The Future of Cloud Services: How to Stay Ahead with Smart Selection

Authors

• Prabhakar Vagvala Head of Global ERP Operations, Dallas-Fort Worth Metroplex, USA.

Abstract

Introduction: The Cloud Service Selection

       The process of choosing and assessing cloud services from different vendors to satisfy certain demands and goals is referred to as cloud service selection. The resources and applications that make up cloud services are made available over the Internet and give the necessary flexibility, scalability, and cost-effectiveness.

Research Significance: The impact of choosing a cloud service on an organization's decision-making, effectiveness, cost optimisation, security, customization, and technology evolution is emphasised in research. Effective frameworks and strategies for choosing cloud services assist organisations in making decisions that increase resource allocation and operational efficiency. Research in this area assists organisations in enhancing cloud service selection procedures and reducing risks by taking into account variables including performance, reliability, security, & pricing. It also answers the requirement for specialised solutions that meet certain requirements and guarantee compatibility with current systems. In addition, studies into the cloud's selection keeps businesses current on new technological developments and market trends, enabling them to make wise choices in a fast changing technological environment. In the end, analysis of cloud service selection enables businesses to take use of the advantages of computing in the cloud while lowering risks and boosting productivity.

METHOD: A multi-criteria decision making tool called the Estimation based on Distance from Average Solution method, or assessment based on distance from average answer, is used to rank and evaluate options in complicated decision-making problems. It was created to deal with the difficulties brought on by scenarios with various criteria and opposing objectives. When calculating each alternative's distance from the mean solution, the EDAS technique takes positive as well as negative deviations into account. It considers the importance of the criteria in the process of making choices by giving each one a weight.

Alternate Parameters: quote of the day, xignite quotes, stock quotes, real time quotes, delayed stock quotes, historical stock quotes

Evaluation Parameters: throughput, reliability, portability, response time

Result: Through the rank table, we can get the rank of alternative parameters. Whereas Historical Stock Quotes is in 1^st position and Xignite Quotes is in 6^th position.

Conclusion: first ranking Historical Stock Quotes is obtained with the lowest quality of Xignite Quotes

