Abstract: A device may receive load data identifying a load on a radio access network (RAN), and may select one or more time series forecasting models and a classification model based on seasonality metrics associated with the load data. The device may process the load data, with the one or more time series forecasting models, to forecast a capacity for the RAN, and may process the load data and the capacity, with the classification model, to determine whether the capacity exceeds a capacity threshold. The device may selectively determine that the RAN does not need an upgrade based on determining that the capacity fails to exceed the capacity threshold, or may adjust, based on determining that the capacity exceeds the capacity threshold, the capacity to generate an adjusted capacity. The device may perform one or more actions based on the adjusted capacity.

Abstract: A system is described for forming accurately spherical and centered fluid-filled shells, especially of high melting temperature material. Material which is to form the shells is placed in a solid form in a container, and the material is rapidly heated to a molten temperature to avoid recrystallization and the possible generation of unwanted microbubbles in the melt. Immediately after the molten shells are formed, they drop through a drop tower whose upper end is heated along a distance of at least one foot to provide time for dissipation of surface waves on the shells while they cool to a highly viscous, or just above melting temperature so that the bubble within the shell will not rise and become off centered. The rest of the tower is cryogenically cooled to cool the shell to a solid state.