the end-to-end delay by bringing about more failure, migration, and reboot of VMs in a given time. ...
Context 17
... when the failure rate is low, the first impact is more significant. Similar results are shown by Figure 13b, where with no BVM or extremely few BVMs, VTR monotonically increases as the number of TVMs grows, indicating that the first impact is more significant. However, with more BVMs, VTR monotonically decreases as the number of TVMs grows, indicating that the second impact is more significant. ...
Context 18
... to the above findings, the resource manager can allocate an appropriate number of TVMs according to the above-mentioned analysis, which can be a guidance for the initial configuration of VMs. As for the number of BVMs, Figure 14 shows that VTR monotonically increases as the number of BVM grows. Table 3. ...
Context 19
... number of TVMs and BVMs are also influential factors of VTR. Results in Figure 13a show that VTR is higher with the increase in the number of TVMs when the failure rate is high. The reason is that more VMs mean the server can process more tasks at the same time. ...
Context 20
... reason is that more VMs mean the server can process more tasks at the same time. However, when the failure rate is low, we have an interesting finding that VTR monotonically decreases as the number of TVMs grows, such as the cases when the failure rate equals 0.0002 or 0.0004 in Figure 13a. In fact, the increase in the number of TVMs influences VTR by two means, i.e., (1) reducing the end-to-end delay by processing more tasks at the same time and (2) increasing the end-to-end delay by bringing about more failure, migration, and reboot of VMs in a given time. ...
Context 21
... when the failure rate is low, the first impact is more significant. Similar results are shown by Figure 13b, where with no BVM or extremely few BVMs, VTR monotonically increases as the number of TVMs grows, indicating that the first impact is more significant. However, with more BVMs, VTR monotonically decreases as the number of TVMs grows, indicating that the second impact is more significant. ...
Context 22
... to the above findings, the resource manager can allocate an appropriate number of TVMs according to the above-mentioned analysis, which can be a guidance for the initial configuration of VMs. As for the number of BVMs, Figure 14 shows that VTR monotonically increases as the number of BVM grows. ...
Context 23
... number of TVMs and BVMs are also influential factors of VTR. Results in Figure 13a show that VTR is higher with the increase in the number of TVMs when the failure rate is high. The reason is that more VMs mean the server can process more tasks at the same time. ...
Context 24
... reason is that more VMs mean the server can process more tasks at the same time. However, when the failure rate is low, we have an interesting finding that VTR monotonically decreases as the number of TVMs grows, such as the cases when the failure rate equals 0.0002 or 0.0004 in Figure 13a. In fact, the increase in the number of TVMs influences VTR by two means, i.e., (1) reducing the end-to-end delay by processing more tasks at the same time and (2) increasing the end-to-end delay by bringing about more failure, migration, and reboot of VMs in a given time. ...
Context 25
... when the failure rate is low, the first impact is more significant. Similar results are shown by Figure 13b, where with no BVM or extremely few BVMs, VTR monotonically increases as the number of TVMs grows, indicating that the first impact is more significant. However, with more BVMs, VTR monotonically decreases as the number of TVMs grows, indicating that the second impact is more significant. ...
Context 26
... the increase in the number of TVMs and the number of BVMs both improve VTR generally, to achieve the highest VTR, there is a trade-off between the number of TVMs and the number of BVMs when the total number of VMs is limited. Figure 15a reveals that when the failure rate of VM is low, only assigning one VM as TVM is the best solution. Figure 15b shows that when the failure rate is high, more VMs should be assigned as TVMs to achieve the highest VTR. ...
Context 27
... 15a reveals that when the failure rate of VM is low, only assigning one VM as TVM is the best solution. Figure 15b shows that when the failure rate is high, more VMs should be assigned as TVMs to achieve the highest VTR. Therefore, to achieve the highest VTR, based on the analysis method of this paper, the resource manager can find the optimal allocation of VMs according to the related parameters of the edge computing network and the tasks. ...
Context 28
... to the above findings, the resource manager can allocate an appropriate number of TVMs according to the above-mentioned analysis, which can be a guidance for the initial configuration of VMs. As for the number of BVMs, Figure 14 shows that VTR monotonically increases as the number of BVM grows. ...
Context 29
... the increase in the number of TVMs and the number of BVMs both improve VTR generally, to achieve the highest VTR, there is a trade-off between the number of TVMs and the number of BVMs when the total number of VMs is limited. Figure 15a reveals that when the failure rate of VM is low, only assigning one VM as TVM is the best solution. Figure 15b shows that when the failure rate is high, more VMs should be assigned as TVMs to achieve the highest VTR. ...
Context 30
... 15a reveals that when the failure rate of VM is low, only assigning one VM as TVM is the best solution. Figure 15b shows that when the failure rate is high, more VMs should be assigned as TVMs to achieve the highest VTR. Therefore, to achieve the highest VTR, based on the analysis method of this paper, the resource manager can find the optimal allocation of VMs according to the related parameters of the edge computing network and the tasks. ...
Context 31
... the increase in the number of TVMs and the number of BVMs both improve VTR generally, to achieve the highest VTR, there is a trade-off between the number of TVMs and the number of BVMs when the total number of VMs is limited. Figure 15a reveals that when the failure rate of VM is low, only assigning one VM as TVM is the best solution. Figure 15b shows that when the failure rate is high, more VMs should be assigned as TVMs to achieve the highest VTR. ...
Context 32
... 15a reveals that when the failure rate of VM is low, only assigning one VM as TVM is the best solution. Figure 15b shows that when the failure rate is high, more VMs should be assigned as TVMs to achieve the highest VTR. Therefore, to achieve the highest VTR, based on the analysis method of this paper, the resource manager can find the optimal allocation of VMs according to the related parameters of the edge computing network and the tasks. ...