Introduction

By negotiated agreements among service providers and consumers, cloud computing technology allows the dynamic deployment of virtualized computers for computing resources. It provides a wide variety of IT resources, and cloud services over the Internet have grown quickly. The selection and discovery of cloud services are complicated by the number of providers, though. In order to overcome these difficulties, researchers have concentrated on creating cutting-edge methods that help people select the best services. Clouds are sophisticated systems that place a strong emphasis on virtualization. They enable the management of connected, dispersed systems wherein resources can be converted into specialised goods in accordance with predetermined service-level agreements. Due to the development of cloud services, it is now essential for decision-makers to quickly and precisely identify and choose services that meet their unique needs. These methods are intended to deal with two basic problems. First and foremost, standard interfaces & specification formats are required to provide a market infrastructure that is commoditized for service trading between various Internet users. Second, decision-making techniques are required to aid in the choice of relevant services depending on the needs of individual users [1]. A distributed computing architecture known as "cloud computing" makes computing services and resources available to consumers on a flexible. By enabling on-demand available from any place, it seeks to improve user access to software and hardware applications. Users may now take advantage of cutting-edge information and services thanks to this ground-breaking concept, which opens up new opportunities for information technology services. The idea of MCC has been made possible by the introduction of mobile devices and the rising popularity of cloud computing. Cloud computing, portable computing, & seamless connectivity are all combined by MCC to provide a dispersed computing environment which accept users to access services and resources conveniently while on the go [2]. The delivery of software and applications is gradually changing as a result of the rapid development of cloud computing. As the emphasis turns to depending on powerful services and assets remotely rather than locally based hardware, this shift also has repercussions for hardware vendors. This offers potential and problems towards mobile pervasive computing. Users can access a dynamic, lightweight, affordable, transparent, dependable, and largely private remote service thanks to cloud computing. Numerous cost and benefit factors are included in the cloud service idea. Cloud computing platforms and service clouds are predicted to make an expanding variety of services available in the future [3]. A contemporary method of computing known as "cloud computing" allows users to access hardware and software via services over the Internet. It provides elastic computing, which enables enterprises to scale their assets as necessary. The pay as you go model of cloud computing, which only charges users for the computing power they actually utilise, is one of the main financial benefits of this technology. This saves money and reduces the need to invest in new infrastructure. Furthermore, cloud computing can easily handle peak demands, guaranteeing that companies can meet heavy workloads without incurring extra costs [4]. For small- to medium-sized organisations in particular, cloud services provide scalable and flexible IT resources. However, customers now find it hard to navigate and pick the best solutions due to the multitude of cloud services offered. To solve this problem, a further layer known as a brokerage network is required to make duties like discovery, negotiation, and monitoring easier. Similar to a stock broker, an online broker helps customers choose the best services based on their unique needs by acting as a connection between them and service providers. Industry experts like Gardner have recognised many number of cloud brokering, includes arbitrage, aggregation, alongside intermediation, and have emphasised the importance of such brokerage services [5]. Existing methods for choosing cloud services make the assumption that the evaluation parameters are independent and ignore any potential linkages. However, the efficacy of the service choice system might be significantly impacted by these correlations. Furthermore, the improvement of decision making approaches in this field has been hampered by the lack of suitable measurement indices to assess the efficacy of service selection strategies. By concentrating on modelling the interconnections between factors in cloud service choice and establishing validation frameworks to feed service selection methods, this research article addresses these important concerns. The Cloud Service Selection using Scale Correlation Framework , which is the name of the proposed framework, makes use of fuzzy measures and the Choquet integral to quantify and incorporate nonlinear correlations among scales and to facilitate more reliable and accurate service selection decisions [6]. The process of choosing a cloud service is complicated and requires a number of different decision-making criteria, different service configurations, and the active involvement of human decision-makers. However, current methods for choosing cloud services fall short of fully addressing each of these issues at once. In this study, we suggest a unique method for capturing the capabilities and needs of cloud services that makes use of variability modelling. In a CSSP that incorporates human decision-makers, we specifically use cloud feature models as a representation method to efficiently elicit and filter needs. We can decrease the number of valid cloud service configurations by using filtering approaches, enabling a quicker and more accurate selection procedure. Through the incorporation of models, methodologies, and tools, this strategy offers thorough support [7]. The use of cloud computing is growing in popularity as more people and businesses look for adaptable and economical solutions. The choice of the best cloud service has become increasingly important for potential consumers due to the growing number within cloud service providers. Cloud computing has recently become the go-to method for storage & service solutions. Utilising