Short Term Load Forecasting in Smart Grids: Case Study of the City of Évora

Chemetova, Svetlana; Santos, Paulo; Neves, Mário Ventim

doi:10.20897/jisem.201718

Cited by 7 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Price is not the sole parameter influencing load; various factors, including temperature, humidity, sunlight, etc ., can impact load prediction in an area ( Ayub et al, 2019 ). Load diagrams are constructed using average power values, obtained by dividing instant power integration by the time interval, for each 15 min ( Chemetova, Santos & Ventim-Neves, 2017 ). Load forecasting is crucial, especially for interconnected utilities that share their anticipated loads during peak hours, thus reducing the burden on individual utilities.…”

Section: Introductionmentioning

confidence: 99%

Demand-side load forecasting in smart grids using machine learning techniques

Masood,

Aurangzeb,

Aleem

et al. 2024

PeerJ Computer Science

View full text Add to dashboard Cite

Electrical load forecasting remains an ongoing challenge due to various factors, such as temperature and weather, which change day by day. In this age of Big Data, efficient handling of data and obtaining valuable information from raw data is crucial. Through the use of IoT devices and smart meters, we can capture data efficiently, whereas traditional methods may struggle with data management. The proposed solution consists of two levels for forecasting. The selected subsets of data are first fed into the “Daily Consumption Electrical Networks” (DCEN) network, which provides valid input to the “Intra Load Forecasting Networks” (ILFN) network. To address overfitting issues, we use classic or conventional neural networks. This research employs a three-tier architecture, which includes the cloud layer, fog layer, and edge servers. The classical state-of-the-art prediction schemes usually employ a two-tier architecture with classical models, which can result in low learning precision and overfitting issues. The proposed approach uses more weather features that were not previously utilized to predict the load. In this study, numerous experiments were conducted and found that support vector regression outperformed other methods. The results obtained were 5.055 for mean absolute percentage error (MAPE), 0.69 for root mean square error (RMSE), 0.37 for normalized mean square error (NRMSE), 0.0072 for mean squared logarithmic error (MSLE), and 0.86 for R2 score values. The experimental findings demonstrate the effectiveness of the proposed method.

show abstract

Section: Introductionmentioning

confidence: 99%

Demand-side load forecasting in smart grids using machine learning techniques

Masood,

Aurangzeb,

Aleem

et al. 2024

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…The evolutionary methods are more desirable due to their stochastically behavior and their capability for efficient global exploration . In this field, most of studies are performed for handling the parameter identification problems like GA, PSO, differential evolution, simulated annealing, artificial bee colony, harmony searching, and P‐system–based algorithm . From these algorithms, the bioinspired computation has shown more proper results.…”

Section: Introductionmentioning

confidence: 99%

Parameter derivation of a proton exchange membrane fuel cell based on coevolutionary ribonucleic acid genetic algorithm

Erlin

Ebadi

Mavaluru

et al. 2019

Computational Intelligence

View full text Add to dashboard Cite

Precise modeling of a polymer electrolyte membrane fuel cell (PEMFC) is a crucial issue in analyzing and controlling electrical energy production. In this paper, a novel semiexperimental model is proposed for forecasting of PEMFC output voltage. As well, the coevolution ribonucleic acid genetic algorithm (coRNA‐GA) is presented as a novel estimation approach for determination of proposed model coefficients. This optimization method is motivated by the biological RNA, encodes the chromosomes by RNA nucleotide basics, and accepts a few RNA operations. This paper proposed several genetic operators to preserve the diversity of particles, and two sets from particles are chosen using various validation functions. In these two subpopulations, different evolutionary methods have been employed for balancing of seeking and extraction. Input pressure of cathode is chosen in this paper as a further parameter for modifying the depiction of concentration overvoltage (Vcon) in the case of conventional Amphlett's PEMFC system. Finally, the performance of the coRNA‐GA algorithm, as well as the precision of the obtained model, is authenticated via empirical results. Also, the obtained results are compared with some other methods, and the superiority of the proposed model is demonstrated in voltage prediction accuracy.

show abstract