Demand forecast in supply chain
This work is confidential. I worked on demand forecast for an international brand of clothing business. I was responsible for the module of categorical feature encoding for model training, which achieved a significant increase in the forecast accuracy. Our team implemented backtests for all markets in global. Meanwhile, I identified a key issue that caused overfitting in the on-line operation of the project. We managed to proposed a method for dealing against the noise in datasets, which, as proved by backtests, significantly alleviated overfitting.
Facilitating radio resource management with fixed-point theory
This is my PhD dissertation work. The rapid growth from 4G to 5G of mobile communications poses significant challenges in providing high rate and capacity, making it more crucial for efficient utilization of time-frequency resource via optimally configuring the network. Mathematical optimization serves as a powerful tool for addressing these types of problems. However, gauging its potential in large scale cellular networks is non-trivial due to the inherent coupling of interference among cells. To address this issue, the dissertation adopts a so-called load-coupling system that mathematically formulates the mutual influence caused by radio resource allocation among cells. The model defines the time-frequency resource consumption in each cell as the cell load. The load of one cell governs the interference the cell generates to the others, since the cell transmits more frequently with higher load. The model enables joint optimization of multi-cell resource allocation with respect to the dynamics of resource occupancy of cells. The theoretical tool for solving this load-coupling system is fixed-point theory.
Six research papers are included in the dissertation:
Paper I: L. You and D. Yuan, “Load Optimization with User Association in Cooperative and Load-Coupled LTE Networks”, IEEE Transactions on Wireless Communications, vol. 16, no. 5, 2017.
Paper II: L. You, D. Yuan, N. Pappas, and P. Värbrand, “Energy-Aware Wireless Relay Selection in Load-Coupled OFDMA Cellular Networks”, IEEE Communications Letters, vol. 21, no. 1, 2017.
Paper III: L. You and D. Yuan, “User-centric Performance Optimization with Remote Radio Head Cooperation in C-RAN”, accepted in IEEE Transactions on Wireless Communications.
Paper IV: L. You, L. Lei, D. Yuan, S. Sun, S. Chatzinotas, and B. Ottersten, “A Framework for Optimizing Multi-cell NOMA: Delivering Demand with Less Resource”, in IEEE GLOBECOM, Singapore, 2017.
Paper V: L. You, D. Yuan, L. Lei, S. Sun, S. Chatzinotas, and B. Ottersten, “Resource Optimization with Load Coupling in Multi-cell NOMA”, IEEE Transactions on Wireless Communications, vol 17, no. 7, 2018.
Paper VI: L. You and D. Yuan, “A Note on Decoding Order in Optimizing Multi-Cell NOMA”, submitted to IEEE Transactions on Wireless Communications.
Paper I addresses the question of how network planning and coordination may increase the efficiency of spectrum usage, by jointly optimizing user association and resource allocation with coordinated multipoint (CoMP) transmission. Paper II investigates the potential of relay cooperation with CoMP for energy saving. As an extension to Papers I and II, Paper III studies the capacity maximization for any target group of users, keeping the quality-of-service (QoS) of other users being strictly met. Paper IV provides a general framework and a series of theoretical analysis for algorithmically enabling resource optimization in multi-cell non-orthogonal multiple access (NOMA) with load coupling, where users are allowed to group together for sharing time-frequency resource by successive interference cancellation (SIC). Under this framework, Paper V thoroughly explores the potential of NOMA networks, by achieving globally optimal resource usage efficiency with a mild condition, in terms of power allocation, user pair selection, and time-frequency resource allocation. Finally, Paper VI, serving as a complementary note, overcomes a key obstacle in analyzing load coupling convergence in NOMA networks.
Data-driven E-CMR platform for freight forwarding
The project is funded by ALMI.