cloud services & outsourcing the IT infrastructure and applications to various cloud providers can help businesses save a lot of money. With this strategy, clients can reduce worries about maintenance, depreciation, and technical upgrades while avoiding sizable upfront investments in pricey equipment. With this paradigm shift, customers can deploy resources when required without having to pay a large upfront cost, allowing them to concentrate on their primary businesses [8]. In the modern era, cloud computing has seen a huge increase in popularity. It is a synthesis of many computing ideas, such as automated computing, utility computing, grid computing, and heterogeneous distributed computing. A wide range of configurable resources, including software, operating systems, and computational infrastructure, can be made available to computers as well as additional devices as services in the cloud. It has become very popular to build cloud apps using these cloud services. Notably, less and medium-sized businesses are using cloud services to set up their company infrastructure, including storage, the database, & search services. Best cloud computing services exhibit identical functional characteristics because the high competition among different cloud service providers, which emphasises the necessity for rigorous assessment and choice to determine the best [9]. A network of connected computers that work together to provide consumers with a huge selection of applications & business operations is what is known to as the "cloud." The capacity of cloud computing to provide software to customers as a flexible, affordable, and on-demand service is a fundamental feature. This makes it possible for software developers to use cutting-edge technology without having to make substantial upfront hardware purchases. Additionally, it enables them to connect with a global consumer audience. Users of the cloud now have the option to access a variety of software programmes via the Internet, often on the basis of a subscription-based business model. It is essential for cloud service developers to assure the supply of high-quality work in order to live up to user expectations as they offer various service models, including IaaS, PaaS, SaaS, and other cloud services [10]. The process of choosing the best solution for customers has grown more difficult due to the expanding availability of cloud services. Decision-making gets difficult when there are many options to pick from, necessitating methodical techniques to help people make wise choices. Cloud computing has many advantages over traditional computing models, including increased flexibility and adaptability, which encourage enterprises to create new cloud-based apps as well as make application migration easier. Users of cloud services must make sure that their unique application demands and requirements correspond with the offers of the chosen service provider in order take advantage the benefits of cloud computing [11]. With big IT businesses as Google, IBM, Microsoft, & Amazon entering the market to offer these services to clients, cloud services are seeing a spike in popularity. As a result, choosing the best cloud service has grown to be a difficult task that has attracted the interest of the research community. Today's market frequently offers a large range of domain-specific cloud services, all of which provide comparable functionality. Typically, these services fall under the categories of cloud apps for private users or enterprise cloud services for small and medium-sized enterprises (SMEs). The analysis of the quality factors in cloud service selection has drawn the attention of the service-oriented computing & cloud computing communities during the past two decades, sparking increased interest in the field. Choosing the best service from a variety of providers offering comparable functional qualities presents a barrier for both SMEs developing their cloud-based service platforms and consumers using mobile applications [12]. Choosing the best cloud services has grown more difficult for potential customers as cloud computing popularity has increased. During the decision-making process, a number of variables are taken into account, including user requirements, subject-matter expertise, service level agreements (SLAs), & the various traits and models of cloud services. By providing adaptable, scalable, & on-demand IT services through the Internet, cloud computing has completely changed how businesses of all sizes utilise IT resources. Numerous technological firms are aggressively vying for a piece of this rising industry as demand for cloud services rises. [13]. In the setting of numerous cloud computing, the selection of cloud services has become crucial. Due to the abundance of possibilities, users may find it challenging to select the best cloud service providers for their applications, particularly for real-time applications that necessitate online decision making. This issue is addressed by a method for choosing cloud services that is based on the concept of cloud service brokers. DCS, a dynamic mechanism for choosing cloud services, is advised as the framework for this paradigm. Each cloud service broker in this plan manages a particular group of cloud services using the TCS (Task Completion Strategy) technique. The TCS strategy includes an adaptive learning mechanism with induction, forgetting, and degradation components. The system aims to continuously improve the cloud service selection process, ensuring users get the best service results.-paraphrase and rephrase without plagiarism [14]. Particularly for medium-sized and small organisations, the scalability of storage space and computational power provided by cloud services is highly sought. A number of cloud brokerage techniques have been proposed to help cloud customers in a number of areas, including service discovery, mediation, as monitoring. Among these strategies, a cloud broker's assistance in helping users choose the cloud services that best meet their needs is a vital duty. Existing research mostly focuses on identifying the relevant factors, such as cost and quality of service, as well as the relative weight of these criteria for cloud customers. However, there is a new problem in the cloud due to the continued increase of cloud use and the appearance of new providers & service kind [15].

