With the rapid increase in demand for mobile data, mobile network operators are trying to expand wireless network capacity by deploying wireless local area network (LAN) hotspots on to which they can offload their mobile traffic. However, these network-centric methods usually do not fulfill the interests of mobile users (MUs). Taking into consideration many issues such as different applications' deadlines, monetary cost and energy consumption, how the MU decides whether to offload their traffic to a complementary wireless LAN is an important issue. Previous studies assume the MU's mobility pattern is known in advance, which is not always true. In this paper, we study the MU's policy to minimize his monetary cost and energy consumption without known MU mobility pattern. We propose to use a kind of reinforcement learning technique called deep Q-network (DQN) for MU to learn the optimal offloading policy from past experiences. In the proposed DQN based offloading algorithm, MU's mobility pattern is no longer needed. Furthermore, MU's state of remaining data is directly fed into the convolution neural network in DQN without discretization. Therefore, not only does the discretization error present in previous work disappear, but also it makes the proposed algorithm has the ability to generalize the past experiences, which is especially effective when the number of states is large. Extensive simulations are conducted to validate our proposed offloading algorithms.
Cheng ZHANG
Waseda University
Zhi LIU
Shizuoka University
Bo GU
Kogakuin University
Kyoko YAMORI
Asahi University,Waseda University
Yoshiaki TANAKA
Waseda University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Cheng ZHANG, Zhi LIU, Bo GU, Kyoko YAMORI, Yoshiaki TANAKA, "A Deep Reinforcement Learning Based Approach for Cost- and Energy-Aware Multi-Flow Mobile Data Offloading" in IEICE TRANSACTIONS on Communications,
vol. E101-B, no. 7, pp. 1625-1634, July 2018, doi: 10.1587/transcom.2017CQP0014.
Abstract: With the rapid increase in demand for mobile data, mobile network operators are trying to expand wireless network capacity by deploying wireless local area network (LAN) hotspots on to which they can offload their mobile traffic. However, these network-centric methods usually do not fulfill the interests of mobile users (MUs). Taking into consideration many issues such as different applications' deadlines, monetary cost and energy consumption, how the MU decides whether to offload their traffic to a complementary wireless LAN is an important issue. Previous studies assume the MU's mobility pattern is known in advance, which is not always true. In this paper, we study the MU's policy to minimize his monetary cost and energy consumption without known MU mobility pattern. We propose to use a kind of reinforcement learning technique called deep Q-network (DQN) for MU to learn the optimal offloading policy from past experiences. In the proposed DQN based offloading algorithm, MU's mobility pattern is no longer needed. Furthermore, MU's state of remaining data is directly fed into the convolution neural network in DQN without discretization. Therefore, not only does the discretization error present in previous work disappear, but also it makes the proposed algorithm has the ability to generalize the past experiences, which is especially effective when the number of states is large. Extensive simulations are conducted to validate our proposed offloading algorithms.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2017CQP0014/_p
Copy
@ARTICLE{e101-b_7_1625,
author={Cheng ZHANG, Zhi LIU, Bo GU, Kyoko YAMORI, Yoshiaki TANAKA, },
journal={IEICE TRANSACTIONS on Communications},
title={A Deep Reinforcement Learning Based Approach for Cost- and Energy-Aware Multi-Flow Mobile Data Offloading},
year={2018},
volume={E101-B},
number={7},
pages={1625-1634},
abstract={With the rapid increase in demand for mobile data, mobile network operators are trying to expand wireless network capacity by deploying wireless local area network (LAN) hotspots on to which they can offload their mobile traffic. However, these network-centric methods usually do not fulfill the interests of mobile users (MUs). Taking into consideration many issues such as different applications' deadlines, monetary cost and energy consumption, how the MU decides whether to offload their traffic to a complementary wireless LAN is an important issue. Previous studies assume the MU's mobility pattern is known in advance, which is not always true. In this paper, we study the MU's policy to minimize his monetary cost and energy consumption without known MU mobility pattern. We propose to use a kind of reinforcement learning technique called deep Q-network (DQN) for MU to learn the optimal offloading policy from past experiences. In the proposed DQN based offloading algorithm, MU's mobility pattern is no longer needed. Furthermore, MU's state of remaining data is directly fed into the convolution neural network in DQN without discretization. Therefore, not only does the discretization error present in previous work disappear, but also it makes the proposed algorithm has the ability to generalize the past experiences, which is especially effective when the number of states is large. Extensive simulations are conducted to validate our proposed offloading algorithms.},
keywords={},
doi={10.1587/transcom.2017CQP0014},
ISSN={1745-1345},
month={July},}
Copy
TY - JOUR
TI - A Deep Reinforcement Learning Based Approach for Cost- and Energy-Aware Multi-Flow Mobile Data Offloading
T2 - IEICE TRANSACTIONS on Communications
SP - 1625
EP - 1634
AU - Cheng ZHANG
AU - Zhi LIU
AU - Bo GU
AU - Kyoko YAMORI
AU - Yoshiaki TANAKA
PY - 2018
DO - 10.1587/transcom.2017CQP0014
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E101-B
IS - 7
JA - IEICE TRANSACTIONS on Communications
Y1 - July 2018
AB - With the rapid increase in demand for mobile data, mobile network operators are trying to expand wireless network capacity by deploying wireless local area network (LAN) hotspots on to which they can offload their mobile traffic. However, these network-centric methods usually do not fulfill the interests of mobile users (MUs). Taking into consideration many issues such as different applications' deadlines, monetary cost and energy consumption, how the MU decides whether to offload their traffic to a complementary wireless LAN is an important issue. Previous studies assume the MU's mobility pattern is known in advance, which is not always true. In this paper, we study the MU's policy to minimize his monetary cost and energy consumption without known MU mobility pattern. We propose to use a kind of reinforcement learning technique called deep Q-network (DQN) for MU to learn the optimal offloading policy from past experiences. In the proposed DQN based offloading algorithm, MU's mobility pattern is no longer needed. Furthermore, MU's state of remaining data is directly fed into the convolution neural network in DQN without discretization. Therefore, not only does the discretization error present in previous work disappear, but also it makes the proposed algorithm has the ability to generalize the past experiences, which is especially effective when the number of states is large. Extensive simulations are conducted to validate our proposed offloading algorithms.
ER -