Greener RAN Operation Through Machine Learning

Vallero, Greta; Renga, Daniela; Meo, Michela; Marsan, Marco Ajmone

doi:10.1109/tnsm.2019.2923881

Cited by 36 publications

(63 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The information collected from Wi-Fi networks, used to build a dataset and create a prediction system, is not always the same, as can be observed in [1], [3]- [5], [8], [10]- [13], [22]- [24]. However, the key concept behind those studies is collecting data about the Wi-Fi network to create a detection or counting system using machine learning algorithms.…”

Section: Related Workmentioning

confidence: 99%

“…The work presented in [9] used algorithm adaptation multi-label methods to deal with the classification problem for HVAC systems. Regression models using Wi-Fi data to give an estimated users count are mostly used in HVAC scheduling systems [10], [11], [18], but some studies have also used regression models to develop ROD strategy mechanisms [23], [24]. Table 1 compares related work about how they build occupancy prediction models.…”

Section: Related Workmentioning

confidence: 99%

“…Also, those studies did not compare and evaluate single-label and multi-label methods to determine which would give the best predictions, as our work does. It is worth mentioning that while the study of Vallero et al [24] use and compare both individual and collective models, it does not compare them using the same machine learning algorithms, but it rather compares collective and individual models using several machine learning algorithms. Moreover, Table 1 shows that there was no consensus on whether to use collective or individual models to give predictions and that no other study compares them, as our work does.…”

Section: Related Workmentioning

confidence: 99%

“…However, it is important to mention that the results achieved with this analysis are merely a baseline estimation. The mechanism proposed for this evaluation scenario is simple and does not take several aspects of the Wi-Fi network into consideration as others do [5], [6], [15], [16], [23], [24]. Even though, it is fair enough to assume that it gives a good baseline estimation of how much energy could have been saved using such principles with more complex and complete mechanisms, which we are going to address as future work.…”

Section: Energy-saving Analysismentioning

confidence: 99%

See 3 more Smart Citations

A Unified Methodology to Predict Wi-Fi Network Usage in Smart Buildings

et al. 2021

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Energy-saving Analysismentioning

confidence: 99%

See 2 more Smart Citations

A Unified Methodology to Predict Wi-Fi Network Usage in Smart Buildings

et al. 2021

View full text Add to dashboard Cite

“…Recent advances in both machine learning (ML) and communication technologies offer the opportunity to solve such a challenge [10]. On the one hand, deep neural networks as well as novel techniques for time series forecasting have gained increasing accuracy [11], in addition to the ability to characterize the uncertainty of predictions [12]. On the other hand, modern cellular networks (i.e., 4G and 5G) allow for significant flexibility in managing radio resources through software components running in virtualized environments, for instance, at the edge of the access network [10,13].…”

Section: Introductionmentioning

confidence: 99%

Data-Driven Energy Conservation in Cellular Networks: A Systems Approach

Premsankar

Piao

Nicholson

et al. 2021

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

The energy consumption of mobile networks is already substantial nowadays, and only expected to further increase with the roll-out of 5G. Base stations are the key elements in this context: reducing their energy consumption is of paramount importance for network operators, not only to lower operating costs, but also to meet sustainable development goals. Today's base stations are typically over-provisioned, i.e., they comprise multiple cells to meet the peak load in a region. Therefore, substantial energy savings are possible by switching off cells that are under-utilized. This article proposes a datadriven approach to determine the time periods when a cell can be switched off. Forecasting is used to accurately predict network utilization and automatically find the time intervals to reliably switch off a cell. We carefully analyze the requirements of the system as a whole, from data collection to forecasting methods, to enable effective energy savings in practice. Considering several real-world traces from LTE networks, we show that an average of 10.24% energy savings is possible. We explore the tradeoffs between energy savings and overhead in switching off cells, and provide insights into the choice of methods accordingly. In particular, we show that the accuracy of forecasting is not the most important factor in achieving energy savings; instead, the prediction (uncertainty) interval plays a key role in being able to achieve energy savings with less impact on end-users. Finally, we propose a model to generate utilization traces that match the distribution of real-world traces obtained from cellular networks.

show abstract

Recent Progress in Reconfigurable and Intelligent Metasurfaces: A Comprehensive Review of Tuning Mechanisms, Hardware Designs, and Applications

Saifullah

Boag

et al. 2022

Advanced Science

View full text Add to dashboard Cite

Intelligent metasurfaces have gained significant importance in recent years due to their ability to dynamically manipulate electromagnetic (EM) waves. Their multifunctional characteristics, realized by incorporating active elements into the metasurface designs, have huge potential in numerous novel devices and exciting applications. In this article, recent progress in the field of intelligent metasurfaces are reviewed, focusing particularly on tuning mechanisms, hardware designs, and applications. Reconfigurable and programmable metasurfaces, classified as space gradient, time modulated, and space-time modulated metasurfaces, are discussed. Then, reconfigurable intelligent surfaces (RISs) that can alter their wireless environments, and are considered as a promising technology for sixth-generation communication networks, are explored. Next, the recent progress made in simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) that can achieve full-space EM wave control are summarized. Finally, the perspective on the challenges and future directions of intelligent metasurfaces are presented.

show abstract

Greener RAN Operation Through Machine Learning

Cited by 36 publications

References 34 publications

A Unified Methodology to Predict Wi-Fi Network Usage in Smart Buildings

A Unified Methodology to Predict Wi-Fi Network Usage in Smart Buildings

Data-Driven Energy Conservation in Cellular Networks: A Systems Approach

Recent Progress in Reconfigurable and Intelligent Metasurfaces: A Comprehensive Review of Tuning Mechanisms, Hardware Designs, and Applications

Contact Info

Product

Resources

About