Methodology

A multi-criteria decision-making method called estimation determined by distance to the mean solution assesses options based on how much they deviate from the average scores for the attributes. The EDAS technique, which was first introduced by Keshavers Korabe et al. (2015), uses an average solution to evaluate alternatives. For evaluation reasons, the two measures Positive Distance from Mean & Negative Distance from Mean have been employed in this procedure. EDAS is especially helpful when resolving overlapping requirements. In contrast to compromise MCDM techniques like VIKOR & TOPSIS, which calculate the distance between the best alternative and both the negative and positive best solutions, EDAS concentrates on the distance between the best alternative and the mean solution. Additionally, modifications to the standard EDAS system were proposed to deal with ambiguous and missing data [16]. Ghorabaee et al. (2015) were the first to present the EDAS method in the setting of inventory classification. In comparison to other classification techniques, it has clear advantages because it performs accurately while requiring fewer calculations in mathematics. According to Ghorabaee et al. (2015), the EDAS methodology bases the evaluation of alternatives on how closely they adhere to the standard solution for each criterion. While Kahraman et al. (2017) suggested an intuitive fuzzy model based on EDAS for selecting solid waste disposal sites, Ghorabaee et al. (2016) expanded the EDAS technique to supplier selection. Another use of EDAS is in the incorporation of MULTIMOORA, which was used to examine obstacles to the development of renewable energy sources (Kahraman et al., 2017) [17]. A useful method for handling real-world decision-making difficulties is discrete stochastic multi-criteria decision making .The estimation utilising distance from mean solution, which provides effective multi-criteria decision-making capabilities, is a promising and useful tool in this discipline. The choice of alternatives is determined by EDAS by taking into account how far they are from the average answer. The EDAS method is effective for dealing with stochastic issues since the mean answer is obtained from the arithmetic mean. Several EDAS technique extensions have been created to address multi-criteria decision-making issues in ambiguous situations. In these extensions, options are ranked and evaluated based on a variety of criteria using both negative and positive distances from the average answer [18]. An MCDM process that takes into accounts various options and conflicting criteria is used to evaluate the dye house's potential steam boiler replacements. Since it immediately affects operating expenses, this decision-making process is crucial for the textile company. Numerous MCDM techniques have been proposed in the literature to assess and choose the best alternative steam boiler. The estimation based on the distance from the mean solution ,which provides a framework to evaluate the steam boiler alternatives, is one such technique. First, the MACBETH method is used to determine the weights of the assessment criterion. After that, the EDAS approach is used [19]. A multi-attribute decision-making method called Estimation Based on Distance from Average answer calculates the distance between each alternative and the average answer. It is comparable to other distance-based techniques like TOPSIS and VIKOR. As an extension of regular fuzzy sets, reluctant fuzzy sets introduce hesitation when determining the membership degrees of set items. When there are conflicting criteria in an MCDM problem, the EDAS approach is especially helpful. In a manner akin to VIKOR and TOPSIS, EDAS determines how far alternatives are from both positive and negative ideal solutions. However, in EDAS, rather than the positive and negative ideal solutions, the emphasis is on the positive and negative distances (PDA and NDA) from the mean solution. Choosing the highest PDA value yields the best alternative [20]. By Cashavers Korabe et al., the EDAS technique is a fresh and successful method. It was additionally expanded to allow its use in unclear and uncertain circumstances. The EDAS method's evaluation procedure centres on calculating the distance of each alternative from the average solution. The options are divided into two categories, with both positive and negative the distance, and then the utility of every choice is determined using these distances. The interval type-2 fuzzy sets, period-valued neutrosopic sets, period-valued fuzzy soft sets, neutrosopic soft sets, interval grey numbers, and intuitionist fuzzy sets are only a few of the uncertain situations that the EDAS approach has been specifically developed to manage. Furthermore, real-world multi-criteria decision-making has been successfully addressed by the EDAS technique [21]. Making decisions, which involve assessing and choosing the best option based on the facts at hand, is a regular activity in practical circumstances. However, because of the inherent complexity & ambiguity of decision-making challenges, decision-makers sometimes run into difficulties. An effective computational strategy for handling decision-making issues including uncertainty is rough set theory RST. In order to address uncertainty in diverse decision-making issues, we offer a unique model in this research study that is based on approximate sets. We also provide a fresh approach created especially for Multiple Attribute Decision Making (MADM) issues. This strategy seeks to address the problems brought on by ambiguity in decision-making processes and find effective solutions [22]. The process of choosing the most advantageous option from a range of possibilities based on the judgements of the decision makers is an essential element of our daily lives. Multi-criteria group decision-making MCGDM is a critical component of decision-making since it calls for several decision-makers to agree on the best option based on a set of evaluation criteria. However, in real-world circumstances, decision makers frequently present subjective and imprecise assessment information because of the information's inherent nature and the absence of precise quantitative statistic [23]. China has acknowledged that a crucial approach for achieving sustainability economic development is to move towards a low-carbon & circular economy. Company managers must now weigh economic benefits against a priority placed on their organisations' green image in order to balance economic benefits and maintain market competitiveness in light of the growing public awareness of protecting the environment. Using probabilistic linguistic term sets PLTSs, decision makers can convey their hazy and unsure understanding of certain aspects. In order to solve multi-attribute group decision making MAGDM utilising PLTSs, this research study suggests an extension of the distance-based estimation from average solution method. The study gives a succinct overview of PLTSs, covering their idea, comparison formula, and associated distances. In order to solve these issues, an expanded version of the EDAS approach is offered [24]. For evaluating reluctant qualitative data in the context of multi-criteria group decision-making, an Extended Hesitancy Fuzzy Linguistic Terminology is a very successful method. In this study, we suggest expanding the assessment based on distance from average solution approach to include an extended reluctant fuzzy linguistic framework, where the average solution is employed to evaluate alternatives. The prolonged hesitant fuzzy linguistic centre Ordered Weighted Averaging manager, which combines two EHFLTSs and the centre OWA operator utilising convergent combinations, is used to get the average answers for all criteria. We offer a probability ratio calculation made expressly for comparing EHFLTS that may be used to determine the positive and negative distances from the mean [25].

