A Simple Value Model

Here we consider a general case, where the service has several features, each described by a parameter, Si. The (yet to be designed) plant providing the service will consist of many different parts, each of which is composed of a number of components that have a variable performance. As a result, the service parameters are stochastic variables, each with a probability distribution q i(5,). The value of the service, W, is therefore also a stochastic variable, as illustrated in Fig. C6.3. 

The proposed simple value function is then defined by 

The form of the w-functions assumes that the value of a feature of the service always increases with increasing value of the associated parameter. If this is not the case, as e.g. in the case of failure rates, it can always be achieved by redefining the parameter (e.g. taking the inverse value). 

We note that the mean of this triangular distribution, p, is given by 

The expectation value of a component of the value function is then given by the 

---