Real-Time Anomaly Detection – Protect yourself from malicious spend attacks on clouds

As stated in our previous blogs, FittedCloud applies many kinds of AI-driven algorithms to analyze contextual data and behaviors in your Cloud environment to identify opportunities to optimize system’s performance, increase resource utilization, and reduce your total cost. In this … Read More

8 New Features Recently Announced by AWS That Help Reduce Spend

We’re always on the alert for new angles to save money on cloud services, which is often exciting and sometimes challenging, considering the pace at which providers introduce new services. AWS continues to announce new features on a daily basis … Read More

Achieving significant cost savings using machine learning in elastic public clouds – A cost savings analysis

For many years, traditional information technology (IT) departments are required to build and maintain IT infrastructures (e.g., servers, networks, etc.) and services (e.g., data base management, email, technique issue solving, etc.) to support the company’s business. It is also known … Read More

FittedCloud Announces Machine Learning Driven Cloud Cost Optimization for Amazon Relational Database Services (RDS)

By adding RDS support to its cloud cost optimization solution, customers can automatically control and optimize a range of AWS services, from infrastructure to platform, reducing costs up to 50%. Acton, MA. — FEBRUARY 7, 2018 — FittedCloud, the leading … Read More

Simple AWS EC2 scheduler vs Machine Learning driven EC2 scheduler

AWS EC2 power ON/OFF Turning off EC2 instances when they are not in use is a simple and effective way of reducing AWS cost. It works especially well in environments such as development/test where EC2 instances are used only during … Read More

5 Ways of Cloud Optimization to Reduce Your Cost

According to Forbes, the cloud computing marketplace is expected to increase from $67B in 2015 to $162B in 2020 attaining a compound annual growth rate (CAGR) of 19%. While customers are spending more on public cloud, resources are often over-provisioned. … Read More

Using Efficiency Metrics to Monitor Public Cloud Costs

In a previous blog, How to Measure Resource Cost Efficiency in Public Clouds, we proposed several metrics to measure cost efficiency in public clouds, including resource utilization, service utilization, cost efficiency, and cost saving efficiency. While resource utilization and service … Read More

Machine-learning driven Optimization outperforms Auto Scaling in DynamoDB capacity management

DynamoDB is a fully managed, high performance, highly scalable NoSQL database service offered by AWS.  DynamoDB offers virtually unlimited performance and storage capacity and supports dynamic scaling. One of the challenges with using DynamoDB is provisioning read/write capacity. Under provisioning … Read More

FittedCloud Enhances Actionable Advisories to Help Enterprise Customers and MSPs save More in AWS Cloud

We are excited to announce  many enhancements to FittedCloud’s popular Actionable Advisories, which are integral to our AWS Cost Optimization solution. FittedCloud offers both semi-automated and fully automated cloud resource optimization. Actionable Advisories, which are our semi-automated cost optimization feature, … Read More

Automation – Moving Beyond Visibility and Insights to Optimize Public Cloud Costs

You fly into an airport, call a taxi, get in and look up to tell the driver where to go only to notice that there is no driver. It’s a driverless car.  If that scenario were to happen today, I … Read More

How to reduce AWS costs using machine learning driven EBS IOPS provisioning

Elastic Block Store (EBS) is an AWS service providing raw block-level storage volume that can be attached to Amazon EC2 instances. There are two major categories: SSD-backed storage and HDD-backed storage. The performance of SSD-backed storage for transactional workloads such … Read More

The Use of Learning Curves for Machine Learning Diagnostic in Cloud Resource Optimization

Bias vs. Variance Diagnosis of bias vs. variance is always a good practice in developing successful machine learning models. It helps us understand why the model is not working well and how to improve it. Let’s take polynomial regression as … Read More

AWS Elastic Volumes and FittedCloud EBS Optimizer

AWS released a new Amazon EBS feature called Elastic Volumes last year. This new feature supports the following capabilities. Dynamic capacity increase Dynamic IOPS changes (increase or decrease) Change volume types (for e.g. gp2 to st1 or sc1) All of … Read More

Feature Selection in Machine Learning for Dynamic Cloud Resource Optimization: Part II

In my previous post, I mentioned that there are three types of feature selection methods: wrappers, filters, and embedding methods. Since wrappers are commonly computationally heavy, we only discuss the latter two approaches in this post. Filter Approaches Filter approaches … Read More

Feature Selection in Machine Learning for Dynamic Cloud Resource Optimization: Part I

Introduction Feature selection, also known as attribution selection or feature subset selection, is a very important process in data mining and analytics, which aims to select a subset of relevant and irredundant features for use. Its significance in machine learning … Read More

Anomaly Detection in Dynamic Cloud Resource Optimization

So far we have presented several machine learning use cases at FittedCloud, including Adaptive Machine Learning for Cloud Resource Provisioning, Time Series Models for Forecasting Cloud Resource Provisioning, Capacity Optimization in AWS DynamoDB, and AWS EC2 Scheduling. In all these … Read More

Adaptive Machine Learning for Cloud Resource Provisioning

Overview of Machine Learning During the past few decades, we have witnessed tremendous growths in the study of machine learning. Machine learning has been widely and successfully used in many practical systems to bring intelligence or smartness to the systems, … Read More

Machine Learning – Time Series Models for Forecasting Cloud Resource Provisioning

A time series is a series of data points indexed in time order, usually sampled at equally spaced points in time. Time series data can be unprocessed data sampled from continuous signals. For example, physiological signals such as ECG, PPG, … Read More

12 Important Concepts in Machine Learning – Part II

This is the continuation of the blog series on “12 Important Concepts in Machine Learning” (see Part I here). This blog will summarize the rest of the black-art concepts in machine learning from Dr. Pedro Domingos’ paper “A Few Useful … Read More

12 Important Concepts in Machine Learning – Part I

Dr. Pedro Domingos’ paper “A Few Useful Things to Know about Machine Learning” outlines 12 importance concepts in machine learning learned from experience. These “black arts” are not always well explained in textbooks but are the keys in developing successful … Read More