Alternate Parameters

Quoteoftheday: QuoteofTheDay is a feature or service that cloud service providers offer that gives consumers a daily motivational or thought-provoking phrase. It is used in the context of choosing a cloud service. With the help of this functionality, consumers should have a satisfying and inspiring experience utilising the cloud service. The cloud service's "QuoteofTheDay" function, which offers customers daily motivation or reflection, adds a touch of customization and engagement. It is frequently included as an extra value-added feature to improve user experience and set the provider of cloud services apart from rivals. Citations are frequently shown prominently in the user's experience for the platform used for cloud services and may be drawn from a variety of writers, famous people, or user-submitted information.

Xignitequotes: A financial information service called XigniteQuotes offers historical and real-time stock quotes & market data. A comprehensive range of financial data, such as stock prices, trade volumes, market indices, and other pertinent data points, is provided. Developers, financial institutions, and individual investors who need precise and timely financial data during analysis, research, and decision-making are the target audience for XigniteQuotes. The service is renowned for its dependability, extensive coverage, and simple integration with a variety of systems and applications. Users can get the most recent market data using XigniteQuotes, track stock performance, and make knowledgeable investing decisions.

Stockquotes: "StockQuotes" is a term used in the financial markets to describe pricing information and statistics pertaining to publicly traded bonds or stocks. It covers the stock's current trading price, ask and bid prices, trading volume, and other important information. StockQuotes enables investors, traders, and financial professionals to make well-informed decisions about buying, selling, or holding stocks by providing real-time or postponed information on the market's value and performance of stocks, frequently, exchanges for stocks, financial data suppliers, or specialised websites that compile and disseminate stock market information are used to access this data. For tracking stock prices, conducting technical and fundamental analysis, and keeping up with market trends and movements, StockQuotes is crucial. They are crucial to the operations of portfolio management and investment decision-making.

Realtimequotes: Real-time and current price data are referred to as "RealTimeQuotes" when referring to financial products like stocks, bonds, commodities, or currencies. Real-time quotes give instant access to the most recent trade prices, bid & ask prices, trading volume, and other pertinent information, in contrast to delayed quotations, which require some wait between the actual market action and information dissemination. For active traders, investors, and professionals in finance who require the most precise and current information to arrive at informed decisions and respond fast to market changes, real-time quotes are crucial. Typically, real-time data feeds are used to collect these quotes from exchanges for stocks, financial data providers, or specialised platforms. Users can make trades, track the performance of certain assets, and keep up with the latest market developments with RealTimeQuotes.

Delayedstockquotes: The term "DelayedStockQuotes" relates to price data and information for financial assets like stocks, bonds, commodities, or currency that are not instantly updated in real time. Between actual marketplace activity and the release of information to users, these price quotes involve a time lag. Delayed stock quotes, in contrast to real-time quotes, show prices that are often delayed by a predetermined amount of time, ranging from a few moments to many hours. Compared to real-time quotations, delayed stock quotes are frequently provided for free or at a discounted cost. Delay quotes are nonetheless helpful for non-real-time assessment, historical research, or for persons who don't want rapid access to live market information, even though they don't offer the most recent market data.

