Prediction of Photovoltaic Power Using Nature-Inspired Computing

Sumega, Miroslav; Ezzeddine, Anna Bou; Grmanová, Gabriela; Rozinajová, Viera

doi:10.1007/978-3-030-53956-6_3

Cited by 3 publications

(2 citation statements)

References 16 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this sense, many methods are used and that are broadly categorized in physical and statistical models. In fact, the first ones depend on the solar radiation and the ambient temperature, whereas numerical weather forecast (NWP) [ 7 ] leans on environmental measurements. Indeed, in [ 8 ], the forecast precision is improved by including the effects of the weather characteristics, such as wind direction, strength and temperature.…”

Section: Introductionmentioning

confidence: 99%

Application of AI for Short-Term PV Generation Forecast

Rocha,

Fiorotti,

Fardin

et al. 2023

Sensors

View full text Add to dashboard Cite

The efficient use of the photovoltaic power requires a good estimation of the PV generation. That is why the use of good techniques for forecast is necessary. In this research paper, Long Short-Term Memory, Bidirectional Long Short-Term Memory and the Temporal convolutional network are studied in depth to forecast the photovoltaic power, voltage and efficiency of a 1320 Wp amorphous plant installed in the Technology Support Centre in the University Rey Juan Carlos, Madrid (Spain). The accuracy of these techniques are compared using experimental data along one year, applying 1 timestep or 15 min and 96 step times or 24 h, showing that TCN exhibits outstanding performance, compared with the two other techniques. For instance, it presents better results in all forecast variables and both forecast horizons, achieving an overall Mean Squared Error (MSE) of 0.0024 for 15 min forecasts and 0.0058 for 24 h forecasts. In addition, the sensitivity analyses for the TCN technique is performed and shows that the accuracy is reduced as the forecast horizon increases and that the 6 months of dataset is sufficient to obtain an adequate result with an MSE value of 0.0080 and a coefficient of determination of 0.90 in the worst scenarios (24 h of forecast).

show abstract

Section: Introductionmentioning

confidence: 99%

Application of AI for Short-Term PV Generation Forecast

Rocha,

Fiorotti,

Fardin

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…These complex features make it difficult for traditional mathematical programming methods such as conjugate gradient, sequential quadratic programming, Newton's method, and quasi-Newton's method to find optimum [3]. Meta-heuristic algorithms (MAs) have become prevalent in many applied disciplines in recent decades because of higher performance and lower required computing capacity and time than deterministic algorithms in various optimization problems [4][5][6][7][8][9]. As a branch of random optimization, meta-heuristic algorithms can find a near-optimal solution by using available resources, although it is not always guaranteed to find the global optimum.…”

Section: Introductionmentioning

confidence: 99%

GPOFWA: A hybrid greedy political optimizer with fireworks algorithm for numerical and engineering optimization problems

Dong

Zou

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper proposes a novel hybrid optimization algorithm named GPOFWA, which integrates political optimizer (PO) with fireworks algorithm (FWA) to solve numerical and engineering optimization problems. The original PO uses subgroup optimal solutions such as party leaders and constituency winners to guide the movement of the search agent. However, the number of such subgroup optimal solutions is limited, which leads to insufficient global exploration capabilities of PO. In addition, the recent past-based position updating strategy (RPPUS) of PO lacks effective verification of the updated candidate solutions, which reduces the convergence speed of the algorithm. The proposed hybrid algorithm uses the spark explosion mechanism in FWA to perform explosion spark and Gauss explosion spark operations on the subgroup optimal solutions (party leader and constituency winner) respectively based on the greedy strategy, which optimizes the subgroup optimal solution and enhances the exploitative ability of the algorithm. Moreover, Gaussian explosion sparks are also used to correct the candidate solutions after RPPUS, which makes up for the shortcomings of the original PO. In addition, a new subgroup optimal solution called the Converged Mobile Center (CMC) based on two-way consideration is designed to guide the movement of search agents. We test the presented hybrid algorithm on 30 well-known benchmark test functions and three engineering optimization problems. The experimental results show that GPOFWA is superior to nine state-of-the-art methods in terms of the quality of the resulting solution.

show abstract