2021 Fiscal Year Research-status Report
Mixed-Clairvoyance Task Offloading and Scheduling in Multi-access Edge Computing Systems: From Combinatorial Optimization to Machine Learning
| Project/Area Number |
20K19794
|
|---|
| Research Institution | Osaka Prefecture University |
|---|
Principal Investigator |
江 易翰 大阪府立大学, 工学(系)研究科(研究院), 助教 (10824196)
|
|---|
| Project Period (FY) |
2020-04-01 – 2023-03-31
|
| Keywords | Age of information / Information freshness / Internet of Things / Serverless computing |
|---|
| Outline of Annual Research Achievements |
In this fiscal year, what we have done can be summarized as follows.
(1) We addressed the problem of information sampling and transmission scheduling for serverless functions in the Internet of Things (IoT) systems with serverless computing to optimize the age of service (AoS) of serverless functions.
(2) We leveraged combinatorial optimization techniques to mathematically formulate the problem and investigated the problem intractability.
(3) We designed both offline and online age-efficient algorithms for the information sampling and transmission scheduling with and without the prior knowledge of the invocations of serverless functions, respectively.
(4) We conducted simulations to demonstrate that the proposed solution outperforms existing ones under various system parameters.
|
| Current Status of Research Progress |
Current Status of Research Progress
2: Research has progressed on the whole more than it was originally planned.
Reason
In this fiscal year, what we have achieved can be summarized as follows.
(1) We investigated the information update delivery and acquisition (IUDA) problem for IoT with serverless computing and formulate it as an integer linear program (ILP) to minimize a weighted sum of the age of service (AoS) of serverless functions, where the AoS of each serverless function is determined by the minimum AoI of the constituent IoT devices.
(2) To address the IUDA problem, we proposed the offline information update scheduling (OFF-IUS) algorithm that sequentially finds out an information update strategy that gives the best AoS performance until no further contributing information updates can be found.
(3) In case that the prior knowledge of the arrivals of serverless functions is not available, we further proposed the online IUS (ON-IUS) algorithm that can schedule information updates for new serverless functions as soon as they arrive.
(4) Our simulation results demonstrated that the proposed solutions outperform various existing solutions in terms of the AoS performance, and we also showed how the achieved AoS performance varies with system parameters.
|
| Strategy for Future Research Activity |
In the next fiscal year, our goals can be enumerated as follows.
(1) We aim to study a concurrent information update scheduling problem in edge-native (EN) systems to minimize the average age of service (AoS) of EN tasks, where the AoS of each EN task is determined by the minimum AoI of the constituent IoT devices.
(2) To address the above problem, we will propose the age efficiency (AE) value for each individual information update, which is defined as the AoS reduction divided by a normalized connection cost.
(3) We will design an AE based flexible lookahead scheduling algorithm to greedily schedule information updates, where the lookahead level is configurable according to the degree of clairvoyance (i.e., the knowledge of channel state information and upcoming EN task arrivals that can be revealed to a system controller).
(4) We will conduct simulations to demonstrate that the proposed solution outperforms the existing solutions in terms of the AoS performance and also show how the achieved AoS performance varies with system parameters.
|
