Abstract: Devices, methods and computer programs for elevator call allocation with stochastic multi-objective optimization are disclosed. At least some of the disclosed embodiments allow an elevator group control to take into account knowledge about possible future passenger arrivals when allocating new calls. At the same time, the new elevator calls can be allocated via optimizing multiple objectives, such as the waiting time, the time to destination, and/or the energy consumption. In other words, the invention makes it possible to both take into account the uncertainty related to future passengers and control the trade-off between different optimization objectives.

Abstract: Various example embodiments relate to control of passenger traffic group systems. In particular, some example embodiments relate to eliciting user preferences for call allocations for the passenger traffic group system. At least one user preference may be considered when determining a set of candidate control parameters for the passenger traffic group system. At least one representative of the operation of the passenger traffic group system may be displayed to the user based on a simulation of the passenger traffic group system. The user may be enabled to accept the candidate control parameters or modify the user preferences to generate a further set of candidate control parameters. Apparatuses, methods, and computer programs are disclosed.

Abstract: According to an aspect, there is provided a method for forecasting elevator passenger traffic of an elevator group. The method comprises training a statistical traffic model describing a traffic profile for a specific cycle with historical timestamped origin-destination passenger counts, obtaining timestamped origin-destination passenger counts for a current cycle, generating an elevator passenger traffic forecast based on the trained statistical traffic model and the timestamped origin-destination passenger counts for the current cycle, and outputting the elevator passenger traffic forecast for use by an elevator group control.

Abstract: A method for elevator call allocations in an elevator group of an elevator system includes applying statistical traffic forecasts modelling future passenger arrivals in the elevator system; receiving an indication of at least one elevator call; generating, for a fixed parameter, a set of scenarios based on the statistical traffic forecasts; determining a quality attribute for each candidate allocation policy of a set of candidate allocation policies by simulating, for each candidate allocation policy, the set of scenarios according to the candidate allocation policy in a current elevator call allocation situation in the elevator system; selecting a candidate allocation policy based on the quality attributes associated with the candidate allocation policies; and allocating the at least one elevator call to at least one elevator in the elevator group according to the selected candidate allocation policy.

Abstract: According to an aspect, there is provided a control device. The control device is configured to receive data from a passenger traffic system configured in a building, the data comprising information associated with operations for transferring passengers of the passenger traffic system; based on the received data, monitor a change in a quality of service level of the passenger traffic system in transferring the passengers and a change in a passenger traffic pattern in transferring the passengers in the passenger traffic system; and in response to detecting the change in the service level or in the passenger traffic pattern, run one or more simulations of the passenger traffic in the passenger traffic system in the at least one building using the received data in order to trigger at least one operation to change a configuration of the passenger traffic system.

Abstract: According to an aspect, there is provided a method for forecasting elevator passenger traffic of an elevator group. The method comprises training a statistical traffic model describing a traffic profile for a specific cycle with historical timestamped origin-destination passenger counts, obtaining timestamped origin-destination passenger counts for a current cycle, generating an elevator passenger traffic forecast based on the trained statistical traffic model and the timestamped origin-destination passenger counts for the current cycle, and outputting the elevator passenger traffic forecast for use by an elevator group control.