Abstract: Aspects of the subject disclosure may include, for example, a method in which a processing system identifies a plurality of performance indicators comprising device performance indicators for a plurality of communication devices on a cellular network and network performance indicators for the cellular network. The method also includes obtaining historical data regarding the plurality of performance indicators for each of a series of time points during a past time period; the historical data for each of the plurality of performance indicators form an array of values for that performance indicator. The method further includes generating from each array a set of inputs to an algorithm for predicting a throughput of the cellular network during a future time period; the set of inputs comprises quantiles of the array, and the algorithm comprises a machine learning algorithm. Other embodiments are disclosed.

Abstract: Aspects of the subject disclosure may include, for example, a method in which a processing system identifies a plurality of performance indicators comprising device performance indicators for a plurality of communication devices on a cellular network and network performance indicators for the cellular network. The method also includes obtaining historical data regarding the plurality of performance indicators for each of a series of time points during a past time period; the historical data for each of the plurality of performance indicators form an array of values for that performance indicator. The method further includes generating from each array a set of inputs to an algorithm for predicting a throughput of the cellular network during a future time period; the set of inputs comprises quantiles of the array, and the algorithm comprises a machine learning algorithm. Other embodiments are disclosed.

Abstract: Aspects of the subject disclosure may include, for example, a method in which a processing system identifies a plurality of performance indicators comprising device performance indicators for a plurality of communication devices on a cellular network and network performance indicators for the cellular network. The method also includes obtaining historical data regarding the plurality of performance indicators for each of a series of time points during a past time period; the historical data for each of the plurality of performance indicators form an array of values for that performance indicator. The method further includes generating from each array a set of inputs to an algorithm for predicting a throughput of the cellular network during a future time period; the set of inputs comprises quantiles of the array, and the algorithm comprises a machine learning algorithm. Other embodiments are disclosed.

Abstract: Aspects of the subject disclosure may include, for example, a method in which a processing system identifies a plurality of performance indicators comprising device performance indicators for a plurality of communication devices on a cellular network and network performance indicators for the cellular network. The method also includes obtaining historical data regarding the plurality of performance indicators for each of a series of time points during a past time period; the historical data for each of the plurality of performance indicators form an array of values for that performance indicator. The method further includes generating from each array a set of inputs to an algorithm for predicting a throughput of the cellular network during a future time period; the set of inputs comprises quantiles of the array, and the algorithm comprises a machine learning algorithm. Other embodiments are disclosed.

Abstract: Aspects of the subject disclosure may include, for example, a method in which a processing system identifies a plurality of performance indicators comprising device performance indicators for a plurality of communication devices on a cellular network and network performance indicators for the cellular network. The method also includes obtaining historical data regarding the plurality of performance indicators for each of a series of time points during a past time period; the historical data for each of the plurality of performance indicators form an array of values for that performance indicator. The method further includes generating from each array a set of inputs to an algorithm for predicting a throughput of the cellular network during a future time period; the set of inputs comprises quantiles of the array, and the algorithm comprises a machine learning algorithm. Other embodiments are disclosed.

Abstract: A communication system comprises a remote optimization server and a central optimization server adapted to communicate with each via a backhaul network. The central optimization server communicates with core network elements for data delivery. The servers provide access to local data servers, manage backhaul links, perform data caching, and optimize transmission of data that needs to be back-hauled in order to reduce data transfer via the backhaul network in a manner which is transparent to users and to core network elements. The servers perform compression and protocol optimization. The remote optimization server comprises a HTTP accelerator which uses client and server side optimization functions to retrieve a bundle of resources associated with a request for base HTML, and maintains a set of persistent connections over which all HTTP traffic is carried.

Abstract: A timeline schedule analysis study is modeled for automatically generating business intelligence information regarding the timeline schedule. A software application program is provided that has equations and business rules that together define a process, a timeline, and deliverables associated with the timeline schedule analysis. The program is populated with timeline schedules prepared using other software. The program provides a process and apparatus for identifying and ranking activities with anomalies in a list based on equations and business rules. In order to evaluate and forecast the performance of the timeline schedule, trend analysis of the anomaly metrics is automatically generated. An apparatus for collaboration between project's parties to enhance the communications and facilitate exchanging the comments and changes of the timeline schedule is provided.

Abstract: A communication system comprises a remote optimisation server and a central optimisation server adapted to communicate with each via a backhaul network. The central optimisation server communicates with core network elements for data delivery. The servers provide access to local data servers, manage backhaul links, perform data caching, and optimise transmission of data that needs to be back-hauled in order to reduce data transfer via the backhaul network in a manner which is transparent to users and to core network elements. The servers perform compression and protocol optimisation. The remote optimisation server comprises a HTTP accelerator which uses client and server side optimisation functions to retrieve a bundle of resources associated with a request for base HTML, and maintains a set of persistent connections over which all HTTP traffic is carried.