【論文略讀】分散式儲存 DAY1

【DAY 1】

【資料安全】PSDS–Proficient Security Over Distributed Storage: A Method for Data Transmission in Cloud*

Abstract：
Cloud Computing facilitates business by storing an enormous amount of data in the cloud transmitted over the Internet with seamless access to the data and no hardware compatibility limitations.However, data during transmission is vulnerable to man in middle,known plain text, chosen cipher text, related key and pollution attack.Therefore,uploading data on a single cloud may increase the risk of damage to the confidential data. Existing literature study uncovered multiple cryptography techniques such as SA-EDS, Reliable Framework for Data Administration (RFDA), Encryption and Splitting Technique (EST) to secure data storage over multi-cloud.However,existing methods are vulnerable to numerous attacks. This article emphasis on data security issues over multi cloud and proposes a Proficient Security over Distributed Storage (PSDS) method.PSDS divides the data is into two categories; normal and sensitive, further more the sensitive data is further divided into two parts. Each part is encrypted and distributed over multi-cloud whereas the normal data is uploaded on a single cloud in encrypted form. At the decryption stage, sensitive data is merged from multi-cloud. The PSDS is tested against multiple attacks and it has been concluded that it is resistant to related key attack, pollution attack, chosen ciphertext attack, and known plain text attack. Furthermore, PSDS has less computational time as compared to the STTN and RFD encryption method.

摘要：雲端計算通過在雲端儲存大量資料通過促進了商業發展，它通過網路無縫儲存資料，並且沒有硬體相容限制。然而，資料在傳輸過程中，中間人攻擊是非常脆弱的，已知純文字，選擇密文、相關祕鑰和汙染攻擊。因此，在單個雲平臺上上傳資料，會增加機密資料毀滅的風險。現存的文學研究解密了多種密碼學技術，例如SA-EDs，資料管理可信賴框架（RFDA），加密和切分技術來確保在多重雲上的資料儲存。然而，現存的方法對於許多攻擊是脆弱的。本文強調在多重雲上的資料安全問題，並提出了PSDS方法。PSDS將資料分成了兩類，正常的和敏感的，敏感資料被進一步劃分成兩部分。每部分都是加密的，並且分佈在多雲端，一般的資料都是以加密的形式在單個雲平臺上傳。在解密階段，敏感資料從多個平臺融合，PSDS測試對抗多種攻擊，並且總結得出它抵制相關的金鑰攻擊，汙染攻擊，被選密文攻擊，和已知純文字攻擊。而且，PSDS比起STTN和RFD加密方法，計算時間更少。

——————————————————————

【邊緣計算資料的K-V儲存】Distributed Key-Value Storage for Edge Computing and its Explicit Data Distribution Method

Abstract:
In this article, we provide a data framework for edge computing where developers can easily attain efficient data transfer between devices or users. We propose a distributed key-value storage platform for edge computing and its explicit data distribution management method. In this platform, edge servers organize the distributed key-value storage in a uniform namespace. To enable fast data access to a record in edge computing, the allocation strategy of the record and its cache on the edge servers is important. Our platform offers a distributed objects that can dynamically change home server and allocate cache objects following user defined rules. A rule is defined in a declarative manner and specifies where to place cache objects depending on the status of the target record and its associated records. We also integrate a push notification system using WebSocket to immediately notify events on a specified table. We evaluate the performance of our system using a messaging service application between mobile appliances.

摘要：為邊緣計算提供了資料框架，開發者可以在裝置或使用者中獲得有效的資料傳輸。針對邊緣計算，我們提出了分散式K-V儲存平臺以及清晰的資料分佈管理方法。在這個平臺，邊緣伺服器在統一的名稱空間組織分散式K-V儲存。為了使資料快速存取邊緣計算的記錄，記錄的分配策略以及邊緣伺服器的快取非常重要。我們平臺提供的分散式物件能夠動態改變主伺服器，並根據使用者定義的規則分配快取物件。規則以陳述的方式被定義，列舉在哪裡放置快取物件取決於目標記錄的狀態以及相關的記錄。我們也用網路套接字（WebSocket）在指定表上通知相關事件。我們用資訊服務應用在移動應用上評估了系統的效能。

【資料複製置位演算法】A novel replica placement algorithm for minimising communication cost in distributed storage platform

Abstract：
In large-scale distributed systems, replication service has been playing a critical role to improve the availability and reliability of user data. Conventionally, the existing replication services mainly concentrate on how many replicas are needed to maintain desirable availability and reliability rather than how to place replicas on the most suitable storage nodes. As a result, the communication-related costs when accessing data are significantly increased, which in turn degrades the execution performance of user applications. In this paper, we propose a novel replica placement algorithm which is designed to minimise the communication cost when accessing or managing replicas in a large-scale storage platform. In the proposed algorithm, the replica placement problem is formulised a classical multi-knapsack problem, and two heuristic metrics are introduced to obtain the sub-optimal solution of this problem. A lot of experiments are conducted to investigate the performance of the proposed algorithm. The experimental results indicate that our replica placement algorithm outperforms many existing approaches in terms of different performance metrics. In addition, the proposed algorithm can also significantly improve the execution efficiency for data-intensive applications, which are very common in nowadays large-scale distributed systems, such as grid and cloud.
Keywords: data replication, replica service, distributed storage, cloud computing

摘要：在大規模分散式系統裡，複製服務對改善使用者資料的可靠性和可獲得性起著重要的作用。照慣例，現存的複製服務主要集中於，有多少副本需要維持要求的可獲得性和可靠性，而不是如何將副本置於更合適的儲存程式碼裡。因此，訪問資料時通訊相關的花銷顯著增加，這反過來降低了使用者應用的執行效能。在論文中，我們提出了新型副本置位演算法，旨在在大規模儲存平臺中存取和管理資料副本時，能最小化通訊開銷。在提出的演算法中，副本置位問題被抽象成一個多揹包問題，引入了兩個啟發式的度量來得到次優的解決方案。實施了大量的實驗來調查該演算法的效能。實驗結果表明，在不同效能度量下，本演算法優於許多現存的方法。除此之外，本演算法能顯著提高資料密集應用的執行效率，這些應用在當代大規模分散式系統中非常普遍，例如網狀和雲狀。