Relative system response elevator dispatcher system using "artificial intelligence" to vary bonuses and penalties

An elevator system employing a micro-processor-based group controller communicating with the cars to assign cars to hall calls based on a Relative System Response (RSR) approach. However, rather than using unvarying bonuses and penalties, the assigned bonuses and penalties are varied using "artificial intelligence" techniques based on combined historic and real time traffic predictions to predict the number of people behind the hall call, and calculating and using the average boarding and de-boarding rates at "en route" stops and the expected car load at the hall call floor. Prediction of the number of people waiting behind hall calls for a few minute intervals are made using traffic levels measured during the past few time intervals on that day as real time predictors, using a linear exponential smoothing model, and traffic levels measured during similar time intervals on previous similar days as historic traffic predictors, using a single exponential smoothing model. The remaining capacity in the car at the hall call floor is matched to the waiting queue using a hall call mismatch penalty. The car stop and hall stop penalties are varied based on the number of people behind the hall call and the variable dwell times at "en route" stops. The stopping of a heavily loaded car to pick up a few people is penalized using a car load penalty. These enhancements to RSR result in equitable distribution of car stops and car loads, thus improving handling capacity and reducing waiting and service times.