BatAlloc: Effective Battery Allocation against Power Outage for Cellular Base Stations

Base stations play a key role in today's cellular networks. Their reliability and availability heavily depend on the electrical power supply. Modern power grid is known to be highly reliable, but still suffers from outage due to severe weather or human-driven accidents, particularly in remote areas. Most of the base stations are thus equipped with backup battery groups. Given their limited numbers and capacities, they however can hardly sustain a long power outage without a proper allocation strategy. A deep discharge will also accelerate the battery degradation and eventually contribute to a higher battery replacement cost. In this paper, we closely examine the power outage events and the backup battery status from a one-year dataset of a major cellular service provider, including 4206 base stations distributed across 8400 square kilometers and more than 1.5 million records on battery activities. We then develop BatAlloc, a battery allocation framework to address the mismatch between the battery supporting ability and diverse power outage incidents. We build up a deep leaning based approach to accurately profile battery features and present an effective solution that minimizes both service interruption time and the overall cost. Our trace-driven experiments show that BatAlloc cuts down the average service interruption time from 5 hours to nearly zero with only 88% of the overall cost compared to the current practical allocation.

[1]  Yakup S. Ozkazanç,et al.  A new online state-of-charge estimation and monitoring system for sealed lead-acid batteries in Telecommunication power supplies , 2005, IEEE Transactions on Industrial Electronics.

[2]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[3]  David A. Stone,et al.  Nonlinear observers for predicting state-of-charge and state-of-health of lead-acid batteries for hybrid-electric vehicles , 2005, IEEE Transactions on Vehicular Technology.

[4]  John Salvatier,et al.  Theano: A Python framework for fast computation of mathematical expressions , 2016, ArXiv.

[5]  Adnan H. Anbuky,et al.  The behaviour of the coup de fouet of valve-regulated lead–acid batteries , 2002 .

[6]  Chunbo Zhu,et al.  State-of-Charge Determination From EMF Voltage Estimation: Using Impedance, Terminal Voltage, and Current for Lead-Acid and Lithium-Ion Batteries , 2007, IEEE Transactions on Industrial Electronics.

[7]  Adnan H. Anbuky,et al.  VRLA battery state-of-charge estimation in telecommunication power systems , 2000, IEEE Trans. Ind. Electron..

[8]  I. Kurisawa,et al.  Capacity estimating method of lead-acid battery by short-time discharge-introduction of approximate expression of discharge curve obtained by compound expression of straight line and hyperbola , 1997, Proceedings of Power and Energy Systems in Converging Markets.

[9]  A. H. Anbuky,et al.  VRLA battery capacity measurement and discharge reserve time prediction , 1998, INTELEC - Twentieth International Telecommunications Energy Conference (Cat. No.98CH36263).

[10]  C. Hwang.  Multiple Objective Decision Making - Methods and Applications: A State-of-the-Art Survey , 1979 .

[11]  Feng Wang,et al.  Boosting Service Availability for Base Stations of Cellular Networks by Event-driven Battery Profiling , 2016, PERV.

[12]  Feng Wang,et al.  On Backup Battery Data in Base Stations of Mobile Networks: Measurement, Analysis, and Optimization , 2016, CIKM.

[13]  Julian de Hoog,et al.  A Multi-Factor Battery Cycle Life Prediction Methodology for Optimal Battery Management , 2015, e-Energy.

[14]  P.E. Pascoe,et al.  VRLA battery discharge reserve time estimation , 2004, IEEE Transactions on Power Electronics.

[15]  Whitham D. Reeve.  DC Power System Design for Telecommunications: Reeve/dc Power System Design for Telecommunications , 2006 .