Application of fuzzy neural networks and artificial intelligence for load forecasting

Liao, Gwo-Ching; Tsao, Ta‐Peng

doi:10.1016/j.epsr.2003.12.012

Cited by 75 publications

(32 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing prediction models use typically mathematical models, such as artificial neural networks (ANN), auto regressive integrated moving average (ARIMA), fuzzy neural network, time series, or advanced wavelet neural network (AWNN) [25][26][27][28][29]. Many operations such as electricity generation control, energy planning, and security studies are based on STLF.…”

Section: The Fuzzy Logic As a Versatile Methods Used To Predict Electrmentioning

confidence: 99%

The Fuzzy Logic Method to Efficiently Optimize Electricity Consumption in Individual Housing

2017

View full text Add to dashboard Cite

Electricity demand shifting and reduction still raise a huge interest for end-users at the household level, especially because of the ongoing design of a dynamic pricing approach. In particular, end-users must act as the starting point for decreasing their consumption during peak hours to prevent the need to extend the grid and thus save considerable costs. This article points out the relevance of a fuzzy logic algorithm to efficiently predict short term load consumption (STLC). This approach is the cornerstone of a new home energy management (HEM) algorithm which is able to optimize the cost of electricity consumption, while smoothing the peak demand. The fuzzy logic modeling involves a strong reliance on a complete database of real consumption data from many instrumented show houses. The proposed HEM algorithm enables any end-user to manage his electricity consumption with a high degree of flexibility and transparency, and "reshape" the load profile. For example, this can be mainly achieved using smart control of a storage system coupled with remote management of the electric appliances. The simulation results demonstrate that an accurate prediction of STLC gives the possibility of achieving optimal planning and operation of the HEM system.

show abstract

Section: The Fuzzy Logic As a Versatile Methods Used To Predict Electrmentioning

confidence: 99%

The Fuzzy Logic Method to Efficiently Optimize Electricity Consumption in Individual Housing

2017

View full text Add to dashboard Cite

show abstract

“…RBFN has a faster learning speed than the back-propagation (BP) network, and its function approximation ability, model recognition, and classification ability are also better than those of the BP network [29,30]. The BP network is a type of global approximation network that makes a corresponding parameter adjustment for each input and output data.…”

Section: Support Vector Machine (Svm)mentioning

confidence: 99%

A New Hybrid Forecasting Approach Applied to Hydrological Data: A Case Study on Precipitation in Northwestern China

Jiao

Guo

Ding

2016

Water

View full text Add to dashboard Cite

Hydrogeological disasters occur frequently. Proposing an effective prediction method for hydrology data can play a guiding role in disaster prevention; however, due to the complexity and instability of hydrological data, this is difficult. This paper proposes a new hybrid forecasting model based on ensemble empirical mode decomposition (EEMD), radial basis function neural networks (RBFN), and support vector machine (SVM), this is the EEMD-RBFN-SVM method, which has achieved effective results in forecasting hydrologic data. The data were collected from the Yushu Tibetan Autonomous Region of the Qinghai Province. To validate the method, the proposed hybrid model was compared to the RBFN, EEMD-RBFN, and SAM-ESM-RBFN models, and the results show that the proposed hybrid model had a better generalization ability.

show abstract

“…Although many prediction models have been proposed in literature, including multivariate regression [2], artificial neural network [2], [3], [4], Fuzzy model [5], and grey model [6]. Usually, these models are faced with problems including low prediction The original SVM algorithm was invented by Vladimir N. Vapnik and the current standard incarnation (soft margin SVM) was proposed by Corinna Cortes and Vapnik in 1993 and published in 1995 [9].…”

Section: Prediction and Regressionmentioning

confidence: 99%

“…In recent years, many prediction models, including multivariate regression [2], artificial neural network [2], [3], [4], Fuzzy model [5], and grey model [6], are proposed in literature. The application fields of these models differ, depending on the forecast variable, its periodicity, and the forecast horizon [1].…”

Section: Introductionmentioning

confidence: 99%

A Short-Term Prediction Model Based on Support Vector Regression Optimized by Artificial Fish-Swarm Algorithm

Wang¹,

Chen²,

Liu³

et al. 2015

IJCA

View full text Add to dashboard Cite

In urban management, it is important to precisely forecast the short-term demand for necessary resources, including water, electric power, and gas. Although a variety of prediction models have been proposed in literature, the underlying defects and limitations confine the effectiveness and forecasting precision of these models. In this paper, the shortterm prediction problem is modeled as a non-linear multivariate regression problem, which is solved by support vector regression (SVR). The parameters in SVR are optimized by artificial fish-swarm algorithm (AFSA). The proposed prediction model (termed SVR-AFSA) overcomes the defects of existing prediction models, thus promoting forecasting precision. In order to verify the effectiveness and prediction precision of SVR-AFSA, this paper conducts experiments on a real dataset of two-month hourly water consumption. It also compares SVR-AFSA with two commonly adopted models, i.e., traditional BP neural network, and SVR optimized by grid method (SVR-grid). The experiments results show that SVR-AFSA outperforms these two models in prediction precision in terms of mean squared error (MSE) and mean absolute percentage error (MAPE).

show abstract

Application of fuzzy neural networks and artificial intelligence for load forecasting

Cited by 75 publications

References 10 publications

The Fuzzy Logic Method to Efficiently Optimize Electricity Consumption in Individual Housing

The Fuzzy Logic Method to Efficiently Optimize Electricity Consumption in Individual Housing

A New Hybrid Forecasting Approach Applied to Hydrological Data: A Case Study on Precipitation in Northwestern China

A Short-Term Prediction Model Based on Support Vector Regression Optimized by Artificial Fish-Swarm Algorithm

Contact Info

Product

Resources

About