Historicalstockquotes: The term "HistoricalStockQuotes" means historical pricing data and information for financial assets like stocks, bonds, commodities, and currencies. These quotes offer a record of previous market action for a certain time period in the past, including the beginning and ending prices, peak and valley prices, trade volume, and other pertinent information. Users can research and examine the historical price alterations, trends, & patterns of a given securities using historical stock quotations. They are helpful for performing technical analysis, modifying trading plans, looking at prior market behaviour, and making wise investment selections based on past results. Analysts and investors can learn more about the historical performance of a stock or market, spot probable patterns or connections, and forecast or anticipate future price moves by looking at historical stock quotes. It should be reminded that past stock quotes should not be used in place of other data and analysis for making financial decisions because they cannot guarantee future success.

Evaluation Parameters

Throughput: The term "throughput" describes the speed or rate at which information or data can be processed, sent, or transferred via a network or computer. It describes how much data can be properly supplied or processed in a certain length of time. The usefulness and efficiency of many systems, such as computer networks, channels for communication, storage systems, and processing units, are frequently evaluated by their throughput.

Reliability: The term "reliability" describes a system, technology, or process's capacity to continue carrying out its intended purpose or to deliver anticipated results under predetermined circumstances without failure or faults. It serves as a gauge of an organization's dependability and trustworthiness in carrying out its assigned obligations.

Portability: A software application, structure, or device is said to be portable if it has the ability to be quickly transferred or converted to many contexts, platforms, or a operating systems with no requiring major reprogramming or modification. This includes having the same programme run seamlessly across a variety of hardware or operating systems.

Response Time: The term "response time" describes how long it takes for an apparatus, implementation, or device to act on an application request as well as input after it has been made. output that follows a user's request or action.

Results a nd Dicussion

Table 1 show the values like Throughput, Reliability, Portability, Response time for the given six alternative parameters and finally we calculate average value for the each of the values.

Figure 1.Cloud Service Selection

Through figure 1 we can see evaluation parameters of beneficial and non- beneficial for the alternative parameters in a schematic view

Table 2 provides the positive distance from average values for the data set

Through table 3 we can get the NDA value for the alternative parameters

Here we can get the weight of data set through table 4. All the weight of data set is uniformly distributed and has the same value

Through table 5 we can gather the value of weighted Positive Distance from Average and its sum value .the weighted PDA is got from multiplying PDA and the weight of the data set. After the sum is added

Table 6 provides the value of weighted NDA and the sum of weighted Negative Distance from Average

Table 7 provide the normalized value for weighted Positive Distance from Average and weighted Negative Distance from Average

Figure 2. Normalized SPi and SNi

Figure 2 displays the schematic view of the NSPi and the NSNi. NSNi is displayed in red colour and blue bar represents NSPi

Table 8 gives the value of ASI to the respected six alternative parameters of the data set

Figure 3. ASI

Through figure 3 we can see the schematic view of ASI values for given six alternative parameters in the data set

Table 9 provides the rank of every separate alternative parameter like Quote of The Day, Xignite Quotes, Stock Quotes, Real Time Quotes, Delayed Stock Quotes, and Historical Stock Quotes

Figure 4. Rank

Figure 4 shows the schematic view of each alternative parameter in the given data set

Conclusion

Through contractual arrangements between providers and consumers, cloud technology allows the dynamic offering of virtual computers, providing an extensive selection of IT services and resources. Finding and choosing the best cloud services have become more difficult as a result of the Internet's explosive rise in cloud services. A great deal of investigation has been done to provide cutting-edge strategies that help consumers make wise judgements when selecting cloud services in order to overcome these difficulties. Modern virtualization-focused data storage and processing platforms, such as clouds, make it possible to manage connected and dispersed systems effectively. Resources may be seamlessly modified and virtualized to adhere to particular service-level agreements. But with the widening selection of cloud services now accessible online, decision-makers must deal with the major challenge of efficiently and accurately discovering and selecting services that align with their specific requirements. These methods mainly deal with two important problems. In order to develop a standardised market infrastructure for service trading among different categories of Internet users, there is a demand for standard interfaces & specification formats over cloud services. Second, choosing appropriate services presents a substantial challenge that can be overcome by using decision-making procedures. A distributed computing architecture known as cloud computing cc enables customers to access computing resources and facilities on an as-you-go basis. By offering leased hardware and software programmes that may be accessed via anywhere or at any time, its principal goal is to improve user options. In turn, this broadens the scope of IT services by introducing new services and data possibilities through cloud computing. Mobile Cloud Computing has been made possible by the recent boom in cloud computing and the proliferation at smart mobile devices. Cloud computing, mobile computing & seamless connectivity are all combined in the distributed computing concept known as "Mobile Cloud Computing" .Users can utilise mobile devices to access cloud resources while retaining uninterrupted access thanks to it. An innovative approach to multi-criteria decision-making (MCDM) called Estimation Based on Distance Compared to the Average Solution (EDAS) evaluates options based on how far they deviate from attribute mean scores. Using common fuzzy sets, the original EDAS method has been enhanced to take into account ambiguous and partial data. The EDAS approach assesses options by using an average answer. It was initially developed in 2015 by Keshavers Korabe et al. and uses two evaluation metrics called Positive Distance from the Mean & Negative Distance from the Mean (NDA). When dealing with competing criteria, this strategy is quite helpful.

