A Belief Rule Based Expert System for Datacenter PUE Prediction under Uncertainty

Abstract

Abstract-A rapidly emerging trend in the IT landscape is the uptake of large-scale datacenters moving storage and data processing to providers located far away from the end-users or locally deployed servers. For these large-scale datacenters power efficiency is a key metric, with the PUE (Power Usage Effectiveness) and DCiE (Data Centre infrastructure Efficiency) being important examples. This paper proposes a belief rule based expert system to predict datacenter PUE under uncertainty. The system has been evaluated using real-world data from a data center in the UK. The results would help planning construction of new datacenters and the redesign of existing datacenters making them more power efficient leading to a more sustainable computing environment. In addition, an optimal learning model for the BRBES demonstrated which has been compared with ANN and Genetic Algorithm; and the results are promising.

On Energy Efficiency and Performance Evaluation of Single Board Computer Based Clusters: A Hadoop Case Study

“…Finally, the power consumption steadies with minor tails and peaks in the plot towards reduce jobs completion. We observe that the trends for power consumption relevant to task completion are similar for larger data sizes used in this study and is consistent to observations in [34].…”

Indirect disjunctive belief rule base modeling using limited conjunctive rules: Two possible means

“…In this study, the Evidential Reasoning (ER) algorithm is applied for integration. This is due to two main reasons: (1) ER has shown superior performance in handling multiple types of information under uncertainty, including complete and incomplete information [1] [15]- [17] [31]- [34], (2) to maintain consistency since many previous case studies have employed ER for integration, e.g., [27] [28] (for Case II in this study). However, it should also be clear that the use of ER is not compulsory, and integration algorithms of other forms are theoretically applicable as well.…”

“…The conjunctive BRB is used as the benchmark, and the MAE and MAPE are calculated by Eqs. (17)(18) x 1 x 2 Fig. 4 Complete conjunctive BRB with 9 rules for the numerical case…”

“…The Belief Rule Base (BRB) is comprised of multiples belief rules in a single belief structure [29] [30]. As an expert system approach based on the D-S evidence theory [10] [11], BRB has shown superior performance in representing, transforming and integrating multiple types of information under uncertainty, which is quite useful in complex systems modeling [1] [15]- [17] [31]- [34]. Moreover, it is also a white box that provides direct access to experts and decision makers [4] [6] [32].…”

An IoT-Belief Rule Base Smart System to Assess Autism

“…The proper interaction of these components creates a perfect BRB and ER based system which is called RIMER methodology [1]. Each of the components of the BRB architecture is elaborated below [16]:…”