Forecasting of Electricity Demand by Hybrid ANN-PSO Models

Anand, Atul; Suganthi, L.

doi:10.4018/978-1-7998-0414-7.ch048

Cited by 15 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PSO combines the characteristics of both the evolution strategies (ES) and GA and it has more stable convergence features than other stochastic techniques. (see Zuperl et al, 2007;Phanthuna et al, 2013;Anand and Suganthi, 2020). Succinctly, we used this technique due to its advantage in multi-objective optimization, the ability to reduce the cost of estimation and also checks the priority of each variable via permutation and combination.…”

Section: Methodsmentioning

confidence: 99%

The validity of Rodrik’s conclusion on real exchange rate and economic growth: factor priority evidence from feature selection approach

Seraj¹,

Bahramian

Alhassan

et al. 2020

Palgrave Commun

View full text Add to dashboard Cite

The undesirable effect of poor exchange rate policy on economic growth has been firmly established in the literature using various parametric methods of econometric techniques. However, less is known about the prioritization of the exchange rate as a determinant of economic growth using a nonparametric approach. Thus, this study introduced machining learning approach (feature selection, particle swarm optimization-PSO, and genetic algorithm-GA techniques) to evaluate the relative primacy of the exchange rate for sustainable economic growth in Germany, South Africa, and Slovakia using Rodrik model with time series data from 1990 to 2016. The study reveals that GDP per capita is the most crucial variable for economic growth in Germany and South Africa whereas, in Slovakia, the real exchange rate takes precedence over all other determinants of economic growth. That is, exchange rate takes precedence over other factors as a determinant of economic growth in an economy (Slovakia) with the high rate of trade openness while income per capita is the most important determinant of economic growth in economies (Germany and South Africa) with a relatively lower rate of trade openness. This partly supports Rodrik's conclusion. We, therefore, recommend that highly opened economies should focus on viable exchange rate policies, such as undervaluation of currency to enhance sustained economic growth. On the other hand, relatively less open economies should focus on policies that improve income per capita rather than exchange rate policies.

show abstract

Section: Methodsmentioning

confidence: 99%

The validity of Rodrik’s conclusion on real exchange rate and economic growth: factor priority evidence from feature selection approach

Seraj¹,

Bahramian

Alhassan

et al. 2020

Palgrave Commun

View full text Add to dashboard Cite

show abstract

“…Furthermore, they validated its effectiveness using the Electric Reliability Council of Texas (ERCOT). Anand et al [25] deployed an ANN-based PSO model to forecast future energy demand for a state of India. Both particle swarm optimization (PSO) and Genetic algorithm (GA) were developed in linear and quadratic forms, and the hybrid ANN models were applied to different series.…”

Section: Related Workmentioning

confidence: 99%

Robust Multi-Step Predictor for Electricity Markets with Real-Time Pricing

et al. 2021

View full text Add to dashboard Cite

Real-time electricity pricing mechanisms are emerging as a key component of the smart grid. However, prior work has not fully addressed the challenges of multi-step prediction (Predicting multiple time steps into the future) that is accurate, robust and real-time. This paper proposes a novel Artificial Intelligence-based approach, Robust Intelligent Price Prediction in Real-time (RIPPR), that overcomes these challenges. RIPPR utilizes Variational Mode Decomposition (VMD) to transform the spot price data stream into sub-series that are optimized for robustness using the particle swarm optimization (PSO) algorithm. These sub-series are inputted to a Random Vector Functional Link neural network algorithm for real-time multi-step prediction. A mirror extension removal of VMD, including continuous and discrete spaces in the PSO, is a further novel contribution that improves the effectiveness of RIPPR. The superiority of the proposed RIPPR is demonstrated using three empirical studies of multi-step price prediction of the Australian electricity market.

show abstract

“…Fan et al [17] used a multi-layer perception neural network prediction model for carbon prices to explain their nonlinearity. However, Anand and Suganthi [18] suggested that a single prediction approach could not produce better performance all the time because of sampling variation, structural changes, and model uncertainty. Therefore, hybrid models have been proposed to overcome the drawbacks of single models to improve the forecast accuracy of carbon prices.…”

Section: Literature Reviewmentioning

confidence: 99%

Forecasting carbon prices in the Shenzhen market, China: The role of mixed-frequency factors

Han

Ding

Zhao

et al. 2019

Energy

137

View full text Add to dashboard Cite

In this study, the hybrid of combination-mixed data sampling regression model and back propagation neural network (combination-MIDAS-BP) is proposed to perform real-time forecasting of weekly carbon prices in China's Shenzhen carbon market. In addition to daily energy, economy and weather conditions, environmental factor is introduced into predictive indicators. The empirical results show that the carbon price is more sensitive to coal, temperature and AQI (air quality index) than to other factors. It is also shown that the forecast accuracy of the proposed model is approximately 30% and 40% higher than that of combination-MIDAS models and benchmark models, respectively. Given these forecast results, China's government and enterprises can effectively manage nonlinear, nonstationary, and irregular carbon prices, providing a better investing and managing tool from behavioural economics.

show abstract

Forecasting of Electricity Demand by Hybrid ANN-PSO Models

Cited by 15 publications

References 13 publications

The validity of Rodrik’s conclusion on real exchange rate and economic growth: factor priority evidence from feature selection approach

The validity of Rodrik’s conclusion on real exchange rate and economic growth: factor priority evidence from feature selection approach

Robust Multi-Step Predictor for Electricity Markets with Real-Time Pricing

Forecasting carbon prices in the Shenzhen market, China: The role of mixed-frequency factors

Contact Info

Product

Resources

About