EDAS uses distances between the mean solution to determine the best option, compared to compromise MCDM systems like VIKOR and TOPSIS that calculate distances between both the positive and the negative best solutions. The EDAS approach was first presented by Ghorabaee et al. (2015) in their study on inventory classification. High accuracy and a lesser reliance on intricate mathematical computations are two distinguishing features that set EDAS apart from other classification techniques. According to Ghorabaee et al. (2015), the assessment of alternatives in EDAS is based on an assessment of each alternative's separation from the standard answer for each criterion. Later, an extended version of EDAS created exclusively for supplier determination was given by Ghorabaee et al. (2016). In addition, Kahraman et al. (2017) suggested an understandable fuzzy model built around EDAS to aid in the choice of locations for the disposal of solid waste. Another use of EDAS was discovered in a study that examined obstacles to the growth of renewable energy through incorporating it into MULTIMOORA.

References

1. Sun, Le, Hai Dong, Farookh Khadeer Hussain, Omar Khadeer Hussain, and Elizabeth Chang. "Cloud service selection: State-of-the-art and future research directions." Journal of Network and Computer Applications 45 (2014): 134-150.
2. Whaiduzzaman, Md, Abdullah Gani, Nor Badrul Anuar, Muhammad Shiraz, Mohammad Nazmul Haque, and Israat Tanzeena Haque. "Cloud service selection using multicriteria decision analysis." The Scientific World Journal 2014 (2014).
3. Zeng, Wenying, Yuelong Zhao, and Junwei Zeng. "Cloud service and service selection algorithm research." In Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation, pp. 1045-1048. 2009.
4. ur Rehman, Zia, Farookh K. Hussain, and Omar K. Hussain. "Towards multi-criteria cloud service selection." In 2011 fifth international conference on innovative mobile and internet services in ubiquitous computing, pp. 44-48. Ieee, 2011.
5. Sundareswaran, Smitha, Anna Squicciarini, and Dan Lin. "A brokerage-based approach for cloud service selection." In 2012 IEEE Fifth International Conference on Cloud Computing, pp. 558-565. IEEE, 2012.
6. Sun, Le, Hai Dong, Omar Khadeer Hussain, Farookh Khadeer Hussain, and Alex X. Liu. "A framework of cloud service selection with criteria interactions." Future Generation Computer Systems 94 (2019): 749-764.
7. Wittern, Erik, Jörn Kuhlenkamp, and Michael Menzel. "Cloud service selection based on variability modeling." In Service-Oriented Computing: 10th International Conference, ICSOC 2012, Shanghai, China, November 12-15, 2012. Proceedings 10, pp. 127-141. Springer Berlin Heidelberg, 2012.
8. Qu, Lie, Yan Wang, and Mehmet A. Orgun. "Cloud service selection based on the aggregation of user feedback and quantitative performance assessment." In 2013 IEEE international conference on services computing, pp. 152-159. IEEE, 2013.
9. Tang, Mingdong, Xiaoling Dai, Jianxun Liu, and Jinjun Chen. "Towards a trust evaluation middleware for cloud service selection." Future Generation Computer Systems 74 (2017): 302-312.
10. Karim, Raed, Chen Ding, and Ali Miri. "An end-to-end QoS mapping approach for cloud service selection." In 2013 IEEE ninth world congress on services, pp. 341-348. IEEE, 2013.
