Temporal data mining approaches for sustainable chiller management in data centers
Citations
157 citations
157 citations
123 citations
73 citations
Cites background from "Temporal data mining approaches for..."
...State machines can model the operation of HVAC systems [22] and permit to predict or detect the abnormal behavior of HVAC’s components [3]....
[...]
45 citations
Cites background from "Temporal data mining approaches for..."
...Our goal is to predict photovoltaic (PV) power generation from i) historic PV power generation data, and, ii) available weather forecast data....
[...]
...Related Work Comprehensive surveys on time series prediction (Brockwell and Davis 2002; Montgomery, Jennings, and Kulahci 2008) exist that provide overviews of classical methods from ARMA to modeling heteroskedasticity (we implement some of these in this paper for comparison purposes)....
[...]
References
1,922 citations
1,593 citations
"Temporal data mining approaches for..." refers background in this paper
...A contrasting framework, referred to as frequent episode discovery, is an event-based framework that is most applicable to symbolic data that is not uniformly sampled [Laxman et al. 2005, 2008; Mannila et al. 1997; Patnaik et al. 2008]....
[...]
...A contrasting framework, referred to as frequent episode discovery, is an event-based framework that is most applicable to symbolic data that is not uniformly sampled [Laxman et al. 2005, 2008; Mannila et al. 1997; Patnaik et al. 2008]....
[...]
1,452 citations
"Temporal data mining approaches for..." refers background in this paper
...Experiencing SAX: A novel symbolic representation of time series....
[...]
...SAX [Lin et al. 2007] performs a piece-wise aggregate approximation (the aggregate refers to the notion of modeling the given single time series by a linear combination of multiple time-series, each expressed as a box basis function) and symbolize the resulting representation so that techniques from discrete algorithms can be adapted toward querying, matching, and mining the time series....
[...]
...SAX [Lin et al. 2007] performs a piece-wise aggregate approximation (the aggregate refers to the notion of modeling the given single time series by a linear combination of multiple time-series, each expressed as a box basis function) and symbolize the resulting representation so that techniques from discrete algorithms can be adapted toward querying, matching, and mining the time series....
[...]
...As the work closest to ours, we explicitly focus on the SAX representation, which also provides some signi.cant advantages for mining motifs....
[...]
...SAX [Lin et al. 2007] performs a piece-wise aggregate approximation (the aggregate refers to the notion of modeling the given single time series by a linear combination of multiple time-series, each expressed as a box basis function) and symbolize the resulting representation so that techniques…...
[...]
1,387 citations
1,157 citations