*Deep Reinforcement Learning for Online Computation Offloading in Wireless Powered Mobile-Edge Computing Networks*
This folder includs all pre-generated training and testing data set, including:
-**data_#.mat**: , where # = {5, 6, 7, 8, 9, 10, 20, 30} is the number of WDs
-[data_10_WeightsAlternated.mat](data_10_WeightsAlternated.mat): The data set when all WDs' weights are alternated. It contains the same values of 'input_h' as the ones stored in [data_10.mat](data_10.mat). However, the optimal offloading mode, resource allocation, and the maximum computation rate are recalculated since WDs' weights are alternated.
## Data Format
Data samples are generated by enumerating all 2^N binary offloading actions for N <= 10 and by following the CD method presented in [2] for N = 20, 30. There are 30,000 (for N = 10, 20, 30) or 10,000 (otherwise) samples saved in each \*.mat file. Where each data sample includes:
| input_h | The wireless channel gain between WDs and the AP $\mathbf{h}$ |
| output_mode | The optimal binary offloading action $\mathbf{x}^*$ |
| output_a | The optimal fraction of time that the AP broadcasts RF energy for the WDs to harvest $a^*$ |
| output_tau | The optimal fraction of time allocated to WDs for task offloading $\mathbf{\tau}^*$|
| output_obj | The optimal weighted sum computation rate $Q^*$ |
## About our works
1. Liang Huang, Suzhi Bi, and Ying-jun Angela Zhang, "Deep Reinforcement Learning for Online Computation Offloading in Wireless Powered Mobile-Edge Computing Networks", on [arxiv:1808.01977](https://arxiv.org/abs/1808.01977).
2. S. Bi and Y. J. Zhang, "Computation rate maximization for wireless powered mobile-edge computing with binary computation offloading," *IEEE Trans. Wireless Commun.*, vol. 17, no. 6, pp. 4177-4190, Jun. 2018.
## About authors
- Liang HUANG, lianghuang AT zjut.edu.cn
- Suzhi BI, bsz AT szu.edu.cn
- Ying Jun (Angela) Zhang, yjzhang AT ie.cuhk.edu.hk