11. Rehman, Zia Ur, Omar Khadeer Hussain, and Farookh Khadeer Hussain. "Parallel cloud service selection and ranking based on QoS history." International Journal of Parallel Programming 42 (2014): 820-852.
12. Ding, Shuai, Zeyuan Wang, Desheng Wu, and David L. Olson. "Utilizing customer satisfaction in ranking prediction for personalized cloud service selection." Decision Support Systems 93 (2017): 1-10.
13. Eisa, Mona, Muhammad Younas, Kashinath Basu, and Hong Zhu. "Trends and directions in cloud service selection." In 2016 IEEE symposium on service-oriented system engineering (SOSE), pp. 423-432. IEEE, 2016.
14. Wang, Xiaogang, Jian Cao, and Yang Xiang. "Dynamic cloud service selection using an adaptive learning mechanism in multi-cloud computing." Journal of Systems and Software 100 (2015): 195-210.
15. Lin, Dan, Anna Cinzia Squicciarini, Venkata Nagarjuna Dondapati, and Smitha Sundareswaran. "A cloud brokerage architecture for efficient cloud service selection." IEEE Transactions on Services Computing 12, no. 1 (2016): 144-157.
16. Kahraman, Cengiz, Mehdi Keshavarz Ghorabaee, Edmundas Kazimieras Zavadskas, Sezi Cevik Onar, Morteza Yazdani, and Basar Oztaysi. "Intuitionistic fuzzy EDAS method: an application to solid waste disposal site selection." Journal of Environmental Engineering and Landscape Management 25, no. 1 (2017): 1-12.
17. Asante, Dennis, Zheng He, Nana Osae Adjei, and Bismark Asante. "Exploring the barriers to renewable energy adoption utilising MULTIMOORA-EDAS method." Energy Policy 142 (2020): 111479.
18. Keshavarz Ghorabaee, Mehdi, Maghsoud Amiri, Edmundas Kazimieras Zavadskas, Zenonas Turskis, and Jurgita Antucheviciene. "Stochastic EDAS method for multi-criteria decision-making with normally distributed data." Journal of Intelligent & Fuzzy Systems 33, no. 3 (2017): 1627-1638.
19. Kundakcı, Nilsen. "An integrated method using MACBETH and EDAS methods for evaluating steam boiler alternatives." Journal of Multi‐Criteria Decision Analysis 26, no. 1-2 (2019): 27-34.
20. Kutlu Gündoğdu, Fatma, Cengiz Kahraman, and Hatice Nida Civan. "A novel hesitant fuzzy EDAS method and its application to hospital selection." Journal of Intelligent & Fuzzy Systems 35, no. 6 (2018): 6353-6365.
21. Karaşan, Ali, and Cengiz Kahraman. "A novel interval-valued neutrosophic EDAS method: prioritization of the United Nations national sustainable development goals." Soft Computing 22 (2018): 4891-4906.
22. Keshavarz-Ghorabaee, Mehdi, Maghsoud Amiri, Edmundas Kazimieras Zavadskas, Zenonas Turskis, and Jurgita Antucheviciene. "A dynamic fuzzy approach based on the EDAS method for multi-criteria subcontractor evaluation." Information 9, no. 3 (2018): 68.
23. Zhan, Jianming, Haibo Jiang, and Yiyu Yao. "Covering-based variable precision fuzzy rough sets with PROMETHEE-EDAS methods." Information Sciences 538 (2020): 314-336.
24. Li, Ying-ying, Jian-qiang Wang, and Tie-li Wang. "A linguistic neutrosophic multi-criteria group decision-making approach with EDAS method." Arabian Journal for Science & Engineering (Springer Science & Business Media BV) 44, no. 3 (2019).
25. Wei, Guiwu, Cun Wei, and Yanfeng Guo. "EDAS method for probabilistic linguistic multiple attribute group decision making and their application to green supplier selection." Soft Computing 25, no. 14 (2021): 9045-9053.