Fuzzy expert systems: an application to short-term load forecasting

Hsu, Yuan‐Yih; Ho, Ku-Long

doi:10.1049/ip-c.1992.0066

Cited by 72 publications

(17 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Expert system based approach was investigated and advanced by Rahman et al, and applied to the STLF for the members of Old Dominion Electric Cooperative in Virginia [13]. Couple of years later, a fuzzy expert system developed by the same group was applied to the same utility [14]. The proposed fuzzy expert system can be updated hourly, and the uncertainties in weather variables and statistical models were modeled using fuzzy set theory.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Nowadays, several techniques for deriving load forecasting model have been proposed. Traditional load forecasting techniques includes regression technique, time series (univariate) approaches, expert system based methods, hybrid Kalman Filters and Box-Jenkins model (Hsu and Ho, 1992). Generally, these techniques are based on statistical methods and they are used to extrapolate the past load behavior while taking into account the effect of other influencing factors such as the weather and temperature.…”

Section: Introductionmentioning

confidence: 99%

“…Generally, these techniques are based on statistical methods and they are used to extrapolate the past load behavior while taking into account the effect of other influencing factors such as the weather and temperature. (Papalexopoulos et al;1992) uses multivariate linear regression model with a transformation technique for STLF.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Short Term Load Forecasting of 132/33kv Kano Transmission Substation using Fuzzy Logic Model

Abdulazeez¹,

Ibrahim²

2017

IJCA

View full text Add to dashboard Cite

This paper provides a short term load forecasting methodology using fuzzy logic for accurately predicting the load requirement of a utility company located in the Northwest region of Nigeria. Fuzzy logic approach is implemented on the daily average temperature data and historical load data of 132/33KV Kano Transmission Substation obtained from Power Holding Company of Nigeria (PHCN) for a period of one year for forecasting the load. The methodology employed uses fuzzy reasoning decision rules that capture the nonlinear relationships between inputs and outputs. Fuzzy rule base used for the forecast were prepared using mamdani implication. Simulink in MATLAB environment is used in this work. The results for the forecasted load are obtained from fuzzy logic model using triangular membership function. The forecast result deviation from the actual values is presented in the form of Mean Absolute Percentage Error (MAPE). From the analysis carried out, the simulated results of the developed model were found to be very close to the one obtained from the Power Utility with Mean Absolute Percentage Error (MAPE) value of 4.65% for Monday 3 rd March 2014 and a MAPE value of 3.08% for Monday 9 th March 2014 which is an indication that the results obtained using the fuzzy logic approach are accurate enough for electricity load forecast.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Short Term Load Forecasting of 132/33kv Kano Transmission Substation using Fuzzy Logic Model

Abdulazeez¹,

Ibrahim²

2017

IJCA

View full text Add to dashboard Cite

show abstract

“…In the sixties years of the XX century, methodologies mainly based on the regressive approach emerged; in the eighties and early nineties of the last century, methodologies emerged, that are based on knowledge and fuzzy techniques [10], [11], artificial neural networks [12], [13], hybrid systems [14] and genetic algorithms [15].…”

Section: Fig 4 Hv and MV Distribution Network Around éVoramentioning

confidence: 99%

Load Forecasting in Electrical Distribution Grid of Medium Voltage

Chemetova¹,

Santos²,

Neves³

2016

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

Abstract. The importance of forecasting has become more evident with the appearance of the open electricity market and the restructuring of the national energy sector. This paper presents a new approach to load forecasting in the medium voltage distribution network in Portugal. The forecast horizon is short term, from 24 hours up to a week. The forecast method is based on the combined use of a regression model and artificial neural networks (ANN). The study was done with the time series of telemetry data of the DSO (EDP Distribution) and climatic records from IPMA (Portuguese Institute of Sea and Atmosphere), applied for the urban area of Évora -one of the first Smart Cities in Portugal. The performance of the proposed methodology is illustrated by graphical results and evaluated with statistical indicators. The error (MAPE) was lower than 5%, meaning that chosen methodology clearly validate the feasibility of the test.

show abstract

“…For the short term load forecast of the Taiwan power system, a research has embedded the facility to update the fitted model by allowing operators to use their heuristic rules to modify the forecast 8 .…”

Section: A Incorporating Additional Factorsmentioning

confidence: 99%

A Study of the Dynamic Behaviour of Daily Load Curve for Short Term Predictions

Deshani

Liyanage²,

Attygalle³

et al. 2014

Proceedings of the International Symposium for Next Generation Infrastructure

View full text Add to dashboard Cite

Electricity demand is one of the most controversial topics in Sri Lanka as the price of electricity increases rapidly, due to the scarcity of electricity generation sources to meet the demand. Fulfilling the peak demand, starting around 6.30p.m and ending around 9.30p.m, of the load curve is identified as the most crucial aspect that needs to be addressed. During this period, high cost power plants are used to generate electricity, which cannot be met using other low cost options such as hydro power. The Ceylon Electricity Board has to bear a huge loss in order to accommodate this high demand at peak times. Therefore, it is an essential task for a developing country as Sri Lanka to consider developing strategically approached mechanisms to provide a reliable electricity supply at an affordable price. This research focuses on studying the statistical nature of the daily load curve for different consumer categories and for different days of the week to capture the dynamics of electricity usage. An extensive literature is carried out to identify similar research and methodologies used to arrive at a solution by dynamically predicting the daily load curve and smoothing the peak using Demand Side Management strategies.

show abstract

Fuzzy expert systems: an application to short-term load forecasting

Cited by 72 publications

References 5 publications

Short Term Load Forecasting of 132/33kv Kano Transmission Substation using Fuzzy Logic Model

Short Term Load Forecasting of 132/33kv Kano Transmission Substation using Fuzzy Logic Model

Load Forecasting in Electrical Distribution Grid of Medium Voltage

A Study of the Dynamic Behaviour of Daily Load Curve for Short Term Predictions

Contact Info

Product

Resources

About