Returns the number of servers required to achieve a desired average wait time in the Erlang C queueing model.
ErlcNsrvFromWait4( secondsPerPeriod, callsPerPeriod, ahtSeconds, averageWaitSeconds)
secondsPerPeriod is the number of seconds during the period for which we are computing the staffing level.
callsPerPeriod is number of arriving calls during the period.
ahtSeconds is the average handle time (average duration of service) measured in seconds.
averageWaitSeconds is the desired average wait time in seconds.
Formula | Description | Return Value |
---|---|---|
=ErlcNsrvFromWait4(1800, 200, 300, 5) | Calculates the number of servers required to achieve an average wait of 5 seconds, given that the period length is 1800 seconds (30 minutes), number of calls per period is 200, and average handle time is 300 seconds. | 41.22663 |
=ErlcNsrvFromWait4(1800, 200, 300, 30) | Same as the preceding except that the desired average wait time is 30 seconds. | 37.31723 |
Public Function ErlcNsrvFromWait4(secondsPerPeriod As Double,
callsPerPeriod, ahtSeconds As Double, averageWaitSeconds As Double) As Double
ErlcNsrvFromWait4 is similar in application to ErlcNsrvFromWait, but has 4 arguments instead of 3. Often ErlcNsrvFromWait4 is the more convenient of the two functions in work involving call center staffing, because it avoids an intermediate step of calculating the traffic load in erlangs.
If this worksheet function is not available, and returns the #NAME? error, then you must install and load the Erlang Library for Excel from Abstract Micro Systems.
How?
You may use ErlcNsrvFromWait4 to make a staffing calculation for a call center, when the staffing level is to be based on a desired average wait for incoming calls. Suppose that we have a call center with these parameters during a certain period of time:
Maximum number of calls that can be waiting: | Very large |
Period length: | 30 minutes |
Incoming calls offered during the period: | 1000 |
Average handle time: | 3 minutes |
Desired Average Wait for calls | 15 seconds |
Assume further that the calls arrive in a Poisson process, that the handle times are exponentially distributed, and that the queue of waiting calls is processed in a FIFO manner. Finally, assume that if a caller finds that all agents are busy, then the caller will wait until an agent picks up the call.
We are interested in estimating the number n of agents that we must have available in order to achieve the desired wait time. We use the ErlcNsrvFromWait4 function as follows.
Then the required number n of agents is
n = ErlcNsrvFromWait4(secondsPerPeriod,
callsPerPeriod, ahtSeconds, averageWaitSeconds)
= ErlcNsrvFromWait4(1800, 1000, 180, 15) = 105.6403
In other words, we will need between 105 and 106 agents to achieve the desired average wait time of 15 seconds.