Battery-Aware Optimization of Green Small Cells: Sizing and Energy Management

Mendil, Mouhcine; Domenico, Antonio De; Heiries, Vincent; Caire, Raphaël; Hadjsaïd, Nourédine

doi:10.1109/tgcn.2018.2829344

Cited by 31 publications

(13 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite of significant grid energy saving using MEC, the processing and content caching at the mobile edges still causes noticeable energy consumption especially in areas with dense deployment [19]. The integration of ambient renewable energy into the MEC has attracted the attentions from both academia and industry [9], [10], [20], [21]. In renewable energy-powered systems, the design objective should be improving the system performance subject to the available harvested energy since the renewable energy comes with very low cost.…”

Section: Related Workmentioning

confidence: 99%

“…However, these two works consider only either one edge server or one mobile device which can not be extended to large scale system in which the spatial diversity in the energy harvesting at different regions should be taken into account. Discussions on optimal battery storage size and efficient use of harvested energy in green cellular networks are detailed in respectively [20] and [21]. The existing works mainly focus on the computing performance of renewable energy-powered MEC system.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Energy-Aware QoE and Backhaul Traffic Optimization in Green Edge Adaptive Mobile Video Streaming

Mehrabi

Siekkinen

Ylä-Jääski

2019

IEEE Trans. on Green Commun. Netw.

View full text Add to dashboard Cite

Collaborative caching and processing at the network edges through mobile edge computing (MEC) helps to improve the quality of experience (QoE) of mobile clients and alleviate significant traffic on backhaul network. Due to the challenges posed by current grid powered MEC systems, the integration of time-varying renewable energy into the MEC known as green MEC (GMEC) is a viable emerging solution. In this paper, we investigate the enabling of GMEC on joint optimization of QoE of the mobile clients and backhaul traffic in particularly dynamic adaptive video streaming over HTTP (DASH) scenarios. Due to intractability, we design a greedy-based algorithm with self-tuning parameterization mechanism to solve the formulated problem. Simulation results reveal that GMEC-enabled DASH system indeed helps not only to decrease grid power consumption but also significantly reduce backhaul traffic and improve average video bitrate of the clients. We also find out a threshold on the capacity of energy storage of edge servers after which the average video bitrate and backhaul traffic reaches a stable point. Our results can be used as some guidelines for mobile network operators (MNOs) to judge the effectiveness of GMEC for adaptive video streaming in next generation of mobile networks. Index Terms-Green mobile edge computing (GMEC), DASH, Quality of experience (QoE), Fairness, Greedy-based algorithm. Antti Ylä-Jääski received the Ph.D. degree from ETH Zurich in 1993. From 1994 to 2009, he was with Nokia in several research and research management positions, with a focus on future Internet, mobile networks, applications, services, and service architectures. Since 2004, he has been a tenured Professor with the Department of Computer Science, Aalto University. His current research interests include mobile cloud computing, mobile multimedia systems, pervasive computing and communications, indoor positioning and navigation, energy efficient communications and computing, and Internet of Things.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Energy-Aware QoE and Backhaul Traffic Optimization in Green Edge Adaptive Mobile Video Streaming

Mehrabi

Siekkinen

Ylä-Jääski

2019

IEEE Trans. on Green Commun. Netw.

View full text Add to dashboard Cite

show abstract

“…This proposal poses the theoretical basis on the application of RL to energy harvesting networks; however, it is not applicable to multi-agent systems. RL has also been used in [28] to control a single EH SBS as a function of the local harvesting process and storage conditions. The authors design the SBS control with a Fuzzy Q-learning algorithm aimed at improving the battery lifetime and minimizing the electricity expenditures.…”

Section: Related Workmentioning

confidence: 99%

Coordinated Load Control of Renewable Powered Small Base Stations Through Layered Learning

Miozzo

Piovesan

Dini

2020

IEEE Trans. on Green Commun. Netw.

View full text Add to dashboard Cite

The massive deployment of Small Base Stations (SBSs) represents one of the most promising solutions adopted by 5G cellular networks to meet the foreseen huge traffic demand. The usage of renewable energies for powering the SBSs attracted particular attention for reducing the energy footprint and, thus, mitigating the environmental impact of mobile networks and enabling cost saving for the operators. The complexity of the system and the variability of the harvesting process suggest the adoption of learning methods. Here, we investigate techniques based on the Layered Learning paradigm to control dense networks of SBSs powered solely by solar energy. In the first layer, SBSs locally select switch ON/OFF policies according to their energy income and traffic demand based on a Heuristically Accelerated Reinforcement Learning method. The second layer relies on an Artificial Neural Network that estimates the network load conditions to implement a centralized controller enforcing local agent decisions. Simulation results prove that the control of the proposed framework mimics the behavior of the upper bound obtained offline with Dynamic Programming. Moreover, the proposed layered framework outperforms both a greedy and a distributed Reinforcement Learning solution in terms of throughput and energy efficiency under different traffic conditions.

show abstract

“…Here, the authors propose RL based on-line solutions for offloading and auto-scaling in edge computing devices that are powered by EH. On the other hand, the authors in [22] proposed a RL based energy controller for a SC powered by energy harvesting, battery and smart grid by considering battery aging effects. This work is based on FQL and is shown to provide significant extension to the life time of a small cell battery.…”

Section: Related Workmentioning

confidence: 99%

Dynamic control of functional splits for energy harvesting virtual small cells: A distributed reinforcement learning approach

Temesgene

Miozzo

Dini

2019

Computer Communications

View full text Add to dashboard Cite

To meet the growing mobile data traffic demand, Mobile Network Operators (MNOs) are deploying dense infrastructures of small cells as a solution for capacity enhancement. This densification increases the power consumption of mobile networks, thus impacting the environment. As a result, we have seen a recent trend of powering base stations with ambient energy sources to achieve both environmental sustainability and cost reductions. In addition, flexible functional split in Cloud Radio Access Network (CRAN) is a promising solution to overcome the capacity and latency challenges in the fronthaul. In such architecture, local base stations perform partial baseband processing while the remaining part will take place at the central cloud. As the cells become smaller and deployed in a densified manner, it is evident that baseband processing power consumption has a huge share in the total base station power consumption breakdown.In this paper, we propose a network scenario where the baseband processes of the virtual small cells powered solely by energy harvesters and batteries can be opportunistically executed in a grid-connected edge computing server, co-located at the macro base station site. We state the corresponding energy minimization problem and propose multi-agent Reinforcement Learning (RL) to solve it. Distributed Fuzzy Q-Learning and Q-Learning on-line algorithms are tailored for our purposes. Coordination among the multiple agents is favored by broadcasting system level information to the independent learners. The evaluation of the network performance confirms that favoring coordination among the agents via broadcasting may achieve higher system level gains and cumulative rewards closer to the off-line bounds than solutions that are unaware of system level information. Finally, our analysis permits to evaluate the benefits of continuous state/action representation for the learning algorithms in terms of faster convergence, higher cumulative reward and adaptivity to changing environments.

show abstract

Battery-Aware Optimization of Green Small Cells: Sizing and Energy Management

Cited by 31 publications

References 32 publications

Energy-Aware QoE and Backhaul Traffic Optimization in Green Edge Adaptive Mobile Video Streaming

Energy-Aware QoE and Backhaul Traffic Optimization in Green Edge Adaptive Mobile Video Streaming

Coordinated Load Control of Renewable Powered Small Base Stations Through Layered Learning

Dynamic control of functional splits for energy harvesting virtual small cells: A distributed reinforcement learning approach

Contact Info

Product

Resources

About