Abstract

A large number of connected sensors and devices in Internet of Things (IoT) can generate large amounts of computing data and increase massive energy consumption. Real-time states monitoring and data processing of IoT nodes are of great significance, but the processing power of IoT devices is limited. Using the emerging mobile edge computing (MEC), IoT devices can offload computing tasks to an MEC server associated with small or macro base stations. Moreover, the use of renewable energy harvesting capabilities in base stations or IoT nodes may reduce energy consumption. As wireless channel conditions vary with time and the arrival rates of renewable energy, computing tasks are stochastic, and data offloading and renewable energy aware for IoT devices under a dynamic and unknown environment are major challenges. In this work, we design a data offloading and renewable energy aware model considering an MEC server performing multiple stochastic computing tasks and involving time-varied wireless channels. To optimize data transmission delay, energy consumption, and bandwidth allocation jointly, and to avoid the curse of dimensionality caused by the complexity of the action space, we propose a joint optimization method for data offloading, renewable energy aware, and bandwidth allocation for IoT devices based on deep reinforcement learning (JODRBRL), which can handle the continuous action space. JODRBRL can minimize the total system cost(including data buffer delay cost, energy consumption cost, and bandwidth cost) and obtain an efficient solution by adaptively learning from the dynamic IoT environment. The numerical results demonstrate that JODRBRL can effectively learn the optimal policy, which outperforms Dueling DQN, Double DQN (DDQN), and greedy policy in stochastic environments.

Highlights

  • Internet of Things (IoT) devices are widely used in various fields, such as industrial control, network equipment systems, public safety equipment, and environmental monitoring [1]

  • We propose a joint optimization scheme for data transmission delay, energy consumption, and bandwidth allocation based on deep deterministic policy gradient (DDPG), which is a model-free deep-reinforcement learning (DRL) method and can efficiently handle continuous action space

  • Considering the time-varying channel state as well as stochastic computing tasks and renewable energy supply, we proposed a joint optimization scheme for data delay, energy consumption, and bandwidth allocation based on deep reinforcement learning with continuous action space which could minimize the total cost including buffer delay cost, energy consumption cost and bandwidth cost

Read more

Summary

INTRODUCTION

IoT devices are widely used in various fields, such as industrial control, network equipment systems, public safety equipment, and environmental monitoring [1]. MEC has been proposed as a solution that enables wireless IoT devices (e.g., mobile phones and smart watches) to offload computing tasks to MEC servers according to the base station which can significantly improve computing efficiency and reduce processing delays and energy consumption [6]. Under time-varying channel state and renewable energy supply, we propose a joint optimization scheme for transmission delay, renewable energy consumption, and bandwidth allocation based on deep reinforcement learning (JODRBRL). According to the energy supply of the small base station, the computing task can be partially performed by a local processor or partially offloaded to the MEC server. We propose a joint optimization scheme for data transmission delay, energy consumption, and bandwidth allocation based on deep deterministic policy gradient (DDPG), which is a model-free deep-reinforcement learning (DRL) method and can efficiently handle continuous action space.

RELATED WORK
ENERGY MODEL
BANDWIDTH ALLOCATION MODEL
DEEP REINFORCEMENT LEARNING OPTIMIZATION SCHEME
SIMULATION SETUP
5: Reset the simulation environment of the proposed
CONCLUSION
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call