Power Control and Resource Allocation for Multi-Cell OFDM Networks With Load Coupling

Yang, Zhaohui; Pan, Cunhua; Xu, Hao; Shi, Jianfeng; Chen, Ming

doi:10.1109/access.2018.2816916

Cited by 5 publications

(23 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(11) is a nonconvex optimization problem. We use the suboptimal linear programming method proposed in [44] as the benchmark.…”

Section: High Complexity Problemmentioning

confidence: 99%

“…In [44], the problem is converted to a convex optimization problem and solved by sequential least squares programming (SLSQP) optimization.…”

Section: High Complexity Problemmentioning

confidence: 99%

“…Then, we analyze the distribution of power, sum-rate, and user-rate. The proposed model is compared with the suboptimal SLSQP solution [44] and the random power allocation strategy. We also consider the greedy water filling algorithm from Section V-C1 by applying it to each BS independently.…”

Section: High Complexity Problemmentioning

confidence: 99%

“…15 consider the case where there exist N = 16 subcarriers. DNN takes around 0.7 ms to predict the power allocation per sample in the dataset, while it takes around two minutes per sample with SLSQP solution [44]. The dataset consists of 1000 samples.…”

Section: ) Variation Of Efficiency Of the Proposed Dnn Modelmentioning

confidence: 99%

See 3 more Smart Citations

A Study on Deep Learning for Latency Constraint Applications in Beyond 5G Wireless Systems

2020

View full text Add to dashboard Cite

The fifth generation (5G) of wireless communications has led to many advancements in technologies such as large and distributed antenna arrays, ultra-dense networks, software based networks and network virtualization. However, the need for a higher level of automation to establish hyper-low latency and hyper-high reliability for beyond 5G applications requires extensive research on machine learning with applications in wireless communications. Thereby, learning techniques will take a central stage in the sixth generation of wireless communications to cope up with the stringent application requirements. This paper studies the practical limitations of these learning methods in the context of resource management in nonstationary radio environment. Based on the practical limitations we carefully design and propose supervised, unsupervised, and reinforcement learning models to support rate maximization objective under user mobility. We study the effects of practical systems such as latency and reliability on the rate maximization with deep learning models. For common testing in the non-stationary environment, we present a generic dataset generation method to benchmark across different learning models versus traditional optimal resource management solutions. Our results indicate that learning models have practical challenges related to training limiting their applications. These models need an environment-specific design to reach the accuracy of an optimal algorithm. Such an approach is practically not realistic due to the high resource requirement needed for frequent retraining. INDEX TERMS Machine learning, low-latency application, learning model ageing, mobile communications, 6G.

show abstract

“…(11) is a nonconvex optimization problem. We use the suboptimal linear programming method proposed in [44] as the benchmark.…”

Section: High Complexity Problemmentioning

confidence: 99%

“…In [44], the problem is converted to a convex optimization problem and solved by sequential least squares programming (SLSQP) optimization.…”

Section: High Complexity Problemmentioning

confidence: 99%

Section: High Complexity Problemmentioning

confidence: 99%

Section: ) Variation Of Efficiency Of the Proposed Dnn Modelmentioning

confidence: 99%

See 2 more Smart Citations

A Study on Deep Learning for Latency Constraint Applications in Beyond 5G Wireless Systems

2020

View full text Add to dashboard Cite

show abstract

“…In HetNets, the load (average utilization level of the time-frequency resource blocks) conditions in macro BSs and small BSs are in most case coupled. A realistic loadcoupled model was proposed in [17]- [20], which took into account the effect of the load conditions in terms of inter-cell interference. In [21], it was shown that this load-coupled model well models a multi-cell network.…”

Section: Introductionmentioning

confidence: 99%

Association and Load Optimization With User Priorities in Load-Coupled Heterogeneous Networks

Yang

Shi

et al. 2018

IEEE Trans. Wireless Commun.

Self Cite

View full text Add to dashboard Cite

In this paper, we consider the network utility maximization problem with various user priorities via jointly optimizing user association, load distribution and power control in a load-coupled heterogeneous network. In order to tackle the nonconvexity of the problem, we first analyze the problem by obtaining the optimal resource allocation strategy in closed form and characterizing the optimal base station load distribution pattern. Both observations are shown essential in simplifying the original problem and making it possible to transform the nonconvex load distribution and power control problem into convex reformulation via exponential variable transformation. An iterative algorithm with low complexity is accordingly presented to obtain a suboptimal solution to the joint optimization problem. Simulation results show that the proposed algorithm achieves better performance than conventional approaches.

show abstract

Supporting legacy and RF‐energy harvesting devices in multi‐cells OFDMA networks

Sarwar

Chin

2020

IET Communications

View full text Add to dashboard Cite

A multi-cell network that uses orthogonal frequency division multiplexing access (OFDMA) is studied here. Unlike prior works, the proposed network consists of both (i) legacy data users that do not have energy harvesting capability and have a minimum data rate requirement and (ii) radio frequency (RF)-energy harvesting devices with a minimum energy requirement. It studies sub-band allocation to users and transmits power allocation at base stations. The authors formulate a mixed-integer non-linear program and also present two heuristics to assign sub-band to base stations. Numerical results show that RF energy harvesting devices will not affect network capacity if legacy data users require a high data rate. In addition, the results obtained from the two proposed heuristics are ∼95% of the optimal solution.

show abstract

Power Control and Resource Allocation for Multi-Cell OFDM Networks With Load Coupling

Cited by 5 publications

References 46 publications

A Study on Deep Learning for Latency Constraint Applications in Beyond 5G Wireless Systems

A Study on Deep Learning for Latency Constraint Applications in Beyond 5G Wireless Systems

Association and Load Optimization With User Priorities in Load-Coupled Heterogeneous Networks

Supporting legacy and RF‐energy harvesting devices in multi‐cells OFDMA networks

Contact Info

Product

Resources

About