English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

To meet the ever increasing mobile traffic demand in 5G era, base stations(BSs) have been densely deployed in radio access networks (RANs) to increasethe network coverage and capacity. However, as the high density of BSs isdesigned to accommodate peak traffic, it would consume an unnecessarily largeamount of energy if BSs are on during off-peak time. To save the energyconsumption of cellular networks, an effective way is to deactivate some idlebase stations that do not serve any traffic demand. In this paper, we develop atraffic-aware dynamic BS sleep control framework, named DeepBSC, which presentsa novel data-driven learning approach to determine the BS active/sleep modeswhile meeting lower energy consumption and satisfactory Quality of Service(QoS) requirements. Specifically, the traffic demands are predicted by theproposed GS-STN model, which leverages the geographical and semanticspatial-temporal correlations of mobile traffic. With accurate mobile trafficforecasting, the BS sleep control problem is cast as a Markov Decision Processthat is solved by Actor-Critic reinforcement learning methods. To reduce thevariance of cost estimation in the dynamic environment, we propose a benchmarktransformation method that provides robust performance indicator for policyupdate. To expedite the training process, we adopt a Deep Deterministic PolicyGradient (DDPG) approach, together with an explorer network, which canstrengthen the exploration further. Extensive experiments with a real-worlddataset corroborate that our proposed framework significantly outperforms theexisting methods.

Deep Reinforcement Learning with Spatio-temporal Traffic Forecasting for Data-Driven Base Station Sleep Control