Similar publications

Article
Full-text available
The present paper deals with the reliability analysis of a computer network system as series parallel system consisting of two subsystems. Subsystem I consist of four homogeneous clients while subsystem II consist of two homogeneous servers. Both clients and servers have exponential failure whereas repairs follow two types of distributions that are...

Citations

Article
Purpose of research. The purpose of this study is to form a set of basic elements of the methodology for reducing the consumption of the residual resource of computing devices operating as part of distributed computing systems based on the concepts of fog and edge computing. The concepts of fog and edge computing are relatively new and, despite the large volume of publications on this topic, the issue of resource consumption of computing devices in terms of FBG values has not been considered in the literature. At the same time, extending the service life of devices is currently highly desirable, which makes this study relevant. Methods. The main scientific methods used in this study are analysis (of subject areas), numerical simulation and natural experiment, confirming the feasibility of the main aspects of the developed methodology.Within the framework of the concepts of fog and edge computing, it is considered appropriate to shift the computing load to data sources, which, as a rule, are located at the edge of the network. However, modern studies do not affect the estimates of the impact of such a strategy in the placement of functional tasks on the estimated values of the probability of non-failure operation of devices, which characterizes the state of the residual resource of the device. Meanwhile, an increase in the load on devices with less computing power than, say, a device within a data center leads to an acceleration of their wear, which, in turn, translates into economic costs for maintaining a functioning computing infrastructure. At the same time, the load on the intermediate network devices is reduced, since they transmit reduced amounts of data, and the time that can be used for data processing, if the latter is performed at the edge devices, increases. The developed methodology offers an integrated approach to the placement of functional tasks of distributed information systems, taking into account the listed features of using the concepts of fog and edge computing. Results. The main results of this study are the description of a set of basic methods that make up the methodology for reducing the consumption of the residual resource of computing devices of distributed computing systems based on fog and edge computing. The resulting complex is based on the developed models and the results of experimental studies. Conclusion. Currently, despite the massive use of the concepts of fog and edge computing in the implementation of distributed information systems, there has not been developed a unified methodology that would reduce the consumption of resources of computing devices and thereby extend their service life. Within the framework of this work, a set of methods is proposed, the further development of which will increase the service life of devices that make up the computing infrastructure of distributed computing systems.