Comparison of very short-term load forecasting techniques

Journal Article · Wed May 01 00:00:00 EDT 1996 · IEEE Transactions on Power Systems

DOI:https://doi.org/10.1109/59.496169· OSTI ID:264260

Liu, K; Kwan, C; Lewis, F L ^[1]; Subbarayan, S; Shoults, R R; Manry, M T ^[2]; Naccarino, J ^[3]

---

1. Univ. of Texas, Fort Worth, TX (United States). Automation and Robotics Research Inst.
2. Univ. of Texas, Arlington, TX (United States). Energy System Research Center
3. Network Management Technology, Inc., Sugar Land, TX (United States)

Three practical techniques--Fuzzy Logic (FL), Neural Networks (NN), and Auto-regressive model (AR)--for very short-term load forecasting have been proposed and discussed in this paper. Their performances are evaluated through a simulation study. The preliminary study shows that it is feasible to design a simple, satisfactory dynamic forecaster to predict the very short-term load trends on-line. FL and NN can be good candidates for this application.

• OSTI ID: 264260
• Report Number(s): CONF-950727-; ISSN 0885-8950; TRN: 96:016485
• Journal Information: IEEE Transactions on Power Systems, Vol. 11, Issue 2; Conference: 1995 IEEE Power Engineering Society summer meeting, Portland, OR (United States), 23-27 Jul 1995; Other Information: PBD: May 1996
• Country of Publication: United States
• Language: English

Related Subjects

24 POWER TRANSMISSION AND DISTRIBUTION
POWER DEMAND
COMPUTER CALCULATIONS
FORECASTING
REGRESSION ANALYSIS
NEURAL NETWORKS
FUZZY LOGIC
COMPUTERIZED SIMULATION