Future Wei Technologies, Inc.

Huawei Technologies Co., Limited

Kamalaharan Dushyanthan

Iyad Alfalujah

Nandu Gopalakrishnan

Yan Xin

Suman Das

Jin Yang

Mark Ernest Newbury

Yongxi Tan

Yanjie Fu

James Mathew

Lyad Alfalujah

Convergence times associated with simulated annealing based (SA-based) optimization in wireless networks can be reduced by introducing an additional local or cell-level evaluation step into the evaluation of global solutions. In particular, new local solutions may be evaluated based on local performance criteria when the new solutions are in a global solution deemed to have satisfied a global performance criteria. New local solutions that satisfy their corresponding local performance criteria remain in the new global solution. New local solutions that do not satisfy their corresponding local performance criteria are replaced with a corresponding current local solution from a current global solution, thereby modifying the new global solution. The resulting modified global solution includes both new local solutions and current local solutions prior to being accepted as the current global solution for the next iteration.

Autonomous, closed-loop and adaptive simulated annealing based machine learning approach for intelligent analytics-assisted self-organizing-networks (SONs)

Embodiments are provided for calibration, preprocessing, and segmentation for user localization and network traffic density estimation. The embodiments include sending, from a network component, a request to a plurality of user equipment (UEs) to participate in reporting localization data. Reports for localization data including no-lock reports are received from at least some of the UEs. The no-lock reports indicate indoor UEs among the UEs. The network preprocesses the localization data by eliminating, from the localization data, data that increases the total noise to signal ratio. The localization data is then processed using a model that distinguishes between different buildings. This includes associating, according to a radio map, radio characteristics in the localization data with corresponding bins in a non-uniform grid of coverage. The non-uniform grid is predetermined to maximize uniqueness between the radio characteristics. The indoor UEs are associated with corresponding buildings using the no-lock reports data.

System and method for localization and traffic density estimation via segmentation and calibration sampling

Growing community of inventors

Metuchen, NJ, United States of America

Kamalaharan Dushyanthan