distributed generation (dg) sources are becoming more prominent indistribution systems due to the incremental demands for electrical energy. locationsand capacities of dg sources have great impacts on the system losses in adistribution network. this paper presents a study aimed for optimally determiningthe size and location of distributed generation units in distribution systems withdifferent l...

This paper proposes a fully asynchronous scheme for the policy evaluation problem of distributed reinforcement learning (DisRL) over directed peer-to-peer networks. Without waiting any other node network, each can locally update its value function at time using (possibly delayed) information from neighbors. is in sharp contrast to gossip-based where pair nodes concurrently update. Even though s...

We propose a fully distributed actor-critic architecture, named Diff-DAC, with application to multitask reinforcement learning (MRL). During the process, agents communicate their value and policy parameters neighbours, diffusing information across network of no need for central station. Each agent can only access data from its local task, but aims learn common that performs well whole set tasks...

This paper demonstrates that a distributed control and planning system can fulfil an idealised mixed-model assembly problem compete with traditional systems. The anarchic manufacturing is system, based on free market structure, where elements have decision-making authority autonomy. Mixed-model typically managed centrally for production control, using simplification hierarchical structures to m...

Holoparadigm (Holo ) is a multiparadigm model oriented to development of paraUel and distributed programs. In this paper we proposc the Distributed Holo (DHolo ), a model to support the distributed execution of programs developed in Holo. DHolo is based on object mobility and blackboards. This distributed model can be fully implcmented on Java platform. Specifically, mobility is implemcnted usi...