Nowadays several technologies coexist in the same area composing a heterogeneous system. Moreover, this fact is expected to become more and more accentuated with all new technologies that are currently being standardized. So far, generally users are who select the technology they are going to connect to, either configuring the user equipment or using different equipments. Nevertheless, this approach does not take the maximum advantage of the available resources. To this aim, a new set of strategies is necessary. These strategies must manage the radio resources of all technologies commonly and jointly, and they must ensure the satisfaction of users Quality of Service (QoS).

Following this idea, this Thesis proposes two new algorithms. The first one is a Joint Dynamic Resource Allocation (JDRA) algorithm capable of allocating resources to users and distributing users among technologies at the same time. The algorithm is formulated as a multi-objective minimization problem that is solved using Hopfield Neural Networks (HNNs). HNNs are interesting because they are supposed to find suboptimal solutions in very short times. Nevertheless, actual implementations of HNNs in computers lose this fast response. For that reason, this Thesis analyses the causes and studies possible improvements.

The second algorithm is a Joint Call Admission Control (JCAC) algorithm that admits and rejects users taking all technologies into account at the same time. The main difference with other proposed algorithms is that they decide on call admission in each technology separately. Thus, a previous mechanism is needed to select which technology users are going to connect to. On the other hand, the technique proposed in this Thesis is capable of deciding on call admission in the whole heterogeneous system. Therefore, users are not attached to any technology prior to admission.

As a result, this Thesis paves the way to an efficient resource management in heterogeneous systems with new ideas and techniques. The functions of the Radio Resource Management (RRM) are divided into the JDRA and JCAC algorithms so they could work together.