Application of ANN and DSM techniques for peak load management a case study

Babu, P. Ravi; Divya, V.

doi:10.1109/icset.2008.4747037

Cited by 7 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An artificial neural network (ANN) is associated with an information processing system that uses a mathematical model inspired by biological neurons. Based on internal or external information in the network, an ANN can adapt, learn and change its structure to create a precise relationship between variables [50,51]. In the ANN model, nodes called neurons are directly interconnected to form a neural network for distributed parallel processing, as depicted in Figure 5.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Neural Network-Based Demand-Side Management in a Stand-Alone Solar PV-Battery Microgrid Using Load-Shifting and Peak-Clipping

2022

View full text Add to dashboard Cite

Due to failures or even the absence of an electricity grid, microgrid systems are becoming popular solutions for electrifying African rural communities. However, they are heavily stressed and complex to control due to their intermittency and demand growth. Demand side management (DSM) serves as an option to increase the level of flexibility on the demand side by scheduling users’ consumption patterns profiles in response to supply. This paper proposes a demand-side management strategy based on load shifting and peak clipping. The proposed approach was modelled in a MATLAB/Simulink R2021a environment and was optimized using the artificial neural network (ANN) algorithm. Simulations were carried out to test the model’s efficacy in a stand-alone PV-battery microgrid in East Africa. The proposed algorithm reduces the peak demand, smoothing the load profile to the desired level, and improves the system’s peak to average ratio (PAR). The presence of deferrable loads has been considered to bring more flexible demand-side management. Results promise decreases in peak demand and peak to average ratio of about 31.2% and 7.5% through peak clipping. In addition, load shifting promises more flexibility to customers.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

“…external information in the network, an ANN can adapt, learn and change its structure to create a precise relationship between variables [50,51]. In the ANN model, nodes called neurons are directly interconnected to form a neural network for distributed parallel processing, as depicted in Figure 5.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Neural Network-Based Demand-Side Management in a Stand-Alone Solar PV-Battery Microgrid Using Load-Shifting and Peak-Clipping

2022

View full text Add to dashboard Cite

show abstract

“…Voltage optimisation can be beneficial for utilities through peak loading relief of distribution systems, reduction in fuel consumption (if, say, the utilities have local power generation plants), reduction in emissions (should energy regulations place a cost on emissions), and overall cost reductions [11,12]. The technology can also improve power quality by reducing harmonic and transient voltages, as well as balance phase voltages.…”

Section: Voltage Optimisationmentioning

confidence: 99%

Voltage Optimisation Technology for an Australian Abattoir—A Techno-Economic Evaluation

et al. 2017

View full text Add to dashboard Cite

Abstract:Optimising voltage levels to a controlled stable level at a facility can not only reduce the cost of energy but also enhance equipment performance, prolong equipment life, reduce maintenance costs and reduce greenhouse gas emissions. Voltage optimisation (VO) technology has been widely used in a number of different industries locally and internationally, but not to a large extent within the red meat processing sector in Australia. To determine whether VO technology can be implemented, and whether it is technically and economically viable for red meat processing sites, this study investigated, through case study analyses, the potential effectiveness of VO technology in Australian abattoirs. Through an extensive literature survey, the study initially explored the need and considerations of deploying VO technologies at a typical red meat processing plant. To determine the advantages of using VO technology the study then performed site analyses to investigate power quality (PQ) issues, such as voltage regulation, harmonics and power factor, at two typical medium-sized abattoirs, one in Western Australia and another in Queensland. Finally, an economic assessment of the use of VO in the red meat processing industry was undertaken to identify the potential electricity savings and payback periods. From the case study analyses, it is evident that power quality issues, such as under voltage, overvoltage, and harmonic distortion, can be reduced and significant energy savings can be achieved with the optimum selection of VO technology and voltage level. The outcomes of this study will enable engineering and operations staff to be better informed about the economic and technical benefits of (and possible issues with) using VO technologies in an abattoir.

show abstract

“…The study focuses on the implementation of PSO and ACO for reducing the consumer's energy cost. In order to improve energy efficiency in industrial sector, a study in [15] implements artificial neural network (ANN) and DSM strategies. Sulaima et al [16] proposed optimum load profile forecasting model using ANN for industrial sector, where the load shifting strategy has also been applied to reduce the electricity cost under the ETOU tariff.…”

Section: Introductionmentioning

confidence: 99%

Optimum energy management strategy with enhanced time of use tariff for campus building using particle swarm optimization

Mahmud

Dahlan

2022

IJEECS

View full text Add to dashboard Cite

<span>Enhanced time of use (ETOU) tariff was introduced by Tenaga Nasional Berhad (TNB) in 2016 to promote demand response for commercial and industrial consumers. The ETOU tariff scheme offers different tariff rates at different times of the day. However, increment of electricity expenses might occur if consumers fail to optimally shift their consumption to lower rate hours and causing higher usage during peak hours. Furthermore, the time-based pricing tariff is still new to Malaysian consumers, thus consumers have lack of knowledge to perform demand response. Therefore, this research proposes an optimum load management strategy under the ETOU tariff for a commercial building using particle swarm optimization (PSO). The model was applied for Universiti Teknologi MARA (UiTM) Complex Engineering Shah Alam. Load profile of five different buildings in the complex were used as inputs for the study. The analyses were carried out at different controlled loads weightage factors ranged from 10-40% for load shifting strategy to determine the optimal solution. Results show the electricity cost decreases in all the controlled load <span>weightage factors tested on the buildings after applying the load management strategy. The weightage factor of 40% provides the best solution for all buildings, saving 1-4% on the monthly bills.</span></span>

show abstract

Application of ANN and DSM techniques for peak load management a case study

Cited by 7 publications

References 8 publications

Neural Network-Based Demand-Side Management in a Stand-Alone Solar PV-Battery Microgrid Using Load-Shifting and Peak-Clipping

Neural Network-Based Demand-Side Management in a Stand-Alone Solar PV-Battery Microgrid Using Load-Shifting and Peak-Clipping

Voltage Optimisation Technology for an Australian Abattoir—A Techno-Economic Evaluation

Optimum energy management strategy with enhanced time of use tariff for campus building using particle swarm optimization

Contact Info

Product

Resources

About