Cluster analysis is decades’ old concept of data mining which performs division of data into groups of similar objects. It is used in various applications in the real world such as data/text mining, voice mining, image processing, web mining, medical data mining and many others. The clustering algorithms are categorized based on different research strategies. One of the widely used clustering methods is the K-Means clustering method which is increasing in popularity day by day because of its simplicity and linear time complexity. However, it has two main disadvantages: - 1) Its highly sensitive to outlier and 2) Its highly dependent on initialization parameters (random choice of k clusters and position of initial cluster centroids). Due to this parametric nature of obtaining inputs from the user, the performance of this algorithm is highly dependent on the nature of inputs. Many improved variants of K-means method is detailed in literature but still it is an open field of research because of its extensive application in the field of Medical, Business & Marketing, Social Media –Sentiment Analysis etc.The aim of this survey paper is to discuss different integrated approaches of k-means which are developed to overcome the aforementioned limitations of the algorithm. This paper also discusses the overlapping version of the K-means algorithm which gives the concept of overlapped clusters.