Owner of data driven to outsource their composite data management systems from local positions to thecommercial open cloud for prodigious economic savings and flexibility .Keyword search on cloud having numerousadvantages, as the owner of data will get powerful tool to precisely describe his informational need . But forprotecting data confidentiality, sensitive data have to be encrypted before outsourcing, which obsoletes traditionalutilization of data based on keyword query search. Thus, permitting an encrypted cloud data search service is of vitalprominence. In this paper we define and try to solve the stimulating problem of authentication and access control formulti keyword ranked search over encrypted data in cloud computing, and to establish a set of strict confidentialityrequirements for such a secure cloud data utilization system. Among various multi-keyword semantics, and to choosethe efficient similarity measure of “coordinate matching,” i.e., as many matches as possible, to capture the relevance ofdata documents to the search query. Further use “inner product similarity” to quantitatively evaluate such similaritymeasure. In this project first to propose a basic idea for the AMRSED based on secure inner product computation, andthen give two significantly improved AMRSED schemes to achieve various stringent confidentiality requirements intwo different threat models. To improve search experience of the data search service, further extend the two schemes tosupport more search semantics. Extensive performance evaluations have shown that the proposed scheme can achievebetter efficiency in terms of the functionality and computation overhead compared with existing ones. For the futurework, to investigate on the authentication and access control issues in searchable encryption technique.