A comparison of artificial neural networks and support vector machines for short-term load forecasting using various load types

Mitchell, Glen H.; Bahadoorsingh, S.; Ramsamooj, Neil; Sharma, Chandrabhan

doi:10.1109/ptc.2017.7980814

Cited by 21 publications

(15 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The mean prediction error for daily peak load in [24] was achieved 4.65% for weekdays and 7.08% for weekends of three different states of Turkey [35]. This mean prediction error was achieved after smoothing the temperature discrepancies throughout the day.…”

Section: Related Workmentioning

confidence: 81%

“…Moreover, every proposed model has incorporated some techniques. For example, regression based processes are usually comprised of Autoregressive Integrated Moving Average (ARIMA) [22], Auto-Regressive Moving Average (ARMA) [23], Support Vector Regression (SVR) [24], and Auto-Regressive Moving Average with Exogenous variable (ARMAX) [25]. Nevertheless, it is essential for aforementioned techniques to learn the process by bulks of preceding data for tuning of various parameters.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Game Theoretical Demand Response Management and Short-Term Load Forecasting by Knowledge Based Systems on the basis of Priority Index

et al. 2018

View full text Add to dashboard Cite

Demand Response Management (DRM) is considered one of the crucial aspects of the smart grid as it helps to lessen the production cost of electricity and utility bills. DRM becomes a fascinating research area when numerous utility companies are involved and their announced prices reflect consumer’s behavior. This paper discusses a Stackelberg game plan between consumers and utility companies for efficient energy management. For this purpose, analytical consequences (unique solution) for the Stackelberg equilibrium are derived. Besides this, this paper presents a distributed algorithm which converges for consumers and utilities. Moreover, different power consumption activities on the basis of time series are becoming a basic need for load prediction in smart grid. Load forecasting is taken as the significant concerns in the power systems and energy management with growing technology. The better precision of load forecasting minimizes the operational costs and enhances the scheduling of the power system. The literature has discussed different techniques for demand load forecasting like neural networks, fuzzy methods, Naïve Bayes, and regression based techniques. This paper presents a novel knowledge based system for short-term load forecasting. The algorithms of Affinity Propagation and Binary Firefly Algorithm are integrated in knowledge based system. Besides, the proposed system has minimum operational time as compared to other techniques used in the paper. Moreover, the precision of the proposed model is improved by a different priority index to select similar days. The similarity in climate and date proximity are considered all together in this index. Furthermore, the whole system is distributed in sub-systems (regions) to measure the consequences of temperature. Additionally, the predicted load of the entire system is evaluated by the combination of all predicted outcomes from all regions. The paper employs the proposed knowledge based system on real time data. The proposed scheme is compared with Deep Belief Network and Fuzzy Local Linear Model Tree in terms of accuracy and operational cost. In addition, the presented system outperforms other techniques used in the paper and also decreases the Mean Absolute Percentage Error (MAPE) on a yearly basis. Furthermore, the novel knowledge based system gives more efficient outcomes for demand load forecasting.

show abstract

Section: Related Workmentioning

confidence: 81%

Section: Related Workmentioning

confidence: 99%

Game Theoretical Demand Response Management and Short-Term Load Forecasting by Knowledge Based Systems on the basis of Priority Index

et al. 2018

View full text Add to dashboard Cite

show abstract

“…In the iterative training process of DNN, a reasonable weight coefficient ω s is multiplied when calculating the parameter variation Δθ (k) . In this way, the different effects of different samples on parameter adjustment can be reflected through ω s , as shown in Equations (17) to (19).…”

