Query Result Set
Skip Navigation Links
   ActiveUsers:390Hits:20803839Skip Navigation Links
Show My Basket
Contact Us
IDSA Web Site
Ask Us
Today's News
HelpExpand Help
Advanced search

  Hide Options
Sort Order Items / Page
SUPPORT VECTOR REGRESSION (3) answer(s).
 
SrlItem
1
ID:   098631


Application of chaotic ant swarm optimization in electric load / Hong, Wei-Chiang   Journal Article
Hong, Wei-Chiang Journal Article
0 Rating(s) & 0 Review(s)
Publication 2010.
Summary/Abstract Support vector regression (SVR) had revealed strong potential in accurate electric load forecasting, particularly by employing effective evolutionary algorithms to determine suitable values of its three parameters. Based on previous research results, however, these employed evolutionary algorithms themselves have several drawbacks, such as converging prematurely, reaching slowly the global optimal solution, and trapping into a local optimum. This investigation presents an SVR-based electric load forecasting model that applied a novel algorithm, namely chaotic ant swarm optimization (CAS), to improve the forecasting performance by searching its suitable parameters combination. The proposed CAS combines with the chaotic behavior of single ant and self-organization behavior of ant colony in the foraging process to overcome premature local optimum. The empirical results indicate that the SVR model with CAS (SVRCAS) results in better forecasting performance than the other alternative methods, namely SVRCPSO (SVR with chaotic PSO), SVRCGA (SVR with chaotic GA), regression model, and ANN model.
        Export Export
2
ID:   098271


Impact on energy consumption of daylight saving clock changes / Hill, S I; Desobry, F; Garnsey, E W; Chong, Y F   Journal Article
Hill, S I Journal Article
0 Rating(s) & 0 Review(s)
Publication 2010.
Summary/Abstract The focus of this work is an investigation of the effect of prevailing time regime on energy consumption. In particular we perform analysis demonstrating potential energy savings which could be obtained were Great Britain to maintain daylight savings time (DST) over winter, instead of reverting to Greenwich mean time (GMT). We review the literature on the effect of DST on energy consumption and show that this indicates a justification for considering the issue. Our headline result is in agreement with many related studies in that advancing the clock by an hour in winter would lead to energy savings of at least 0.3% of daily demand in Great Britain. In deriving this result we have adopted methodologies currently used in load prediction, in particular Support Vector Regression, to estimate energy demand on a half-hourly basis. Corresponding cost savings are found to be higher (due to the nonlinear increase of costs) and we find them to be on the order of 0.6% over the months considered. In terms of environmental impact we find the saving to be approximately equivalent to 450,000 ton of CO2. In deriving these results we adopt a conservative approach such that we consider them lower bounds on any true savings.
        Export Export
3
ID:   098580


Impact on energy consumption of daylight saving clock changes / Hill, S I; Desobry, F; Garnsey, E W; Chong, Y F   Journal Article
Desobry, F Journal Article
0 Rating(s) & 0 Review(s)
Publication 2010.
Summary/Abstract The focus of this work is an investigation of the effect of prevailing time regime on energy consumption. In particular we perform analysis demonstrating potential energy savings which could be obtained were Great Britain to maintain daylight savings time (DST) over winter, instead of reverting to Greenwich mean time (GMT). We review the literature on the effect of DST on energy consumption and show that this indicates a justification for considering the issue. Our headline result is in agreement with many related studies in that advancing the clock by an hour in winter would lead to energy savings of at least 0.3% of daily demand in Great Britain. In deriving this result we have adopted methodologies currently used in load prediction, in particular Support Vector Regression, to estimate energy demand on a half-hourly basis. Corresponding cost savings are found to be higher (due to the nonlinear increase of costs) and we find them to be on the order of 0.6% over the months considered. In terms of environmental impact we find the saving to be approximately equivalent to 450,000 ton of CO2. In deriving these results we adopt a conservative approach such that we consider them lower bounds on any true savings.
        Export Export