Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Efficient Scheduling of Vehicular Tasks on Edge Systems with Green Energy and Battery Storage

Suvarthi Sarkar, Abinash Kumar Ray, Aryabartta Sahu

TL;DR

This research addresses the scheduling of computational tasks generated by autonomous vehicles to roadside units with power consumption proportional to the cube of the computational load of the server, and proposes an offline heuristics approach based on predicted solar energy and incoming task patterns for different time slots.

Abstract

The autonomous vehicle industry is rapidly expanding, requiring significant computational resources for tasks like perception and decision-making. Vehicular edge computing has emerged to meet this need, utilizing roadside computational units (roadside edge servers) to support autonomous vehicles. Aligning with the trend of green cloud computing, these roadside edge servers often get energy from solar power. Additionally, each roadside computational unit is equipped with a battery for storing solar power, ensuring continuous computational operation during periods of low solar energy availability. In our research, we address the scheduling of computational tasks generated by autonomous vehicles to roadside units with power consumption proportional to the cube of the computational load of the server. Each computational task is associated with a revenue, dependent on its computational needs and deadline. Our objective is to maximize the total revenue of the system of roadside computational units. We propose an offline heuristics approach based on predicted solar energy and incoming task patterns for different time slots. Additionally, we present heuristics for real-time adaptation to varying solar energy and task patterns from predicted values for different time slots. Our comparative analysis shows that our methods outperform state-of-the-art approaches upto 40\% for real-life datasets.

Efficient Scheduling of Vehicular Tasks on Edge Systems with Green Energy and Battery Storage

TL;DR

This research addresses the scheduling of computational tasks generated by autonomous vehicles to roadside units with power consumption proportional to the cube of the computational load of the server, and proposes an offline heuristics approach based on predicted solar energy and incoming task patterns for different time slots.

Abstract

The autonomous vehicle industry is rapidly expanding, requiring significant computational resources for tasks like perception and decision-making. Vehicular edge computing has emerged to meet this need, utilizing roadside computational units (roadside edge servers) to support autonomous vehicles. Aligning with the trend of green cloud computing, these roadside edge servers often get energy from solar power. Additionally, each roadside computational unit is equipped with a battery for storing solar power, ensuring continuous computational operation during periods of low solar energy availability. In our research, we address the scheduling of computational tasks generated by autonomous vehicles to roadside units with power consumption proportional to the cube of the computational load of the server. Each computational task is associated with a revenue, dependent on its computational needs and deadline. Our objective is to maximize the total revenue of the system of roadside computational units. We propose an offline heuristics approach based on predicted solar energy and incoming task patterns for different time slots. Additionally, we present heuristics for real-time adaptation to varying solar energy and task patterns from predicted values for different time slots. Our comparative analysis shows that our methods outperform state-of-the-art approaches upto 40\% for real-life datasets.

Paper Structure

This paper contains 34 sections, 19 equations, 17 figures, 1 table, 6 algorithms.

Table of Contents

  1. Introduction
  2. Literature Review
  3. System Model and Problem Statement
  4. System Model
  5. Task Model
  6. Edge Server Model
  7. Energy Source Model
  8. Problem Statement
  9. Task Scheduling on Edge server with Solar Energy and No Battery Backup (TS-ES-SNB)
  10. Task Scheduling on Edge server with Solar Energy and Infinite Battery Backup (TS-ES-SIB)
  11. Task Scheduling on Edge server with Solar Energy and Finite Battery Backup (TS-ES-SFB)
  12. Solutions Approach
  13. Solution Intuition
  14. Solution to Task Scheduling on ES with Solar Energy with no Battery (TS-ES-SNB)
  15. Special case :
  16. ...and 19 more sections

Figures (17)

  • Figure 1: System Architecture
  • Figure 2: Power model of the considered edge-cloud vehicular computing system
  • Figure 3: A simple example to demonstrate why redistribution of power is beneficial. The power model is used in \ref{['eqn:power']}. For ease of calculation, we considered that the values in$P_s=0$, $U^{max}=1$, $P^{max}=1$ and all tasks with utilization of 1.
  • Figure 4: A sample solution using the proposed approach, which increased the number of completed tasks by 44% with the amount of incoming solar power being constant.
  • Figure 5: The special case of TS-ES-SNB problem is mapped to Maximum Flow problem ford_fulkerson_1956 with the nodes and maximum flow capacities mentioned for a particular ES ($ES_j$).
  • ...and 12 more figures