Optimizing the Freshness of Information in Mobile Edge Computing Networks
Open AccessAge of information (AoI) is now well established as a metric that measures the freshness of information delivered to a receiver from a source that generates status updates. Meanwhile, Mobile Edge Computing (MEC) is an attractive architecture to alleviate the long latency caused by cloud computing with an MEC server close to the end-users. In this work, we propose various models for AoI optimization problems in MEC networks, such as waiting mode, tandem queue model, parallel servers model and multi-sources model. We also propose some new metrics related to AoI that can capture the dimensions missed by AoI in different scenarios. First, we explore the potential of server waiting before packet transmission in improving the AoI in status update systems. We consider a non-preemptive queue and incorporate waiting before serving in two packet management schemes: M/GI/1/1 and M/GI/1/2$^*$. We obtain expressions for average AoI and average peak AoI for both queueing disciplines with waiting. Our numerical results demonstrate that waiting before service can bring significant improvement in average age, particularly, for heavy-tailed service distributions. Then, we model an edge computing system as two queues in tandem whose service times are independent but the transmission service time is monotonically dependent on the computation service time in mean value. This dependence captures the natural decrease in transmission time due to lower offloaded computation. We analyze various queue management schemes in this tandem queue and perform stationary distribution analysis to obtain closed-form expressions for average AoI and average peak AoI. Our numerical results illustrate analytical findings on how computation and transmission times could be traded off to optimize AoI and reveal a consequent tradeoff between average AoI and average peak AoI Besides the tandem queue model, we consider a parallel servers model in MEC networks where the MEC server can either directly transmit the data generated by an IoT sensor/device to the data center or pre-process the data and then transmit it to the data center over a shared channel. We perform stationary distribution analysis in this system and obtain closed-form expressions for average AoI and average peak AoI. We focus on selecting the offloading probabilities in conjunction with the mean service times for each server for optimal operation determined by average AoI and peak AoI. Our numerical results show the effect of path diversity in the selection of the best offloading probability and service times. We also analyze systems with an enforced hard or soft deadline. We propose three metrics for status update systems to measure the ability of different queuing systems to meet a threshold requirement for the AoI and investigate these metrics in three typical status update queuing systems -- M/G/1/1, M/G/1/$2^*$, and M/M/1. Numerical results show the performances for these metrics under different parameter settings and different service distributions. For the system model with multiple sources, we consider a time-slotted system in which packets are generated at Bernoulli sources with different generation probabilities. In each slot, one source will be selected to transmit its packet to the receiver. We present analyses for the average age under several scheduling policies. Our analytical results are validated with simulation results, and a numerical performance comparison of the scheduling policies is presented. In an attempt to go beyond AoI, we propose a new metric called Value of Information(VoI). Update packets carrying a random initial value are generated at the source, and the value either stays constant or decreases until a deterministic deadline after which becomes zero. We investigate various queuing disciplines under potential dependence between value and service time and provide closed-form expressions for VoI. Two versions of VoI, namely average sum VoI and average packet VoI, are investigated.To measure the impact of communication delays and state changes at the source on a remote decision maker we introduce another new metric, named Penalty upon Decision (PuD), which specifically, quantifies the performance degradation at the decision maker's side due to delayed, erroneous, and (possibly) missed decisions. We clarify the rationale for the metric and derive closed-form expressions for its average in various queuing disciplines. Numerical results are then presented to support our expressions and to compare the infinite and zero buffer regimes.
- All rights reserved
Notice to Authors
If you are the author of this work and you have any questions about the information on this page, please use the Contact form to get in touch with us.