Heterogeneous auto-scaling big-data clusters in the cloud

A method for heterogeneously auto-scaling cloud-based big data clusters to use multiple instance types, comprising:

• determining a primary instance type, the primary instance type selected from a group of approved instances with varying amounts of diskspace and/or computer processing units (CPUs);
• determining provisioning requirements based on characteristics of the primary instance type including associated amount of diskspace and/or CPUs;
• assigning a weight of 1.0 to the primary instance type;
• identifying other approved instance types and determining an instance weight for each other approved instance type, wherein the determination of instance weight for each other approved instance type is based upon a comparison with the characteristics of the primary instance;
• determining if using any other instance types is advantageous in that it would result in reduced costs or faster processing;
• if using other instance types is advantageous, determining which other instance types to use, and determining the number of other instance types by using the instance weight to determine corresponding processing power.