EXTENDING BAYESIAN LEARNING BASED NEGOTIATION TECHNIQUE TO A TWO-ISSUE BILATERAL NEGOTIATION IN CLOUD

In cloud computing environment, the price and reliability are two important QoS parameters which need to be considered while negotiating agreements for cloud services. In a bilateral negotiation scenario, generally the negotiating agents (be it buyer or seller) will keep the important parameters like price, reliability and deadline secret. There are techniques wherein the Bayesian Learning based Negotiating Agents (BLNA's) are able to estimate the opponent reserve price and deadline so as to gain advantage in negotiation to achieve higher utility of final accepted offers. To enhance this scheme of negotiation, a new Bayesian learning based negotiation agent is proposed which considers both reserve price(RP) and reserved reliability(RR) as the secret, it tries to estimate the opponent's reserve price (RP) and Reserve reliability(RR) with deadline kept constant for both the parties. To evaluate BLNA's performance, seller agent is set as BL based learning agent and buyer agent is assumed to be incomplete information agent. The BLNA is found to be better with overall utility in 44% cases compared to other possible negotiation strategies like tradeoff, fuzzy concession and simple concession.