Section: Sample Weight Assignment Methods Based On Distancementioning

confidence: 99%

“…List of Symbols and Abbreviations: a l , the output of the l-th layer; W l , the weight matrix connecting the (l-1)-th and l-th layers; b l , is the bias of the l-th layer; s(x), the activation function; m, the number of samples; dθ(k), is the gradient of θ at the k-th update; θ (k -1) , is the coefficient before the k-th update and r θ (k − 1) , O is the partial derivative of the θ' s objective function at the k-th update; r (k) , the moving average of the squared gradient of the parameters at the k-th update; ρ, the decay rate; Δθ(k), is the change amount of parameter at the k-th update; α (k) , is the learning rate at the k-th update; θ (k) , a parameter after the k-th update; ε, the decay rate of the learning rate; ω s , the weight coefficients corresponding to the s-th sample; Δθ (k)s , the variation of parameters with sample weights of the s-th sample; Δθ (k)w , the variation of parameters with sample weights at the k-th update. average, 9,10 wavelet analysis, 11,12 and so on; intelligent methods, such as support vector machine (SVM), 13,14 random forest, [15][16][17] neural networks, [18][19][20] and other intelligent forecasting methods. Other methods, such as hybrid technology, [21][22][23][24] are a combination of more than one technology, that is, a combination of traditional and intelligent method technologies or a combination of different intelligent methods.…”

Section: Auto-regressive Movingmentioning

confidence: 99%

Short‐term load forecasting method based on deep neural network with sample weights

Cai

Yan

et al. 2020

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

Summary The reform of power market has presented new challenges to short‐term load forecasting (STLF), and the accuracy of forecast results is of great significance to the orderly and efficient operation of the market. To improve the accuracy of load forecasting, an STLF method based on deep neural network (DNN) with sample weights is proposed. By filtering samples and assigning corresponding weights to different training samples, this method effectively improves the forecasting accuracy of the DNN model. Two important steps of this method are as follows: (a) calculating the distance between the samples and the forecast day to measure the similarity between them, and the training samples are selected based on the distance; (b) after selecting training samples, corresponding weights can be assigned to training samples according to the distance between the training samples and the forecast day. This allows DNN to focus on the key samples. Finally, we carried out simulation analysis by using the actual load data of Guangdong Power Grid in January 2017. The results show that the proposed method can effectively improve the accuracy and reliability of load forecasting.

show abstract

“…Based on literature review, one can conclude that time series analyses are not effective in highly volatile data [29], and therefore time series methods such as regression models, ARIMA models, GARCH, and hybrid models such as the combination of ARIMA and GARCH using wavelet transform are not considered for short-term forecasting when dealing with volatile data [25,27]. Rather than these, the machine learning techniques like artificial neural networks, support vector machines, or random forests are recently applied in this area with positive outcome [30][31][32][33].…”

Section: Measure Distancementioning

confidence: 99%

Simulation Study on Clustering Approaches for Short‐Term Electricity Forecasting

Gajowniczek

Ząbkowski

2018

Complexity

View full text Add to dashboard Cite

Advanced metering infrastructures such as smart metering have begun to attract increasing attention; a considerable body of research is currently focusing on load profiling and forecasting at different scales on the grid. Electricity time series clustering is an effective tool for identifying useful information in various practical applications, including the forecasting of electricity usage, which is important for providing more data to smart meters. This paper presents a comprehensive study of clustering methods for residential electricity demand profiles and further applications focused on the creation of more accurate electricity forecasts for residential customers. The contributions of this paper are threefold: (1) using data from 46 homes in Austin, Texas, the similarity measures from different time series are analyzed; (2) the optimal number of clusters for representing residential electricity use profiles is determined; and (3) an extensive load forecasting study using different segmentation-enhanced forecasting algorithms is undertaken. Finally, from the operator’s perspective, the implications of the results are discussed in terms of the use of clustering methods for grouping electrical load patterns.

show abstract

A comparison of artificial neural networks and support vector machines for short-term load forecasting using various load types

Cited by 21 publications

References 7 publications

Game Theoretical Demand Response Management and Short-Term Load Forecasting by Knowledge Based Systems on the basis of Priority Index

Game Theoretical Demand Response Management and Short-Term Load Forecasting by Knowledge Based Systems on the basis of Priority Index

Short‐term load forecasting method based on deep neural network with sample weights

Simulation Study on Clustering Approaches for Short‐Term Electricity Forecasting

Contact Info

Product

Resources

About