英文标题：
《Stochastic Estimated Risk for Storage Capacity》
---
作者：
Revathi Anil Kumar and Mark Chamness
---
最新提交年份：
2018
---
英文摘要：
  Managing data storage growth is of crucial importance to businesses. Poor practices can lead to large data and financial losses. Access to storage information along with timely action, or capacity forecasting, are essential to avoid these losses. In addition, ensuring high accuracy of capacity forecast estimates along with ease of interpretability plays an important role for any customer facing tool. In this paper, we introduce Stochastic Estimated Risk (SER), a tool developed at Nutanix that has been in production. SER shifts the focus from forecasting a single estimate for date of attaining full capacity to predicting the risk associated with running out of storage capacity. Using a Brownian motion with drift model, SER estimates the probability that a system will run out of capacity within a specific time frame. Our results showed that a probabilistic approach is more accurate and credible, for systems with non-linear patterns, compared to a regression or ensemble forecasting models.
---
中文摘要：
管理数据存储增长对企业至关重要。不良做法可能导致大量数据和财务损失。访问存储信息以及及时的行动或容量预测对于避免这些损失至关重要。此外，对于任何面向客户的工具，确保容量预测估计的高准确性以及易解释性都起着重要作用。本文介绍了Nutanix开发的已投入生产的随机估计风险（SER）工具。SER将重点从预测达到满容量日期的单一估计转移到预测与存储容量耗尽相关的风险。SER使用带漂移的布朗运动模型估计系统在特定时间范围内耗尽容量的概率。我们的结果表明，与回归或集合预测模型相比，对于具有非线性模式的系统，概率方法更准确和可靠。
---
分类信息：

一级分类：Quantitative Finance        数量金融学
二级分类：General Finance        一般财务
分类描述：Development of general quantitative methodologies with applications in finance
通用定量方法的发展及其在金融中的应用
--
一级分类：Statistics        统计学
二级分类：Applications        应用程序
分类描述：Biology, Education, Epidemiology, Engineering, Environmental Sciences, Medical, Physical Sciences, Quality Control, Social Sciences
生物学，教育学，流行病学，工程学，环境科学，医学，物理科学，质量控制，社会科学
--

---
PDF下载：
-->